Journal of Intelligent & Fuzzy Systems - Volume 43, issue 2

Authors: Hazarika, Ruhul Amin | Maji, Arnab Kumar | Sur, Samarendra Nath | Olariu, Iustin | Kandar, Debdatta

Article Type: Research Article

Abstract: Grey matter (GM) in human brain contains most of the important cells covering the regions involved in neurophysiological operations such as memory, emotions, decision making, etc. Alzheimer’s disease (AD) is a neurological disease that kills the brain cells in regions which are mostly involved in the neurophysiological operations. Mild Cognitive Impairment (MCI) is a stage between Cognitively Normal (CN) and AD, where a significant cognitive declination can be observed. The destruction of brain cells causes a reduction in the size of GM. Evaluation of changes in GM, may help in studying the overall brain transformations and accurate classification of different …stages of AD. In this work, firstly skull of brain images is stripped for 5 different slices, then segmentation of GM is performed. Finally, the average number of pixels in grey region and the average atrophy in grey pixels per year is calculated and compared amongst CN, MCI, and AD patients of various ages and genders. It is observed that, for some subjects (in some particular ages) from different dementia stages, pattern of GM changes is almost identical. To solve this issue, we have used the concept of fuzzy membership functions to classify the dementia stages more accurately. It is observed from the comparison that average difference in the number of pixels between CN and MCI= 10.01%, CN and AD= 19.63%, MCI and AD= 10.72%. It can be also observed from the comparison that, the average atrophy in grey matter per year in CN= 1.92%, MCI= 3.13%, and AD= 4.33%. Show more

Keywords: Alzheimer’s disease (AD), mild cognitive impairment (MCI), grey matter (GM), atrophy, skull stripping, magnetic resonance imaging (MRI), fuzzy membership function

DOI: 10.3233/JIFS-219279

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1779-1792, 2022

Authors: Popa, Mihaela | Alexuta, Daniel | Balas, Valentina E.

Article Type: Research Article

Abstract: This paper is focusing on intelligent rooftop greenhouses. An initial mathematical model implying recirculation factors for greenhouse and underneath building ventilation systems was upgraded in the sense of reducing interactions among parameters, by discarding the recirculation factors. The initial approach relied on basic fuzzy-interpolative temperature controllers working with a network of ventilation fans, adapted to the changes of the weather conditions and of the building configuration by means of a central expert adaptive rule base. This paper proposes a flexible distributed fans network, locally adapted, working under the control of temperature self-adaptive interpolative controllers. This approach enables us to adapt …such buildings, that are now confined to warm temperatures, to a wide range of climates, to value a great part of renewable resources of our cities and to initiate a process of increasing the carbon offset at large scale. The new configuration is tested by simulations. Show more

Keywords: Urban agriculture, intelligent rooftop greenhouse, fuzzy-interpolative adaptive control

DOI: 10.3233/JIFS-219280

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1793-1797, 2022

Authors: Roy, Sanjiban Sekhar | Goti, Vatsal | Sood, Aditya | Roy, Harsh | Gavrila, Tania | Floroian, Dan | Paraschiv, Nicolae | Mohammadi-Ivatloo, Behnam

Article Type: Research Article

Abstract: Fire calamity is one of the worst adversarial events that can happen to the human race. Fire disaster can happen as a manmade disaster or even naturally, and it may cause environmental, social, and financial damages as well. In order to minimalize the unwanted fire calamity, early detection of fire eruptions coupled with immediate and effective response is extremely vital to disaster management systems. The classification of forest fire and non fire images using deep learning techniques has recently received popularity. Detection and prevention of forest fire have lot of significance from the perspective of the forest fire department, specially …for the fire and arson investigators. There are shortcomings in the current mechanisms of forest fire detection in terms of accuracy. Hence, we propose a fire detection model using LeNet5 convolutional neural networks (CNN), which can spot fire in outdoor environments by classifying fire and non fire images. L2 regularization is critical technique that manipulates the complexity of the convolutional neural network model. In our work fire images have certain features that decide if the image is fire or non fire.A weight is assigned to every feature. Regularization used to help to reduce the over fitting that used to caused by plenty of weights. Our proposed provides the directiontowards developing a system that detects the early stages of forest fire.This model can further be utilized to prevent the damage caused by the fire. A CNN is a deep learning method, which has been adopted in order to detect the images of fire and non-fire. With the non sparse solution of L2 regularization we have obtained around 87% of train accuracy, 71% of validation accuracy and 70% of test accuracy after running 10 epochs. Show more

Keywords: Fire detection, convolutional neural networks, LeNet, deep learning, data augmentation

DOI: 10.3233/JIFS-219281

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1799-1810, 2022

Authors: Mng’ong’o, Benito G. | RAD, Dana | Koloseni, David | Balas, Valentina E.

Article Type: Research Article

Abstract: It is a common practice for organisation to carry out assessment exercises regarding performance of their organisational activities and processes. This paper assesses the market performance of five agro-processed crops at Sustainable Agriculture Tanzania (SAT) against some criteria. Experts at SAT supplied useful information by responding through a questionnaire. The fuzzy TOPSIS model was applied in the methodology to rank the processed products. For the sake of comparing results, the fuzzy analytical hierarchy process (AHP) model was also applied to rank the products. It was found that three products maintained their positions in the two models while the other two …products (alternatives) exchanged their positions. It was further suggested that more efforts have to go for lower market performing products by looking upon means to improve on their corresponding low weight criteria/sub-criteria. Show more

Keywords: Agro-processing, fuzzy TOPSIS, fuzzy AHP, linguistic variables, fuzzy aggregation, multi-criteria, decision making

DOI: 10.3233/JIFS-219282

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1811-1826, 2022

Authors: Roy, Sanjiban Sekhar | Mihalache, Sanda Florentina | Pricop, Emil | Rodrigues, Nishant

Article Type: Research Article

Abstract: In the recent time, enviromental sound classification has received much popularity. This area of research comes under domain of non-speech audio classification. In this work, we have proposed a dilated Convolutional Neural Network approch to classify urban sound. We have carried out feature extraction, data augmentation techniques to carry out our experimental strategy smoothly. We also found out the activation maps of each layers of dilated convolution neural network. An increamental dilation rate has exploited Overall we achieved 84.16% of accuracy from the proposed dilated convolutional method. The gradual increaments of dilation rate has exploited the worse effect of grindding …and has lowered down the computational cost. Also, overall classification performance, precision, recall,overall truth and kappa value have been obtained from our proposed method. We have considered 10 fold cross validation for the implementation of the dilated CNN model. Show more

Keywords: Convolutional neural network, classification, environmental sound classification, activation maps and accuracy

DOI: 10.3233/JIFS-219283

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1827-1833, 2022

Authors: Khalifeh, Ala’ F. | AlQammaz, Abdullah Y. | Abualigah, Laith | Khasawneh, Ahmad M. | Darabkh, Khalid A.

Article Type: Research Article

Abstract: Weather prediction is paramount for many applications and scenarios, among them is agriculture. In order to efficiently irrigate the crops with the exact needed water amount, weather forecasting can be used to optimize the quantity of required irrigation water such that the crops are neither dried up nor over-irrigated. This paper proposes a Machine Learning (ML)-based weather forecasting model, which utilizes the Social Spider Algorithm-Least Square-Support Vector Machine (SSA-LS-SVM) algorithm. The simulation results are used to predict the prime weather and soil parameters such as the atmospheric temperature, pressure, and soil humidity for 24, 48, and 72 hours based on …previous 39 days’ hourly data for Amman city. The predicted values showed low relative mean square errors compared with the actual values and the LS-SVM predictor. Show more

Keywords: Weather forecasting, prediction, smart irrigation, artificial intelligence, social spider algorithm-least square support vector machine, least square support vector machine

DOI: 10.3233/JIFS-219284

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1835-1842, 2022

Authors: Anh, Nguyen Thi Ngoc | Anh, Pham Ngoc Quang | Thu, Vu Hoai | Van Thai, Doan | Solanki, Vijender Kumar | Tuan, Dang Minh

Article Type: Research Article

Abstract: Anomaly detection for sensor systems is one of the most researched topics for the Internet of Thing systems. Researchers have been attracted to machine learning classification problems that are considered the most effective techniques. The novel model is proposed by combining anomaly pattern Symbolic Aggregate Approximation (SAX), processing imbalance data and machine learning techniques for sensor anomaly detection. The advantage of anomaly patterns and machine learning leads to the the proposed model to have better performance. The proposed model consists of three phases: finding anomaly pattern features, processing imbalanced data, exploring data by machine learning model. In this paper, the …main contributions with respect to previous works can be listed as follows: (i) Successful modeling the new method of SAX for time series data for finding complex and dynamic anomaly patterns. (ii) Archiving applied anomaly pattern feature into machine learning model Random Forest and hyperparameters optimisation of these model. (iii) Fitfully proposed a model combining SAX, imbalance technique, and random forest to anomaly detection. (iv) Achieving applied proposal model in automatic meter intelligence system in Vietnam. The experiential results of the proposed model have described the robustness and better performance for detecting anomalies of power meter sensors. Show more

Keywords: Time series, anomaly detection, intelligent meter, SAX, machine learning, pattern recognition

DOI: 10.3233/JIFS-219285

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1843-1852, 2022

Authors: Yarbakhsh, Reza | Mortazavi, Seyed Ali Reza | Mortazavi, SM Javad | Parsaei, Hossein | Rad, Dana

Article Type: Research Article

Abstract: The emergence of a new variant of SARS-CoV-2 in the UK that is spreading more rapidly has raised great concerns not only in the UK but also whole Europe and other parts of the globe. The newly identified variant of SARS-CoV-2 that is reported to be more contagious has prompted many countries to ban travel to and from the UK. As of April 2, 2021, nearly 4.35 million confirmed cases of coronavirus (COVID-19) have been reported in the UK out of which more than 127,000 people have died. These numbers reveal a need for predictor models to assist with management, …prevention, and treatment decisions. Here, we presented an Artificial Intelligence (AI) model to predict the death rate in various cities of the United Kingdom. Training and testing the model using the data available on the European data portal showed promising results with predicted R2  = 0.88. Show more

Keywords: COVID-19, artificial intelligence, death rate, prediction, UK

DOI: 10.3233/JIFS-219286

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1853-1857, 2022

Authors: Vallent, Thokozani Felix | Hanyurwimfura, Damien | Kim, Hyunsung | Mikeka, Chomora

Article Type: Research Article

Abstract:  The modern grid has various functionalities by using remote sensor automation in power management, monitoring and controlling the system. Thus, it is imperative to ensure secure communications for various agents in smart grid, since the system is information communication based. Being information based the smart grid encounters security and privacy challenges impeding its adoption. One way of dealing with these cyber concerns is in devising robust cryptosystem for data encryption and authenticated key agreement in the communications of these remotely controlled smart devices. However, many proposed solutions are provided at the expense of computations cost. Thus, this paper designs a …novel authenticated key agreement scheme with anonymity based on widely acceptable elliptic curve cryptography with efficiency. The scheme ensures optimal computation and communication overload whilst achieving mutual authentication and anonymity in the key agreement process. The scheme is proven in both formal and informal security analysis in portraying its satisfaction of the standard and extended Canetti–Krawczyk (eCK) security requirements. A comparative analysis with related schemes indicates that the proposed scheme have merits over others. Show more

Keywords: Smart grid, authenticated key agreement, identity-based key agreement, integrity, non-repudiation, mutual authentication

DOI: 10.3233/JIFS-219287

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1859-1869, 2022

Authors: Tran, Thien Khai | Ta, Chien D.C. | Phan, Tuoi Thi

Article Type: Research Article

Abstract: Semantic relations have been adopted in many research fields, including the semantic web, information retrieval, and Q&A systems. The aim of the semantic relations is to remove conceptual and terminological confusion. This is achieved by specifying a set of general concepts that characterize domains and their definitions and interrelationships. This research describes how to detect semantic relations, including synonyms, hyponyms, and hypernym s based on WordNet and entities of a knowledge graph (KG). This KG was built from two resources: ACM Digital Library and Wikipedia. We used natural language processing and the deep learning approach for processing data before generating …the KG with an effective algorithm. We chose five of 245 categories in the ACM Digital Library to evaluate the proposed method. The generated results show that our system has excellent performance. Show more

Keywords: Semantic relations, knowledge graph, information extraction

DOI: 10.3233/JIFS-219288

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1871-1876, 2022

Authors: Yegnanarayanan, V. | Krithicaa Narayanaa, Y. | Anitha, M. | Ciurea, Rujita | Marceanu, Luigi Geo

Article Type: Research Article

Abstract: Cancer is a major research area in the medical field. Precise assessment of non-similar cancer types holds great significance in according to better treatment and reducing the risk of destructiveness in patients’ health. Cancer comprises a ambient that differs in response to therapy, signaling mechanisms, cytology and physiology. Netting theory and graph theory jointly gives a viable way to probe the proteomic specific data of cancer types such as ovarian, colon, breast, oral, cervical, prostate, and lung. We observe that the P2P(protein-protein) interaction Nettings of the cancerous tissues blended with the seven cancers and normal have same structural attributes. But …some of these point to desultory changes from the disease Nettings to normal implying the variation in the dealings and bring out the redoing in the complicacy of various cancers. The Netting-based approach has a pertinent role in precision oncology. Cancer can be better dealt with through mutated pathways or Nettings in preference to individual mutations and that the utility value of repositioned drugs can be understood from disease modules in molecular Nettings. In this paper, we demonstrate how the graph theory and neural Nettings act as vital tools for understanding cancer and other types such as ovarian cancer at the zeroth level. Show more

Keywords: Cancer, ovarian cancer, graph parameters, protein nettings, fuzzy neural nettings

DOI: 10.3233/JIFS-219289

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1877-1886, 2022

Authors: Gupta, Punit | Saini, Dinesh Kumar | Rawat, Pradeep Singh | Bhagat, Sajit

Article Type: Research Article

Abstract: The service-oriented computing paradigm changes the way of computing. Emerging technologies like grid computing, cloud computing, and smart health care application have changed the way we compute and communicate. Cloud computing has made computing huge data on the fly and uses flexible resources according to the requirement for real-time applications. Cloud computing comes with pay per use model to pay for only those resources that you have used. Inside the cloud there lie many issues related to efficient and cost-effective models to improve cloud performance and complete the client task with the least cost and high performance. E-Health care services …are one of the most computational intensive services in the cloud, they require real-time computing which can only be achieved if the computational resources can compute it in the least time. Cloud can accomplish this using an efficient scheduling algorithm. This manuscript focuses on the task scheduling technique which enhances the performance in real-time with the least execution time, network cost, and execution cost. The presented model is inspired by Big Bang-Big Crunch algorithm in astronomy. The presented algorithm enhances the quality of service by reducing the scheduling delay, network delay with the least resource cost to complete the task in the least cost to the user with high quality of service. Show more

Keywords: BB-BC, cloud infrastructure, genetic algorithm, metaheuristic, task scheduling

DOI: 10.3233/JIFS-219290

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1887-1895, 2022

Authors: Mysore, Aniruddha | TSB, Sudarshan

Article Type: Research Article

Abstract: Swarm Robotics is inspired by the biological swarms of social insects such as ants and bees, where individuals performing basic tasks give rise to complex behavior. It utilizes a team of cooperating robots to perform tasks more efficiently than possible by isolated robots. In this research, we study the exploration of unknown indoor areas using robots that coordinate with each other. In particular, we implement the Reverse Nearest Neighbor coordination algorithm with certain modifications to account for real-world constraints. The library developed as part of this work provides scripts to help with robotic tasks for exploration and robotic arm control …that can be used to set up simulation tools like VREP, without much prior experience thereby lowering the barrier for entry and making the robotics projects more accessible. Show more

Keywords: Multi-robot exploration, pedagogical robotics software

DOI: 10.3233/JIFS-219291

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1897-1909, 2022

Authors: Asad, Muhammad Usman | Gu, Jason | Farooq, Umar | Balas, Marius | Chen, Zheng | Qureshi, Khurram Karim | Abbas, Ghulam | Chang, Chunqi

Article Type: Research Article

Abstract: This paper proposes a disturbance observer supported Takagi-Sugeno (TS) fuzzy model-based control scheme for uncertain systems. The baseline controller is a guaranteed performance fuzzy model based parallel distributed controller (PDC) which is constructed using the nominal system’s parameters. The model approximation error and parametric uncertainties are treated as a lumped disturbance and a nonlinear disturbance observer (NDOB) is introduced to counter the lumped disturbance. The applicability of the proposed scheme is demonstrated on the bilateral control of nonlinear teleoperation system in MATLAB/Simulink/QUARC environment through simulations as well as semi-real time experiments.

Keywords: TS fuzzy modeling, parallel distributed compensation, state convergence, teleoperation, MATLAB/Simulink/QUARC

DOI: 10.3233/JIFS-219292

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1911-1919, 2022

Authors: Sabih, Muhammad | Umer, Muhammad | Farooq, Umar | Gu, Jason | Balas, Marius M. | Asad, Muhammad Usman | Qureshi, Khurram Karim | Khan, Irfan A. | Abbas, Ghulam

Article Type: Research Article

Abstract: This paper is devoted to develop interest of power system engineers in learning basic concepts of image processing and consequently using deep networks to solve problems of complex power system networks. To this end, we study fault classification in a power system through automation of equal area (EAC) criterion. By considering EAC graphs as images and using classical image processing techniques, we successfully distinguish between different transient conditions including sudden change of input power as well as short circuit at the sending end and middle points of a single and double circuit transmission lines. In addition to classification, some parameters …are also determined from EAC images such as initial rotor angle, clearing angle, and maximum rotor angle. Further, the use of deep networks is introduced to perform the same task of fault classification and a comparison is drawn with multilayer perceptron neural networks. Developed algorithms are tested in MATLAB as well as Pytorch environments. Show more

Keywords: Engineering education, power system, equal area criterion, image processing, deep neural networks, MATLAB, pytorch

DOI: 10.3233/JIFS-219293

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1921-1932, 2022

Authors: Mundra, Shikha | Vijay, Shounak | Mundra, Ankit | Gupta, Punit | Goyal, Mayank Kumar | Kaur, Mandeep | Khaitan, Supriya | Rajpoot, Abha Kiran

Article Type: Research Article

Abstract: Thousands of patients around the world affecting their health with various factor as age, body mass index, cholesterol levels, albumin levels and several other factor. Prediction of health outcome due to these factors at a proper time can be served as an early warning. Recent growth in machine learning algorithm inspired us to build a predictive model for better healthcare facilities. In our work we have focused on problem of noisy and imbalanced dataset in which majority class is favored over minority one that leads to false prediction. We have experimented with two publicly available medical imbalanced dataset which varies …in its size as MIT’s GOSSIS death and PIMA Indians Diabetes Dataset based on binary class. In this model we have investigated 3 oversampling techniques (Synthetic Minority Oversampler, Random Oversampler and Adaptive Synthetic Sampler) along with two undersampling techniques (Random Undersampler and Near Miss) which were paired with 3 data reduction and cleaning methods namely Tomek Links, One Sided Selection and Edited Nearest Neighbors. At last, we found that combination of Adaptive Synthetic Sampler along with One Sided Selection perform better in case of large size dataset while combination of random oversampler along with Tomek Link showed better performance in case of low size data dataset. We have also analyzed that oversampling technique gives quite promising results in comparison to undersampling methods specifically when applied with machine learning classifiers as these classifiers are data hungry algorithms. Show more

Keywords: Synthetic Minority Oversampler (SMOTE), Random Oversampler (ROS), Adaptive Synthetic Sampler (ADASYN), Random Undersampler (RUS), near miss, Tomek Link (TL), One Sided Selection (OSS), Edited Nearest Neighbors (ENN)

DOI: 10.3233/JIFS-219294

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1933-1946, 2022

Authors: Gupta, Punit | Mundra, Shikha | Goyal, Mayank Kumar | Khaitan, Supriya | Dewan, Ritu | Mundra, Ankit | Rajpoot, Abha Kiran

Article Type: Research Article

Abstract: This Ongoing COVID-19 epidemic situation, which has resulted in the loss of lives and economics. In this scenario, social distancing is the only way to prevent ourselves. In such a scenario to boost the economy, a globally large number of industries and businesses have shifted their system to cloud-like education, shipping, training and many more globally. To support this transition cloud services are the only solution to provide reliable and secure services to the user to sustain their business. Due to this, the load over the existing cloud infrastructure has drastically increased. So it is the responsibility of the cloud …to manage the load over the existing infrastructure to maintain reliability and serve high-quality services to the user. Task allocation in the cloud is one of the key features to optimize the performance of cloud infrastructure. In this work, we have proposed a prediction-based technique using a pre-trained neural network to find a reliable resource for a task based on previous training and history of cloud and its performance to optimize the performance under the overloaded and under loaded situation. The main aim of this work is to reduce the fault and provide high performance by reducing scheduling time, execution time and network load. The proposed model uses the Big Bang Big Crunch algorithm to generated huge datasets for training our neural model. The accuracy of the BB-BC-ANN model is improved with 98% accuracy. Show more

Keywords: ANN, BB-BC, resource optimization, fault

DOI: 10.3233/JIFS-219295

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1947-1957, 2022

Authors: Gupta, Punit | Rawat, Pradeep | Tripathi, Rajan Prasad | Mundra, Ankit | Mundra, Shikha | Goyal, Mayank Kumar | Kaur, Mandeep | Agarwal, Ruchi

Article Type: Research Article

Abstract: Cloud computing in the current scenario comes with a large pool of resources, pay-per-use model and reliable infrastructure. Cloud optimization relies on resource optimization to improve the performance and reliability of the cloud. Fault in the cloud places an important role in defining the reliability of the cloud. The identification of fault is a challenging issue in a modular cloud environment. The researchers have developed various methods for the fault-aware scheduling of cloud resources. The fault-aware resource allocation includes static, dynamic, meta-heuristic, and learning-based approaches. In this article, we primarily focused on existing fault-aware resource allocation techniques and then we …proposed a model that will primarily focus on fault forecast in tasks allocation. The projected model is based nature-inspired heuristic approach and intelligent artificial neural network. The fault-tolerant aware ANN-based proposed model focuses on performance improvement and reliability testing proactively. The proposed model surpasses the existing state of art methods for proactive and reactive fault-aware scheduling techniques in a large scale datacenter. The results and discussions section support the reliability assertion of the fault-tolerant aware human brain and nature-inspired model. Show more

Keywords: ANN, Bat, cloud infrastructure, meta-heuristic, resource allocation

DOI: 10.3233/JIFS-219296

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1959-1968, 2022

Authors: Sohail, Abid | Tariq, Muhammad Imran | Ali, Sehar | Butt, Muhammad Arif | Ismail, Muhammad | Ahmad, Farooq

Article Type: Research Article

Abstract: Diabetes is a complex disease that can only be controlled and prevented by a healthy lifestyle. We have selected the investigation of diabetes for this research as a substantially large fragment of our society is suffering from diabetes. It has been observed that diabetic patients are more expressive on social media as compared to real-life interactions. Furthermore, online communities are playing a significant role in providing social support and knowledge to patients through their experiences. Diabetes has only been monitored through wearable (sensor-based) and glucose meters. However, the problem arises when the patients become reluctant about giving the required information …themselves. For this purpose, a taxonomic system based on business process models has been developed which uses the textual data from the patients in which they express their emotions regarding Diabetes. Social media support groups related to Diabetes are used to gather data. Diabetic patients tend to share their emotions and feelings with people who are face a similar situation. However, there is no established measure to calculate the behavioral impact of diabetes on diabetic patients. In our research, we have studied how diabetic patients collaborate with each other to help others through social media and the impact of social communities on diabetic patient’s lifestyles. The results show the extent to which diabetic people follow a healthy lifestyle. Show more

Keywords: Diabetes, social media, business process modeling, abstraction, facebook, type 1 diabetic, type 2 diabetic

DOI: 10.3233/JIFS-219297

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1969-1984, 2022

Authors: Naseer-u-Din, | Basit, Abdul | Ullah, Ihsan | Noor, Waheed | Ahmed, Atiq | Sheikh, Naveed

Article Type: Research Article

Abstract: Researchers used visual methods rigorously to improve brain tumor detection in MRI or CT scans, yet there remains a challenge to improve the detection accuracy. Further, the rise of deep learning methods improved tumor detection accuracy up to the mark. But again, many times, we face the challenges of having a bigger dataset and better computing power to achieve an improved and accurate trained model for every object classification problem. In this paper, we propose a deep learning framework single shot multi-box detector (SSD)-based model to detect tumors in the MRI scans. The proposed SSD model is the faster …algorithm to detect the tumor even with the ability to detect the smallest spot in the low-resolution MRI scans. We additionally used a lightweight neural network architecture MobileNet v2 with SSD for faster and accurate object classification. The experimental results showed 98% accuracy with the proposed method after training with the smallest dataset of 250 MRI scans. We used the Kaggle database for training and testing the proposed model. Show more

Keywords: Convolutional neural network (CNN), tumor detection, MobileNet model, segmentation, single shot detector (SSD), medical imaging

DOI: 10.3233/JIFS-219298

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1985-1993, 2022

Authors: Soomro, Saima Siraj | Jalbani, Akhtar Hussain | Channa, Muhammad Ibrahim | Lakho, Shamshad | Memon, Imran Ali

Article Type: Research Article

Abstract: The World Health Organization has stated Covid-19 as a pandemic that has posture a current hazard to humanity. Covid-19 pandemic has magnificently forced global shutdown of several events, including educational activities. This has caused in tremendous crisis-response immigration of educational institutes with online smart learning helping as the educational platform. Smart learning targets at providing universal learning to students consuming modern technology to completely prepare them for a fast-changing world everywhere. In this research paper an evaluation system has been developed that is based on bloom taxonomy. A Neuro-fuzzy system for the training and testing of the data for smart …and traditional learning outcomes has been applied on collected data. For this research work, we have selected students of the computing discipline and focus on core-computing subjects. The findings of this research work shows the importance of smart learning and its positive impact on student learning outcomes. The evaluation criteria are based on revised bloom taxonomy levels, such that all six levels have been covered. The students’ performance are very much encouraging when compared with ground truth values and reported 91.2% overall accuracy of proposed model on collected samples. Show more

Keywords: Revised bloom taxonomy, ITS, smart learning, neuro-fuzzy designer

DOI: 10.3233/JIFS-219299

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 1995-2004, 2022

Authors: Leghari, Mehwish | Memon, Shahzad | Dhomeja, Lachhman Das | Jalbani, Akhtar Hussain | Chandio, Asghar Ali

Article Type: Research Article

Abstract: Handwritten signature for the identification and authentication of an individual has been widely used in the biometric systems. Due to the intra-class and inter-class variabilities, signature verification has become one of the most challenging problem in the biometric technology. Furthermore, the offline handwritten signature can be forged by the skilled persons due to its static nature. Therefore, in this paper a deep learning-based method using convolutional neural network (CNN) for online signature verification has been developed. Different values of the convolutional kernels such as 1×1, 3×3 and 5×5 are used to extract the discriminative features at multi-scales. The features of …the initial and middle layers of the CNN are combined to create more powerful features. An up-sampling method with bilinear interpolation has been used to add the features of convolutional layers with different spatial dimensions. Both the addition and concatenation methods have been used to aggregate the convolutional features. A convolutional transpose method is applied to increase the depth of the convolutional layers while performing an addition operation on the layers with different depths. Finally, the concatenated features are passed to the fully connected layers for high-level feature extraction and classification. To evaluate the performance of the proposed method, an android application was developed where; a custom database of 985 online signatures collected from 197 users has been created. The problem of inadequate training data for online signature verification has been addressed through the data augmentation method. The experimental results show that the deep aggregated convolutional feature representation method achieves an accuracy of 99.32% on the custom developed online signature database. Show more

Keywords: Online signature verification, biometric signature verification, convolutional feature aggregation, deep learning based signature authentication, feature concatenation, convolutional neural network

DOI: 10.3233/JIFS-219300

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2005-2013, 2022

Authors: Lakho, Shamshad | Jalbani, Akhtar Hussain | Memon, Imran Ali | Soomro, Saima Siraj | Chandio, Asghar Ali

Article Type: Research Article

Abstract: With the spread of the COVID-19 pandemic, the importance of online learning has grown up worldwide and many higher education institutions used this mode of learning to save the timings of students. Just Online learning does not fulfill all the learning requirements of undergraduate students, therefore, there is a need for the blended learning (BL) method to be adopted in higher educational institutes for the enhancement of students’ learning outcomes. This research paper focuses on the development of an integrated blended learning model and the performance of the model on students’ learning has been predicted using a Bayesian network (BN) …classifier. The proposed model is based on the medium impact blend of the Rotation model and the Enriched Virtual Model and applied to undergraduate computing students. The Data Structures and Algorithms course is targeted for the prediction of students’ performance. The findings of the proposed Integrated BL model show that when students properly attend the classroom lectures followed by their associated lab practical in the Rotation Model and follow the online learning activities in the Enriched Virtual Model properly, then their learning outcomes may be increased as predicted using BN method. The proposed model also reports an overall accuracy of 88.5% on the collected data. Show more

Keywords: Integrated blended learning model, Bayesian network, data structures & algorithms, student performance, intelligent tutoring system

DOI: 10.3233/JIFS-219301

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2015-2023, 2022

Authors: Narejo, Sanam | Shaikh, Anoud | Memon, Mehak Maqbool | Mahar, Kainat | Aleem, Zonera | Zardari, Bisharat

Article Type: Research Article

Abstract: Hundreds of people dying from heart disease almost every day that is how terrific a delayed diagnosis can be. Living in an advanced era full of intelligent systems, the increasing number of deaths can be reduced. This research paper focuses on the development of a cardiovascular disease prediction system particularly a heart disease, by developing machine learning classifiers, for instance, Support Vector Machine (SVM), Decision Tree, and XGBoost Classifiers. We also scaled the features to standardize unconstrained features in data, available in a fixed range for better optimization of models. For efficiency, the classification of features was also done in …two categories, Independent features, and dependent features. Furthermore, the performance measures helped with best practices for model assessment & classifier performance. Eventually, after tuning hyper-parameters, the results exhibit high accuracy for XGBoost among other trained classifiers. After a comparative analysis, the best-suited algorithm can be utilized for heart disease detection, in the medical field, and regarding the economy, as costly treatments are taken into consideration. This indicates that a non-expert can also attempt for diagnosis without fretting over expensive treatments. Show more

Keywords: Medical diagnosis, heart disease, exploratory data analysis, machine learning classification, support vector machines, decision tree, XGBoost classifiers

DOI: 10.3233/JIFS-219302

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2025-2033, 2022

Authors: Shaikh, Anoud | Mahoto, Naeem Ahmed | Unar, Mukhtiar Ali

Article Type: Research Article

Abstract: The shift in the news consumption from traditional newspapers to online news has led media analysts and researchers to apply powerful text mining techniques on the vast amount of news data. News has a profound influence on public as it informs about the events happening around them and may affect them. It keeps the people connected and allows them to engage in the decision making process. The words used in the news language are sometimes taken from the regional languages so as to express a new phenomenon, event or idea. In this paper, we have proposed a lexicon based framework …named as TextGraph that automatically extracts the concepts from the Dawn news using the Term Frequency–Inverse Document Frequency (TF-IDF) weighting factor and visualizes them in a formal way. To achieve value-add insights, we have developed Pakistani English corpus and used it along with other existing dictionaries. Our proposed corpus incorporates the Pakistani English words used in the Dawn news stories, which are annotated and validated by a human expert. Experimental results show that our concept extraction method out performs and gives more specific concepts. Our research suggests that the proposed framework and corpus opens multiple directions for promising future research in this domain. Show more

Keywords: Lexicon, concept extraction, concept visualization, text analysis

DOI: 10.3233/JIFS-219303

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2035-2044, 2022

Authors: Sanjrani, Anwar Ali | Baber, Junaid | Bakhtyar, Maheen | Ullah, Ihsan | Naveed, M. Shumail | Noor, Waheed | Basit, Abdul | Khan, Azam | Sheikh, Naveed

Article Type: Research Article

Abstract: The accuracy on MINST dataset for roman numerals is already 99.65%. However, same models showed low accuracy on Sindhi numerals. It is because Sindhi numerals have high correlation between the shapes of the numerals. In this paper, correlation based template matching is used to analyze the shape ambiguity by identifying the dominant false positives (FP) and false negatives (FN) for every numeral. Furthermore, the Gradients Histogram Orientation (GOH) features are used to improve the accuracy of existing classifiers by image-to-image matching. The classical OCR using simple binary features are not sufficient to address the problems of shape ambiguity in Sindhi …numerals, i.e., the shape of digits 2, , and 3, , are very similar. The raw pixel values are used as features for the classification in the first stage. In second stage, the input image is matched with the dominant FP and FN of the predicted class, and the final decision is made by the image-to-image matching based on GOH features. Decision based on image to image matching with dominant FP and FN increase the accuracy of the classifier. Support vector machine (SVM), K-nearest neighbor, and template based matching classifiers are used. The proposed extension substantially improves the accuracy of all mentioned classifiers. Show more

Keywords: Gradient orientation histograms, SIFT, gradient based keypoint descriptors, keypoint descriptor quantization

DOI: 10.3233/JIFS-219304

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2045-2056, 2022

Authors: Sabir, Imran | Baber, Junaid | Ahmed, Atiq | Sheikh, Naveed | Bakhtyar, Maheen | Khan, Azam | Devi, Varsha

Article Type: Research Article

Abstract: Electrocardiogram (ECG) data recorded by medical devices are hard to analyze manually. Therefore, it is important to analyze and categorize each heartbeat using machine learning. Recently, advancements in machine learning have made classification of complex data easy and fast. However, these machine learning algorithms require sufficient amount of training data and have limited performance in case the data is imbalance. In case of MIT-BIH arrhythmia dataset, the distribution of training instances are quite imbalance. Many machine learning, particularly deep learning, algorithms give high accuracy on these datasets but still the minority classes have zero accuracy. In this paper, we improve …the accuracy of minority classes without hurting the overall accuracy of other classes using transfer learning. The accuracy of existing deep learning model is increased from 90.67% to 98.47%, respectively. Show more

Keywords: Transfer learning, deep learning, imbalance dataset

DOI: 10.3233/JIFS-219305

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2057-2067, 2022

Authors: Butt, Sahrish | Bakhtyar, Maheen | Noor, Waheed | Baber, Junaid | Ullah, Ihsan | Ahmed, Atiq | Basit, Abdul | Kakar, M. Saeed H.

Article Type: Research Article

Abstract: Unstructured text processing is the first step for several applications such as question answering systems, information retrieval, and recipe classification. In the field of recipe classification, number of frameworks have been proposed. However, it is still very tedious and time consuming to extract the food items from the unstructured text and then process for classification. In this research, an automatic food item detection from unstructured text is proposed based on semantic sense modeling. The candidate nouns are detected which can be food items and then the similarity of those nouns is computed with possible food categories. The candidate noun …is treated as food item if the similarity is high. For similarity between possible food item and food category is computed by WordNet ontology. The proposed framework is evaluated on benchmark datasets and competitive performance have been achieved. The F-score on large dataset that contains around 20 K recipes is 0.89 which is improved from 0.56. Show more

Keywords: Food named entity recognition, recipe text processing, NLP, semantic similarity, WordNet

DOI: 10.3233/JIFS-219306

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2069-2078, 2022

Authors: Ali, Basit | Tayyaba, Shahzadi | Ashraf, Muhammad Waseem | Tariq, Muhammad Imran | Imran, Muhammad | Akhlaq, Maham

Article Type: Research Article

Abstract: IoT systems base devices are considered an excellent research domain owning to its expertise and applications in wide range of areas. IoT in health care domain is gaining attention due to its better access to the doctor and paramedical staff as well as sensor based studies which results in less man to man interacting and less fault in the data. The health care provider can easily access the vitals and various other medical parameters by even staying miles away from the patient. However, large amount of data transfer over various communication mediums results in more data traffic. This data transfer …will require more power which will be utilized to transfer the data. To reduce this data traffic issues, an efficient method is used in this work in which only the data that is predominantly important to be send to the health care provider is send via the communication medium. Rule based fuzzy logic tool is used in this work for an elder patient having cardiac issues. Blood sugar (After eating), Blood pressues (systolic), Blood pressure (Diastolic) and cholesterol level are taken as the parameter that are examined for the patient and the medical treatment required is calculated. The rules are set on the basis of real time data and human knowledge. The results from the fuzzy logic interference shows that the health care provider will be alarmed using communication medium only when active or emergency medical treatment of the patient is required. A comparative study between the power utilized in normal data driven method and fuzzy method shows that the fuzzy method utilize 8 times less power than the normal method. The simulated and MAMDANI model calculated values shows less than 1% error which shows the accuracy of the work in health care domain. Show more

Keywords: Fuzzy logic, healthcare system, Internet of Things

DOI: 10.3233/JIFS-219307

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2079-2085, 2022

Authors: Tariq, Nimra | Ashraf, Muhammad Waseem | Tayyaba, Shahzadi

Article Type: Research Article

Abstract: The uniformly smooth and sharp microneedles have great significance in contact spectroscopy, 3D printing, biomedical and nanotechnology. The stability, bio-stability, conductivity and mechanical properties of the gold (Au) make it effective rather than the other metals such as tungsten, copper, platinum and graphite. The surface quality, proper dimension such as the tip, cone angle is the matter of the trial and practice matter. It was the main issue to develop a controlled optimized methodology to obtain the gold needles of specific dimensions in regular and systematic way. The Ansys simulation of solid microneedle has been done to check on what …stress the deflection occurs on microneedles. Then fuzzy optimization has performed to optimize the parameter of the etching set up such as the voltage, current and time of etching as an input parameter and the tip size and the conical section length as the output parameters. After the simulation and optimization the experiment of the etching has performed with the 3M solution of NaCl in deionized water and small amount of hydropercaloric acid. The fabricated needles have been then characterized by Scanning electron microscopy (SEM) to observe the morphology and the dimensions. The fuzzy analysis has been performed for optimization of the inputs voltage of range 1–10volt, current of range 1–100 mA and etching times from 1–15minutes. These optimized values are calculated by the fuzzy analysis such as the voltage is 58.6 mA, etching time 15 minutes and the voltages found to be 10 volt. Fuzzy analysis gives the simulated size of the tip 10.6μm and Mamdani models gives the 10.7μm which have the 0.01% error and the cone length for the Mamdani was found to be 500μm and the simulated values 497 having the 0.03% error which have very close approximation with the experimental values from the SEM micrographs that which also gives the values of the cone length from 400–500μm and the tip size from 10-20μm for the time 10-15minute whose values was optimized by the fuzzy analysis. Show more

Keywords: Microneedles, ANSYS simulation, fuzzification

DOI: 10.3233/JIFS-219308

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2087-2097, 2022

Authors: Manzoor, Saher | Tayyaba, Shahzadi | Ashraf, Muhammad Waseem

Article Type: Research Article

Abstract: Microfluidic filtration is an essential process in many biomedical applications. Micro or nanoporous membranes are used for colloidal retention. During the membrane filtration process visualization of various phenomena is challenging. Theoretical models have been proposed to visualize the transport mechanism. In this work, ANSYS Fluent is used for 3D designing of the microfluidic system and Fuzzy simulations are used to study flow rate and velocity, to get the maximum benefit from Anodized Aluminium oxide membrane in practical applications. The proposed method exploits relations between driving force, membrane area, and fluid flow. After optimization of parameters for the filtration, the AAO …membrane with desired pore diameter was fabricated using the two-step anodization method. Scanning electron microscope is used for characterization of fabricated AAO membrane. The simulated and theoretical results using computer-based programs are then compared for manipulation of flow rate during the filtration process. Along with the manipulation of flow rate from nanoporous membrane other challenges faced during the filtration process are also highlighted with possible solutions. Show more

Keywords: AAO, microfluidic analysis, fuzzy analysis, filtration

DOI: 10.3233/JIFS-219309

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2099-2108, 2022

Authors: Imran, Muhammad | Butt, Alvina Rafiq | Qasim, Faheem | Fahad, Hafiz Muhammad | Sher, Falk | Waseem, Muhammad Faisal

Article Type: Research Article

Abstract: ZnO is promising material for the electronic and optoelectronic devices. In present work we have fabricated the ZnO film by DC reactive magnetron sputtering. The variations of reactive and sputtering gases affect the crystallite size and band gap of ZnO film. In present work the ZnO film is prepared at 50 watt power by DC reactive spurting method. The fuzzy simulation has been performed to estimate the best argon oxygen gas ratio which gives the better crystallinity and band-gap. The structural analysis shows that the ZnO film has hexagonal wurtzite structure. The UV-vis spectroscopy has been employed to find the …band gap.the measured band gap value of ZnO is 3.21 eV. The fuzzy rule based system and characterization results are in accordance with each other with a minimal difference of less than 1%. Show more

Keywords: DC Sputtering, Zinc oxide film, band gap, resistivity

DOI: 10.3233/JIFS-219310

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2109-2114, 2022

Authors: Awan, Saima Ashraf | Tariq, Muhammad Imran | Zhuang, Peifen

Article Type: Research Article

Abstract: This research analyzed the relationship between openness to agricultural exchange, foreign direct investment, capital, consumer price index, and GDP in Pakistan utilizing time series data for the 1971-2019 period. We used autoregressive distributed lag ARDL-bound testing method to analyze the long-run and short-run correlation between projected variables. The study’s findings also confirmed a positive and important long-term correlation between openness to agricultural trade, foreign direct investment and Pakistan’s economic development. There is no long-run relationship between consumer price and economic growth.

Keywords: Agricultural trade openness, foreign direct investment, ARDL approach

DOI: 10.3233/JIFS-219311

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2115-2119, 2022

Authors: Ma, Yingran | Peng, Yanjun | Wu, Tsu-Yang

Article Type: Research Article

Abstract: Transfer learning technique is popularly employed for a lot of medical image classification tasks. Here based on convolutional neural network (CNN) and sparse coding process, we present a new deep transfer learning architecture for false positive reduction in lymph node detection task. We first convert the linear combination of the deep transferred features to the pre-trained filter banks. Next, a new point-wise filter based CNN branch is introduced to automatically integrate transfer features for the false and positive image classification purpose. To lower the scale of the proposed architecture, we bring sparse coding process to the fixed transferred convolution filter …banks. On this basis, a two-stage training strategy with grouped sparse connection is presented to train the model efficiently. The model validity is tested on lymph node dataset for false positive reduction and our approach indicates encouraging performances compared to prior approaches. Our method reaches sensitivities of 71% /85% at 3 FP/vol. and 82% /91% at 6 FP/vol. in abdomen and mediastinum respectively, which compare competitively to previous approaches. Show more

Keywords: Deep learning, lymph node false positive reduction, transfer learning method, sparse coding algorithm

DOI: 10.3233/JIFS-219312

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2121-2133, 2022

Authors: Jia, Han-Dong | Li, Wei | Pan, Jeng-Shyang | Chai, Qing-Wei | Chu, Shu-Chuan

Article Type: Research Article

Abstract: Wireless sensor network (WSN) is a network composed of a group of wireless sensors with limited energy. With the proliferation of sensor nodes, organization and management of sensor nodes become a challenging task. In this paper, a new topology is proposed to solve the routing problem in wireless sensor networks. Firstly, the sensor nodes are layered to avoid the ring path between cluster heads. Then the nodes of each layer are clustered to facilitate the integration of information and reduce energy dissipation. Moreover, we propose efficient multiverse optimization to mitigate the impact of local optimal solution prematurely and the population …diversity declines prematurely. Extensive empirical studies on the CEC 2013 benchmark demonstrate the effectiveness of our new approach. The improved algorithm is further combined with the new topology to handle the routing problem in wireless sensor networks. The energy dissipation generated in routing is significantly lower than that of Multi-Verse Optimizer, Particle Swarm Optimization, and Parallel Particle Swarm Optimization in a wireless sensor network consisting of 5000 nodes. Show more

Keywords: Routing, clustering, layering, WSN, multi-verse optimizer

DOI: 10.3233/JIFS-219313

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2135-2146, 2022

Authors: Feng, Naidan | Wu, Tsu-Yang | Liang, Yongquan

Article Type: Research Article

Abstract: The electrocardiogram (ECG) signal is a kind of time-varying signal, which has the characteristics and difficulties of variability, instability, and noise. Aiming at that, this paper put forward a novel 13-layer deep dynamic neural network model (DDNN) for the ECG signal learning and classification. The proposed DDNN model is a dynamic hybrid deep learning model. It includes a wavelet block, a convolutional block, a recurrent block, and a classification block, which combines the learning property and classification mechanism of convolutional neural network for the large-scale data sets, the learning and memory ability of Long Short-Term Memory (LSTM) for time series, …and the noise reduction and processing ability of wavelet basis for the signals to meet the requirement of the learning and classification of ECG signal characteristics. Sufficient experimental results show that the proposed model is feasible and effective in the electrocardiogram signal pattern classification. Show more

Keywords: Dynamic signal classification, deep dynamic neural network, time-varying signal, ECG signal classification

DOI: 10.3233/JIFS-219314

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2147-2154, 2022

Authors: Feng, Qing | Pan, Jeng-Shyang | Du, Zhi-Gang | Peng, Yan-jun | Chu, Shu-Chuan

Article Type: Research Article

Abstract: Antlion Optimization Algorithm (ALO) is a promising bionic swarm intelligence algorithm, which has good robustness and convergence, but there are still many areas to be improved and modified. Aiming at the fact that the ALO algorithm is more likely to fall into the local optimum, proposes three strategies to improve the classic ALO algorithm in this paper. First of all, we adopt a parallel idea in the algorithm, through the communication strategy between groups based on Quantum-Behaved to enhance the diversity of the population. Secondly, we adopted two strategies, Opposition Learning, and Gaussian Mutation, to balance the performance of exploration …and exploitation during the execution of the algorithm, further formed the MSALO algorithm. The CEC2013 Benchmark function is selected as the standard, and MSALO is compared with other intelligent optimization algorithms. The experimental results show that MSALO has stronger optimization performance compared with other intelligent algorithms. Besides, we applied MSALO to the practical scenarios of feature selection, and use SVM classifiers as training evaluators to improve the accuracy of feature extraction from high-dimensional data. Show more

Keywords: ALO, quantum-behaved, opposite learning, gaussian mutation, feature selection

DOI: 10.3233/JIFS-219315

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2155-2166, 2022

Authors: Wu, Jimmy Ming-Tai | Tsai, Meng-Hsiun | Li, Tu-Wei | Pirouz, Matin

Article Type: Research Article

Abstract: Estimating similarity using multiple similarity measures or machine learning prediction models is a popular solution to the link prediction problem. The Relation Pattern Deep Learning Classification (RPDLC) technique is proposed in this study, and it is based on multiple neighbor-based similarity metrics and convolution neural networks. The RPDLC first calculates the characteristics for a pair of nodes using neighbor-based metrics and impact nodes. Second, the RPDLC creates a heat map using node characteristics to assess the similarity of the nodes’ connection patterns. Third, the RPDLC uses convolution neural network architecture to build a prediction model for missing relationship prediction. On …three separate social network datasets, this method is compared to other state-of-the-art algorithms. On all three datasets, the suggested method achieves the greatest AUC, hovering around 99 percent. The use of convolution neural networks and features via relational patterns to create a prediction model are the paper’s primary contributions. Show more

Keywords: Link prediction problem, convolution neural network, relation pattern, social network

DOI: 10.3233/JIFS-219316

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2167-2178, 2022

Authors: Wu, Jimmy Ming-Tai | Tsai, Meng-Hsiun | Cheng, Chao-Chieh | Wu, Mu-En

Article Type: Research Article

Abstract: With the rise in popularity of personal computers and decreasing cost, even a personal computer can execute complex and large calculations. So more researchers can invest in AI and machine learning. Humans can’t handle massive data sets or data that requires a long time to read and evaluate, whereas big data frameworks can read and analyze in a reasonable time. So relevant research has increased recently. In the social sciences, machine learning is used to forecast future trends and the index trend. Keeping up with current events is crucial nowadays to debate countermeasures in time. This study combines economic indicators …from 1988 to 2017 with leading indicators and other types of indicators. The recurrent neural network model predicts economic index trends and tests multiple variables. The proposed methods measure the error in predicting future trends in different models to learn which indicators work well together. Show more

Keywords: Machine learning, leading indicator, recurrent neural network, long short term memory, forecast trend

DOI: 10.3233/JIFS-219317

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2179-2189, 2022

Authors: Moghadam, Arman Balali | Rafsanjani, Marjan Kuchaki | Balas, Valentina Emilia

Article Type: Research Article

Abstract: This study takes a new perspective on the procedural content generation (PCG) evaluation problem, extracts current PCG evaluation methods from previous works, and presents a novel classification of these methods while showing each method’s capabilities. Also, the present study introduces a novel concept called Panda Evaluation. Additionally, the soft and hard launches were presented as two evaluation methods and possible building blocks of PE. A group of papers was analyzed to understand previous works and find new opportunities. In doing so, some missing PCG evaluation areas were found, and some new methods were proposed for future PCG evaluations. To the …best of our knowledge, this is the first time these concepts have been presented in PCG evaluation. Show more

Keywords: Procedural content generation (PCG), platformer, soft launch, panda evaluation (PE), machine learning (ML), evaluation graph

DOI: 10.3233/JIFS-219318

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2191-2210, 2022

Authors: Tran, Duc-Nghia | Phi Khanh, Phung Cong | Solanki, Vijender Kumar | Tran, Duc-Tan

Article Type: Research Article

Abstract: Modern methods of monitoring help cow farmers save significantly monitoring time and improve cow health care efficiency. Behavioral changes when cows are sick may include increased or decreased daily activities such as increased lying or decreased walking time. Accelerometer advantages are low power consumption, small size, and lightweight. Thus, accelerometers have been widely used to monitor cow behavior. A cow monitoring system usually includes a central processor for receiving and processing information according to a behavioral classification algorithm through the cows’ movements. This paper introduces an effective classification system for Southern Yellow cow behavior using three degrees of freedom (3-DoF) …accelerometers. The proposed classifier applied GBDT algorithm (16 seconds window) with five features, offers the good performance while investigating with four Southern Yellow cattle. The classification achievement was assessed and compared to existing ones regarding sensitivity, accuracy, and positive predictive value. Show more

Keywords: 3-DoF, accelerometer, behavior, cow, classification

DOI: 10.3233/JIFS-219319

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 2, pp. 2211-2218, 2022