Pub Date : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251874
Rizal Broer Bahaweres, Fajar Agustian, I. Hermadi, A. Suroso, Y. Arkeman
Software defect prediction is a practical approach to improve the quality and efficiency of time and costs for software testing by focusing on defect modules. The dataset of software defect prediction naturally has a class imbalance problem with very few defective modules compared to non-defective modules. This situation has a negative impact on the Neural Network, which can lead to overfitting and poor accuracy. Synthetic Minority Over-sampling Technique (SMOTE) is one of the popular techniques that can solve the problem of class imbalance. However, Neural Network and SMOTE both have hyperparameters which must be determined by the user before the modelling process. In this study, we applied the Neural Networks Based SMOTE, a combination of Neural Network and SMOTE with each hyperparameter of SMOTE and Neural Network that are optimized using random search to solve the class imbalance problem in the six NASA datasets. The results use a 5*5 cross-validation show that increases Bal by 25.48% and Recall by 45.99% compared to the original Neural Network. We also compare the performance of Neural Network-based SMOTE with “Traditional” Machine Learning-based SMOTE. The Neural Network-based SMOTE takes first place in the average rank.
{"title":"Software Defect Prediction Using Neural Network Based SMOTE","authors":"Rizal Broer Bahaweres, Fajar Agustian, I. Hermadi, A. Suroso, Y. Arkeman","doi":"10.23919/EECSI50503.2020.9251874","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251874","url":null,"abstract":"Software defect prediction is a practical approach to improve the quality and efficiency of time and costs for software testing by focusing on defect modules. The dataset of software defect prediction naturally has a class imbalance problem with very few defective modules compared to non-defective modules. This situation has a negative impact on the Neural Network, which can lead to overfitting and poor accuracy. Synthetic Minority Over-sampling Technique (SMOTE) is one of the popular techniques that can solve the problem of class imbalance. However, Neural Network and SMOTE both have hyperparameters which must be determined by the user before the modelling process. In this study, we applied the Neural Networks Based SMOTE, a combination of Neural Network and SMOTE with each hyperparameter of SMOTE and Neural Network that are optimized using random search to solve the class imbalance problem in the six NASA datasets. The results use a 5*5 cross-validation show that increases Bal by 25.48% and Recall by 45.99% compared to the original Neural Network. We also compare the performance of Neural Network-based SMOTE with “Traditional” Machine Learning-based SMOTE. The Neural Network-based SMOTE takes first place in the average rank.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"5 1","pages":"71-76"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82662590","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-01DOI: 10.23919/eecsi50503.2020.9251880
{"title":"[Copyright notice]","authors":"","doi":"10.23919/eecsi50503.2020.9251880","DOIUrl":"https://doi.org/10.23919/eecsi50503.2020.9251880","url":null,"abstract":"","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76125431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251896
Aldi Sidik Permana, E. C. Djamal, Fikri Nugraha, Fatan Kasyidi
Human-robot interaction can be through several ways, such as through device control, sounds, brain, and body, or hand gesture. There are two main issues: the ability to adapt to extreme settings and the number of frames processed concerning memory capabilities. Although it is necessary to be careful with the selection of the number of frames so as not to burden the memory, this paper proposed identifying hand gesture of video using Spatial Convolutional Neural Networks (CNN). The sequential image's spatial arrangement is extracted from the frames contained in the video so that each frame can be identified as part of one of the hand movements. The research used VGG16, as CNN architecture is concerned with the depth of learning where there are 13 layers of convolution and three layers of identification. Hand gestures can only be identified into four movements, namely ‘right’, ‘left’, ‘grab’, and ‘phone’. Hand gesture identification on the video using Spatial CNN with an initial accuracy of 87.97%, then the second training increased to 98.05%. Accuracy was obtained after training using 5600 training data and 1120 test data, and the improvement occurred after manual noise reduction was performed.
{"title":"Hand Movement Identification Using Single-Stream Spatial Convolutional Neural Networks","authors":"Aldi Sidik Permana, E. C. Djamal, Fikri Nugraha, Fatan Kasyidi","doi":"10.23919/EECSI50503.2020.9251896","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251896","url":null,"abstract":"Human-robot interaction can be through several ways, such as through device control, sounds, brain, and body, or hand gesture. There are two main issues: the ability to adapt to extreme settings and the number of frames processed concerning memory capabilities. Although it is necessary to be careful with the selection of the number of frames so as not to burden the memory, this paper proposed identifying hand gesture of video using Spatial Convolutional Neural Networks (CNN). The sequential image's spatial arrangement is extracted from the frames contained in the video so that each frame can be identified as part of one of the hand movements. The research used VGG16, as CNN architecture is concerned with the depth of learning where there are 13 layers of convolution and three layers of identification. Hand gestures can only be identified into four movements, namely ‘right’, ‘left’, ‘grab’, and ‘phone’. Hand gesture identification on the video using Spatial CNN with an initial accuracy of 87.97%, then the second training increased to 98.05%. Accuracy was obtained after training using 5600 training data and 1120 test data, and the improvement occurred after manual noise reduction was performed.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"28 1","pages":"172-176"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78276667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-01DOI: 10.23919/EECSI50503.2020.9251884
S. Mukherjee, Somnath Chakraborty, D. Diwakar, A. Laha, U. Ganguly, S. Ganguly
Traditional Gate engineered Metal Oxide Semiconductor (MOS) technology faced serious challenges in terms of greater sensitivity for target biomolecules and to be utilized as the state-of-the-art Nano-recognition tool. Research on a tunnel field-effect transistor (TFET) started with the aim to achieve fast detection, low power consumption, and its potential for on-chip integration capability. Dielectric Modulated TFET (DMTFET) has established itself to be a primary candidate for sensing both charged and charge-neutral species with volumetric sensitivity. As extended gate DMTFET happens to be inferior to its short gate counterpart, we have devised ways to achieve superior performance only by making variations over structural electrostatics. With the incorporation of most possible ways of modulation, we present two orders of magnitude on-current increment and a considerable percentage of sensitivity improvement over the conventional one. Future scopes having noteworthy diversifications have also been analyzed with proper justification.
{"title":"Investigation of Structural Parameter Variation on Extended Gate TFET for Bio-Sensor Applications","authors":"S. Mukherjee, Somnath Chakraborty, D. Diwakar, A. Laha, U. Ganguly, S. Ganguly","doi":"10.23919/EECSI50503.2020.9251884","DOIUrl":"https://doi.org/10.23919/EECSI50503.2020.9251884","url":null,"abstract":"Traditional Gate engineered Metal Oxide Semiconductor (MOS) technology faced serious challenges in terms of greater sensitivity for target biomolecules and to be utilized as the state-of-the-art Nano-recognition tool. Research on a tunnel field-effect transistor (TFET) started with the aim to achieve fast detection, low power consumption, and its potential for on-chip integration capability. Dielectric Modulated TFET (DMTFET) has established itself to be a primary candidate for sensing both charged and charge-neutral species with volumetric sensitivity. As extended gate DMTFET happens to be inferior to its short gate counterpart, we have devised ways to achieve superior performance only by making variations over structural electrostatics. With the incorporation of most possible ways of modulation, we present two orders of magnitude on-current increment and a considerable percentage of sensitivity improvement over the conventional one. Future scopes having noteworthy diversifications have also been analyzed with proper justification.","PeriodicalId":6743,"journal":{"name":"2020 7th International Conference on Electrical Engineering, Computer Sciences and Informatics (EECSI)","volume":"106 1","pages":"187-191"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85745670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：