Journal of Intelligent & Fuzzy Systems - Volume 45, issue 6

Authors: Cheng, Shumin | Zhou, Yan | Bao, Yanling

Article Type: Research Article

Abstract: With the increasing diversification and complexity of information, it is vital to mine effective knowledge from information systems. In order to extract information rapidly, we investigate attribute reduction within the framework of dynamic incomplete decision systems. Firstly, we introduce positive knowledge granularity concept which is a novel measurement on information granularity in information systems, and further give the calculation method of core attributes based on positive knowledge granularity. Then, two incremental attribute reduction algorithms are presented for incomplete decision systems with multiple objects added and deleted on the basis of positive knowledge granularity. Furthermore, we adopt some numerical examples to …illustrate the effectiveness and rationality of the proposed algorithms. In addition, time complexity of the two algorithms are conducted to demonstrate their advantages. Finally, we extract five datasets from UCI database and successfully run the algorithms to obtain corresponding reduction results. Show more

Keywords: Incomplete decision system, positive knowledge granularity, incremental attribute reduction

DOI: 10.3233/JIFS-230349

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 11937-11947, 2023

Authors: Wei, Qiuyue | Yang, Dong | Zhang, Mingjie

Article Type: Research Article

Abstract: Aspect-based sentiment analysis is a fine-grained task in the field of sentiment analysis. Various GCN approaches have recently emerged to work on this, but many approaches ignored the critical role of aspectual word information and the effect of noise. In view of this situation, we propose an aspect-based word embedding graph convolutional network (AWEGCN) model. In order to make good use of the aspect information and distinguish the contextual information that is more important for a particular aspect, the aspect information is embedded in the output of the hidden layer. To reduce the noise effect when multiple aspect words appear …in a sentence, after going through the bidirectional graph convolutional network, the aspect information is embedded. A specific contextual representation is computed through an attention mechanism, which is used as the final classification feature. Experiments show that our model achieves impressive performance on five public datasets, and we also apply BERT and XLNet pre-trained models to this task and obtain advanced results that validate the effectiveness of our model. Show more

Keywords: Aspect-level sentiment classification, aspect word embeddings, graph convolutional networks, attention mechanisms

DOI: 10.3233/JIFS-230537

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 11949-11962, 2023

Authors: Cheng, Tao | Cheng, Hua | Fang, Yiquan | Liu, Yufei | Gao, Caiting

Article Type: Research Article

Abstract: As prototype-based Few-Shot Learning methods, Prototypical Network generates prototypes for each class in a low-resource state and classify by a metric module. Therefore, the quality of prototypes matters but they are inaccurate from the few support instances, and the domain-specific information of training data are harmful to the generalizability of prototypes. We propose a C onceptual P rototype (CP), which contains both rich instance and concept features. The numerous query data can inspire the few support instances. An interactive network is designed to leverage the interrelation between support set and query-detached set to acquire a rich Instance Prototype which is …typical on the whole data. Besides, class labels are introduced to prototype by prompt engineering, which makes it more conceptual. The label-only concept makes prototype immune to domain-specific information in training phase to improve its generalizability. Based on CP, C onceptual P rototypical C ontrastive L earning (CPCL) is proposed where PCL brings instances closer to its corresponding prototype and pushes away from other prototypes. “2-way 5-shot” experiments show that CPCL achieves 92.41% accuracy on ARSC dataset, 2.30% higher than other prototype-based models. Meanwhile, the 0-shot performance of CPCL is comparable to Induction Network in the 5-shot way, indicating that our model is adequate for 0-shot tasks. Show more

Keywords: Prototypical network, text classification, Few-Shot learning, prompt learning

DOI: 10.3233/JIFS-231570

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 11963-11975, 2023

Authors: AlAlaween, Wafa’ H. | AlAlawin, Abdallah H. | AbuHamour, Saif O. | Gharaibeh, Belal M.Y. | Mahfouf, Mahdi | Alsoussi, Ahmad | AbuKaraky, Ashraf E.

Article Type: Research Article

Abstract: Right-first-time production enables manufacturing companies to be profitable as well as competitive. Ascertaining such a concept is not as straightforward as it may seem in many industries, including 3D printing. Therefore, in this research paper, a right-first-time framework based on the integration of fuzzy logic and multi-objective swarm optimization is proposed to reverse-engineer the radial based integrated network. Such a framework was elicited to represent the fused deposition modelling (FDM) process. Such a framework aims to identify the optimal FDM parameters that should be used to produce a 3D printed specimen with the desired mechanical characteristics right from the first …time. The proposed right-first-time framework can determine the optimal set of the FDM parameters that should be used to 3D print parts with the required characteristics. It has been proven that the right-first-time model developed in this paper has the ability to identify the optimal set of parameters successfully with an average error percentage of 4.7%. Such a framework is validated in a real medical case by producing three different medical implants with the desired mechanical characteristics for a 21-year-old patient. Show more

Keywords: Fuzzy logic, particle swarm optimization, radial based integrated network, right-first-time production

DOI: 10.3233/JIFS-232135

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 11977-11991, 2023

Authors: Uganya, G. | Bommi, R.M. | Muthu Krishnammal, P. | Vijayaraj, N.

Article Type: Research Article

Abstract: Internet of things (IoT) is a recent developing technology in the field of smart healthcare. But it is difficult to transfer the patient’s health record as a centralized network. So, “blockchain technology” has excellent consideration due to its unique qualities such as decentralized network, openness, irreversible data, and cryptography functions. Blockchain technology depends on cryptography hash techniques for safe transmission. For increased security, it transforms the variable size inputs into a constant length hash result. Current cryptographic hash algorithms with digital signatures are only able to access keys up to a size of 256 bytes and have concerns with single …node accessibility. It just uses the bits that serve as the key to access the data. This paper proposes the “Revised Elliptic Curve Cryptography Multi-Signature Scheme” (RECC-MSS) for multinode availability to find the nearest path for secure communications with the medical image as keys. Here, the input image key can be converted into an array of data that can be extended up to 512 bytes of size. The performance of the proposed algorithm is analyzed with other cryptography hash functions like Secure Hashing Algorithms (SHAs) such as “SHA224”, “SHA256”, “SHA384”, “SHA512”, “SHA3-224”, “SHA3-256”, “SHA3-384”, “SHA3-512”, and “Message Digest5” (MD5) by “One-way ANOVA” test in terms of “accuracy”, “throughput” and “time complexity”. The proposed scheme with ECC achieved the throughput of 17.07 kilobytes per 200 nano seconds, 93.25% of accuracy, 1.5 nanoseconds latency of signature generation, 1.48 nanoseconds latency of signature verification, 1.5 nanoseconds of time complexity with 128 bytes of hash signature. The RECC-MSS achieved the significance of 0.001 for accuracy and 0.002 for time complexity which are less than 0.05. From the statistical analysis, the proposed algorithm has significantly high accuracy, high throughput and less time complexity than other cryptography hash algorithms. Show more

Keywords: Internet of Things, blockchain technology, multi-signature, Secure Hash Algorithm, Revised Elliptic Curve Cryptography, medical image

DOI: 10.3233/JIFS-232802

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 11993-12012, 2023

Authors: Zhang, Guowei | Tang, Yutong | Tang, Hulin | Li, Wuzhi | Wang, Li

Article Type: Research Article

Abstract: Unmanned sorting technology can significantly improve the transportation efficiency of the logistics industry, and package detection technology is an important component of unmanned sorting. This paper proposes a lightweight deep learning network called EPYOLO, in which a lightweight self-attention feature extraction backbone network named EPnet is also designed. It also reduces the Floating-Point Operations (FLOPs) and parameter count during the feature extraction process through an improved Contextual Transformer-slim (CoTs) self-attention module and GSNConv module. To balance network performance and obtain semantic information for express packages of different sizes and shapes, a multi-scale pyramid structure is adopted using the Feature Pyramid …Network (FPN) and the Path Aggregation Network (PAN). Finally, comparative experiments were conducted with the state-of-the-art (SOTA) model by using a self-built dataset of express packages by using a self-built dataset of express packages, results demonstrate that the mean Average Precision (mAP) of the EPYOLO network reaches 98.8%, with parameter quantity only 11.63% of YOLOv8 s and FLOPs only 9.16% of YOLOv8 s. Moreover, compared to the YOLOv8 s network, the EPYOLO network shows superior detection performance for small targets and overlapping express packages. Show more

Keywords: Object detection, express package detection, lightweight, deep learning

DOI: 10.3233/JIFS-232874

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 12013-12025, 2023

Authors: Li, Yue | Mao, Liang

Article Type: Research Article

Abstract: Automatic detection of defects in mature litchi plays a vital role in the classification of fruit grades. The existing method mainly relies on manual, it is difficult to meet the needs of different varieties of litchi various types of commodity packaging, and there are problems such as low efficiency, high cost and poor quality of goods. To address the above problems, this paper proposes an improved You Only Look Once(YOLO)v7 algorithm for the automatic detection of post-harvest mature litchi epidermal defects. First, a dataset of litchi defects (black spot, fall off, crack) was constructed, in which the train and test …sets had 4133 and 516; Next, A Simple Parameter-Free Attention(SimAM) mechanism is introduced into the original YOLOv7 backbone network, while GSconv is used in the neck instead of convolution, and the shallow network is used instead of the deep network for lateral linking, finally, the Mish function is used as the activation function. Experimental results show the precious and mAP of the original YOLOv7 are 87.66% and 88.98%, and those of the improved YOLOv7 are 91.56% and 93.42%, improvements of 3.9% and 4.44%. A good foundation is laid for the automated classification of ripe litchi after harvesting. Show more

Keywords: YOLOv7, litchi epidermal defects, SimAM, GSconv, shallow networks

DOI: 10.3233/JIFS-233440

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 12027-12036, 2023

Authors: He, Ping | Chen, Jingfang

Article Type: Research Article

Abstract: In this paper, a question answering method is proposed for educational knowledge bases (KBQA) using a question-aware graph convolutional network (GCN). KBQA provides instant tutoring for learners, improving their learning interest and efficiency. However, most open domain KBQA methods model question sentences and candidate answer entities independently, limiting their effectiveness. The proposed method extracts description information and query entity sets for a specific question, processes them with Transformer and pre-trained embeddings of the knowledge base, and extracts a subgraph of candidate answer sets from the knowledge base. The node information is updated by GCN with two attention mechanisms expressed by …the question description and query entity set, respectively. The query description information, query entity set, and candidate entity representation are fused to calculate the score and predict the answer. Experiments on MOOC Q&A dataset show that the proposed method outperforms benchmark models. Show more

Keywords: Educational knowledge base, data-driven intelligent education, question answering method, Graph convolutional network (GCN), prediction accuracy

DOI: 10.3233/JIFS-233915

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 12037-12048, 2023

Authors: Wang, Yashao

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-234605

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 12049-12063, 2023

Authors: Zhao, Jie | Wang, Shuo | Wu, Haotian

Article Type: Research Article

Abstract: To effectively enhance the safety, stability, and economic operation capability of DC microgrids, an optimized control strategy for DC microgrid hybrid energy storage system (HESS)(The abbreviation table is shown in Table 2 ) based on model predictive control theory is proposed. Based on the characteristics of supercapacitors and batteries, system safety requirements, and various constraints, a predictive model for a hybrid energy storage DC microgrid is established. By defining its optimization indicators, designing an energy optimization management strategy, and transforming it into a quadratic programming problem for solution, the reasonable scheduling of power in the DC microgrid has been achieved. In …addition, a power control method was proposed for the system without constraints. The simulation experiment results show that at the initial sampling time, the system operates normally, and the MPC algorithm allocates two types of energy storage devices to discharge to meet the net load demand, without absorbing electricity from the external network. At the 30th sampling point, the net load increases, and the MPC controller obtains the optimal solution of the control problem based on the known net load prediction data at the previous sampling time. It outputs the operating reference values of each output unit at the next time. Starting from the 100th to 199th sampling points, SOC UC falls below the lower limit of the safety interval, and the system enters situation 4 mode. The external network output assists the battery in working. At the 131st sampling point, the net load decreases, the system enters Situation 3 mode, and the battery operates independently. Until the 179th point, SOC B was also below the lower limit of its safety interval, and the system entered situation 5 mode, completely maintaining system power balance by external network power. Starting from point 201, the net load becomes negative, and the system charges the HESS according to instructions and stops the external power grid energy transmission. Conclusion: The feasibility and effectiveness of the proposed optimization management strategy have been verified. Show more

Keywords: DC microgrid, model predictive control, mixed energy storage, objective function, secondary planning

DOI: 10.3233/JIFS-234849

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 12065-12077, 2023