Pub Date : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689860
Shad Al Kaiser, S. Mandal, Ashraful Kalam Abid, Ekhfa Hossain, Ferdous Bin Ali, Intisar Tahmid Naheen
Social media holds the freedom to express anyone as they are. Still, people fail to follow community standards and cross the boundary of self-limit, hurting other people, sometimes leading to cyberbullying. Social media mining is the frontier where researchers contend with ensuring safe cyberspace with the help of robust information retrieval and data mining techniques. In this paper, we are aiming towards achieving such a goal for Bangla language-spoken people. We have created a corpus that contains 11006 Bangla comments from Facebook, analyzed them demographically, annotated them to create robust classifiers to classify these comments as positive, negative, and neutral polarity. We have decomposed these polarities to further sentiments based on contents of the text varying from wishful thinking to gender-based hate speech. Our multiclass classification algorithm, consisting of TF-IDF vectorizer alongside uni-gram, bi-gram, and tri-gram followed by MNB, MNB, and KNN, gives 82.60%, 82.33%, and 79.63% accuracy, respectively.
{"title":"Social Media Opinion Mining Based on Bangla Public Post of Facebook","authors":"Shad Al Kaiser, S. Mandal, Ashraful Kalam Abid, Ekhfa Hossain, Ferdous Bin Ali, Intisar Tahmid Naheen","doi":"10.1109/ICCIT54785.2021.9689860","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689860","url":null,"abstract":"Social media holds the freedom to express anyone as they are. Still, people fail to follow community standards and cross the boundary of self-limit, hurting other people, sometimes leading to cyberbullying. Social media mining is the frontier where researchers contend with ensuring safe cyberspace with the help of robust information retrieval and data mining techniques. In this paper, we are aiming towards achieving such a goal for Bangla language-spoken people. We have created a corpus that contains 11006 Bangla comments from Facebook, analyzed them demographically, annotated them to create robust classifiers to classify these comments as positive, negative, and neutral polarity. We have decomposed these polarities to further sentiments based on contents of the text varying from wishful thinking to gender-based hate speech. Our multiclass classification algorithm, consisting of TF-IDF vectorizer alongside uni-gram, bi-gram, and tri-gram followed by MNB, MNB, and KNN, gives 82.60%, 82.33%, and 79.63% accuracy, respectively.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128602615","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689858
L. Paul, Golam Arman Shaki, Md. Fatin Ishraque, Papon Kumar Paul, M. Samsuzzaman
This paper presents a wide band novel-shaped microstrip antenna with a parasitic element for 5G wireless application. The Rogers RT 5880 substrate (2.2, 0.0009) having a compact size of $32.5times 25.25mm^{2}$ and a height of 1.575 millimetres is selected for the 5G antenna design. The results of the designed antenna show a reflection coefficient of -38.15dB, a gain of 2.43 dB and directivity of 3.63 dBi at 4.22 GHz. It also shows that the average radiation efficiency of the antenna is 76.2% over the 1.56 GHz large operating band. Moreover, it is found from the simulation results that the voltage standing wave ratio is 1.02 at 4.22 GHz. All the parameters used in designing the antenna help to achieve a large operating bandwidth of 1.56 GHz, which ranges from 3.33 GHz to 4.89 GHz. The antenna described in this paper can be a good contestant for WLAN as well as 5G communications because of its Omni-directional stable radiation pattern, acceptable efficiency and gain with a compact volume.
{"title":"An Omni-directional Novel-shaped Patch Antenna with a Parasitic Element for 5G Communication","authors":"L. Paul, Golam Arman Shaki, Md. Fatin Ishraque, Papon Kumar Paul, M. Samsuzzaman","doi":"10.1109/ICCIT54785.2021.9689858","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689858","url":null,"abstract":"This paper presents a wide band novel-shaped microstrip antenna with a parasitic element for 5G wireless application. The Rogers RT 5880 substrate (2.2, 0.0009) having a compact size of $32.5times 25.25mm^{2}$ and a height of 1.575 millimetres is selected for the 5G antenna design. The results of the designed antenna show a reflection coefficient of -38.15dB, a gain of 2.43 dB and directivity of 3.63 dBi at 4.22 GHz. It also shows that the average radiation efficiency of the antenna is 76.2% over the 1.56 GHz large operating band. Moreover, it is found from the simulation results that the voltage standing wave ratio is 1.02 at 4.22 GHz. All the parameters used in designing the antenna help to achieve a large operating bandwidth of 1.56 GHz, which ranges from 3.33 GHz to 4.89 GHz. The antenna described in this paper can be a good contestant for WLAN as well as 5G communications because of its Omni-directional stable radiation pattern, acceptable efficiency and gain with a compact volume.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121651114","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689879
Ummay Kulsum Shakila, Sadia Sultana
Centralized marketplaces run on a process where a single authority has control over all activity. They suffer from limitation such as- mandatory fees to be paid to the platform for listing and selling items, lack of privacy and control over account, improper transaction security and so on. This paper presents a decentralized application aiming to reduce these drawbacks using Ethereum blockchain. It was implemented using truffle evolvement framework with solidity language. Ethereum smart contracts contain all functions of this application. Client-side application was created through an API called web3.js. Analytical analyses of this application using Kovan test network show least transactional fees reported in literature till date. The application was shown to have average transaction fee of 0.1524472 (eth) with average run time of 3.5 seconds and average gas consumption of 4.6 gwei, these are the best results obtained till date for such system ensuring cost effectiveness and reducing time complexity. The contract making time was less than a second. Comparison with well-known centralized online marketplaces revealed that proposed system was more economical than current centralized online applications in terms of profit margin.
{"title":"A Decentralized Marketplace Application based on Ethereum Smart Contract","authors":"Ummay Kulsum Shakila, Sadia Sultana","doi":"10.1109/ICCIT54785.2021.9689879","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689879","url":null,"abstract":"Centralized marketplaces run on a process where a single authority has control over all activity. They suffer from limitation such as- mandatory fees to be paid to the platform for listing and selling items, lack of privacy and control over account, improper transaction security and so on. This paper presents a decentralized application aiming to reduce these drawbacks using Ethereum blockchain. It was implemented using truffle evolvement framework with solidity language. Ethereum smart contracts contain all functions of this application. Client-side application was created through an API called web3.js. Analytical analyses of this application using Kovan test network show least transactional fees reported in literature till date. The application was shown to have average transaction fee of 0.1524472 (eth) with average run time of 3.5 seconds and average gas consumption of 4.6 gwei, these are the best results obtained till date for such system ensuring cost effectiveness and reducing time complexity. The contract making time was less than a second. Comparison with well-known centralized online marketplaces revealed that proposed system was more economical than current centralized online applications in terms of profit margin.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121541786","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}
Multiple Choice Question (MCQ) answering is a strenuous task intended to determine the right answer from a set of given options. It demands a deep semantic understanding of the question, answer, and knowledge. In this article, we present a Convolutional Neural Networks (CNN) based model extended with Bidirectional Encoder Representations from Transformers (BERT) to answer complex multiple-choice questions. Given an article and a MCQ, the model selects the correct option by ranking each question-option tuple. The proposed CNN based model uses question-option tuple as input to perform better than Long Short-Term Memory(LSTM) based baselines by 22.7 for the Textbook Question Answering (TQA) [1] and SciQ [2] datasets.
{"title":"Augmenting BERT with CNN for Multiple Choice Question Answering","authors":"Shishir Roy, Nayeem Ehtesham, Md Saiful Islam, Marium-E-Jannat","doi":"10.1109/ICCIT54785.2021.9689877","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689877","url":null,"abstract":"Multiple Choice Question (MCQ) answering is a strenuous task intended to determine the right answer from a set of given options. It demands a deep semantic understanding of the question, answer, and knowledge. In this article, we present a Convolutional Neural Networks (CNN) based model extended with Bidirectional Encoder Representations from Transformers (BERT) to answer complex multiple-choice questions. Given an article and a MCQ, the model selects the correct option by ranking each question-option tuple. The proposed CNN based model uses question-option tuple as input to perform better than Long Short-Term Memory(LSTM) based baselines by 22.7 for the Textbook Question Answering (TQA) [1] and SciQ [2] datasets.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129392780","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689814
Md. Shajjed Hossan, Mst. Lelana Khatun, Shadia Rahman, Saha Reno, Mamun Ahmed
When using the ride-sharing service, users may run across difficulties. For example, the driver may misconduct with them, have trouble hiring, verbalize abusively, or be a victim of harassment. So, the protection of the rider is extremely important in RSSs. We suggest a method to ensure protection that is based on private blockchain, in light of the current RSS’s security concerns and centralism. Blockchain is a platform in which the stored transactions become immutable. Hyperledger is a blockchain that is better than public blockchain in almost every aspect. The benefits of the hyperledger is that the information which is stored in the hyperledger blockchain and can’t be accessed outside the multiple organization. In our paper, we have secured the RSS by utilizing hyperledger predicated on a private blockchain system. If the users or riders faced any quandaries and they endeavored their issues via our hyperledger private blockchain, the organization could not modify or expunge the subsist report. In classical RSS, the ascendancy could modify or efface the report and they are able to expunge the riders ride information. To stop the unethical comfort, we have provided this hyperledger based private blockchain solution.
{"title":"Securing Ride-Sharing Service Using IPFS and Hyperledger Based on Private Blockchain","authors":"Md. Shajjed Hossan, Mst. Lelana Khatun, Shadia Rahman, Saha Reno, Mamun Ahmed","doi":"10.1109/ICCIT54785.2021.9689814","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689814","url":null,"abstract":"When using the ride-sharing service, users may run across difficulties. For example, the driver may misconduct with them, have trouble hiring, verbalize abusively, or be a victim of harassment. So, the protection of the rider is extremely important in RSSs. We suggest a method to ensure protection that is based on private blockchain, in light of the current RSS’s security concerns and centralism. Blockchain is a platform in which the stored transactions become immutable. Hyperledger is a blockchain that is better than public blockchain in almost every aspect. The benefits of the hyperledger is that the information which is stored in the hyperledger blockchain and can’t be accessed outside the multiple organization. In our paper, we have secured the RSS by utilizing hyperledger predicated on a private blockchain system. If the users or riders faced any quandaries and they endeavored their issues via our hyperledger private blockchain, the organization could not modify or expunge the subsist report. In classical RSS, the ascendancy could modify or efface the report and they are able to expunge the riders ride information. To stop the unethical comfort, we have provided this hyperledger based private blockchain solution.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129506058","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689861
Md. Sabbir Hossain Polak
Dealing with a high-performance graphics system in the embedded system domain is always a difficult job. Due to its high practicality, flexibility, efficiency, and cost per unit, the Field Programmable Gate Array (FPGA) has gained considerable attention in recent years for developing Graphics Frameworks on its processor. I provide design views and a schematic layout for the Graphics framework, which is used to implement graphics capabilities on FPGA-based 8-bit processors. I have built an 8-bit processor using the ISE (Integrated Synthesis Environment) design suite and then tested and validated it on both software and hardware using the ISim (ISE Simulator) and a Xilinx Spartan-6 LX16 FPGA. The processor framework was designed using the Hardware Description Language (Verilog). The initial purpose of this research was to create real-time primitive projections of basic wireframe models on a single chip. As a result, I develop an 8-bit RISC-based SoftCPU. Although this difficulty extends beyond the capabilities of conventional microcontrollers/CPUs, the answer has resulted in the development of a hardware graphics pipeline capable of drawing on a screen through the VGA interface in conjunction with a monitor.
{"title":"SoftCPU: A flexible and simple CPU design in FPGA for educational purpose","authors":"Md. Sabbir Hossain Polak","doi":"10.1109/ICCIT54785.2021.9689861","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689861","url":null,"abstract":"Dealing with a high-performance graphics system in the embedded system domain is always a difficult job. Due to its high practicality, flexibility, efficiency, and cost per unit, the Field Programmable Gate Array (FPGA) has gained considerable attention in recent years for developing Graphics Frameworks on its processor. I provide design views and a schematic layout for the Graphics framework, which is used to implement graphics capabilities on FPGA-based 8-bit processors. I have built an 8-bit processor using the ISE (Integrated Synthesis Environment) design suite and then tested and validated it on both software and hardware using the ISim (ISE Simulator) and a Xilinx Spartan-6 LX16 FPGA. The processor framework was designed using the Hardware Description Language (Verilog). The initial purpose of this research was to create real-time primitive projections of basic wireframe models on a single chip. As a result, I develop an 8-bit RISC-based SoftCPU. Although this difficulty extends beyond the capabilities of conventional microcontrollers/CPUs, the answer has resulted in the development of a hardware graphics pipeline capable of drawing on a screen through the VGA interface in conjunction with a monitor.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134638031","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689880
M. Billah, Sunanda Das
In recent decades, gold has been one of the most sought-after commodities for long-term and short-term investments, as investors perceive gold as a hedge against unanticipated market occurrences. Gold can be purchased, stored, and is rarely utilized as a payment method. However, it is pretty simple to convert gold into cash in almost any currency. As gold is essential for maintaining value, investment, and national economic stability, it is undoubtedly vital to forecast the price of gold accurately. In this paper, we proposed a hybrid method for forecasting the price of gold based on the combination of 1D Convolutional Neural Networks (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU). Though CNN-GRU, CNN-LSTM, CNN-RNN based hybrid networks or, the individual CNN, Bi-GRU, and GRU provide satisfactory results, our proposed hybrid approach is more reliable since it outperforms other networks and achieves the MAE, MAPE, MedAE, RMSE, MSE, MSLE of 11.88, 0.67%, 8.41, 15.59, 242.90, $76.08times 10^{-6}$ respectively and $mathrm{R}^{2}$ Score of 93.56%.
{"title":"Analysis and Prediction of Gold Price using CNN and Bi-GRU based Neural Network Model","authors":"M. Billah, Sunanda Das","doi":"10.1109/ICCIT54785.2021.9689880","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689880","url":null,"abstract":"In recent decades, gold has been one of the most sought-after commodities for long-term and short-term investments, as investors perceive gold as a hedge against unanticipated market occurrences. Gold can be purchased, stored, and is rarely utilized as a payment method. However, it is pretty simple to convert gold into cash in almost any currency. As gold is essential for maintaining value, investment, and national economic stability, it is undoubtedly vital to forecast the price of gold accurately. In this paper, we proposed a hybrid method for forecasting the price of gold based on the combination of 1D Convolutional Neural Networks (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU). Though CNN-GRU, CNN-LSTM, CNN-RNN based hybrid networks or, the individual CNN, Bi-GRU, and GRU provide satisfactory results, our proposed hybrid approach is more reliable since it outperforms other networks and achieves the MAE, MAPE, MedAE, RMSE, MSE, MSLE of 11.88, 0.67%, 8.41, 15.59, 242.90, $76.08times 10^{-6}$ respectively and $mathrm{R}^{2}$ Score of 93.56%.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129497580","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689799
Mohammad Monirujjaman Khan, Md. Hafizur Rahman, Eshan Barua
As the Covid-19 pandemic locked everyone in their house, people felt it necessary for several services to survive this situation. This paper presents the development of web applications that contains some essential services during the pandemic situation for the people of Bangladesh. Via this web application, the admin and users can sign in and log in. Admin can add products related to pandemic on the shop service, and then the users can buy these products. Also, the admin can add nurses, burial and funeral volunteers, Covid-19 test sample collectors to different cities. The service providers will sign up and add services with proper certificates to provide services. Then admin will verify the vendors certificate. If the certificates are valid, vendors will be visible on the websites, and users will get service from them. Users can get these services by providing their addresses and date. Users also can cancel service requests before the service giving time. Vendors can view the pending services list and provide services. Vendors can also cancel the service before the service providing time if any problem occurs on vendors side. After providing the service, both vendors and users can confirm that the service is done. Users also can give feedback on vendors listing after getting the service. Also, there will be registered fitness and nutrition coaches on the website. Users can get advice for fitness and nutrition through private messages via this website. As it's risky to go out from home during this situation, the necessity for going out will be lessened if people get these services online. And their hassles will be lower if people can find all these services on one website.
{"title":"Development of Web-Based System for Essential Services During the COVID-19 Pandemic","authors":"Mohammad Monirujjaman Khan, Md. Hafizur Rahman, Eshan Barua","doi":"10.1109/ICCIT54785.2021.9689799","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689799","url":null,"abstract":"As the Covid-19 pandemic locked everyone in their house, people felt it necessary for several services to survive this situation. This paper presents the development of web applications that contains some essential services during the pandemic situation for the people of Bangladesh. Via this web application, the admin and users can sign in and log in. Admin can add products related to pandemic on the shop service, and then the users can buy these products. Also, the admin can add nurses, burial and funeral volunteers, Covid-19 test sample collectors to different cities. The service providers will sign up and add services with proper certificates to provide services. Then admin will verify the vendors certificate. If the certificates are valid, vendors will be visible on the websites, and users will get service from them. Users can get these services by providing their addresses and date. Users also can cancel service requests before the service giving time. Vendors can view the pending services list and provide services. Vendors can also cancel the service before the service providing time if any problem occurs on vendors side. After providing the service, both vendors and users can confirm that the service is done. Users also can give feedback on vendors listing after getting the service. Also, there will be registered fitness and nutrition coaches on the website. Users can get advice for fitness and nutrition through private messages via this website. As it's risky to go out from home during this situation, the necessity for going out will be lessened if people get these services online. And their hassles will be lower if people can find all these services on one website.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123629658","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689915
Narimene Bair, L. Hamza, Lillia Ouali
In this paper, we define a new technique for analysing attack graphs in order to protect networks and computer systems from the risks and threats that can affect them. Our approach is based on logic expression of attacks scenarios, generated by any tool, in order to obtain a minimal set of vulnerabilities to remove. After identifying the dependencies between these vulnerabilities we propose the best cost paths to remove. As a result, we obtain the deleted paths with a minimal cost.
{"title":"Costs Technique for Analysis Attacks Graphs in Computer Systems","authors":"Narimene Bair, L. Hamza, Lillia Ouali","doi":"10.1109/ICCIT54785.2021.9689915","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689915","url":null,"abstract":"In this paper, we define a new technique for analysing attack graphs in order to protect networks and computer systems from the risks and threats that can affect them. Our approach is based on logic expression of attacks scenarios, generated by any tool, in order to obtain a minimal set of vulnerabilities to remove. After identifying the dependencies between these vulnerabilities we propose the best cost paths to remove. As a result, we obtain the deleted paths with a minimal cost.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115344501","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 : 2021-12-18DOI: 10.1109/ICCIT54785.2021.9689817
Mayeesha Mahzabin, M. Hasan, Sabrina Nahar, Mosabber Uddin Ahmed
The hand gesture and sign language are extraordinary means of communication between ordinary people and the deaf-mute people. Although an ordinary person usually does not understand sign language, automated recognition systems can be used to overcome this barrier. In this research, we opted for accurate recognition of hand gestures using four different machine learning models on two different datasets- American Sign Language (ASL) and a general gesture set to classify both static and dynamic gestures for the English Language. All the classifiers used had shown good accuracy on both datasets, and we got even better results after normalization. The first model of Artificial Neural Network (ANN) was proposed by varying the input, hidden and output layers that gave an accuracy of 99.40%. The second model of K-Nearest Neighbors (KNN) acquired an accuracy of 99.14%. The third model of Decision Tree (DT) achieved an accuracy of 94.52%. Finally, we took the ensemble of these models using the Ensemble vote classifier which demonstrated an overall predictive performance and proved to be a much more generalized model with an accuracy of 99.45%. In the case of dynamic gestures, we got 100% accuracy for three gestures.
{"title":"Automated Hand Gesture Recognition Using Machine Learning","authors":"Mayeesha Mahzabin, M. Hasan, Sabrina Nahar, Mosabber Uddin Ahmed","doi":"10.1109/ICCIT54785.2021.9689817","DOIUrl":"https://doi.org/10.1109/ICCIT54785.2021.9689817","url":null,"abstract":"The hand gesture and sign language are extraordinary means of communication between ordinary people and the deaf-mute people. Although an ordinary person usually does not understand sign language, automated recognition systems can be used to overcome this barrier. In this research, we opted for accurate recognition of hand gestures using four different machine learning models on two different datasets- American Sign Language (ASL) and a general gesture set to classify both static and dynamic gestures for the English Language. All the classifiers used had shown good accuracy on both datasets, and we got even better results after normalization. The first model of Artificial Neural Network (ANN) was proposed by varying the input, hidden and output layers that gave an accuracy of 99.40%. The second model of K-Nearest Neighbors (KNN) acquired an accuracy of 99.14%. The third model of Decision Tree (DT) achieved an accuracy of 94.52%. Finally, we took the ensemble of these models using the Ensemble vote classifier which demonstrated an overall predictive performance and proved to be a much more generalized model with an accuracy of 99.45%. In the case of dynamic gestures, we got 100% accuracy for three gestures.","PeriodicalId":166450,"journal":{"name":"2021 24th International Conference on Computer and Information Technology (ICCIT)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130814878","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：