The Blockchain is one of the recent technologies that have emerged in the last decade. Blockchain has become a topic of many researches in several fields and it was implemented in some industries like finance, energy, health care, and electronic voting. Blockchain presents some great potential solutions that help to tackle difficulties. In this work we will focus on e-voting using blockchain technology. As we all know the voting is a way that leads the governments to approach democracy in their countries by an electoral process. The blockchain voting has replaced the traditional vote paper, also it replaced the voting systems that store data in central database. That gave much efficiency to the blockchain technology through a decentralized system that requires anonymity, confidentiality and transparency.
{"title":"A survey on e-voting based on blockchain","authors":"Fatih Rabia, Sara Arezki, T. Gadi","doi":"10.1145/3454127.3457626","DOIUrl":"https://doi.org/10.1145/3454127.3457626","url":null,"abstract":"The Blockchain is one of the recent technologies that have emerged in the last decade. Blockchain has become a topic of many researches in several fields and it was implemented in some industries like finance, energy, health care, and electronic voting. Blockchain presents some great potential solutions that help to tackle difficulties. In this work we will focus on e-voting using blockchain technology. As we all know the voting is a way that leads the governments to approach democracy in their countries by an electoral process. The blockchain voting has replaced the traditional vote paper, also it replaced the voting systems that store data in central database. That gave much efficiency to the blockchain technology through a decentralized system that requires anonymity, confidentiality and transparency.","PeriodicalId":432206,"journal":{"name":"Proceedings of the 4th International Conference on Networking, Information Systems & Security","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122906009","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}
Aouatif Arqane, Omar Boutkhoum, Hicham Boukhriss, A. Moutaouakkil
At the present time, Security is a crucial issue for all organizations and companies, because intruders are constantly developing new techniques to infiltrate their infrastructure to steal or manipulate sensitive data. Thus, Intrusion Detection System (IDS) has emerged as new technology to protect networks and systems against suspicious activities. Numerous cybersecurity experts highlight the importance of IDS to strength the defensive capacities of systems by alerting for suspicious activities and malicious attacks. Over the years, many techniques like Machine learning (ML) and Deep Learning (DL) have been used to increase the detection accuracy and reduce the false alerts of IDSs. This survey paper presents an overview of some ML and DL algorithms among the most used for IDS. Additionally, because these algorithms depend on the characteristics of malicious events stored in datasets to identify anomalies, we list some publicly available cybersecurity datasets. Furthermore, we highlight the challenges that experts must overcome to enhance the performance of their methods.
{"title":"A Review of Intrusion Detection Systems: Datasets and machine learning methods","authors":"Aouatif Arqane, Omar Boutkhoum, Hicham Boukhriss, A. Moutaouakkil","doi":"10.1145/3454127.3456576","DOIUrl":"https://doi.org/10.1145/3454127.3456576","url":null,"abstract":"At the present time, Security is a crucial issue for all organizations and companies, because intruders are constantly developing new techniques to infiltrate their infrastructure to steal or manipulate sensitive data. Thus, Intrusion Detection System (IDS) has emerged as new technology to protect networks and systems against suspicious activities. Numerous cybersecurity experts highlight the importance of IDS to strength the defensive capacities of systems by alerting for suspicious activities and malicious attacks. Over the years, many techniques like Machine learning (ML) and Deep Learning (DL) have been used to increase the detection accuracy and reduce the false alerts of IDSs. This survey paper presents an overview of some ML and DL algorithms among the most used for IDS. Additionally, because these algorithms depend on the characteristics of malicious events stored in datasets to identify anomalies, we list some publicly available cybersecurity datasets. Furthermore, we highlight the challenges that experts must overcome to enhance the performance of their methods.","PeriodicalId":432206,"journal":{"name":"Proceedings of the 4th International Conference on Networking, Information Systems & Security","volume":"362 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122826283","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}
The autonomous car has been in the headlines for a decade and still continues to dominate auto headlines The autonomous car has attracted the researchers, robotics communities and the automobile industries, an autonomous car is a vehicle capable of detecting its environment and driving without human intervention, A human passenger is not required to take control of the vehicle at all times, nor is a human passenger to be present at all in the vehicle, the autonomous car can go wherever a traditional car goes and do whatever a experienced human driver made, the development of autonomous vehicles requires communication between cars and infrastructure, this communication is based on protocols allowing the exchange of information we can cite the Dedicated Short Range Communication (DSRC) protocol, Cellular V2X technology (C-V2X) LTE-V2X and 5G which presents the next generation of communication allowing the exchange of very large volumes of data also participating in the development of the autonomous car ,the paper presents a comparative study of the different protocols used by the autonomous car.
{"title":"Comparative Study on the protocols used by autonomous car,DSRC, C-V2X, 5G","authors":"Jellid Kawtar, T. Mazri","doi":"10.1145/3454127.3456616","DOIUrl":"https://doi.org/10.1145/3454127.3456616","url":null,"abstract":"The autonomous car has been in the headlines for a decade and still continues to dominate auto headlines The autonomous car has attracted the researchers, robotics communities and the automobile industries, an autonomous car is a vehicle capable of detecting its environment and driving without human intervention, A human passenger is not required to take control of the vehicle at all times, nor is a human passenger to be present at all in the vehicle, the autonomous car can go wherever a traditional car goes and do whatever a experienced human driver made, the development of autonomous vehicles requires communication between cars and infrastructure, this communication is based on protocols allowing the exchange of information we can cite the Dedicated Short Range Communication (DSRC) protocol, Cellular V2X technology (C-V2X) LTE-V2X and 5G which presents the next generation of communication allowing the exchange of very large volumes of data also participating in the development of the autonomous car ,the paper presents a comparative study of the different protocols used by the autonomous car.","PeriodicalId":432206,"journal":{"name":"Proceedings of the 4th International Conference on Networking, Information Systems & Security","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131509252","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}
In recent times, health-IoT and fifth generation technologies provide special health services for the patient including continuous and remote monitoring, besides other services. The combination of those previous concepts with virtual doctor system technology can offer several benefits such as remote and reliable diagnosis and treatment in real-time. Unfortunately, during the monitoring and diagnosis dialogue, illegitimate users can get unauthorized access to the VDS and disclose a valuable diagnosis, due to the lack of security and privacy of patients. To overcome this issue, some authentication schemes used in e-health applications over 5G networks will be presented. The aim of this paper is to choose a suitable authentication method for gaining access to remote VDS connected with the internet of medical things via the 5G network. So, the comparison between existing mechanisms will be done and the result will be announced after.
{"title":"Secure user authentication scheme for the Virtual Doctor System enabled H-IoT through 5G Network: A comparison study","authors":"F. Rougaii, T. Mazri","doi":"10.1145/3454127.3457624","DOIUrl":"https://doi.org/10.1145/3454127.3457624","url":null,"abstract":"In recent times, health-IoT and fifth generation technologies provide special health services for the patient including continuous and remote monitoring, besides other services. The combination of those previous concepts with virtual doctor system technology can offer several benefits such as remote and reliable diagnosis and treatment in real-time. Unfortunately, during the monitoring and diagnosis dialogue, illegitimate users can get unauthorized access to the VDS and disclose a valuable diagnosis, due to the lack of security and privacy of patients. To overcome this issue, some authentication schemes used in e-health applications over 5G networks will be presented. The aim of this paper is to choose a suitable authentication method for gaining access to remote VDS connected with the internet of medical things via the 5G network. So, the comparison between existing mechanisms will be done and the result will be announced after.","PeriodicalId":432206,"journal":{"name":"Proceedings of the 4th International Conference on Networking, Information Systems & Security","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131226928","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}
Deep learning today surpasses various machine learning approaches in performance and is widely used for variety of different tasks. Deep learning has increased accuracy compared to other approaches for tasks like language translation and image recognition. However, training a deep learning model on a large dataset is a challenging and expensive task that can be time consuming and require large computational resources. Therefore, Different architectures have been proposed for the implementation of deep learning models in machine vision systems to deal with this problem. Currently, the application of deep learning in the cloud is the most common and typical method. Nevertheless, the challenge of having to move the data from where it is generated to a cloud data center so that it can be used to prepare and develop machine learning models represents a major limitation of this approach. As a result, it is becoming increasingly important to consider moving aspects of deep learning to the edge, instead of the cloud, especially with the rapid increase in data volumes and the growing need to act in real time. From this perspective, a comparative study between the full edge and the full cloud architectures based on the performance of the deep learning models implemented in both architectures is elaborated. The results of this study lead us to specify the strengths of both the cloud and the edge for deploying deep learning models, and to choose the optimal architecture to deal with the rapid increase in data volumes and the growing need for real-time action.
{"title":"On the Performance of Deep Learning in the Full Edge and the Full Cloud Architectures","authors":"Tajeddine Benbarrad, Marouane Salhaoui, M. Arioua","doi":"10.1145/3454127.3457632","DOIUrl":"https://doi.org/10.1145/3454127.3457632","url":null,"abstract":"Deep learning today surpasses various machine learning approaches in performance and is widely used for variety of different tasks. Deep learning has increased accuracy compared to other approaches for tasks like language translation and image recognition. However, training a deep learning model on a large dataset is a challenging and expensive task that can be time consuming and require large computational resources. Therefore, Different architectures have been proposed for the implementation of deep learning models in machine vision systems to deal with this problem. Currently, the application of deep learning in the cloud is the most common and typical method. Nevertheless, the challenge of having to move the data from where it is generated to a cloud data center so that it can be used to prepare and develop machine learning models represents a major limitation of this approach. As a result, it is becoming increasingly important to consider moving aspects of deep learning to the edge, instead of the cloud, especially with the rapid increase in data volumes and the growing need to act in real time. From this perspective, a comparative study between the full edge and the full cloud architectures based on the performance of the deep learning models implemented in both architectures is elaborated. The results of this study lead us to specify the strengths of both the cloud and the edge for deploying deep learning models, and to choose the optimal architecture to deal with the rapid increase in data volumes and the growing need for real-time action.","PeriodicalId":432206,"journal":{"name":"Proceedings of the 4th International Conference on Networking, Information Systems & Security","volume":"222 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114405304","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}
The paper introduces the hybrid method of Convolutional Neural Network (CNN) and machine learning methods as a classifier, that is Support Vector Machines and K-Nearest Neighbors for classifying the ischemic stroke based on CT scan images. CNN is used as a feature extraction and the machine learning methods used to replace the fully connected layers in CNN. The proposed method is used to reduce computation time and improve accuracy in classifying image data, because we know that deep learning is not efficient for small amounts of data, where the data we use is only 93 CT scan images obtained from Cipto Mangunkusumo General Hospital (RSCM), Indonesia. The architecture of CNN used in this research consists of 5 layers convolutional layers, ReLU, MaxPooling, batch normalization and dropout. The elapsed time required for CNN is 7.631490 seconds. The output of feature extraction is used as an input for SVM and KNN. SVM with linear kernel can correctly classify ischemic stroke, with 100% accuracy in the training model and 96% accuracy in testing model with a test size of 60%. KNN classify ischemic stroke, with 97.3% (#neighbors = 5) accuracy in training model with a test size of 60% and 90% (#neighbors = 10, 15, 25) accuracy in the testing model with a test size of 10%. Based on these results, the SVM produces the higher accuracy compared to KNN in classifying ischemic stroke using CNN as feature extraction based on CT scan images with a computation time of only 8.0973 seconds.
{"title":"Comparison Support Vector Machines and K-Nearest Neighbors in Classifying Ischemic Stroke by Using Convolutional Neural Networks as a Feature Extraction","authors":"G. Saragih, Z. Rustam","doi":"10.1145/3454127.3456606","DOIUrl":"https://doi.org/10.1145/3454127.3456606","url":null,"abstract":"The paper introduces the hybrid method of Convolutional Neural Network (CNN) and machine learning methods as a classifier, that is Support Vector Machines and K-Nearest Neighbors for classifying the ischemic stroke based on CT scan images. CNN is used as a feature extraction and the machine learning methods used to replace the fully connected layers in CNN. The proposed method is used to reduce computation time and improve accuracy in classifying image data, because we know that deep learning is not efficient for small amounts of data, where the data we use is only 93 CT scan images obtained from Cipto Mangunkusumo General Hospital (RSCM), Indonesia. The architecture of CNN used in this research consists of 5 layers convolutional layers, ReLU, MaxPooling, batch normalization and dropout. The elapsed time required for CNN is 7.631490 seconds. The output of feature extraction is used as an input for SVM and KNN. SVM with linear kernel can correctly classify ischemic stroke, with 100% accuracy in the training model and 96% accuracy in testing model with a test size of 60%. KNN classify ischemic stroke, with 97.3% (#neighbors = 5) accuracy in training model with a test size of 60% and 90% (#neighbors = 10, 15, 25) accuracy in the testing model with a test size of 10%. Based on these results, the SVM produces the higher accuracy compared to KNN in classifying ischemic stroke using CNN as feature extraction based on CT scan images with a computation time of only 8.0973 seconds.","PeriodicalId":432206,"journal":{"name":"Proceedings of the 4th International Conference on Networking, Information Systems & Security","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123176070","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}
Djerassembe Laouhingamaye Frédéric, Awatif Rouijel, Hassan El Ghazi
Polysomnography (PSG) is a technique involved on the sleep disorders diagnostic. The signals acquired in a PSG study contain at least the electroencephalogram, the electrocardiogram, the electromiogram,the electrooculogram. Component Independent Analysis is a blindsource separation technique that has been shown to be very effec-tive in removing noise and artifacts that contaminate EEG signals.Inthis article, we will discuss the different ICA algorithms and thenapply them to denoising the EEG signal. This lead to well making decision regarding to this kind of disorder. These algorithms will beapplied for the denoising of the EEG signal containing insomniadisorders. The database used is the “CAP Sleep database” which isa collection of 108 polysomnographic recordings recorded in theCenter of Sleep Disorders at Ospedale Maggiore in Parma, Italy.Finally, theoretical and simulation results are presented to comparethe differents ICA algorithms applied to Insomnia EEG signals
{"title":"INSOMNIA EEG SIGNAL PREPROCESSING USING ICA ALGORITHMS","authors":"Djerassembe Laouhingamaye Frédéric, Awatif Rouijel, Hassan El Ghazi","doi":"10.1145/3454127.3457630","DOIUrl":"https://doi.org/10.1145/3454127.3457630","url":null,"abstract":"Polysomnography (PSG) is a technique involved on the sleep disorders diagnostic. The signals acquired in a PSG study contain at least the electroencephalogram, the electrocardiogram, the electromiogram,the electrooculogram. Component Independent Analysis is a blindsource separation technique that has been shown to be very effec-tive in removing noise and artifacts that contaminate EEG signals.Inthis article, we will discuss the different ICA algorithms and thenapply them to denoising the EEG signal. This lead to well making decision regarding to this kind of disorder. These algorithms will beapplied for the denoising of the EEG signal containing insomniadisorders. The database used is the “CAP Sleep database” which isa collection of 108 polysomnographic recordings recorded in theCenter of Sleep Disorders at Ospedale Maggiore in Parma, Italy.Finally, theoretical and simulation results are presented to comparethe differents ICA algorithms applied to Insomnia EEG signals","PeriodicalId":432206,"journal":{"name":"Proceedings of the 4th International Conference on Networking, Information Systems & Security","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125968469","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}
Traditional networks are complex and hard to manage due to many reasons such as manual configuration requirements of dedicated devices, lack of flexibility and a non-dynamic approach. To overcome these limitations and to meet the challenges of modern networks a new networking paradigm Software Defined Networking (SDN) has been introduced. SDN presents a centralized and completely dynamic environment which provides flexibility and programmability in networks. It enables the network to be controlled centrally and intelligently using multiple software applications. SDN being in its infancy, brings along new challenges. Standardization of various interfaces, scalability, compatibility of contrasting or divergent networks, and vulnerability issues are few of them. This paper discusses various vulnerabilities and possible attacks on every layer of an SDN and focuses on control plane attacks. Further, it presents a comprehensive survey on numerous attacks on the brain of an SDN i.e. the control plane along with existing solutions. The study concludes that despite the challenges that are worth debating, SDN has many characteristics that make it an ideal candidate for future networks.
{"title":"SDN Control Plane Security: Attacks and Mitigation Techniques","authors":"Kiran Fatima, Kanwal Zahoor, N. Bawany","doi":"10.1145/3454127.3456612","DOIUrl":"https://doi.org/10.1145/3454127.3456612","url":null,"abstract":"Traditional networks are complex and hard to manage due to many reasons such as manual configuration requirements of dedicated devices, lack of flexibility and a non-dynamic approach. To overcome these limitations and to meet the challenges of modern networks a new networking paradigm Software Defined Networking (SDN) has been introduced. SDN presents a centralized and completely dynamic environment which provides flexibility and programmability in networks. It enables the network to be controlled centrally and intelligently using multiple software applications. SDN being in its infancy, brings along new challenges. Standardization of various interfaces, scalability, compatibility of contrasting or divergent networks, and vulnerability issues are few of them. This paper discusses various vulnerabilities and possible attacks on every layer of an SDN and focuses on control plane attacks. Further, it presents a comprehensive survey on numerous attacks on the brain of an SDN i.e. the control plane along with existing solutions. The study concludes that despite the challenges that are worth debating, SDN has many characteristics that make it an ideal candidate for future networks.","PeriodicalId":432206,"journal":{"name":"Proceedings of the 4th International Conference on Networking, Information Systems & Security","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128354294","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}
The usage of Internet of Things has increased in the recent years allowing a new way of connecting devices together. Many transactions happen over the IoT calling for protocols to ensure the efficiency and management of the communication traffic. This paper examines 2 particular protocols, Message Queuing Telemetry Transport (MQTT) and Constrained application protocol (CoAP). The main differences between MQTT and CoAP that MQTT runs over TCP and CoAP runs over UDP. MQTT uses three level of QoS to ensure the message delivery while CoAP uses 4 types of transmission attempts which are confirmable, non-confirmable, acknowledgment, and rest. Through a set of experiments, we show that MQTT is more accurate when ensuring packet delivery. However, CoAP is better when it comes to performance when sending a limited number of messages.
{"title":"IoT Protocols – MQTT versus CoAP","authors":"Alyaziya Almheiri, Z. Maamar","doi":"10.1145/3454127.3456594","DOIUrl":"https://doi.org/10.1145/3454127.3456594","url":null,"abstract":"The usage of Internet of Things has increased in the recent years allowing a new way of connecting devices together. Many transactions happen over the IoT calling for protocols to ensure the efficiency and management of the communication traffic. This paper examines 2 particular protocols, Message Queuing Telemetry Transport (MQTT) and Constrained application protocol (CoAP). The main differences between MQTT and CoAP that MQTT runs over TCP and CoAP runs over UDP. MQTT uses three level of QoS to ensure the message delivery while CoAP uses 4 types of transmission attempts which are confirmable, non-confirmable, acknowledgment, and rest. Through a set of experiments, we show that MQTT is more accurate when ensuring packet delivery. However, CoAP is better when it comes to performance when sending a limited number of messages.","PeriodicalId":432206,"journal":{"name":"Proceedings of the 4th International Conference on Networking, Information Systems & Security","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131472770","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}
Music genre classification (MGC) is the process of tagging music with their appropriate genres by analyzing music signals or the lyrics. With the accelerated surge in music data repositories, MGC can be extensively used in music recommendation systems, advertisement, and streaming services for systematic and efficient management. However, there have been many works on English music classification using different statistical and machine learning approaches, but there is no notable progress found in the arena of Bengali music. Besides, a few significant works have been found in utilizing Deep Learning (DL) methods to classify different music genres. Bengali music is significantly enriched with its contents and uniqueness. Moreover, the extent and scope of exploring the DL approach in Bengali music ground are still latent. Therefore, Bengali music genre classification is quite a new research area in the Deep learning field. In this work, we have constructed a Bengali Music Genre Classifier (BMGC) to categorize 6 Bengali music genres: ‘Adhunik’, ‘Band’, ‘Hiphop’, ‘Nazrulgeeti’, ‘Lalon’, and ‘Rabindra Sangeet’. We have created a Bengali music genre classification dataset (hereafter named BMGCD) containing 2944 Bengali music clips, and a Gated Recurrent Unit based deep learning model has been developed to predict the music genre from audio signals. Our developed model achieved an accuracy of 80.4% and 80.6% F1-score which surpasses the related existing works.
{"title":"BMGC: A Deep Learning Approach to Classify Bengali Music Genres","authors":"Moumita Sen Sarma, Avishek Das","doi":"10.1145/3454127.3456593","DOIUrl":"https://doi.org/10.1145/3454127.3456593","url":null,"abstract":"Music genre classification (MGC) is the process of tagging music with their appropriate genres by analyzing music signals or the lyrics. With the accelerated surge in music data repositories, MGC can be extensively used in music recommendation systems, advertisement, and streaming services for systematic and efficient management. However, there have been many works on English music classification using different statistical and machine learning approaches, but there is no notable progress found in the arena of Bengali music. Besides, a few significant works have been found in utilizing Deep Learning (DL) methods to classify different music genres. Bengali music is significantly enriched with its contents and uniqueness. Moreover, the extent and scope of exploring the DL approach in Bengali music ground are still latent. Therefore, Bengali music genre classification is quite a new research area in the Deep learning field. In this work, we have constructed a Bengali Music Genre Classifier (BMGC) to categorize 6 Bengali music genres: ‘Adhunik’, ‘Band’, ‘Hiphop’, ‘Nazrulgeeti’, ‘Lalon’, and ‘Rabindra Sangeet’. We have created a Bengali music genre classification dataset (hereafter named BMGCD) containing 2944 Bengali music clips, and a Gated Recurrent Unit based deep learning model has been developed to predict the music genre from audio signals. Our developed model achieved an accuracy of 80.4% and 80.6% F1-score which surpasses the related existing works.","PeriodicalId":432206,"journal":{"name":"Proceedings of the 4th International Conference on Networking, Information Systems & Security","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131077615","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：