Pub Date : 2018-07-01DOI: 10.1109/ICSCEE.2018.8538376
Fadhil Mukhlif, Kamarul Ariffin Bin Nooridin, Y. Al-Gumaei, Abdu Saif AL-Rassas
The design of traditional mobile wireless network emphasises on large capacity as well as ubiquitous access. However, environmental protection and energy saving may soon become inevitable trends due to rising global demands. In the wireless networking field, researchers should shift their focus towards efficient networks and energy harvesting (EH). In this work, we consider energy efficiency and EH to address the issue of energy shortage, which also represents the ratio of the quantity of data that have been transferred to the dissipated energy within the system, simultaneously. The simulation-based mathematics signifies the relation between energy efficiency $(C_{E})$ against the training interval $(T_{t})$ and how the energy efficiency is impacted by the change in block size and number of users.
{"title":"Energy Harvesting For Efficient 5G Networks","authors":"Fadhil Mukhlif, Kamarul Ariffin Bin Nooridin, Y. Al-Gumaei, Abdu Saif AL-Rassas","doi":"10.1109/ICSCEE.2018.8538376","DOIUrl":"https://doi.org/10.1109/ICSCEE.2018.8538376","url":null,"abstract":"The design of traditional mobile wireless network emphasises on large capacity as well as ubiquitous access. However, environmental protection and energy saving may soon become inevitable trends due to rising global demands. In the wireless networking field, researchers should shift their focus towards efficient networks and energy harvesting (EH). In this work, we consider energy efficiency and EH to address the issue of energy shortage, which also represents the ratio of the quantity of data that have been transferred to the dissipated energy within the system, simultaneously. The simulation-based mathematics signifies the relation between energy efficiency $(C_{E})$ against the training interval $(T_{t})$ and how the energy efficiency is impacted by the change in block size and number of users.","PeriodicalId":265737,"journal":{"name":"2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE)","volume":"205 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132022661","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 : 2018-07-01DOI: 10.1109/ICSCEE.2018.8538379
Umara Noor, Z. Anwar, Umara Noor, Z. Anwar, Zahid Rashid
Tactics Techniques and Procedures (TTPs) in cyber domain is an important threat information that describes the behavior and attack patterns of an adversary. Timely identification of associations between TTPs can lead to effective strategy for diagnosing the Cyber Threat Actors (CTAs) and their attack vectors. This study profiles the prevalence and regularities in the TTPs of CTAs. We developed a machine learning-based framework that takes as input Cyber Threat Intelligence (CTI) documents, selects the most prevalent TTPs with high information gain as features and based on them mine interesting regularities between TTPs using Association Rule Mining (ARM). We evaluated the proposed framework with publicly available TTPbased CTI documents. The results show that there are 28 TTPs more prevalent than the other TTPs. Our system identified 155 interesting association rules among the TTPs of CTAs. A summary of these rules is given to effectively investigate threats in the network.
{"title":"An Association Rule Mining-Based Framework for Profiling Regularities in Tactics Techniques and Procedures of Cyber Threat Actors","authors":"Umara Noor, Z. Anwar, Umara Noor, Z. Anwar, Zahid Rashid","doi":"10.1109/ICSCEE.2018.8538379","DOIUrl":"https://doi.org/10.1109/ICSCEE.2018.8538379","url":null,"abstract":"Tactics Techniques and Procedures (TTPs) in cyber domain is an important threat information that describes the behavior and attack patterns of an adversary. Timely identification of associations between TTPs can lead to effective strategy for diagnosing the Cyber Threat Actors (CTAs) and their attack vectors. This study profiles the prevalence and regularities in the TTPs of CTAs. We developed a machine learning-based framework that takes as input Cyber Threat Intelligence (CTI) documents, selects the most prevalent TTPs with high information gain as features and based on them mine interesting regularities between TTPs using Association Rule Mining (ARM). We evaluated the proposed framework with publicly available TTPbased CTI documents. The results show that there are 28 TTPs more prevalent than the other TTPs. Our system identified 155 interesting association rules among the TTPs of CTAs. A summary of these rules is given to effectively investigate threats in the network.","PeriodicalId":265737,"journal":{"name":"2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134643862","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 : 2018-07-01DOI: 10.1109/ICSCEE.2018.8538361
Faiza Tahir, Mahum Adil
Now a day’s software engineering has inclination towards formality. Many formal and mathematical mergers have taken place in theoretical software engineering. Giving mathematical foundation to various aspects of software engineering enhance their practicability and predictability. Cost estimation models like Constructive Cost Model (COCOMO) is one major proven example. COCOMO effort and time calculation is based on mathematical foundations. Several cost drivers having mathematical values also contributed in these calculations. This paper presents a sensitivity analysis using on Constructive Cost Model II (COCOMO II) and their relationships with the projects taken on undergraduate level using web based estimation tool Estimator. The analysis studies the behavior of cost drivers having higher impact on these projects and needs detail understanding and some has low impact. This categorization further used in functional and nonfunctional requirements level. As which nonfunctional requirement need more and detailed understanding at undergraduate study level
{"title":"An Empirical Analysis of Cost Estimation Models on Undergraduate Projects Using COCOMO II","authors":"Faiza Tahir, Mahum Adil","doi":"10.1109/ICSCEE.2018.8538361","DOIUrl":"https://doi.org/10.1109/ICSCEE.2018.8538361","url":null,"abstract":"Now a day’s software engineering has inclination towards formality. Many formal and mathematical mergers have taken place in theoretical software engineering. Giving mathematical foundation to various aspects of software engineering enhance their practicability and predictability. Cost estimation models like Constructive Cost Model (COCOMO) is one major proven example. COCOMO effort and time calculation is based on mathematical foundations. Several cost drivers having mathematical values also contributed in these calculations. This paper presents a sensitivity analysis using on Constructive Cost Model II (COCOMO II) and their relationships with the projects taken on undergraduate level using web based estimation tool Estimator. The analysis studies the behavior of cost drivers having higher impact on these projects and needs detail understanding and some has low impact. This categorization further used in functional and nonfunctional requirements level. As which nonfunctional requirement need more and detailed understanding at undergraduate study level","PeriodicalId":265737,"journal":{"name":"2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116087790","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 : 2018-07-01DOI: 10.1109/ICSCEE.2018.8538404
Satyo Pradana, A. Syahriar, Ahmad H. Lubis, S. Rahardjo
Long distance Optical Communications are affected by many problems; loss of signal is one of them. Erbium Doped Fiber Amplifier (EDFA) is the key to solve it. By using Semiconductor Laser as pumping source for EDFA, the signal can be brought back to it is normal condition. EDFA has a good wavelength operation at 1480nm. To achieve selected wavelength, we must construct the Semiconductor Laser that suitable in 1480nm. In that case, InGaAs and InGaAsP are the base materials to construct the Semiconductor Laser. At wavelength of 1480nm the materials that used are InGaAs and InGaAsP. The reason is it is suitable for wavelength selection. By using selected wavelength and materials, the Semiconductor Laser can be produced properly. Also, determining the parameter is the important thing to construct the Laser. By using Rate Equation, comparison of output power for InGaAs and InGaAsP at wavelength of 1480nm based on rate equation and can obtained four result. Those are injection current vs voltage, carrier density, photon density and output power vs injection current.
{"title":"Comparison Power of Semiconductor Lasers at wavelength 1480nm using InGaAs InGaAsP Materials for EDFA Pumping Scheme","authors":"Satyo Pradana, A. Syahriar, Ahmad H. Lubis, S. Rahardjo","doi":"10.1109/ICSCEE.2018.8538404","DOIUrl":"https://doi.org/10.1109/ICSCEE.2018.8538404","url":null,"abstract":"Long distance Optical Communications are affected by many problems; loss of signal is one of them. Erbium Doped Fiber Amplifier (EDFA) is the key to solve it. By using Semiconductor Laser as pumping source for EDFA, the signal can be brought back to it is normal condition. EDFA has a good wavelength operation at 1480nm. To achieve selected wavelength, we must construct the Semiconductor Laser that suitable in 1480nm. In that case, InGaAs and InGaAsP are the base materials to construct the Semiconductor Laser. At wavelength of 1480nm the materials that used are InGaAs and InGaAsP. The reason is it is suitable for wavelength selection. By using selected wavelength and materials, the Semiconductor Laser can be produced properly. Also, determining the parameter is the important thing to construct the Laser. By using Rate Equation, comparison of output power for InGaAs and InGaAsP at wavelength of 1480nm based on rate equation and can obtained four result. Those are injection current vs voltage, carrier density, photon density and output power vs injection current.","PeriodicalId":265737,"journal":{"name":"2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121118474","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 : 2018-07-01DOI: 10.1109/ICSCEE.2018.8538413
SK Ahammad Fahad, Abdulsamad E. Yahya
A tremendous amount of data comes with a vast amount of knowledge. Decent use of the persistent information can assist to overcome provocations and support to establish further sophisticated judgment. Data visualization techniques are authenticated scientifically as thousand times reliable rather than textual representation. The premature data visualization system met some difficulties and there has some solution for handle this kind of big quantity of data. Data science used two distinct languages Python and R to visualize big data undeviatingly. There also have a lot of tools in operating business. This paper is focused on the visualization technique of Python and R. R appears including the extraordinary visualization library alike ggplot2, leaflet, and lattice to defeat the provocation of the extensive volume. Python has several particular libraries for data visualization. Commonly they are Bokeh, Seaborn, Altair, ggplot and Pygal. Also, with most modern, secure and powerful zero coding GUI's accessories to describe big data visualization for genuine recognition with practical determination. Method and process of visual description of data are significant to recover specific knowledge from the large-scale dataset.
{"title":"Big Data Visualization: Allotting by R and Python with GUI Tools","authors":"SK Ahammad Fahad, Abdulsamad E. Yahya","doi":"10.1109/ICSCEE.2018.8538413","DOIUrl":"https://doi.org/10.1109/ICSCEE.2018.8538413","url":null,"abstract":"A tremendous amount of data comes with a vast amount of knowledge. Decent use of the persistent information can assist to overcome provocations and support to establish further sophisticated judgment. Data visualization techniques are authenticated scientifically as thousand times reliable rather than textual representation. The premature data visualization system met some difficulties and there has some solution for handle this kind of big quantity of data. Data science used two distinct languages Python and R to visualize big data undeviatingly. There also have a lot of tools in operating business. This paper is focused on the visualization technique of Python and R. R appears including the extraordinary visualization library alike ggplot2, leaflet, and lattice to defeat the provocation of the extensive volume. Python has several particular libraries for data visualization. Commonly they are Bokeh, Seaborn, Altair, ggplot and Pygal. Also, with most modern, secure and powerful zero coding GUI's accessories to describe big data visualization for genuine recognition with practical determination. Method and process of visual description of data are significant to recover specific knowledge from the large-scale dataset.","PeriodicalId":265737,"journal":{"name":"2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122334966","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 : 2018-07-01DOI: 10.1109/ICSCEE.2018.8538364
M. Al-Khasawneh, S. Shamsuddin, S. Hasan, A. Bakar
MapReduce encompasses a framework in the processing and management of large scale datasets within a distributed cluster. The framework has been employed in several applications including search indexes generation, analysis of access log, document clustering, and other data analytics. A flexible computation model is adopted in MapReduce in addition to plain interface which comprises the functions of map and reduce. The interface is customizable based on application developers. MapReduce has captured the interest among many scholars whereby the interest has been on increasing its usability and efficiency in support to database-centric operations. Accordingly, this paper provides a complete review regarding a vast continuum of proposals and systems concentrating basically on the support of distributed data management and processing with the use of the framework of MapReduce.
{"title":"MapReduce a Comprehensive Review","authors":"M. Al-Khasawneh, S. Shamsuddin, S. Hasan, A. Bakar","doi":"10.1109/ICSCEE.2018.8538364","DOIUrl":"https://doi.org/10.1109/ICSCEE.2018.8538364","url":null,"abstract":"MapReduce encompasses a framework in the processing and management of large scale datasets within a distributed cluster. The framework has been employed in several applications including search indexes generation, analysis of access log, document clustering, and other data analytics. A flexible computation model is adopted in MapReduce in addition to plain interface which comprises the functions of map and reduce. The interface is customizable based on application developers. MapReduce has captured the interest among many scholars whereby the interest has been on increasing its usability and efficiency in support to database-centric operations. Accordingly, this paper provides a complete review regarding a vast continuum of proposals and systems concentrating basically on the support of distributed data management and processing with the use of the framework of MapReduce.","PeriodicalId":265737,"journal":{"name":"2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE)","volume":"294 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127768365","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 : 2018-07-01DOI: 10.1109/ICSCEE.2018.8538419
Farid Saleh Amer, W. Yafooz, Ahmed Abdo Abdullah Al-Manakhi
This paper aims to identify the main obstacles to the application of electronic administration, ways and mechanisms to overcome the obstacles from the point of view of administrative and academic staff. The researcher used the descriptive (procedural) approach and the questionnaire was used as a tool for collecting information. The study community is composed of administrative and academic staff working at the University of Aden. The paper reached many results, the most important of which are the following. There is an agreement among the sample of the study on the obstacles to the application of electronic administration in the Yemeni universities (Aden University as a model). The most prominent of these constraints are inadequate funding and lack of financial incentives for workers in the field of electronic management, adherence to the centralization of the university administration and administrative burdens of some administrative leader. The members of the sample of the study agreed on some certain ways and mechanisms to overcome obstacles to the application of electronic administration at the University of Aden, and the most prominent of these mechanisms: Providing means of funding to activate electronic management, Training the administrative staff to deal with the applications of electronic management efficiently. Providing material incentives for employees in the field of electronic management and recruitment of specialists in the operation and maintenance of electronic management techniques, and in light of the results reached, the researcher recommends some procedures to overcome these obstacles. The results showed that the lack of financial incentives for employees in the field of electronic administration hindered the application of management away from centralization in the university administration and to delegate a part of the powers (responsibilities) to the employees.
{"title":"Obstacles to the application of electronic administration in the Yemeni universities (University of Aden as a model) and solutions","authors":"Farid Saleh Amer, W. Yafooz, Ahmed Abdo Abdullah Al-Manakhi","doi":"10.1109/ICSCEE.2018.8538419","DOIUrl":"https://doi.org/10.1109/ICSCEE.2018.8538419","url":null,"abstract":"This paper aims to identify the main obstacles to the application of electronic administration, ways and mechanisms to overcome the obstacles from the point of view of administrative and academic staff. The researcher used the descriptive (procedural) approach and the questionnaire was used as a tool for collecting information. The study community is composed of administrative and academic staff working at the University of Aden. The paper reached many results, the most important of which are the following. There is an agreement among the sample of the study on the obstacles to the application of electronic administration in the Yemeni universities (Aden University as a model). The most prominent of these constraints are inadequate funding and lack of financial incentives for workers in the field of electronic management, adherence to the centralization of the university administration and administrative burdens of some administrative leader. The members of the sample of the study agreed on some certain ways and mechanisms to overcome obstacles to the application of electronic administration at the University of Aden, and the most prominent of these mechanisms: Providing means of funding to activate electronic management, Training the administrative staff to deal with the applications of electronic management efficiently. Providing material incentives for employees in the field of electronic management and recruitment of specialists in the operation and maintenance of electronic management techniques, and in light of the results reached, the researcher recommends some procedures to overcome these obstacles. The results showed that the lack of financial incentives for employees in the field of electronic administration hindered the application of management away from centralization in the university administration and to delegate a part of the powers (responsibilities) to the employees.","PeriodicalId":265737,"journal":{"name":"2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130527470","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 : 2018-07-01DOI: 10.1109/ICSCEE.2018.8538382
J. Teo, J. Chia
Emotion recognition has become a major endeavor in artificial general intelligence applications in recent years. Although significant progress has been made in emotion recognition for music, image and video stimuli, it remains largely unexplored for immersive virtual stimuli. Our main objective for this line of investigation is to enable consistently reliable emotion recognition for virtual reality stimuli using only cheap, commercial-off-the-shelf electroencephalography (EEG) headsets which have significantly less recording channels and far lower signal resolution commonly called “Wearable EEG” as opposed to medical-grade EEG headsets with the ultimate goal of applying EEG-based emotion prediction to procedurally-generated affective content such as immersive computer games and virtual learning environments through machine learning. Our prior preliminary study has found that the use of a 4-channel, 256-Hz was indeed able to perform the required emotion recognition tasks from VR stimuli albeit at classification rates of between 65-89% classification accuracy only using Support Vector Machines (SVMs) and K-Nearest Neighbor (KNN) classifiers. For this particular study, we attempt to improve the classification rates to above 95% by conducting a comprehensive investigation into the use of various deep neural-based learning architectures for this domain. By tuning the deep neural classifiers in terms of the number of hidden layers, number of hidden nodes and the nodal dropout ratio, the emotion prediction accuracy was able to be improved to over 96%. This shows the continued promise of the application of wearable EEG for emotion prediction as a cost-effective and userfriendly approach for consistent and reliable prediction deployment in virtual reality-related content and environments through deep learning approaches.
{"title":"Deep Neural Classifiers For Eeg-Based Emotion Recognition In Immersive Environments","authors":"J. Teo, J. Chia","doi":"10.1109/ICSCEE.2018.8538382","DOIUrl":"https://doi.org/10.1109/ICSCEE.2018.8538382","url":null,"abstract":"Emotion recognition has become a major endeavor in artificial general intelligence applications in recent years. Although significant progress has been made in emotion recognition for music, image and video stimuli, it remains largely unexplored for immersive virtual stimuli. Our main objective for this line of investigation is to enable consistently reliable emotion recognition for virtual reality stimuli using only cheap, commercial-off-the-shelf electroencephalography (EEG) headsets which have significantly less recording channels and far lower signal resolution commonly called “Wearable EEG” as opposed to medical-grade EEG headsets with the ultimate goal of applying EEG-based emotion prediction to procedurally-generated affective content such as immersive computer games and virtual learning environments through machine learning. Our prior preliminary study has found that the use of a 4-channel, 256-Hz was indeed able to perform the required emotion recognition tasks from VR stimuli albeit at classification rates of between 65-89% classification accuracy only using Support Vector Machines (SVMs) and K-Nearest Neighbor (KNN) classifiers. For this particular study, we attempt to improve the classification rates to above 95% by conducting a comprehensive investigation into the use of various deep neural-based learning architectures for this domain. By tuning the deep neural classifiers in terms of the number of hidden layers, number of hidden nodes and the nodal dropout ratio, the emotion prediction accuracy was able to be improved to over 96%. This shows the continued promise of the application of wearable EEG for emotion prediction as a cost-effective and userfriendly approach for consistent and reliable prediction deployment in virtual reality-related content and environments through deep learning approaches.","PeriodicalId":265737,"journal":{"name":"2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131888843","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 : 2018-07-01DOI: 10.1109/ICSCEE.2018.8538414
A. Winursito, Risanuri Hidayat, Agus Bejo, Muhammad Nur Yasir Utomo
The development of the pattern recognition system has increased rapidly in this century. Many developments of methods have been done. Mel Frequency Cepstral Coefficients (MFCC) is a popular feature extraction method but still has many disadvantages, especially regarding the level of accuracy and the high dimensional feature of the extraction method. This paper presents the feature data reduction of MFCC using Principal Component Analysis (PCA) and Singular Value Decomposition (SVD). Combining MFCC and data reduction methods, it is expected to improve the accuracy and increase the computational speed of the classification process by decreasing the dimensions of feature data. The result of extraction MFCC feature data plus the delta coefficient forms the matrix data which will be combined with the data reduction method. The data reduction process is designed into two versions. Then the results of data reduction are done classification process with Support Vector Machine (SVM) method. The dataset is composed of 140 recorded speech data from 28 speakers. The results showed that MFCC + PCA version 2 and MFCC + SVD version 1 were able to provide the maximum accuracy improvement with an increase of accuracy from conventional MFCC method from 83.57% to 90.71%. In addition, MFCC + PCA version 2 and MFCC + SVD version 1 method can accelerate the process of classification in speech recognition system from 7.819 seconds into for about 7.6 seconds by decreasing dimension of feature data from 26 into 10 for MFCC + PCA version 2 and decreasing dimension of feature data from 26 into 14 for MFCC + SVD version 1.
模式识别系统在本世纪发展迅速。许多方法的发展已经完成。Mel频率倒谱系数(MFCC)是一种流行的特征提取方法，但它仍然存在许多缺点，特别是在提取精度水平和高维特征方面。本文利用主成分分析(PCA)和奇异值分解(SVD)对MFCC的特征数据进行约简。结合MFCC和数据约简方法，期望通过降低特征数据的维数来提高分类过程的准确率和计算速度。MFCC特征数据的提取结果加上delta系数形成矩阵数据，并与数据约简方法相结合。数据约简过程被设计成两个版本。然后利用支持向量机方法对数据约简后的结果进行分类处理。该数据集由28位说话者的140个记录语音数据组成。结果表明，MFCC + PCA版本2和MFCC + SVD版本1的准确率提高幅度最大，比传统MFCC方法的准确率从83.57%提高到90.71%。此外，MFCC + PCA version 2和MFCC + SVD version 1方法通过将MFCC + PCA version 2的特征数据从26维降为10维，将MFCC + SVD version 1的特征数据从26维降为14维，将语音识别系统的分类过程从7.819秒加快到7.6秒左右。
{"title":"Feature Data Reduction of MFCC Using PCA and SVD in Speech Recognition System","authors":"A. Winursito, Risanuri Hidayat, Agus Bejo, Muhammad Nur Yasir Utomo","doi":"10.1109/ICSCEE.2018.8538414","DOIUrl":"https://doi.org/10.1109/ICSCEE.2018.8538414","url":null,"abstract":"The development of the pattern recognition system has increased rapidly in this century. Many developments of methods have been done. Mel Frequency Cepstral Coefficients (MFCC) is a popular feature extraction method but still has many disadvantages, especially regarding the level of accuracy and the high dimensional feature of the extraction method. This paper presents the feature data reduction of MFCC using Principal Component Analysis (PCA) and Singular Value Decomposition (SVD). Combining MFCC and data reduction methods, it is expected to improve the accuracy and increase the computational speed of the classification process by decreasing the dimensions of feature data. The result of extraction MFCC feature data plus the delta coefficient forms the matrix data which will be combined with the data reduction method. The data reduction process is designed into two versions. Then the results of data reduction are done classification process with Support Vector Machine (SVM) method. The dataset is composed of 140 recorded speech data from 28 speakers. The results showed that MFCC + PCA version 2 and MFCC + SVD version 1 were able to provide the maximum accuracy improvement with an increase of accuracy from conventional MFCC method from 83.57% to 90.71%. In addition, MFCC + PCA version 2 and MFCC + SVD version 1 method can accelerate the process of classification in speech recognition system from 7.819 seconds into for about 7.6 seconds by decreasing dimension of feature data from 26 into 10 for MFCC + PCA version 2 and decreasing dimension of feature data from 26 into 14 for MFCC + SVD version 1.","PeriodicalId":265737,"journal":{"name":"2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115349567","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 : 2018-07-01DOI: 10.1109/ICSCEE.2018.8538378
A. Altrad, Angela Amphwan, Shadi M. S. Hilles
Resources allocation has become an essential component for high-speed networking data systems. Several studies have proven that conventional spectrum allocation approaches are becoming insufficient to address the rapid demand in networking spectrum which resulted in spectrum under utilization. The main goal of this work is to develop a new model for resource allocation using Shuffled Frog Leap Algorithm (SFLA). Thus, a modified power for optimal allocation strategy is introduced and integrated to a simple OFDM functions according to the research’s aims. Then, the solution has been numerically validated and verified by simulations based powerline channel. Finally, the system performance was evaluated in term of system’s capacity, allocated bit/power, and convergence.
{"title":"Adaptive Shuffled Frog Leaping Algorithm For Optimal Power Rate Allocation: Power Line","authors":"A. Altrad, Angela Amphwan, Shadi M. S. Hilles","doi":"10.1109/ICSCEE.2018.8538378","DOIUrl":"https://doi.org/10.1109/ICSCEE.2018.8538378","url":null,"abstract":"Resources allocation has become an essential component for high-speed networking data systems. Several studies have proven that conventional spectrum allocation approaches are becoming insufficient to address the rapid demand in networking spectrum which resulted in spectrum under utilization. The main goal of this work is to develop a new model for resource allocation using Shuffled Frog Leap Algorithm (SFLA). Thus, a modified power for optimal allocation strategy is introduced and integrated to a simple OFDM functions according to the research’s aims. Then, the solution has been numerically validated and verified by simulations based powerline channel. Finally, the system performance was evaluated in term of system’s capacity, allocated bit/power, and convergence.","PeriodicalId":265737,"journal":{"name":"2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128229942","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：