Pub Date : 2021-09-01DOI: 10.6688/JISE.202109_37(5).0001
Ravinder Ahuja, S. C. Sharma
Machine learning has emerged as the most important and widely used tool in resolving the administrative and other educational related problems. Most of the research in the educational field centers on demonstrating the student's potential rather than focusing on faculty quality. In this paper the performance of the instructor is evaluated through feedback collected from students in the questionnaire form. The unlabelled dataset is taken from UCI machine learning repository consisting of 5820 records with 33 attributes. Firstly, the dataset is labelled(three labels) using agglomerative clustering and the k-means algorithms. Further, five feature selection techniques (Random Forest,Principal Component Analysis, Recursive Feature Selection, Univariate Feature Selection, and Genetic Algorithm) are applied to extract essential features. After feature selection, twelve classification algorithms (K Nearest Neighbor, XGBoost, Multi-Layer Perceptron, AdaBoost, Random Forest, Logistic Regression, Decision Tree, Bagging, LightGBM, Support Vector Machine, Extra Tree and Naive Bayes) are applied using Python language. Out of all algorithms applied, Support Vector Machine with PCA feature selection technique has given the highest accuracy value 99.66%, recall value 99.66%, precision value 99.67%, and f-score value 99.67%. To prove that results are statistically different, we have applied ANOVA one way test.
{"title":"Exploiting Machine Learning and Feature Selection Algorithms to Predict Instructor Performance in Higher Education","authors":"Ravinder Ahuja, S. C. Sharma","doi":"10.6688/JISE.202109_37(5).0001","DOIUrl":"https://doi.org/10.6688/JISE.202109_37(5).0001","url":null,"abstract":"Machine learning has emerged as the most important and widely used tool in resolving the administrative and other educational related problems. Most of the research in the educational field centers on demonstrating the student's potential rather than focusing on faculty quality. In this paper the performance of the instructor is evaluated through feedback collected from students in the questionnaire form. The unlabelled dataset is taken from UCI machine learning repository consisting of 5820 records with 33 attributes. Firstly, the dataset is labelled(three labels) using agglomerative clustering and the k-means algorithms. Further, five feature selection techniques (Random Forest,Principal Component Analysis, Recursive Feature Selection, Univariate Feature Selection, and Genetic Algorithm) are applied to extract essential features. After feature selection, twelve classification algorithms (K Nearest Neighbor, XGBoost, Multi-Layer Perceptron, AdaBoost, Random Forest, Logistic Regression, Decision Tree, Bagging, LightGBM, Support Vector Machine, Extra Tree and Naive Bayes) are applied using Python language. Out of all algorithms applied, Support Vector Machine with PCA feature selection technique has given the highest accuracy value 99.66%, recall value 99.66%, precision value 99.67%, and f-score value 99.67%. To prove that results are statistically different, we have applied ANOVA one way test.","PeriodicalId":50177,"journal":{"name":"Journal of Information Science and Engineering","volume":"41 1","pages":"993-1009"},"PeriodicalIF":1.1,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86839919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-01DOI: 10.6688/JISE.202109_37(5).0016
Guangyuan Zhang, Ning Wang
By harnessing human intelligence, crowdsourcing can solve problems that are difficult for computers. A fundamental problem in crowdsourcing is truth inference, which decides how to infer the truth effectively. We propose MFICrowd, a novel truth inference framework which takes multi-factor into account for profiling workers accurately and improving answer accuracy effectively. Based on the diversity degree of task domains and the semantic similarity of candidate answers, we quantify task difficulty for modeling tasks and workers objectively and exactly. By integrating task domains, task difficulty and answer similarity into truth inference, MFICrowd aggregates answers from a group of workers effectively. The comprehensive experimental results on both simulated and real datasets show that our truth inference framework based on multi-factor is effective, and it outperforms existing state-of-the-art approaches in both answer accuracy and time efficiency.
{"title":"Multi-Factor Influencing Truth Inference in Crowdsourcing","authors":"Guangyuan Zhang, Ning Wang","doi":"10.6688/JISE.202109_37(5).0016","DOIUrl":"https://doi.org/10.6688/JISE.202109_37(5).0016","url":null,"abstract":"By harnessing human intelligence, crowdsourcing can solve problems that are difficult for computers. A fundamental problem in crowdsourcing is truth inference, which decides how to infer the truth effectively. We propose MFICrowd, a novel truth inference framework which takes multi-factor into account for profiling workers accurately and improving answer accuracy effectively. Based on the diversity degree of task domains and the semantic similarity of candidate answers, we quantify task difficulty for modeling tasks and workers objectively and exactly. By integrating task domains, task difficulty and answer similarity into truth inference, MFICrowd aggregates answers from a group of workers effectively. The comprehensive experimental results on both simulated and real datasets show that our truth inference framework based on multi-factor is effective, and it outperforms existing state-of-the-art approaches in both answer accuracy and time efficiency.","PeriodicalId":50177,"journal":{"name":"Journal of Information Science and Engineering","volume":"29 1","pages":"1231-1246"},"PeriodicalIF":1.1,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83547032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-09-01DOI: 10.6688/JISE.202109_37(5).0006
A. Rosário, Luís Bettencourt Moniz, Rui Cruz
{"title":"Data Science Applied to Marketing: A Literature Review","authors":"A. Rosário, Luís Bettencourt Moniz, Rui Cruz","doi":"10.6688/JISE.202109_37(5).0006","DOIUrl":"https://doi.org/10.6688/JISE.202109_37(5).0006","url":null,"abstract":"","PeriodicalId":50177,"journal":{"name":"Journal of Information Science and Engineering","volume":"251 1","pages":"1067-1081"},"PeriodicalIF":1.1,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72886931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-19DOI: 10.21203/rs.3.rs-552378/v1
Zhifang Liu
Today's technology products are changing with each day, the purpose is to bring more convenience to people, but also the competition among the technology industries is more competitive. In such environment, whether the company's decision-making is correct or not will directly affect the future development of an enterprise. Therefore, how an enterprise can formulate and construct a set of appropriate decision-making systems to accurately predict the future market will be the first important issue for enterprises. This research proposed an artificial intelligence predicting system to estimate manufacturing capacities and client demands, and providing it to manufacturing managers as a reference for inventory arrangements so that inventory can be adjusted appropriately to avoid excessive inventory levels. In recent years, neural networks have been widely and effectively applied to many predicting problems. The main reason is that most of the predicting problems are nonlinear models. And the backward neural network has the ability to construct nonlinear models. In this study, a predicting model combining grey correlation and neural network will be used to establish a high-accuracy predition system for the production predict of IC product. First, grey correlation analysis will be used to screen out the most relevant factors among many factors. And then put these factors into the neural network prediction model for training and prediction. The results show that the training prediction error and the empirical error value are about 14%. This value indicates that the prediction ability is better, so the proposed prediction model can be applied to the prediction of IC substrate production. It provided a predictive reference material and provide decision making with a more accurate, convenient and a fast tool to enhance the company’s competitiveness.
{"title":"Using Artificial Intelligence in IC Substrate Production Predicting","authors":"Zhifang Liu","doi":"10.21203/rs.3.rs-552378/v1","DOIUrl":"https://doi.org/10.21203/rs.3.rs-552378/v1","url":null,"abstract":"\u0000 Today's technology products are changing with each day, the purpose is to bring more convenience to people, but also the competition among the technology industries is more competitive. In such environment, whether the company's decision-making is correct or not will directly affect the future development of an enterprise. Therefore, how an enterprise can formulate and construct a set of appropriate decision-making systems to accurately predict the future market will be the first important issue for enterprises. This research proposed an artificial intelligence predicting system to estimate manufacturing capacities and client demands, and providing it to manufacturing managers as a reference for inventory arrangements so that inventory can be adjusted appropriately to avoid excessive inventory levels. In recent years, neural networks have been widely and effectively applied to many predicting problems. The main reason is that most of the predicting problems are nonlinear models. And the backward neural network has the ability to construct nonlinear models. In this study, a predicting model combining grey correlation and neural network will be used to establish a high-accuracy predition system for the production predict of IC product. First, grey correlation analysis will be used to screen out the most relevant factors among many factors. And then put these factors into the neural network prediction model for training and prediction. The results show that the training prediction error and the empirical error value are about 14%. This value indicates that the prediction ability is better, so the proposed prediction model can be applied to the prediction of IC substrate production. It provided a predictive reference material and provide decision making with a more accurate, convenient and a fast tool to enhance the company’s competitiveness.","PeriodicalId":50177,"journal":{"name":"Journal of Information Science and Engineering","volume":"79 1","pages":"637-654"},"PeriodicalIF":1.1,"publicationDate":"2021-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73334808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-01DOI: 10.6688/JISE.202107_37(4).0008
J. Tsai, Y. Han
{"title":"A Cooperative Rotational Sweep Scheme to Bypass Network Holes in Wireless Geographic Routing","authors":"J. Tsai, Y. Han","doi":"10.6688/JISE.202107_37(4).0008","DOIUrl":"https://doi.org/10.6688/JISE.202107_37(4).0008","url":null,"abstract":"","PeriodicalId":50177,"journal":{"name":"Journal of Information Science and Engineering","volume":"136 1","pages":"859-883"},"PeriodicalIF":1.1,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77846952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-01DOI: 10.6688/JISE.202107_37(4).0006
Natinai Jinsakul, Cheng-Fa Tsai, Chia-En Tsai
Chicken cell abnormal identification by manual method that clearly lacks speed and accuracy. However, the success of deep learning techniques from the convolutional neural network (CNN), it may be providing solutions to cell biology laboratory tasks. This paper collected the novel chicken cell microscopic image datasets for training the different kinds of CNN models and optimizers to find promising applications that might be developed. The top model indicates that ResNet34 with Adam optimizer achieved training accuracy of 100%, testing accuracy of 98.14%, and the lower time on the outstanding confusion matrix. In addition, the validation result represented correct identification, guaranteeing by experts. This study shows the potential method to be improved to an application of identification systems in the actual animal and biology laboratories.
{"title":"Anomaly Chicken Cell Identification Using Deep Learning Techniques","authors":"Natinai Jinsakul, Cheng-Fa Tsai, Chia-En Tsai","doi":"10.6688/JISE.202107_37(4).0006","DOIUrl":"https://doi.org/10.6688/JISE.202107_37(4).0006","url":null,"abstract":"Chicken cell abnormal identification by manual method that clearly lacks speed and accuracy. However, the success of deep learning techniques from the convolutional neural network (CNN), it may be providing solutions to cell biology laboratory tasks. This paper collected the novel chicken cell microscopic image datasets for training the different kinds of CNN models and optimizers to find promising applications that might be developed. The top model indicates that ResNet34 with Adam optimizer achieved training accuracy of 100%, testing accuracy of 98.14%, and the lower time on the outstanding confusion matrix. In addition, the validation result represented correct identification, guaranteeing by experts. This study shows the potential method to be improved to an application of identification systems in the actual animal and biology laboratories.","PeriodicalId":50177,"journal":{"name":"Journal of Information Science and Engineering","volume":"10 1","pages":"827-838"},"PeriodicalIF":1.1,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74718557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-07-01DOI: 10.6688/JISE.202107_37(4).0005
Zih-Ching Chen, Sin-Ye Jhong, Chin-Hsien Hsia
Palm-vein authentication is a secure and highly accurate vein feature authentication technology that has recently gained a lot of attention. Convolutional neural networks (CNNs) provide relatively high performance in the field of image processing, computer vision, and have been adapted for feature learning of palm-vein images. However, they often require high computation that not only are infeasible for real-time vein verification but also a challenge to apply on mobile devices. To address this limitation, we proposed a lightweight MobileNet based deep learning (DL) architecture with depthwise separable convolution (DSC) and adopt a knowledge distillation (KD) method to learn the knowledge from the more complex CNN, which makes it small but effective. Through the depth of separable convolution, the number of model parameters is significantly decreased, while still remaining high accuracy and stable performance. Experiments demonstrated that the size of the proposed model is 100 times less than the Inception_v3 model, while the performance can go beyond 98% correct identification rate (CIR) for the CASIA database.
{"title":"Design of a Lightweight Palmf-Vein Authentication System Based on Model Compression","authors":"Zih-Ching Chen, Sin-Ye Jhong, Chin-Hsien Hsia","doi":"10.6688/JISE.202107_37(4).0005","DOIUrl":"https://doi.org/10.6688/JISE.202107_37(4).0005","url":null,"abstract":"Palm-vein authentication is a secure and highly accurate vein feature authentication technology that has recently gained a lot of attention. Convolutional neural networks (CNNs) provide relatively high performance in the field of image processing, computer vision, and have been adapted for feature learning of palm-vein images. However, they often require high computation that not only are infeasible for real-time vein verification but also a challenge to apply on mobile devices. To address this limitation, we proposed a lightweight MobileNet based deep learning (DL) architecture with depthwise separable convolution (DSC) and adopt a knowledge distillation (KD) method to learn the knowledge from the more complex CNN, which makes it small but effective. Through the depth of separable convolution, the number of model parameters is significantly decreased, while still remaining high accuracy and stable performance. Experiments demonstrated that the size of the proposed model is 100 times less than the Inception_v3 model, while the performance can go beyond 98% correct identification rate (CIR) for the CASIA database.","PeriodicalId":50177,"journal":{"name":"Journal of Information Science and Engineering","volume":"16 1","pages":"809-825"},"PeriodicalIF":1.1,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77644310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-01DOI: 10.6688/JISE.202105_37(3).0002
Hanhua Zhu, Tomoyuki Kaneko
{"title":"Residual Network for Deep Reinforcement Learning with Attention Mechanism","authors":"Hanhua Zhu, Tomoyuki Kaneko","doi":"10.6688/JISE.202105_37(3).0002","DOIUrl":"https://doi.org/10.6688/JISE.202105_37(3).0002","url":null,"abstract":"","PeriodicalId":50177,"journal":{"name":"Journal of Information Science and Engineering","volume":"52 1","pages":"517-533"},"PeriodicalIF":1.1,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83957901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Local Community Detection by Local Structure Expansion and Exploring the Local Communities for Target Nodes in Complex Networks","authors":"Hao-Shang Ma, Shiou-Chi Li, Zhi-Jia Jian, You-Hua Kuo, You-Hua Huang","doi":"10.6688/JISE.20210537(3).0001","DOIUrl":"https://doi.org/10.6688/JISE.20210537(3).0001","url":null,"abstract":"","PeriodicalId":50177,"journal":{"name":"Journal of Information Science and Engineering","volume":"17 1","pages":"499-511"},"PeriodicalIF":1.1,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85417010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-01DOI: 10.6688/JISE.20210537(3).0003
Hsiang-Yu Yang, Chien-Chou Wong, Sai-Keung Wong
This paper focuses on push-manipulation in an agent-based animation. A policy is learned in a learning session in which an agent perceives its own internal state and the surrounding environment and determines its actions. In each time step, the agent performs an action. Then it receives a reward that is a combination of different types of reward terms, including forward progress, orientation progress, collision avoidance, and finish time. Based on the received reward, the policy is improved gradually. We develop a system that controls an agent to transport a box. We investigate the effects of each reward term and study the impacts of various inputs on the performance of the agent in environments with obstacles. The inputs include the number of rays for perceiving the environment, obstacle settings, and box sizes. We performed some experiments and analyzed our findings in details. The experiment results show that the behaviors of agents are affected by the reward terms and various inputs in certain aspects, such as the movement smoothness of the agents, wandering about the box, loss of orientation, sensitivity about collision avoidance, and pushing styles.
{"title":"A Study on Agent-Based Box-Manipulation Animation Using Deep Reinforcement Learning","authors":"Hsiang-Yu Yang, Chien-Chou Wong, Sai-Keung Wong","doi":"10.6688/JISE.20210537(3).0003","DOIUrl":"https://doi.org/10.6688/JISE.20210537(3).0003","url":null,"abstract":"This paper focuses on push-manipulation in an agent-based animation. A policy is learned in a learning session in which an agent perceives its own internal state and the surrounding environment and determines its actions. In each time step, the agent performs an action. Then it receives a reward that is a combination of different types of reward terms, including forward progress, orientation progress, collision avoidance, and finish time. Based on the received reward, the policy is improved gradually. We develop a system that controls an agent to transport a box. We investigate the effects of each reward term and study the impacts of various inputs on the performance of the agent in environments with obstacles. The inputs include the number of rays for perceiving the environment, obstacle settings, and box sizes. We performed some experiments and analyzed our findings in details. The experiment results show that the behaviors of agents are affected by the reward terms and various inputs in certain aspects, such as the movement smoothness of the agents, wandering about the box, loss of orientation, sensitivity about collision avoidance, and pushing styles.","PeriodicalId":50177,"journal":{"name":"Journal of Information Science and Engineering","volume":"16 4 1","pages":"535-551"},"PeriodicalIF":1.1,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79805935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：