Pub Date : 2022-12-04DOI: 10.1109/CICN56167.2022.10008252
Walter Udeze, Sarhan M. Musa
Companies throughout the world are making an innovative switch from oil and gas to renewable energy sources, such as wind and solar power. As the world transitions to renewable energy, the demand for electric vehicles (EVs) has increased significantly. EVs mainly use Lithium-ion batteries because of their durability and efficiency. However, as the number of Lithium-ion batteries increases with the goal of reduction of emission and low energy cost, it comes with a major drawback of safety which affects efficiency. To address these challenges, this study investigates ways on how to improve the storage management system in an EV. In this research, different Lithium-ion battery states of an EV were monitored to effectively improve the battery management system (BMS). Two different drive cycles, federal test procedure (FTP) 75 and wide-open throttle (WOT) simulation time of 2474 seconds are used to obtain the results. The implementation of State of charge (SOC) technique has been applied to evaluate the energy remaining in the battery as well as the aging effects/dynamic load. The results obtained show a rate that gradually slows down in a linear manner. In addition, EVs have a less likely chance of experiencing power loss due to a very sophisticated gear system and it is very similar to a hybrid electric vehicle or internal combustion engine.
{"title":"Performance and Efficiency Analysis for Lithium-ion Battery Using State of Charge Method","authors":"Walter Udeze, Sarhan M. Musa","doi":"10.1109/CICN56167.2022.10008252","DOIUrl":"https://doi.org/10.1109/CICN56167.2022.10008252","url":null,"abstract":"Companies throughout the world are making an innovative switch from oil and gas to renewable energy sources, such as wind and solar power. As the world transitions to renewable energy, the demand for electric vehicles (EVs) has increased significantly. EVs mainly use Lithium-ion batteries because of their durability and efficiency. However, as the number of Lithium-ion batteries increases with the goal of reduction of emission and low energy cost, it comes with a major drawback of safety which affects efficiency. To address these challenges, this study investigates ways on how to improve the storage management system in an EV. In this research, different Lithium-ion battery states of an EV were monitored to effectively improve the battery management system (BMS). Two different drive cycles, federal test procedure (FTP) 75 and wide-open throttle (WOT) simulation time of 2474 seconds are used to obtain the results. The implementation of State of charge (SOC) technique has been applied to evaluate the energy remaining in the battery as well as the aging effects/dynamic load. The results obtained show a rate that gradually slows down in a linear manner. In addition, EVs have a less likely chance of experiencing power loss due to a very sophisticated gear system and it is very similar to a hybrid electric vehicle or internal combustion engine.","PeriodicalId":287589,"journal":{"name":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115008831","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}
This paper makes a comparison between 3 systems deployed on different platforms (Web, Desktop, Mobile) which implement the DEMUCS neural network, responsible for separating sources of musical origin. The objective of this work is to determine on which platform the neural network can be executed more quickly for the use of the average user and from this to propose an optimal architecture for standard development. For this purpose, we selected 12 songs to be separated in the systems of the 3 platforms mentioned and we measured the time it takes for each system to execute the required separation and thus choose the best platform as a starting point. The results and conclusions of the work support the reason for choosing the platform, from which the development architecture was proposed.
{"title":"Comparison of the Use of the DEMUCS Neural Network On Different Platforms for the Separation of Sources Of Musical Origin","authors":"Raul Pérez Alarcón, Luis Marcelo Pacheco Alvaro, Ciro Rodríguez, Favio Guevara Puente, Iván Petrlik, Yuri Pomachagua","doi":"10.1109/CICN56167.2022.10008289","DOIUrl":"https://doi.org/10.1109/CICN56167.2022.10008289","url":null,"abstract":"This paper makes a comparison between 3 systems deployed on different platforms (Web, Desktop, Mobile) which implement the DEMUCS neural network, responsible for separating sources of musical origin. The objective of this work is to determine on which platform the neural network can be executed more quickly for the use of the average user and from this to propose an optimal architecture for standard development. For this purpose, we selected 12 songs to be separated in the systems of the 3 platforms mentioned and we measured the time it takes for each system to execute the required separation and thus choose the best platform as a starting point. The results and conclusions of the work support the reason for choosing the platform, from which the development architecture was proposed.","PeriodicalId":287589,"journal":{"name":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124884905","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 : 2022-12-04DOI: 10.1109/CICN56167.2022.10008308
N. Tayem, Ahmed A. Hussain, AbuMuhammad Moinuddeen, R. Radaydeh, J. Alghazo
Two-dimensional direction of arrival estimation is a computationally complex problem that has been the focus of research in the area of array signal processing for several decades now. This paper proposes a novel2D DOA azimuth and elevation angle estimation algorithm for multiple RF noncoherent sources using an L-shaped array antenna configuration. The proposed method employs a MUSIC-like estimation algorithm in conjunction with QR decomposition to improve the accuracy of 2D DOA estimation and provide much lower computational complexity when compared with existing methods such as the Capon method. It does not require knowing the number of sources in advance and pairs the estimated azimuth and elevation angles automatically for multiple sources. Simulation results are presented to validate the efficacy of the proposed method and its performance is compared with the Capon method.
{"title":"Improved Performance Two-Dimensional Direction of Arrival Estimation Algorithm with Unknown Number of Noncoherent Sources","authors":"N. Tayem, Ahmed A. Hussain, AbuMuhammad Moinuddeen, R. Radaydeh, J. Alghazo","doi":"10.1109/CICN56167.2022.10008308","DOIUrl":"https://doi.org/10.1109/CICN56167.2022.10008308","url":null,"abstract":"Two-dimensional direction of arrival estimation is a computationally complex problem that has been the focus of research in the area of array signal processing for several decades now. This paper proposes a novel2D DOA azimuth and elevation angle estimation algorithm for multiple RF noncoherent sources using an L-shaped array antenna configuration. The proposed method employs a MUSIC-like estimation algorithm in conjunction with QR decomposition to improve the accuracy of 2D DOA estimation and provide much lower computational complexity when compared with existing methods such as the Capon method. It does not require knowing the number of sources in advance and pairs the estimated azimuth and elevation angles automatically for multiple sources. Simulation results are presented to validate the efficacy of the proposed method and its performance is compared with the Capon method.","PeriodicalId":287589,"journal":{"name":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127044320","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 : 2022-12-04DOI: 10.1109/CICN56167.2022.10008302
Razan Alzaben, Shuruq Fallatah, Haneen Quraishi, Sadiq Alhuwaidi, Ahmed A. Hussain
As one of the nations that produce and supply dates, the Kingdom of Saudi Arabia has long been interested in the date palm, its cultivation, and the support of farmers, making it a significant economic component. One of the most devastating problems for these palms is the red palm weevil, as it lives inside the trunk of the palm for a duration of six to eight months. An integrated smart system is designed to diagnose the existence of the red palm weevil. Such a system determines if the palm is infected or not in the early stages, which makes the problem easier to deal with and allows the progression of the healing process. The integrated work: (1) is an environmentally friendly system based on solar energy (2) monitors the condition of the palm and the possibility of injury remotely for each area (3) tracks and catches the palm weevils for each area, and (4) alerts the user if weevils are present. The user can know the condition of all palms and know the possibility of the presence of weevils using a set of sensors. The data are accessed remotely from the communication systems developed via algorithms.
{"title":"loT-based Red Palm Weevil Early Detection and Tracking System","authors":"Razan Alzaben, Shuruq Fallatah, Haneen Quraishi, Sadiq Alhuwaidi, Ahmed A. Hussain","doi":"10.1109/CICN56167.2022.10008302","DOIUrl":"https://doi.org/10.1109/CICN56167.2022.10008302","url":null,"abstract":"As one of the nations that produce and supply dates, the Kingdom of Saudi Arabia has long been interested in the date palm, its cultivation, and the support of farmers, making it a significant economic component. One of the most devastating problems for these palms is the red palm weevil, as it lives inside the trunk of the palm for a duration of six to eight months. An integrated smart system is designed to diagnose the existence of the red palm weevil. Such a system determines if the palm is infected or not in the early stages, which makes the problem easier to deal with and allows the progression of the healing process. The integrated work: (1) is an environmentally friendly system based on solar energy (2) monitors the condition of the palm and the possibility of injury remotely for each area (3) tracks and catches the palm weevils for each area, and (4) alerts the user if weevils are present. The user can know the condition of all palms and know the possibility of the presence of weevils using a set of sensors. The data are accessed remotely from the communication systems developed via algorithms.","PeriodicalId":287589,"journal":{"name":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130207961","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 : 2022-12-04DOI: 10.1109/CICN56167.2022.10008378
Zulfi, J. Suryana, A. Munir
This paper presents a reconfigurable phase difference of hybrid coupler design. The proposed design is developed based on a branch-line coupler structure where a pair of conventional lines directly connecting the input and output ports are replaced by variable electrical length lines. To realize variable-length lines, a loaded-line structure composed of three microstrip line segments with four loading capacitors is adopted. A circuit prototype working at 2.4 GHz frequency is realized and measured for verification. Measurement results demonstrate that the proposed coupler can exhibit a reconfigurable phase difference characteristic. By varying capacitances of 0.5 pF to 2.5 pF, a phase difference range of 45° from -67.5° to -112.5° can be achieved. The prototype has the size of 18.2 mm by 41.2 mm, which is smaller than the conventional one.
提出了一种可重构的混合式耦合器相位差设计方法。所提出的设计是基于分支线耦合器结构开发的，其中一对直接连接输入和输出端口的传统线路被可变电气长度线取代。为了实现变长线路，采用了由3个微带线段和4个负载电容组成的负载线结构。实现了工作在2.4 GHz频率下的电路样机，并进行了测试验证。测量结果表明，该耦合器具有可重构的相位差特性。通过改变0.5 pF到2.5 pF的电容，可以实现45°的相位差范围从-67.5°到-112.5°。原型机的尺寸为18.2 mm × 41.2 mm，比传统的尺寸要小。
{"title":"Phase Reconfigurable Hybrid Coupler Implemented Using Capacitor-Loaded Transmission Lines","authors":"Zulfi, J. Suryana, A. Munir","doi":"10.1109/CICN56167.2022.10008378","DOIUrl":"https://doi.org/10.1109/CICN56167.2022.10008378","url":null,"abstract":"This paper presents a reconfigurable phase difference of hybrid coupler design. The proposed design is developed based on a branch-line coupler structure where a pair of conventional lines directly connecting the input and output ports are replaced by variable electrical length lines. To realize variable-length lines, a loaded-line structure composed of three microstrip line segments with four loading capacitors is adopted. A circuit prototype working at 2.4 GHz frequency is realized and measured for verification. Measurement results demonstrate that the proposed coupler can exhibit a reconfigurable phase difference characteristic. By varying capacitances of 0.5 pF to 2.5 pF, a phase difference range of 45° from -67.5° to -112.5° can be achieved. The prototype has the size of 18.2 mm by 41.2 mm, which is smaller than the conventional one.","PeriodicalId":287589,"journal":{"name":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130889332","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 : 2022-12-04DOI: 10.1109/CICN56167.2022.10008293
Mohammed Gollapalli, B. Saad, Jomana Alabdulkarim, Razan Sendi, Reema Alsabt, Sarah Alsharif
The slow progression of chronic kidney disease (CKD) makes early detection and effective treatment the only ways to prevent the mortality rates. In this study, an amalgamation of ensemble machine learning (ML) models has been leveraged in an effort to support clinicians in their goal of faster, more accurate CKD recognition and detection. By detecting and assessing the risk variables early on, patients could limit the ramifications of this disease on their health. Consequently, binary categorization is the basis of this proposed ML technique. The CKD dataset, obtained from the UCI machine learning repository was utilized in this research consisting of 400 instances and 24 attributes, which is comprised of indicators, symptoms, and risk factors. 80% of the data was used to train the model, while the remaining 20% was used for testing. While utilizing the entire set of 25 features, the CatBoost and Random Forest models outperformed and outmatched the remaining algorithms with an accuracy of 99%. The Decision Tree, Ada Boost, and SVM algorithms were then used, with a constructive accuracy rate of 98%, 98%, and 95%, respectively. Furthermore, ROC curve for the five chosen ML models was used as a significant evaluation metric to help improve and supplement our understanding of the performance of the CKD categorization challenges. The results showed that the CatBoost model is more efficient and competent in successfully and accurately classifying a patient's CKD status, with an accuracy of 99.9% when critical attributes were used.
{"title":"Detection of Chronic Kidney Disease Using Machine Learning Approach","authors":"Mohammed Gollapalli, B. Saad, Jomana Alabdulkarim, Razan Sendi, Reema Alsabt, Sarah Alsharif","doi":"10.1109/CICN56167.2022.10008293","DOIUrl":"https://doi.org/10.1109/CICN56167.2022.10008293","url":null,"abstract":"The slow progression of chronic kidney disease (CKD) makes early detection and effective treatment the only ways to prevent the mortality rates. In this study, an amalgamation of ensemble machine learning (ML) models has been leveraged in an effort to support clinicians in their goal of faster, more accurate CKD recognition and detection. By detecting and assessing the risk variables early on, patients could limit the ramifications of this disease on their health. Consequently, binary categorization is the basis of this proposed ML technique. The CKD dataset, obtained from the UCI machine learning repository was utilized in this research consisting of 400 instances and 24 attributes, which is comprised of indicators, symptoms, and risk factors. 80% of the data was used to train the model, while the remaining 20% was used for testing. While utilizing the entire set of 25 features, the CatBoost and Random Forest models outperformed and outmatched the remaining algorithms with an accuracy of 99%. The Decision Tree, Ada Boost, and SVM algorithms were then used, with a constructive accuracy rate of 98%, 98%, and 95%, respectively. Furthermore, ROC curve for the five chosen ML models was used as a significant evaluation metric to help improve and supplement our understanding of the performance of the CKD categorization challenges. The results showed that the CatBoost model is more efficient and competent in successfully and accurately classifying a patient's CKD status, with an accuracy of 99.9% when critical attributes were used.","PeriodicalId":287589,"journal":{"name":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127869857","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 : 2022-12-04DOI: 10.1109/CICN56167.2022.10008331
Yazid M. Khattabi, S. Alkhawaldeh
In this paper, a spatial modulation (SM)-based multiple input multiple output (MIMO) wireless communication system that is operating over time-variant Rayleigh fading channels is considered. The channel state information (CSI) is assumed to be estimated perfectly and on the basis of the piloted estimation method. For such a system, an analytical approach is proposed to derive the system”s conditional pairwise-error-probability (PEP) exactly. The approach starts by reducing the SM maximum likelihood (ML) decoding rule to classical decision-statistic rule. The distribution of the decision-statistic is then determined to be zero-mean Gaussian, which helps in obtaining the conditional PEP directly in terms of the Q-function. The derived conditional PEP expression is new, explicitly expressed in terms of variant system and channel parameters, and directly used to compute the system”s average bit error probability. Numerical and simulation results are presented to verify the derivations and to demonstrate some insightful performance observations.
{"title":"New Approach in the Error Performance Analysis of SM over Time-Variant Rayleigh Fading Channels","authors":"Yazid M. Khattabi, S. Alkhawaldeh","doi":"10.1109/CICN56167.2022.10008331","DOIUrl":"https://doi.org/10.1109/CICN56167.2022.10008331","url":null,"abstract":"In this paper, a spatial modulation (SM)-based multiple input multiple output (MIMO) wireless communication system that is operating over time-variant Rayleigh fading channels is considered. The channel state information (CSI) is assumed to be estimated perfectly and on the basis of the piloted estimation method. For such a system, an analytical approach is proposed to derive the system”s conditional pairwise-error-probability (PEP) exactly. The approach starts by reducing the SM maximum likelihood (ML) decoding rule to classical decision-statistic rule. The distribution of the decision-statistic is then determined to be zero-mean Gaussian, which helps in obtaining the conditional PEP directly in terms of the Q-function. The derived conditional PEP expression is new, explicitly expressed in terms of variant system and channel parameters, and directly used to compute the system”s average bit error probability. Numerical and simulation results are presented to verify the derivations and to demonstrate some insightful performance observations.","PeriodicalId":287589,"journal":{"name":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125577296","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 : 2022-12-04DOI: 10.1109/CICN56167.2022.10008260
R. Parashar, D. Yadav, A. Saharia, M. Tiwari, G. Singh
A tetra band slotted structure is designed detail analysis with compactness in dimensions $mathbf{29}.mathbf{5} mathbf{mm} times mathbf{22} mathbf{mm} times mathbf{1}.mathbf{6}$ mm. Proposed antenna is operating at four resonant microwave frequency bands to cover the WiMAX (3.34 - 4.42 GHz), Upper C band radio telecommunication (7.20-7.43 GHz), Lower X band amateur radio application (8.91-10.72 GHz) and middle $mathbf{K}_{mathbf{U}}$ band molecular rotational spectroscopy (14.2514.94 GHz) wireless applications. The slotted octagonal shape radiating patch and trapezoidal shape partial ground section is implemented on FR-4 dielectric substrate material. Antenna achieve the tetra band configuration with appropriate simulated results of return loss, radiation patterns, gain and radiation efficiency. Simulated results are stable at achieved resonating modes.
设计了一种四频带开槽结构，详细分析了其在维度$mathbf{29}上的紧凑性。mathbf{5} mathbf{mm} times mathbf{22} mathbf{mm} times mathbf{1}。该天线工作在四个谐振微波频段，覆盖WiMAX (3.34 - 4.42 GHz)、上C波段无线电通信(7.20-7.43 GHz)、下X波段业余无线电应用(8.91-10.72 GHz)和中$mathbf{K}_{mathbf{U}}$波段分子旋转光谱(14.2514.94 GHz)无线应用。在FR-4介电衬底材料上实现开槽的八边形辐射片和梯形局部接地段。天线通过适当的回波损耗、辐射方向图、增益和辐射效率模拟结果实现了四频带配置。仿真结果在实现的谐振模式下是稳定的。
{"title":"Implementation of four-band slotted patch Antenna","authors":"R. Parashar, D. Yadav, A. Saharia, M. Tiwari, G. Singh","doi":"10.1109/CICN56167.2022.10008260","DOIUrl":"https://doi.org/10.1109/CICN56167.2022.10008260","url":null,"abstract":"A tetra band slotted structure is designed detail analysis with compactness in dimensions $mathbf{29}.mathbf{5} mathbf{mm} times mathbf{22} mathbf{mm} times mathbf{1}.mathbf{6}$ mm. Proposed antenna is operating at four resonant microwave frequency bands to cover the WiMAX (3.34 - 4.42 GHz), Upper C band radio telecommunication (7.20-7.43 GHz), Lower X band amateur radio application (8.91-10.72 GHz) and middle $mathbf{K}_{mathbf{U}}$ band molecular rotational spectroscopy (14.2514.94 GHz) wireless applications. The slotted octagonal shape radiating patch and trapezoidal shape partial ground section is implemented on FR-4 dielectric substrate material. Antenna achieve the tetra band configuration with appropriate simulated results of return loss, radiation patterns, gain and radiation efficiency. Simulated results are stable at achieved resonating modes.","PeriodicalId":287589,"journal":{"name":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","volume":"272 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115852794","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 : 2022-12-04DOI: 10.1109/CICN56167.2022.10008340
M. Aljabri, Dorieh M. Alomari, Menna Aboulnour
Nowadays, with the widespread use of technology, fake news and rumors are spreading too. People and society are greatly impacted by fake news, which also can be used as phishing attempts and a way of stealing their information. In many areas of our lives, Artificial Intelligence (AI) and Machine Learning (ML) have demonstrated their effectiveness. Furthermore, Natural Language Processing (NLP) has shown promising results in text classification applications. In this study, we proposed an experimental study for detecting fake news using ML models. The proposed model analyzes the main text of the news using NLP techniques and then classifies the news into fake or real news. We used a new dataset that combined multiple fake news datasets. Moreover, we studied the impact of features extraction methods on the performance of the developed models. Eight experiments were performed using Random Forest (RF) and Support Vector Machines (SVM) models, each with a different features extraction technique. The SVM model resulted in the best performance with an accuracy level of 98%. This result proves the model ability to be deployed and used in real-world with high reliability, to detect fake news.
{"title":"Fake News Detection Using Machine Learning Models","authors":"M. Aljabri, Dorieh M. Alomari, Menna Aboulnour","doi":"10.1109/CICN56167.2022.10008340","DOIUrl":"https://doi.org/10.1109/CICN56167.2022.10008340","url":null,"abstract":"Nowadays, with the widespread use of technology, fake news and rumors are spreading too. People and society are greatly impacted by fake news, which also can be used as phishing attempts and a way of stealing their information. In many areas of our lives, Artificial Intelligence (AI) and Machine Learning (ML) have demonstrated their effectiveness. Furthermore, Natural Language Processing (NLP) has shown promising results in text classification applications. In this study, we proposed an experimental study for detecting fake news using ML models. The proposed model analyzes the main text of the news using NLP techniques and then classifies the news into fake or real news. We used a new dataset that combined multiple fake news datasets. Moreover, we studied the impact of features extraction methods on the performance of the developed models. Eight experiments were performed using Random Forest (RF) and Support Vector Machines (SVM) models, each with a different features extraction technique. The SVM model resulted in the best performance with an accuracy level of 98%. This result proves the model ability to be deployed and used in real-world with high reliability, to detect fake news.","PeriodicalId":287589,"journal":{"name":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131283771","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 : 2022-12-04DOI: 10.1109/CICN56167.2022.10008309
Ashraf Mohammed Saeed, Zaid Alyafeai, Ashraf Mahmoud
Intrusion detection systems (IDS) have been used to identify several types of attacks. Several issues can affect the classification of attacks, such as classification results which can be biased due to unbalanced data that have been used in the training of the classifier. Moreover, the detection rate of these IDS has to be improved to detect as many as possible of several attacks. In this paper, we propose to use a complex sequential model such as Gated Recurrent Units to classify different kinds of attacks. We use the NSL-KDD dataset to train our model. This dataset has unbalanced data which might affect the results of our classifier. To fix this issue, we use Dropout and weighted cross entropy loss function to overcome the issue of unbalanced data. Our results show that there is an enhancement in the detection rate of the classifier. we have achieved a higher detection rate compared with previous studies.
{"title":"Network Traffic Classifications using Gated Recurrent Units with Weighted Cross-entropy","authors":"Ashraf Mohammed Saeed, Zaid Alyafeai, Ashraf Mahmoud","doi":"10.1109/CICN56167.2022.10008309","DOIUrl":"https://doi.org/10.1109/CICN56167.2022.10008309","url":null,"abstract":"Intrusion detection systems (IDS) have been used to identify several types of attacks. Several issues can affect the classification of attacks, such as classification results which can be biased due to unbalanced data that have been used in the training of the classifier. Moreover, the detection rate of these IDS has to be improved to detect as many as possible of several attacks. In this paper, we propose to use a complex sequential model such as Gated Recurrent Units to classify different kinds of attacks. We use the NSL-KDD dataset to train our model. This dataset has unbalanced data which might affect the results of our classifier. To fix this issue, we use Dropout and weighted cross entropy loss function to overcome the issue of unbalanced data. Our results show that there is an enhancement in the detection rate of the classifier. we have achieved a higher detection rate compared with previous studies.","PeriodicalId":287589,"journal":{"name":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133921036","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：