Pub Date : 2021-08-08DOI: 10.5815/ijitcs.2021.04.03
A. Makolo, Tayo Adeboye
The security of any system is a key factor toward its acceptability by the general public. We propose an intuitive approach to fraud detection in financial institutions using machine learning by designing a Hybrid Credit Card Fraud Detection (HCCFD) system which uses the technique of anomaly detection by applying genetic algorithm and multivariate normal distribution to identify fraudulent transactions on credit cards. An imbalance dataset of credit card transactions was used to the HCCFD and a target variable which indicates whether a transaction is deceitful or otherwise. Using F-score as performance metrics, the model was tested and it gave a prediction accuracy of 93.5%, as against artificial neural network, decision tree and support vector machine, which scored 84.2%, 80.0% and 68.5% respectively, when trained on the same data set. The results obtained showed a significant improvement as compared with the other widely used algorithms.
{"title":"Credit Card Fraud Detection System Using Machine Learning","authors":"A. Makolo, Tayo Adeboye","doi":"10.5815/ijitcs.2021.04.03","DOIUrl":"https://doi.org/10.5815/ijitcs.2021.04.03","url":null,"abstract":"The security of any system is a key factor toward its acceptability by the general public. We propose an intuitive approach to fraud detection in financial institutions using machine learning by designing a Hybrid Credit Card Fraud Detection (HCCFD) system which uses the technique of anomaly detection by applying genetic algorithm and multivariate normal distribution to identify fraudulent transactions on credit cards. An imbalance dataset of credit card transactions was used to the HCCFD and a target variable which indicates whether a transaction is deceitful or otherwise. Using F-score as performance metrics, the model was tested and it gave a prediction accuracy of 93.5%, as against artificial neural network, decision tree and support vector machine, which scored 84.2%, 80.0% and 68.5% respectively, when trained on the same data set. The results obtained showed a significant improvement as compared with the other widely used algorithms.","PeriodicalId":130361,"journal":{"name":"International Journal of Information Technology and Computer Science","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128219564","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 : 2021-08-08DOI: 10.5815/ijitcs.2021.04.01
Paul Dayang, Cyrille Sepele Petsou, Damien Wohwe Sambo
Recommendation systems are a type of systems that are able to help users finding relevant and personalized content in a wide variety of possibilities. To help computers perform recommendations, there are several approaches used nowadays such as the Content-based approach, the Collaborative filtering approach and the Hybrid recommendation approach. However, these approaches are sometimes inappropriate for use cases where there is no prior large datasets of users’ feedbacks or ratings needed for training Machine Learning models. Thus, in this work, we proposed a novel approach based on the combination of Fuzzy Logic and the k-Nearest neighbor algorithm (KNN). The proposed approach can be applied without any prior collected feedbacks of users and performs good recommendations. Moreover, our proposal uses Fuzzy Logic to infer values based on inputs and a set of rules. Furthermore, the KNN uses the output values of the Fuzzy Logic system to do some retrieval tasks based on existing distance measures. In order to evaluate our approach, we considered an expert system of food recommendation for people suffering from the two deadliest diseases in Cameroon: HIV/AIDS and Malaria. The obtained results are closed to the recommendation made by nutritionists. These results demonstrate how effective our approach can be used to solve a real nutrition problem for people suffering from Malaria or HIV/AIDS. Furthermore, this approach can be extended to other fields and even be used to perform any recommendation task where there is no prior collected user’s feedback or ratings by using the proposed approach as a framework.
{"title":"Combining Fuzzy Logic and k-Nearest Neighbor Algorithm for Recommendation Systems","authors":"Paul Dayang, Cyrille Sepele Petsou, Damien Wohwe Sambo","doi":"10.5815/ijitcs.2021.04.01","DOIUrl":"https://doi.org/10.5815/ijitcs.2021.04.01","url":null,"abstract":"Recommendation systems are a type of systems that are able to help users finding relevant and personalized content in a wide variety of possibilities. To help computers perform recommendations, there are several approaches used nowadays such as the Content-based approach, the Collaborative filtering approach and the Hybrid recommendation approach. However, these approaches are sometimes inappropriate for use cases where there is no prior large datasets of users’ feedbacks or ratings needed for training Machine Learning models. Thus, in this work, we proposed a novel approach based on the combination of Fuzzy Logic and the k-Nearest neighbor algorithm (KNN). The proposed approach can be applied without any prior collected feedbacks of users and performs good recommendations. Moreover, our proposal uses Fuzzy Logic to infer values based on inputs and a set of rules. Furthermore, the KNN uses the output values of the Fuzzy Logic system to do some retrieval tasks based on existing distance measures. In order to evaluate our approach, we considered an expert system of food recommendation for people suffering from the two deadliest diseases in Cameroon: HIV/AIDS and Malaria. The obtained results are closed to the recommendation made by nutritionists. These results demonstrate how effective our approach can be used to solve a real nutrition problem for people suffering from Malaria or HIV/AIDS. Furthermore, this approach can be extended to other fields and even be used to perform any recommendation task where there is no prior collected user’s feedback or ratings by using the proposed approach as a framework.","PeriodicalId":130361,"journal":{"name":"International Journal of Information Technology and Computer Science","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125425771","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 : 2021-08-08DOI: 10.5815/ijitcs.2021.04.02
Prashengit Dhar, Sunanda Guha
Classification of fish image is a complex issue in the field of pattern recognition. Fish classification is a complicated task. Physical shape, size, orientation etc. made it complex to classify. Selection of appropriate feature is also a great issue in image classification. Classification of fish image is very important in fishing service and agricultural field, fish industry, survey applications of fisheries and in other related area. For the assessment and counting of fishes, classification of fish image is also necessary as it can save time. This paper presents a fish image classification method with the robust Gist feature and Gray Level Co-occurrence Matrix (GLCM) feature. Noise removal and resizing of image is applied as pre-processing task. Gist and GLCM feature are combined to make a better feature matrix. Features are also tested separately. But combined feature vector performs better than individual. Classification is made on ten types of raw images of fish from two datasets -QUT and F4K dataset. The feature set is trained with different machine learning models. Among them, XgBoost performs with 90.2% and 98.08% accuracy for QUT and F4K dataset respectively.
{"title":"Fish Image Classification by XgBoost Based on Gist and GLCM Features","authors":"Prashengit Dhar, Sunanda Guha","doi":"10.5815/ijitcs.2021.04.02","DOIUrl":"https://doi.org/10.5815/ijitcs.2021.04.02","url":null,"abstract":"Classification of fish image is a complex issue in the field of pattern recognition. Fish classification is a complicated task. Physical shape, size, orientation etc. made it complex to classify. Selection of appropriate feature is also a great issue in image classification. Classification of fish image is very important in fishing service and agricultural field, fish industry, survey applications of fisheries and in other related area. For the assessment and counting of fishes, classification of fish image is also necessary as it can save time. This paper presents a fish image classification method with the robust Gist feature and Gray Level Co-occurrence Matrix (GLCM) feature. Noise removal and resizing of image is applied as pre-processing task. Gist and GLCM feature are combined to make a better feature matrix. Features are also tested separately. But combined feature vector performs better than individual. Classification is made on ten types of raw images of fish from two datasets -QUT and F4K dataset. The feature set is trained with different machine learning models. Among them, XgBoost performs with 90.2% and 98.08% accuracy for QUT and F4K dataset respectively.","PeriodicalId":130361,"journal":{"name":"International Journal of Information Technology and Computer Science","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125284976","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 : 2021-06-08DOI: 10.5815/ijitcs.2021.03.05
Nabil Ahmed, Sifat E. Rabbi, Tazmilur Rahman, Rubel Mia, M. Rahman
Traffic signs are symbols erected on the sides of roads that convey the road instructions to its users. These signs are essential in conveying the instructions related to the movement of traffic in the streets. Automation of driving is essential for efficient navigation free of human errors, which could otherwise lead to accidents and disorganized movement of vehicles in the streets. Traffic sign detection systems provide an important contribution to automation of driving, by helping in efficient navigation through relaying traffic sign instructions to the system users. However, most of the existing techniques have proposed approaches that are mostly capable of detection through static images only. Moreover, to the best of the author’s knowledge, there exists no approach that uses video frames. Therefore, this article proposes a unique automated approach for detection and recognition of Bangladeshi traffic signs from the video frames using Support Vector Machine and Histogram of Oriented Gradient. This system would be immensely useful in the implementation of automated driving systems in Bangladeshi streets. By detecting and recognizing the traffic signs in the streets, the automated driving systems in Bangladesh will be able to effectively navigate the streets. This approach classifies the Bangladeshi traffic signs using Support Vector Machine classifier on the basis of Histogram of Oriented Gradient property. Through image processing techniques such as binarization, contour detection and identifying similarity to circle etc., this article also proposes the actual detection mechanism of traffic signs from the video frames. The proposed approach detects and recognizes traffic signs with 100% precision, 95.83% recall and 96.15% accuracy after running it on 78 Bangladeshi traffic sign videos, which comprise 6 different kinds of Bangladeshi traffic signs. In addition, a public dataset for Bangladeshi traffic signs has been created that can be used for other research purposes.
{"title":"Traffic Sign Detection and Recognition Model Using Support Vector Machine and Histogram of Oriented Gradient","authors":"Nabil Ahmed, Sifat E. Rabbi, Tazmilur Rahman, Rubel Mia, M. Rahman","doi":"10.5815/ijitcs.2021.03.05","DOIUrl":"https://doi.org/10.5815/ijitcs.2021.03.05","url":null,"abstract":"Traffic signs are symbols erected on the sides of roads that convey the road instructions to its users. These signs are essential in conveying the instructions related to the movement of traffic in the streets. Automation of driving is essential for efficient navigation free of human errors, which could otherwise lead to accidents and disorganized movement of vehicles in the streets. Traffic sign detection systems provide an important contribution to automation of driving, by helping in efficient navigation through relaying traffic sign instructions to the system users. However, most of the existing techniques have proposed approaches that are mostly capable of detection through static images only. Moreover, to the best of the author’s knowledge, there exists no approach that uses video frames. Therefore, this article proposes a unique automated approach for detection and recognition of Bangladeshi traffic signs from the video frames using Support Vector Machine and Histogram of Oriented Gradient. This system would be immensely useful in the implementation of automated driving systems in Bangladeshi streets. By detecting and recognizing the traffic signs in the streets, the automated driving systems in Bangladesh will be able to effectively navigate the streets. This approach classifies the Bangladeshi traffic signs using Support Vector Machine classifier on the basis of Histogram of Oriented Gradient property. Through image processing techniques such as binarization, contour detection and identifying similarity to circle etc., this article also proposes the actual detection mechanism of traffic signs from the video frames. The proposed approach detects and recognizes traffic signs with 100% precision, 95.83% recall and 96.15% accuracy after running it on 78 Bangladeshi traffic sign videos, which comprise 6 different kinds of Bangladeshi traffic signs. In addition, a public dataset for Bangladeshi traffic signs has been created that can be used for other research purposes.","PeriodicalId":130361,"journal":{"name":"International Journal of Information Technology and Computer Science","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132369147","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 : 2021-04-08DOI: 10.5815/IJITCS.2021.02.05
Zainab Javed, Waqas Mahmood
In this day and age, the rise in technological advancements has the potential to improve and transform our lives every day. The rapid technology innovation can have a great impact on our business operations. Currently, Cloud computing services are popular and offer a wide range of opportunities for their customers. This paper presents a survey on a more recent computing architecture paradigm known as Fog Computing. Fog networking is a beneficial solution that offers the greater facility of data storage, enhanced computing, and networking resources. This new concept of fog complements cloud solution by facilitating its customers with better security, real-time analysis improved efficiency. To get a clear picture and understanding of how fog computing functions, we have performed an extensive literature review. We also presented a comparative study of fog computing with cloud and grid computing architectures. In this study, we have conducted a survey that led us to the conclusion that fog computing solution is still not applicable and implemented in most of the IoT industries due to the lack of awareness and the high architecture’s cost. Results of the study also indicate that optimized data storage and security are a few of the factors that can motivate organizations to implement the Fog computing architecture. Furthermore, the challenges related to fog computing solution are reviewed for progressive developments in the future.
{"title":"A Survey Based Study on Fog Computing Awareness","authors":"Zainab Javed, Waqas Mahmood","doi":"10.5815/IJITCS.2021.02.05","DOIUrl":"https://doi.org/10.5815/IJITCS.2021.02.05","url":null,"abstract":"In this day and age, the rise in technological advancements has the potential to improve and transform our lives every day. The rapid technology innovation can have a great impact on our business operations. Currently, Cloud computing services are popular and offer a wide range of opportunities for their customers. This paper presents a survey on a more recent computing architecture paradigm known as Fog Computing. Fog networking is a beneficial solution that offers the greater facility of data storage, enhanced computing, and networking resources. This new concept of fog complements cloud solution by facilitating its customers with better security, real-time analysis improved efficiency. To get a clear picture and understanding of how fog computing functions, we have performed an extensive literature review. We also presented a comparative study of fog computing with cloud and grid computing architectures. In this study, we have conducted a survey that led us to the conclusion that fog computing solution is still not applicable and implemented in most of the IoT industries due to the lack of awareness and the high architecture’s cost. Results of the study also indicate that optimized data storage and security are a few of the factors that can motivate organizations to implement the Fog computing architecture. Furthermore, the challenges related to fog computing solution are reviewed for progressive developments in the future.","PeriodicalId":130361,"journal":{"name":"International Journal of Information Technology and Computer Science","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126200654","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 : 2021-04-08DOI: 10.5815/IJITCS.2021.02.03
S. Bjelić, F. Marković, N. Marković
This document proposes a model of the process of atmospheric discharge of overhead lines followed by an electric arc. The intensity of atmospheric discharges, followed by electric arc and destruction, is determined by the difference in potential and current. Such a structure and form of discharge make it difficult to analyze the transient process and obtain adequate solutions. That is why the model of the transient process in the electric arc of the switch under the conditions of interruption of the AC circuit is specially analyzed. Simple equivalent schemes for the analysis of phenomena with given values of linear parameters are presented, which are very simple to apply. All influential parameters by which the overvoltage values in the model can be estimated were also taken into account. The evaluation of the proposed model was performed using the adapted MATLAB program psbsurlightcuurent for atmospheric electrical discharge, which contains a high frequency current source. The verified simulation method was used to verify the results as part of a method derived from artificial intelligence algorithms. The process simulation program, the obtained voltage and current diagrams confirm the application of the simulation algorithm model.
本文提出了一个架空线大气放电过程的模型。大气放电的强度，其次是电弧和破坏，是由电位和电流的差异决定的。这种放电结构和形式给瞬态过程的分析和求解带来了困难。因此，本文对交流电路中断条件下开关电弧暂态过程模型进行了专门的分析。给出了分析具有给定线性参数值的现象的简单等价格式，应用起来非常简单。同时考虑了所有影响模型过电压值的参数。利用改进的MATLAB程序psbsurlightcurrent for atmospheric discharge，其中包含一个高频电流源，对所提出的模型进行了评估。验证的仿真方法用于验证结果，作为人工智能算法派生方法的一部分。通过程序仿真，得到的电压和电流图证实了仿真算法模型的应用。
{"title":"Transient Process at Atmospheric Discharge into the Landline and the Appearance of an Electric Arc in the Switch","authors":"S. Bjelić, F. Marković, N. Marković","doi":"10.5815/IJITCS.2021.02.03","DOIUrl":"https://doi.org/10.5815/IJITCS.2021.02.03","url":null,"abstract":"This document proposes a model of the process of atmospheric discharge of overhead lines followed by an electric arc. The intensity of atmospheric discharges, followed by electric arc and destruction, is determined by the difference in potential and current. Such a structure and form of discharge make it difficult to analyze the transient process and obtain adequate solutions. That is why the model of the transient process in the electric arc of the switch under the conditions of interruption of the AC circuit is specially analyzed. Simple equivalent schemes for the analysis of phenomena with given values of linear parameters are presented, which are very simple to apply. All influential parameters by which the overvoltage values in the model can be estimated were also taken into account. The evaluation of the proposed model was performed using the adapted MATLAB program psbsurlightcuurent for atmospheric electrical discharge, which contains a high frequency current source. The verified simulation method was used to verify the results as part of a method derived from artificial intelligence algorithms. The process simulation program, the obtained voltage and current diagrams confirm the application of the simulation algorithm model.","PeriodicalId":130361,"journal":{"name":"International Journal of Information Technology and Computer Science","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121107566","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 : 2021-04-08DOI: 10.5815/IJITCS.2021.02.04
G. Mostafa, Ikhtiar Ahmed, M. Junayed
In recent years, with the advancement of the internet, social media is a promising platform to explore what going on around the world, sharing opinions and personal development. Now, Sentiment analysis, also known as text mining is widely used in the data science sector. It is an analysis of textual data that describes subjective information available in the source and allows an organization to identify the thoughts and feelings of their brand or goods or services while monitoring conversations and reviews online. Sentiment analysis of Twitter data is a very popular research work nowadays. Twitter is that kind of social media where many users express their opinion and feelings through small tweets and different machine learning classifier algorithms can be used to analyze those tweets. In this paper, some selected machine learning classifier algorithms were applied on crawled Twitter data after applying different types of preprocessors and encoding techniques, which ended up with satisfying accuracy. Later a comparison between the achieved accuracies was showed. Experimental evaluations show that the Neural Network Classifier’ algorithm provides a remarkable accuracy of 81.33% compared with other classifiers.
{"title":"Investigation of Different Machine Learning Algorithms to Determine Human Sentiment Using Twitter Data","authors":"G. Mostafa, Ikhtiar Ahmed, M. Junayed","doi":"10.5815/IJITCS.2021.02.04","DOIUrl":"https://doi.org/10.5815/IJITCS.2021.02.04","url":null,"abstract":"In recent years, with the advancement of the internet, social media is a promising platform to explore what going on around the world, sharing opinions and personal development. Now, Sentiment analysis, also known as text mining is widely used in the data science sector. It is an analysis of textual data that describes subjective information available in the source and allows an organization to identify the thoughts and feelings of their brand or goods or services while monitoring conversations and reviews online. Sentiment analysis of Twitter data is a very popular research work nowadays. Twitter is that kind of social media where many users express their opinion and feelings through small tweets and different machine learning classifier algorithms can be used to analyze those tweets. In this paper, some selected machine learning classifier algorithms were applied on crawled Twitter data after applying different types of preprocessors and encoding techniques, which ended up with satisfying accuracy. Later a comparison between the achieved accuracies was showed. Experimental evaluations show that the Neural Network Classifier’ algorithm provides a remarkable accuracy of 81.33% compared with other classifiers.","PeriodicalId":130361,"journal":{"name":"International Journal of Information Technology and Computer Science","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129828829","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 : 2021-04-08DOI: 10.5815/IJITCS.2021.02.01
Quazi Ghulam Rafi, Mohammed Noman, Sadia Zahin Prodhan, S. Alam, Dipannyta Nandi
Among the many music information retrieval (MIR) tasks, music genre classification is noteworthy. The categorization of music into different groups that came to existence through a complex interplay of cultures, musicians, and various market forces to characterize similarities between compositions and organize collections is known as a music genre. The past researchers extracted various hand-crafted features and developed classifiers based on them. But the major drawback of this approach was the requirement of field expertise. However, in recent times researchers, because of the remarkable classification accuracy of deep learning models, have used similar models for MIR tasks. Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and the hybrid model, Convolutional Recurrent Neural Network (CRNN), are such prominently used deep learning models for music genre classification along with other MIR tasks and various architectures of these models have achieved state-of-the-art results. In this study, we review and discuss three such architectures of deep learning models, already used for music genre classification of music tracks of length of 29-30 seconds. In particular, we analyze improved CNN, RNN, and CRNN architectures named Bottom-up Broadcast Neural Network (BBNN) [1], Independent Recurrent Neural Network (IndRNN) [2] and CRNN in Time and Frequency dimensions (CRNNTF) [3] respectively, almost all of the architectures achieved the highest classification accuracy among the variants of their base deep learning model. Hence, this study holds a comparative analysis of the three most impressive architectural variants of the main deep learning models that are prominently used to classify music genre and presents the three architecture, hence the models (CNN, RNN, and CRNN) in one study. We also propose two ways that can improve the performances of the RNN (IndRNN) and CRNN (CRNN-TF) architectures.
{"title":"Comparative Analysis of Three Improved Deep Learning Architectures for Music Genre Classification","authors":"Quazi Ghulam Rafi, Mohammed Noman, Sadia Zahin Prodhan, S. Alam, Dipannyta Nandi","doi":"10.5815/IJITCS.2021.02.01","DOIUrl":"https://doi.org/10.5815/IJITCS.2021.02.01","url":null,"abstract":"Among the many music information retrieval (MIR) tasks, music genre classification is noteworthy. The categorization of music into different groups that came to existence through a complex interplay of cultures, musicians, and various market forces to characterize similarities between compositions and organize collections is known as a music genre. The past researchers extracted various hand-crafted features and developed classifiers based on them. But the major drawback of this approach was the requirement of field expertise. However, in recent times researchers, because of the remarkable classification accuracy of deep learning models, have used similar models for MIR tasks. Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and the hybrid model, Convolutional Recurrent Neural Network (CRNN), are such prominently used deep learning models for music genre classification along with other MIR tasks and various architectures of these models have achieved state-of-the-art results. In this study, we review and discuss three such architectures of deep learning models, already used for music genre classification of music tracks of length of 29-30 seconds. In particular, we analyze improved CNN, RNN, and CRNN architectures named Bottom-up Broadcast Neural Network (BBNN) [1], Independent Recurrent Neural Network (IndRNN) [2] and CRNN in Time and Frequency dimensions (CRNNTF) [3] respectively, almost all of the architectures achieved the highest classification accuracy among the variants of their base deep learning model. Hence, this study holds a comparative analysis of the three most impressive architectural variants of the main deep learning models that are prominently used to classify music genre and presents the three architecture, hence the models (CNN, RNN, and CRNN) in one study. We also propose two ways that can improve the performances of the RNN (IndRNN) and CRNN (CRNN-TF) architectures.","PeriodicalId":130361,"journal":{"name":"International Journal of Information Technology and Computer Science","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133356664","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 : 2021-02-08DOI: 10.5815/IJITCS.2021.01.02
Yazid Hambally Yacouba, Training, A. Diabagaté, Abdou Maiga, A. Coulibaly
The smart meter can process sensor data in a residential grid. These sensors transmit different parameters or measurement data (index, power, temperature, fluctuation of voltage and electricity, etc.) to the smart meter. All of these measurement data can come in different ways at the smart meter. The sensors transmit each measurement data to the smart meter. In addition, the collection of this data to a central system is a significant concern to ensure data integrity and protect the privacy of residents. The complexity of these data management also lies in their volume, frequency, and scheduling. This work presents a scheduling and a collection mechanism in private power consumption data between both sensors and smart meters on one hand and between smart meters and the central data collection system on other hand. We have found several approaches to intelligent meter data management in scientific researches. We propose another approach in response to this concern for the scheduling and collection of measurement data to a central system from residential areas of sensors’ network connected to smart meters. This work is also an example of a link between data collection and data scheduling in intelligent information management, transmission, and protection. We also propose a modeling of the measurement objects of smart grid and highlight the changes made to these objects throughout the process of data processing. It should be noted that this smart grid system consists of three main active systems namely sensors, smart meters and central system. In addition to these three systems, there are other systems that communicate with the smart meters and the central system. We have identified three implementation models for the smart metering system. We also present an intelligent architecture based on multi-agent systems for the smart grid. Most current electricity management systems are not adapted to the new challenges imposed by social and economic development in Africa. The objectives of this study are to initiate the design of a smart grid system for the management of electricity data.
{"title":"Multi-agent System for Management of Data from Electrical Smart Meters","authors":"Yazid Hambally Yacouba, Training, A. Diabagaté, Abdou Maiga, A. Coulibaly","doi":"10.5815/IJITCS.2021.01.02","DOIUrl":"https://doi.org/10.5815/IJITCS.2021.01.02","url":null,"abstract":"The smart meter can process sensor data in a residential grid. These sensors transmit different parameters or measurement data (index, power, temperature, fluctuation of voltage and electricity, etc.) to the smart meter. All of these measurement data can come in different ways at the smart meter. The sensors transmit each measurement data to the smart meter. In addition, the collection of this data to a central system is a significant concern to ensure data integrity and protect the privacy of residents. The complexity of these data management also lies in their volume, frequency, and scheduling. This work presents a scheduling and a collection mechanism in private power consumption data between both sensors and smart meters on one hand and between smart meters and the central data collection system on other hand. We have found several approaches to intelligent meter data management in scientific researches. We propose another approach in response to this concern for the scheduling and collection of measurement data to a central system from residential areas of sensors’ network connected to smart meters. This work is also an example of a link between data collection and data scheduling in intelligent information management, transmission, and protection. We also propose a modeling of the measurement objects of smart grid and highlight the changes made to these objects throughout the process of data processing. It should be noted that this smart grid system consists of three main active systems namely sensors, smart meters and central system. In addition to these three systems, there are other systems that communicate with the smart meters and the central system. We have identified three implementation models for the smart metering system. We also present an intelligent architecture based on multi-agent systems for the smart grid. Most current electricity management systems are not adapted to the new challenges imposed by social and economic development in Africa. The objectives of this study are to initiate the design of a smart grid system for the management of electricity data.","PeriodicalId":130361,"journal":{"name":"International Journal of Information Technology and Computer Science","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127016209","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 : 2021-02-08DOI: 10.5815/IJITCS.2021.01.01
Donatien Koulla Moulla, A. Abran, Kolyang
For software organizations that rely on Open Source Software (OSS) to develop customer solutions and products, it is essential to accurately estimate how long it will take to deliver the expected functionalities. While OSS is supported by government policies around the world, most of the research on software project estimation has focused on conventional projects with commercial licenses. OSS effort estimation is challenging since OSS participants do not record effort data in OSS repositories. However, OSS data repositories contain dates of the participants’ contributions and these can be used for duration estimation. This study analyses historical data on WordPress and Swift projects to estimate OSS project duration using either commits or lines of code (LOC) as the independent variable. This study proposes first an improved classification of contributors based on the number of active days for each contributor in the development period of a release. For the WordPress and Swift OSS projects environments the results indicate that duration estimation models using the number of commits as the independent variable perform better than those using LOC. The estimation model for full-time contributors gives an estimate of the total duration, while the models with part-time and occasional contributors lead to better estimates of projects duration with both for the commits data and the lines of data.
{"title":"Duration Estimation Models for Open Source Software Projects","authors":"Donatien Koulla Moulla, A. Abran, Kolyang","doi":"10.5815/IJITCS.2021.01.01","DOIUrl":"https://doi.org/10.5815/IJITCS.2021.01.01","url":null,"abstract":"For software organizations that rely on Open Source Software (OSS) to develop customer solutions and products, it is essential to accurately estimate how long it will take to deliver the expected functionalities. While OSS is supported by government policies around the world, most of the research on software project estimation has focused on conventional projects with commercial licenses. OSS effort estimation is challenging since OSS participants do not record effort data in OSS repositories. However, OSS data repositories contain dates of the participants’ contributions and these can be used for duration estimation. This study analyses historical data on WordPress and Swift projects to estimate OSS project duration using either commits or lines of code (LOC) as the independent variable. This study proposes first an improved classification of contributors based on the number of active days for each contributor in the development period of a release. For the WordPress and Swift OSS projects environments the results indicate that duration estimation models using the number of commits as the independent variable perform better than those using LOC. The estimation model for full-time contributors gives an estimate of the total duration, while the models with part-time and occasional contributors lead to better estimates of projects duration with both for the commits data and the lines of data.","PeriodicalId":130361,"journal":{"name":"International Journal of Information Technology and Computer Science","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128264758","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：