Journal of Intelligent & Fuzzy Systems - Volume 36, issue 2

Authors: Li, Hao | Pu, Bin | Kang, Yan | Lu, Chen Yang

Article Type: Research Article

Abstract:  There exists a huge amount of ECG data available in heart disease diagnosis which is found difficult in handing. Recently, many researchers focused on mining disease diagnosis to innovate the hidden patterns and their relevant features. Mining bio-medical data is one of the predominant research areas where clustering techniques are emphasized in heart disease diagnosis. But few people deal with large heart disease datasets and then classify disease data sets according to heart disease feature. We propose a method of anomaly threshold based on multiple classifiers can be well suited to datasets containing abnormal data, and use XGBoost algorithm as …a sub-classifier to process massive ECG data. This research focuses on the heart disease classification problem. The data set is divided into two categories, and then it was classified into more specific categories, experimental results show that this method can improve classification accuracy. The experiments are conducted on massive instances of different heart disease obtained from the hospital actual cases and two data sets of UCI. In fact, we compared SVM, C4.5, Naive Bayes, Logistic, RandomForest and XGBoost algorithms, and found that tree-based model classifier is the best fit to predict arrhythmia. The method proposed in this paper is of great significance to the processing and forecasting system of large medical data sets, and promote the development of wisdom medical care. Show more

Keywords: ECG, heart disease diagnosis, heart disease, intelligent medical

DOI: 10.3233/JIFS-169890

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 2, pp. 1161-1169, 2019

Authors: Hsia, Chih-Hsien | Chien, Chin-Hsiang | Hsu, Hao-Wei | Chiang, Jen-Shiun | Tseng, Hsien-Wei

Article Type: Research Article

Abstract:  This study proposes a method that uses the Time-of-Flight (ToF) for an assisting device. A contactless Kinect device is used to obtain images of basketball players Field Goal Shooting (FGS) is used to detect posture. The method classifies the FGS postures of players into 3-stage routines for analysis. The ToF first sets the posture correcting conditions using the data provided by professional players and analyzes the postures with the highest and lowest FGS percentage and the most and least data from the statistical results. This gives a stable FGS reference value for the basketball player. The proposed technique has a …higher correction rate for the FGS posture (for 100 continuous shots) for a player and allows processing in real-time, with a delay of only 0.4μ s. Show more

Keywords: Time-of-Flight (ToF), Field Goal Shooting (FGS), Player movement correction

DOI: 10.3233/JIFS-169891

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 2, pp. 1171-1181, 2019

Authors: Kang, Yan | Li, Hao | Lu, Chenyang | Pu, Bin

Article Type: Research Article

Abstract: In this paper, we present a novel method for data-mining large informal product descriptions rather than extracting requirement features from proprietary project repositories. Our algorithm hybridizes deep-learning algorithms such as word2vec and recurrent neural network (RNN) with classical techniques to improve the performance of text analysis. Given the inaccuracy and incompleteness of the software requirement descriptions on websites, the instance-transfer learning method is utilized to construct a robust classifier and predict domain feature knowledge based on domain knowledge similar to the target domain. The bagging clustering algorithm is utilized with multiple clustering algorithms to help select transfer instances. [Author to …confirm changes.]The RNN-based algorithm is utilized as a useful alternative to predict missing features by studying the requirement descriptions of a related software system, while word2vec is utilized to extract sensible feature keywords for the specific software domain. [Author to confirm changes.]Our RNN model for every subclass is based on the clustering result, and we construct subclass classifiers to recommend requirement keywords. Requirement features recommended by our algorithm potentially increase opportunities for requirement classification, promote software requirement quality, and deliver more reliable software products. We explain the details of implementation and perform experimental work on real requirement descriptions to establish its worth. Show more

Keywords: Word2vec, RNN, transfer learning, feature model, software requirement

DOI: 10.3233/JIFS-169892

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 2, pp. 1183-1191, 2019

Authors: Qian, Junbing | Bao, Liping | Pan, Nan | Ji, Chuankun

Article Type: Research Article

Abstract: This paper presents a method to suppress the thrust disturbance for the permanent magnet linear synchronous motor (PMLSM), which is used as an actuator in an active vibration absorber. Because the characteristics of the working transmission structure of the PMLSM are relatively special, the thrust ripple and load disturbance will yield in the operation, and they will directly affect the control accuracy and positioning precision. Simultaneously, the thrust of the PMLSM directly acts on the object, and the thrust disturbance of the PMLSM will appear in the payload of the vibration absorber. Based on the actuator, the Proportional-integral-derivative (PID) control …is investigated, and the transfer function of the actuator is obtained. Then, the thrust disturbance of the PMLSM is theoretical studied by analyzing the current flows through the PMLSM. A new method of trajectory overlay planning is presented, where the original input is divided into two inputs with different amplitudes and they suppress each other. Based on the method, the PID control can restrain the disturbance to achieve a predesigned output. The effectiveness of the proposed method is verified by simulation and experimental results. Show more

Keywords: PMLSM, actuator, thrust disturbance, active vibration absorber, PID control

DOI: 10.3233/JIFS-169893

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 2, pp. 1193-1203, 2019

Authors: Lu, Guang-Qing | Čereška, Audrius | Augustinavičius, Giedrius | Maskeliunas, Rimas | Ragulskis, Minvydas

Article Type: Research Article

Abstract: A novel planar precise positioning stage on the rotating platform for calibration on raster scales of the rotary encoder is proposed in this paper. The monolithic structure is constructed with a flexible element and two ultra-fine adjustment screws. The structure for required motion is designed and optimized by software package of Solid Works Simulation, and then their performances are evaluated using numerical modelling approach. The mathematical model is then verified by resorting to finite element analysis (FEA) and experiment. The established analytical FEA models are helpful for optimizing a reliable architecture and improving performance of the precise positioning system.

Keywords: Positioning stage, flexible element, finite element analysis, simulation

DOI: 10.3233/JIFS-169894

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 2, pp. 1205-1214, 2019

Authors: Luo, Yung-Chang | Chen, Yu-Hsiang

Article Type: Research Article

Abstract: In this study an adaptive on-line speed estimation approach has been proposed for a sensor-less indirect air-gap field orientation controlled (AGFOC) induction motor (IM) drive. The indirect AGFOC IM drive was established by utilizing the stator current and air-gap flux. The estimated synchronous speed was derived from the developed reactive power based adaptive air-gap flux estimator, and the estimation of rotor speed was made by subtracting the slip speed from the estimated synchronous speed. Speed estimation and control by the AGFOC IM drive could be extended to include constant power operation mode by utilizing the field weakening technique. The MATLAB® …∖Simulink ® toolbox was used to simulate this system and all the control algorithms were realized using a TI DSP 6713-and-F2812 card to generate pulse width modulation (PWM) signals to the power stage, actuate an IM to validate this approach (sensor-less AGFOC). Both simulation and experimental responses confirmed the effectiveness of the proposed system. Show more

Keywords: Speed estimation, air-gap field orientation controlled (AGFOC), adaptive air-gap flux estimator, field weakening technique

DOI: 10.3233/JIFS-169895

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 2, pp. 1215-1230, 2019

Authors: Hu, Ming-Sen

Article Type: Research Article

Abstract: The chemical compound NOx is one of the biggest sources of air pollution, and presently Selective Catalytic Reduction (SCR) is the most frequently used method to dispose of NOx. A proportion of NH3 as a reducer is injected into the system and mixed with the NOx waste gas so as to be treated thoroughly. With sufficient O2 , NOx is reduced to innocuous N2 and H2 O by the catalytic reduction of the catalyst. The purpose of this study is to develop a monitoring system for blending the mixing ratio and concentration of NO automatically and for SCR …catalyst De-NOx performance test analysis. This monitoring system enables the user to set various control parameters and instrument parameters, executes user calibration operations (e.g. zero calibration, full scale calibration and low concentration calibration), and tests the De-NOx performance of the plate type catalyst. In the catalyst De-NOx performance testing process, the system prepares the NO mixing ratio and concentration automatically according to the blending concentration and temperature control curves set by the user and then implements the catalyst bed multi-stage temperature control, so as to complete NO or NH3 concentration detection and automatic data logging as the base of De-NOx performance test analysis. Show more

Keywords: Nitrogen oxides, selective catalytic reduction, De-NOx performance, automatic control system

DOI: 10.3233/JIFS-169896

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 2, pp. 1231-1244, 2019

Authors: Weng, Jian-Fu | Su, Kuo-Lan

Article Type: Research Article

Abstract: Automated guided vehicle is the most important research issues for mobile robot development. The important research issue of the automated guided vehicle (AGV) is navigation system in recent years. Navigation system can be divided into self-localization, path planning and obstacle avoidance for indoor service execution. The application fields have security patrol or package delivery. Furthermore, recharging is necessary before the battery power has exhausted. The paper develops the automated guided vehicle that is designed and built with a 4WD mecanum wheel platform. Due to the laser ranger’s high precision, we applied the laser range finder to achieve the environment map …construction, so the self-localization via particles filter (PF) and the path planning algorithms can be utilized with the map. The practical motion and safety avoidance strategies are also proposed for robot motion control. Finally, the sensory fusion methods are also integrated with the laser ranger and RGB-D camera for automated guided vehicle while performing the docking process. The experimental results show the successful demonstrations of autonomous patrol and docking for self-recharging. Show more

Keywords: Automated guided vehicle, particles filter, sensory fusion methods, RGB-D camera

DOI: 10.3233/JIFS-169897

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 2, pp. 1245-1257, 2019

Authors: Wong, Ching-Chang | Chen, Hua-Ching | Lee, Chin-Tan | Wang, Chien-Chung | Feng, Hsuan-Ming.

Article Type: Research Article

Abstract: A high sensory robot system conveniently controls the mobile robot action through the Natural human-machine interaction. Therefore, different hand motions are realized to approximate the required service tasks. Magnetic sensors are located at the defined path to guide the robot platform. Three ultrasonic sensors settle at the outside of mobile robot platform to detect possible blocks in an unknown environment. The RFID reader is proposed to understand the real position of mobile robot in the dynamic space. In data fusion machine, some matched position signals are selected into database for extracting the possible tracks in advance. Therefore, the appropriate path …is remembered and will be reloaded again to guide the mobile robot into the desired target at the patrol mode. In practical experiments, people communicate with robot through the hand recognitions of Kinect sensor. Sensor information is suitable to handle various service tasks, i.e. pull the pallet in or extend it out, by the human-like movement. A fuzzy system with suitable rules is utilized to drive the server motor for achieving the great performance. The robot system is not only controlled by an interactive interface but also reached an autonomous navigation by extracting the appropriate mapping information. The high sensory robot system obtains interactive actions with the combinations of image recognitions, suitable path planning and obstacle detecting technologies to approach the guiding goal. In the implementation of hardware, the architectures of mobile robot and motor drivers are completely assembled to support the home tasks. The soft fuzzy system generates the robust robot regulation to automatically achieve the perfect feasibility of fetch-and-give tasks. Show more

Keywords: High sensory, mobile robot, fuzzy system, indoor applications

DOI: 10.3233/JIFS-169898

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 2, pp. 1259-1271, 2019

Authors: You, Peng-Sheng | Hsieh, Yi-Chih

Article Type: Research Article

Abstract: Bicycle-sharing systems are commonly established at geographically dispersed locations to create their rental service networks. To provide customers with flexibility and convenience, bicycle-sharing systems commonly allow them to pick up bicycles from one station and return them to a different one. However, allowing customers to return their rented bicycles to different stations can possibly lead to an imbalance in the bicycle rental network. One of the approaches to overcome the bicycle imbalance problem is to apply dynamic pricing to motivate consumers to return the rented bicycles to stations without a sufficient number of bicycles. This study developed a constrained dynamic …pricing model to address the bicycle imbalance problem. Moreover, this study aimed to maximize the total revenues over a planning horizon through dynamic pricing strategies. We identify some necessary conditions for optimal sale prices. Using these conditions, we develop a heuristic algorithm based on linear programming and an evolutionary algorithm to efficiently produce comprise solutions. The proposed model and solution procedure were applied to analyze the bicycle system in Taiwan. Sensitivity analyses were also conducted to investigate the effects of various system parameters. Show more

Keywords: Bicycle sharing, rental network, imbalance, dynamic pricing, algorithm

DOI: 10.3233/JIFS-169899

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 2, pp. 1273-1285, 2019