Pub Date : 2020-10-24DOI: 10.1109/NILES50944.2020.9257942
Yasmeen M. Abdelradi, A. El-Sherif, Laila H. Afify
Traffic offloading is considered a promising solution to relieve the explosive congestion of future cellular networks. Existing works in the literature focus on increasing the number of offloaded users. Nevertheless, users’ traffic load plays a critical role in having the ability to relay the data intended for the cellular users. In this paper, we consider the traffic offloading problem in a heterogeneous network (HetNet), with emphasis on the traffic load of each user in the network. Our objective is to maximize the total network energy efficiency (EE) while maintaining the system queues stability. We propose a heuristic offloading algorithm due to the non-convexity of the EE problem. Numerical results demonstrate that the proposed offloading algorithm outperforms similar algorithms in the literature that do not take the users’ traffic load into consideration during the offloading process.
{"title":"A Queueing Theory Approach for Maximized Energy Efficiency Traffic Offloading","authors":"Yasmeen M. Abdelradi, A. El-Sherif, Laila H. Afify","doi":"10.1109/NILES50944.2020.9257942","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257942","url":null,"abstract":"Traffic offloading is considered a promising solution to relieve the explosive congestion of future cellular networks. Existing works in the literature focus on increasing the number of offloaded users. Nevertheless, users’ traffic load plays a critical role in having the ability to relay the data intended for the cellular users. In this paper, we consider the traffic offloading problem in a heterogeneous network (HetNet), with emphasis on the traffic load of each user in the network. Our objective is to maximize the total network energy efficiency (EE) while maintaining the system queues stability. We propose a heuristic offloading algorithm due to the non-convexity of the EE problem. Numerical results demonstrate that the proposed offloading algorithm outperforms similar algorithms in the literature that do not take the users’ traffic load into consideration during the offloading process.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131490090","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257949
Ali Amin, Salmeen Bahnasy, Asmaa Elhadidy, M. Elattar
Since traffic congestion is becoming a regular part of commuters’ life, there is a pressing need for better traffic management. Most current traffic control systems are not sensitive to the current state of the roads being controlled, instead they are fixed, timed traffic signals that do not respond to unpredicted congestion. Solutions have been proposed to solve this problem including creating a large database for each traffic stop and determining the optimal traffic signals for the best vehicle flow based on the statistics collected, which does not react to data outliers. Other solutions suggest installing weight sensors under roads to detect the number of vehicles waiting then setting the duration of the next green light accordingly. This paper proposes an image analysis work flow to analyze the number of waiting vehicles as well as moving vehicles in each arm of a 4-way intersection. Then the collected data is utilized to control the state of the entire intersection to ensure the best traffic flow for all waiting and moving vehicles. Results from this approach yielded an absolute mean error of 0.559 detected representative vehicles with standard deviation of 0.93 on the first dataset and mean absolute error of 0.554 with 1.20 standard deviation for the second dataset. This level of accuracy conformed with the finite state machine control logic of the intersection, moving from one state to the other according to the analyzed images in real-time without causing starvation to any of the intersection arms.
{"title":"Real-time 4-way Intersection Smart Traffic Control System","authors":"Ali Amin, Salmeen Bahnasy, Asmaa Elhadidy, M. Elattar","doi":"10.1109/NILES50944.2020.9257949","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257949","url":null,"abstract":"Since traffic congestion is becoming a regular part of commuters’ life, there is a pressing need for better traffic management. Most current traffic control systems are not sensitive to the current state of the roads being controlled, instead they are fixed, timed traffic signals that do not respond to unpredicted congestion. Solutions have been proposed to solve this problem including creating a large database for each traffic stop and determining the optimal traffic signals for the best vehicle flow based on the statistics collected, which does not react to data outliers. Other solutions suggest installing weight sensors under roads to detect the number of vehicles waiting then setting the duration of the next green light accordingly. This paper proposes an image analysis work flow to analyze the number of waiting vehicles as well as moving vehicles in each arm of a 4-way intersection. Then the collected data is utilized to control the state of the entire intersection to ensure the best traffic flow for all waiting and moving vehicles. Results from this approach yielded an absolute mean error of 0.559 detected representative vehicles with standard deviation of 0.93 on the first dataset and mean absolute error of 0.554 with 1.20 standard deviation for the second dataset. This level of accuracy conformed with the finite state machine control logic of the intersection, moving from one state to the other according to the analyzed images in real-time without causing starvation to any of the intersection arms.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130607637","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257983
Omar Laimona, Mohamed A. Manzour, Omar M. Shehata, E. I. Morgan
For an autonomous vehicle driving on a public road, the safety of the passengers and the efficiency of the trip taken are prioritized causing the main function of the autonomous vehicle to be interpreting and inferring the intention of surrounding vehicles, and warning the driver accordingly. Recent Advanced Driving Assistance Systems (ADAS) are capable of and usually limited to, support features like forward-collision warnings, alerting the driver of hazardous road conditions, detecting road markings, and warning the driver if they are changing lanes. However, modern ADAS are still unable to perform basic vehicle-behavior-prediction humans are capable of. In this paper, we introduce and compare the results of two different methodologies, Recurrent Neural Networks (RNN) and Long Short-Term Memory networks (LSTM), for lane-changing intention prediction of surrounding vehicles. For the LSTM model, the F1-score achieved was 0.944 for lane-keeping, 0.781 for left lane-changing, and 0.942 for right lane-changing. The RNN-based model reached an F1-score of 0.704 for lane-keeping, 0.533 for left lane-changing, and 0.714 for right lane-changing. The training process of these data-driven based methodologies can be implemented using sequences of changing centroids of vehicles along with the frames and labeling of the maneuvers introduced by the PREVENTION dataset.
{"title":"Implementation and Evaluation of an Enhanced Intention Prediction Algorithm for Lane-Changing Scenarios on Highway Roads","authors":"Omar Laimona, Mohamed A. Manzour, Omar M. Shehata, E. I. Morgan","doi":"10.1109/NILES50944.2020.9257983","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257983","url":null,"abstract":"For an autonomous vehicle driving on a public road, the safety of the passengers and the efficiency of the trip taken are prioritized causing the main function of the autonomous vehicle to be interpreting and inferring the intention of surrounding vehicles, and warning the driver accordingly. Recent Advanced Driving Assistance Systems (ADAS) are capable of and usually limited to, support features like forward-collision warnings, alerting the driver of hazardous road conditions, detecting road markings, and warning the driver if they are changing lanes. However, modern ADAS are still unable to perform basic vehicle-behavior-prediction humans are capable of. In this paper, we introduce and compare the results of two different methodologies, Recurrent Neural Networks (RNN) and Long Short-Term Memory networks (LSTM), for lane-changing intention prediction of surrounding vehicles. For the LSTM model, the F1-score achieved was 0.944 for lane-keeping, 0.781 for left lane-changing, and 0.942 for right lane-changing. The RNN-based model reached an F1-score of 0.704 for lane-keeping, 0.533 for left lane-changing, and 0.714 for right lane-changing. The training process of these data-driven based methodologies can be implemented using sequences of changing centroids of vehicles along with the frames and labeling of the maneuvers introduced by the PREVENTION dataset.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133569159","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257882
Adel Samir EL-Zemity, A. Gaafar, Ahmed Khaled Abdella Ahmed, A. Abdelwahab, Hatim Mohamed Saad, Mostafa Khaled Elboushi, Amira Mofreh Ibraheem
In this paper the activated sludge wastewater treatment process is modeled mathematically and explored. In addition, irrigation was recommended as a valid application for the reuse of wastewater. Other wastewater treatment processes (WWTP) were compared to the one chosen to justify the choice and a detailed expiation of the general wastewater treatment process was provided. Furthermore, PI, and PID controller were developed to further improve the performance of the activated sludge process. The controllers were devolved and tuned using MATLAB, and SIMULINK, and had a positive correlation on the performance of the wastewater treatment process, and consequently the irrigation systems.
{"title":"Wastewater Treatment Model with Smart Irrigation Utilizing PID Control","authors":"Adel Samir EL-Zemity, A. Gaafar, Ahmed Khaled Abdella Ahmed, A. Abdelwahab, Hatim Mohamed Saad, Mostafa Khaled Elboushi, Amira Mofreh Ibraheem","doi":"10.1109/NILES50944.2020.9257882","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257882","url":null,"abstract":"In this paper the activated sludge wastewater treatment process is modeled mathematically and explored. In addition, irrigation was recommended as a valid application for the reuse of wastewater. Other wastewater treatment processes (WWTP) were compared to the one chosen to justify the choice and a detailed expiation of the general wastewater treatment process was provided. Furthermore, PI, and PID controller were developed to further improve the performance of the activated sludge process. The controllers were devolved and tuned using MATLAB, and SIMULINK, and had a positive correlation on the performance of the wastewater treatment process, and consequently the irrigation systems.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128651105","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257918
Lamis Sharawy, M. Tantawy, Yara A. Ahmed, A. Taha, Omar Soliman, Tamer M. Ibrahim, M. El-Hadidi
In the current SARS-CoV2 pandemic, identification and differentiation between SARS-COV2 strains are vital to attain efficient therapeutic targeting, drug discovery and vaccination. In this study, we investigate how the viral genetic code mutated locally and what variations is the Egyptian population most susceptible to in comparison with different strains isolated from Asia, Europe and other countries in Africa. Our aim is to evaluate the significance of these variations and whether they constitute a change on the protein level and identify if any of these variations occurred in the conserved domain of the virus. The available Covid-19 complete genome nucleotide sequences on NCBI were gathered and filtered, and representative sequences were selected from each of the mentioned continents to make the population of our sample 1535 sequences. Multiple sequence alignment was conducted for all the 1535 sequences obtained from NCBI. For higher accuracy, we used the MAFFT iterative refinement method. Conserved domain extraction was carried out for all 1535 sequence for mutation evaluation. When the mutations were evaluated, Spike_D614G, NSP12_P323L, NS3_Q57H and N_R203K were found to be the most common amino acid substitutions among the viral isolates from Egypt. All retrieved mutations were processed and analyzed with principal component analysis (PCA). In general, no clear clusters were clustered based on the mutation pattern of different continents, including Africa, Asia, and Europe. However, PCA shows that the African mutation pattern is a partial subset of the complete European mutation pattern.
{"title":"In-Silico Comparative Analysis of Egyptian SARS CoV-2 with Other Populations: a Phylogeny and Mutation Analysis","authors":"Lamis Sharawy, M. Tantawy, Yara A. Ahmed, A. Taha, Omar Soliman, Tamer M. Ibrahim, M. El-Hadidi","doi":"10.1109/NILES50944.2020.9257918","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257918","url":null,"abstract":"In the current SARS-CoV2 pandemic, identification and differentiation between SARS-COV2 strains are vital to attain efficient therapeutic targeting, drug discovery and vaccination. In this study, we investigate how the viral genetic code mutated locally and what variations is the Egyptian population most susceptible to in comparison with different strains isolated from Asia, Europe and other countries in Africa. Our aim is to evaluate the significance of these variations and whether they constitute a change on the protein level and identify if any of these variations occurred in the conserved domain of the virus. The available Covid-19 complete genome nucleotide sequences on NCBI were gathered and filtered, and representative sequences were selected from each of the mentioned continents to make the population of our sample 1535 sequences. Multiple sequence alignment was conducted for all the 1535 sequences obtained from NCBI. For higher accuracy, we used the MAFFT iterative refinement method. Conserved domain extraction was carried out for all 1535 sequence for mutation evaluation. When the mutations were evaluated, Spike_D614G, NSP12_P323L, NS3_Q57H and N_R203K were found to be the most common amino acid substitutions among the viral isolates from Egypt. All retrieved mutations were processed and analyzed with principal component analysis (PCA). In general, no clear clusters were clustered based on the mutation pattern of different continents, including Africa, Asia, and Europe. However, PCA shows that the African mutation pattern is a partial subset of the complete European mutation pattern.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124159160","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257874
Hanaa Abohashima, M. Gheith, A. Eltawil
Smart traffic lights control systems started to appear in use on our roads particularly in the metropolitan areas. The technology aims to smoothen the flow of vehicles within junctions with the least waiting time and queue length which are the most popular metrics of traffic lights system. In this type of control system, traffic lights scheduling, and duration have to be dynamically controlled, which needs an intelligent traffic control scheme. In this paper, a framework of applying Vehicle-to-vehicle communications (V2V), Vehicle-to-infrastructure (V2I), Vehicle-to-everything (V2X), Internet of things (IoT) and Artificial intelligent techniques (AI) in the context of traffic lights management and control in an Internet of Things environment is introduced. Also, the dynamic scheduling of traffic lights given the real-time data from road and vehicle embedded sensors is elaborated. The paper also integrated the mathematical methods with the Neuro-Fuzzy based traffic control system for taking an intelligent decision based on the present traffic flows.
{"title":"A proposed IoT based Smart traffic lights control system within a V2X framework","authors":"Hanaa Abohashima, M. Gheith, A. Eltawil","doi":"10.1109/NILES50944.2020.9257874","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257874","url":null,"abstract":"Smart traffic lights control systems started to appear in use on our roads particularly in the metropolitan areas. The technology aims to smoothen the flow of vehicles within junctions with the least waiting time and queue length which are the most popular metrics of traffic lights system. In this type of control system, traffic lights scheduling, and duration have to be dynamically controlled, which needs an intelligent traffic control scheme. In this paper, a framework of applying Vehicle-to-vehicle communications (V2V), Vehicle-to-infrastructure (V2I), Vehicle-to-everything (V2X), Internet of things (IoT) and Artificial intelligent techniques (AI) in the context of traffic lights management and control in an Internet of Things environment is introduced. Also, the dynamic scheduling of traffic lights given the real-time data from road and vehicle embedded sensors is elaborated. The paper also integrated the mathematical methods with the Neuro-Fuzzy based traffic control system for taking an intelligent decision based on the present traffic flows.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128801224","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257967
Mohamed Shelkamy, Catherine M. Elias, Dalia M. Mahfouz, Omar M. Shehata
Nowadays, The dependency on robotic fleets is increasing all over the globe. As a result of this increase, the Multi-Robot Systems (MRS) become a topic of considerable interest. One of the most problems solved by the introduction of MRS is the Multi-Robot Task Allocation (MRTA) problem. In order to determine the most suitable technique used in solving the MRTA problem, optimization based approaches are investigated. This paper represents a guide for researchers in the field of MRTA application to choose the suitable algorithm to solve the problem depending on the problem space and constraints. This paper introduces two different stochastic approaches to solve such problem which are the Genetic Algorithm (GA) and the Ant-Colony Optimization (ACO) algorithm. The two algorithms are tested and compared through several test cases. Results show that both algorithms have acceptable performance in terms of minimum distance and time convergence with certain limitations for each algorithm that are discussed through out the study.
{"title":"Comparative Analysis of Various Optimization Techniques for Solving Multi-Robot Task Allocation Problem","authors":"Mohamed Shelkamy, Catherine M. Elias, Dalia M. Mahfouz, Omar M. Shehata","doi":"10.1109/NILES50944.2020.9257967","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257967","url":null,"abstract":"Nowadays, The dependency on robotic fleets is increasing all over the globe. As a result of this increase, the Multi-Robot Systems (MRS) become a topic of considerable interest. One of the most problems solved by the introduction of MRS is the Multi-Robot Task Allocation (MRTA) problem. In order to determine the most suitable technique used in solving the MRTA problem, optimization based approaches are investigated. This paper represents a guide for researchers in the field of MRTA application to choose the suitable algorithm to solve the problem depending on the problem space and constraints. This paper introduces two different stochastic approaches to solve such problem which are the Genetic Algorithm (GA) and the Ant-Colony Optimization (ACO) algorithm. The two algorithms are tested and compared through several test cases. Results show that both algorithms have acceptable performance in terms of minimum distance and time convergence with certain limitations for each algorithm that are discussed through out the study.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126450156","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257876
Mohamed A. Wahby Shalaby, Marwa T. Saleh, H. Elmahdy
Human’s health information is considered momentous information, which is represented in medical systems. The amount of medical image information available for analysis is increasing with the modern medical image devices and biomedical image processing techniques. To prevent data modification from unauthorized persons from an insecure network, medical images should be encrypted efficiently. In this paper, a novel chaotic-based medical image encryption technique is proposed. This technique uses first a Butterworth High Pass Filter (BHPF) to enhance the medical image’s details to avoid any possible loss of medical details during the encryption-decryption process. The proposed technique is then developed by modifying Arnold’s cat map technique combined with the well-known Advanced Encryption Standard (AES) algorithm. By modifying Arnold’s cat map technique, three bits are formulated and added to the regular AES encryption key to increase the overall encryption robustness. A comparative study is conducted to compare first the efficiency of the proposed technique concerning Arnold’s Cat Map with AES (Cat-AES) and AES in its standard form. Then, the proposed encryption technique is also compared to the state-of-the-art chaotic-based medical image encryption techniques. It is shown from the comparative study that the proposed approach is capable of increasing both the strength of the encryption/decryption process and the quality of medical images with a reduction of the overall computational cost.
人体健康信息被认为是医疗系统中重要的信息。随着现代医学图像设备和生物医学图像处理技术的发展，可供分析的医学图像信息量不断增加。为了防止未经授权的人在不安全的网络中修改数据，医学图像必须进行有效的加密。提出了一种新的基于混沌的医学图像加密技术。该技术首先使用巴特沃斯高通滤波器(BHPF)增强医学图像的细节，以避免在加解密过程中可能丢失的医疗细节。然后，通过修改Arnold的猫图技术并结合著名的高级加密标准(AES)算法，开发了所提出的技术。通过修改Arnold的cat map技术，将三个比特添加到常规AES加密密钥中，以提高整体加密的鲁棒性。本文首先进行了一项比较研究，比较了所提出的关于Arnold’s Cat Map with AES (Cat-AES)和AES标准形式的效率。然后，将所提出的加密技术与最先进的基于混沌的医学图像加密技术进行了比较。对比研究表明，该方法能够提高加解密过程的强度和医学图像的质量，同时降低总体计算成本。
{"title":"Enhanced Arnold’s Cat Map-AES Encryption Technique for Medical Images","authors":"Mohamed A. Wahby Shalaby, Marwa T. Saleh, H. Elmahdy","doi":"10.1109/NILES50944.2020.9257876","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257876","url":null,"abstract":"Human’s health information is considered momentous information, which is represented in medical systems. The amount of medical image information available for analysis is increasing with the modern medical image devices and biomedical image processing techniques. To prevent data modification from unauthorized persons from an insecure network, medical images should be encrypted efficiently. In this paper, a novel chaotic-based medical image encryption technique is proposed. This technique uses first a Butterworth High Pass Filter (BHPF) to enhance the medical image’s details to avoid any possible loss of medical details during the encryption-decryption process. The proposed technique is then developed by modifying Arnold’s cat map technique combined with the well-known Advanced Encryption Standard (AES) algorithm. By modifying Arnold’s cat map technique, three bits are formulated and added to the regular AES encryption key to increase the overall encryption robustness. A comparative study is conducted to compare first the efficiency of the proposed technique concerning Arnold’s Cat Map with AES (Cat-AES) and AES in its standard form. Then, the proposed encryption technique is also compared to the state-of-the-art chaotic-based medical image encryption techniques. It is shown from the comparative study that the proposed approach is capable of increasing both the strength of the encryption/decryption process and the quality of medical images with a reduction of the overall computational cost.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124316619","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257961
Haneen G. Hezayyin, Nariman A. Khalil, A. Madian
The paper aims to propose three different inverse memristor emulators based on serveral active blocks. One of the presented emulator realizes employing second generation current conveyor (CCII) andcanalog voltage multiplier with passive elements. The other two introduced emulators are designed using cureent feedback operational amplifier (CFOA) with two switches or two BJT transistor. One of the proposed emulators has the advantages that it switches between the inverse and memristor at the same time but in different frequency with less number of components. The introduced circuitry are simulated to validate the concept of inverse memristor showing the pinched hysteresis loop in the I-V plane. Selected emulator is verified experimentally. A comparison of the three proposed emulators is presented to highlight the number ofcactive, passive components, and the range of frequency.
{"title":"Inverse memrsitor emulator active Realizations","authors":"Haneen G. Hezayyin, Nariman A. Khalil, A. Madian","doi":"10.1109/NILES50944.2020.9257961","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257961","url":null,"abstract":"The paper aims to propose three different inverse memristor emulators based on serveral active blocks. One of the presented emulator realizes employing second generation current conveyor (CCII) andcanalog voltage multiplier with passive elements. The other two introduced emulators are designed using cureent feedback operational amplifier (CFOA) with two switches or two BJT transistor. One of the proposed emulators has the advantages that it switches between the inverse and memristor at the same time but in different frequency with less number of components. The introduced circuitry are simulated to validate the concept of inverse memristor showing the pinched hysteresis loop in the I-V plane. Selected emulator is verified experimentally. A comparison of the three proposed emulators is presented to highlight the number ofcactive, passive components, and the range of frequency.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121539796","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 : 2020-10-24DOI: 10.1109/NILES50944.2020.9257979
Hossam Elghamry, Mohamed S. Ghoneim, Aya Abo Haggag, M. Darweesh, T. Ismail
Epileptic seizures occur as a result of functional brain dysfunction and can affect the health of the patient. Prediction of epileptic seizures before the onset is beneficial for the prevention of seizures through medication. Electroencephalograms (EEG) signals are used to predict epileptic seizures using machine learning techniques and feature extractions. Nevertheless, the pre-processing of EEG signals for noise removal and extraction of features are two significant problems that have an adverse effect on both anticipation time and true positive prediction performance. Considering this, the proposed model will provide remarkable methods for both pre-processing and extraction of features. The proposed model detects various brain states and accounts for both epileptic seizures detection and prediction. Using the EEG CHB-MIT dataset, the support vector machine (SVM) model was trained, tested, and compared, having a best true positive percentage of 91% for a single patient and 82% for multiple patients. The SVM algorithm was also compared to other machine learning algorithms such as K-Nearest Neighbors (KNN) proving to be more efficient with a true positive percentage of 82% than KNN with 80%.
{"title":"Comparative Analysis of Various Machine Learning Techniques for Epileptic Seizures Detection and Prediction Using EEG Data","authors":"Hossam Elghamry, Mohamed S. Ghoneim, Aya Abo Haggag, M. Darweesh, T. Ismail","doi":"10.1109/NILES50944.2020.9257979","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257979","url":null,"abstract":"Epileptic seizures occur as a result of functional brain dysfunction and can affect the health of the patient. Prediction of epileptic seizures before the onset is beneficial for the prevention of seizures through medication. Electroencephalograms (EEG) signals are used to predict epileptic seizures using machine learning techniques and feature extractions. Nevertheless, the pre-processing of EEG signals for noise removal and extraction of features are two significant problems that have an adverse effect on both anticipation time and true positive prediction performance. Considering this, the proposed model will provide remarkable methods for both pre-processing and extraction of features. The proposed model detects various brain states and accounts for both epileptic seizures detection and prediction. Using the EEG CHB-MIT dataset, the support vector machine (SVM) model was trained, tested, and compared, having a best true positive percentage of 91% for a single patient and 82% for multiple patients. The SVM algorithm was also compared to other machine learning algorithms such as K-Nearest Neighbors (KNN) proving to be more efficient with a true positive percentage of 82% than KNN with 80%.","PeriodicalId":253090,"journal":{"name":"2020 2nd Novel Intelligent and Leading Emerging Sciences Conference (NILES)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126736490","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：