Pub Date : 2020-10-24DOI: 10.1109/NILES50944.2020.9257954
Youssef A. Elbadri, Y. El-Batawy
Concentrated Solar Power (CSP) systems have a good potential as a renewable energy candidate that are based on converting the incident solar thermal energy to an electrical energy. In this paper, CSP using spot Fresnel lens instead of traditional lenses is presented to enhance the efficiency of the system, where Silicon Carbide (SiC) is used as a coating material for the receiver of the system due to its high thermal conductivity. The presented prototype has been investigated for uncoated spot Fresnel lens CSP, and for spot Fresnel lens CSP with the SiC as a coating material showing the enhancement of the presented design. The experimental efficiency of this design shows a significant improvement in the CSP efficiency.
{"title":"Enhancing CSP using Spot Fresnel Lens and SiC Coating","authors":"Youssef A. Elbadri, Y. El-Batawy","doi":"10.1109/NILES50944.2020.9257954","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257954","url":null,"abstract":"Concentrated Solar Power (CSP) systems have a good potential as a renewable energy candidate that are based on converting the incident solar thermal energy to an electrical energy. In this paper, CSP using spot Fresnel lens instead of traditional lenses is presented to enhance the efficiency of the system, where Silicon Carbide (SiC) is used as a coating material for the receiver of the system due to its high thermal conductivity. The presented prototype has been investigated for uncoated spot Fresnel lens CSP, and for spot Fresnel lens CSP with the SiC as a coating material showing the enhancement of the presented design. The experimental efficiency of this design shows a significant improvement in the CSP efficiency.","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":"126446956","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/NILES50944.2020.9257891
A. Alghamdi, G. Healy, Hoda A. Abdelhafez
Machine learning algorithms, such as ConvTasNet and Demucs, can separate between two interfering signals like music and speech, without any prior information about the mixing operation. The Conv-TasNet algorithm is a fully convolutional time-domain audio separation network while Demucs algorithm is a new waveform-to-waveform model. The Demucs algorithm employs a technique similar to the audio generation model and has larger decoder capacity. The criteria for comparison of these algorithms include high-quality signal separation (no artefacts) and less delay in the execution time. This research examined both algorithms in four experiments: music and male, music and female, music and conversation and music and child. The results were evaluated based on mir_eval and R square, root mean square error (RMSE) and mean absolute Error (MAE) scores. Conv-TasNet had the highest SDR score for music in the music and female experiment, with a high SDR score for child experiment. The SDR value of music in the music and female experiment was high using the Demucs algorithm (7.8), while the child experiment had the highest SDR value (8.15). In terms of average execution time, Conv-TasNet was seven times faster than Demucs. RMSE and MAE were also used for measuring accuracy. RMSE indicates absolute values, and MAE computes the average magnitude of errors between observations and prediction data. Both algorithms showed excellent results and high accuracy in the separation process.
{"title":"Real Time Blind Audio Source Separation Based on Machine Learning Algorithms","authors":"A. Alghamdi, G. Healy, Hoda A. Abdelhafez","doi":"10.1109/NILES50944.2020.9257891","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257891","url":null,"abstract":"Machine learning algorithms, such as ConvTasNet and Demucs, can separate between two interfering signals like music and speech, without any prior information about the mixing operation. The Conv-TasNet algorithm is a fully convolutional time-domain audio separation network while Demucs algorithm is a new waveform-to-waveform model. The Demucs algorithm employs a technique similar to the audio generation model and has larger decoder capacity. The criteria for comparison of these algorithms include high-quality signal separation (no artefacts) and less delay in the execution time. This research examined both algorithms in four experiments: music and male, music and female, music and conversation and music and child. The results were evaluated based on mir_eval and R square, root mean square error (RMSE) and mean absolute Error (MAE) scores. Conv-TasNet had the highest SDR score for music in the music and female experiment, with a high SDR score for child experiment. The SDR value of music in the music and female experiment was high using the Demucs algorithm (7.8), while the child experiment had the highest SDR value (8.15). In terms of average execution time, Conv-TasNet was seven times faster than Demucs. RMSE and MAE were also used for measuring accuracy. RMSE indicates absolute values, and MAE computes the average magnitude of errors between observations and prediction data. Both algorithms showed excellent results and high accuracy in the separation 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":"132249254","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/NILES50944.2020.9257964
M. A. Saleh, Mennaallah Soliman, M. Mousa, M. Elsamanty
Soft pneumatic actuators grasping tasks is one of the essential rules in robot manipulation methods. The grasping forces can be adapted to handle delicate and hard objects without leaving any damages on the object surfaces. This paper investigates the influence of the inclination angle of the soft pneumatic actuator (SPA) on its gripping force at its end tip. A range of inclination angles for SPA is analyzed using Finite Element Analysis (FEA) to estimate the gripping force at the end tip regarding SPA inner faces pressure. FEA study is conducted based on Hyperelastic material modeling employing non-linear analysis. Experimental validation is performed for three different air pillow inclined angle of SPAs fabricated by Fused Deposition Modeling (FDM) 3D printing. Experimental and FEA simulated data are compared to each other. Finally, a regression-based mathematical model is developed to obtain a direct correlation between the SPAs gripping force behavior concerning the inclination angle and applied pressure based on FEA data.
{"title":"Gripping Force Modeling of a Variable Inclined Air Pillow Soft Pneumatic Actuator","authors":"M. A. Saleh, Mennaallah Soliman, M. Mousa, M. Elsamanty","doi":"10.1109/NILES50944.2020.9257964","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257964","url":null,"abstract":"Soft pneumatic actuators grasping tasks is one of the essential rules in robot manipulation methods. The grasping forces can be adapted to handle delicate and hard objects without leaving any damages on the object surfaces. This paper investigates the influence of the inclination angle of the soft pneumatic actuator (SPA) on its gripping force at its end tip. A range of inclination angles for SPA is analyzed using Finite Element Analysis (FEA) to estimate the gripping force at the end tip regarding SPA inner faces pressure. FEA study is conducted based on Hyperelastic material modeling employing non-linear analysis. Experimental validation is performed for three different air pillow inclined angle of SPAs fabricated by Fused Deposition Modeling (FDM) 3D printing. Experimental and FEA simulated data are compared to each other. Finally, a regression-based mathematical model is developed to obtain a direct correlation between the SPAs gripping force behavior concerning the inclination angle and applied pressure based on FEA data.","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":"130083965","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/NILES50944.2020.9257976
Karim E. Ismail, Mohamed A. AbouRizka, F. Maghraby
Cancer detection is one of the most important research fields in the area of intelligent computing. Skin lesion diagnosis is a challenging topic, and several models have experimented on different datasets. Researchers proposed classification models that classify the lesion type if it is malignant or benign. The aim of this research is to propose a multiclass machine learning model that detect the lesion diagnosis rather than its type. The used dataset was retrieved from the International Skin Imaging Collaboration datasets archive since it is a benchmark that has thousands of dermoscopic images of different diagnoses. Melanoma, Nevus, and Seborrheic keratosis were the used lesion diagnosis. The proposed model consists of sequential phases, that start with the filtering and end with the classification. Kernel Support Vector Machine and Random Forest were the classifiers of the proposed model and their performance was measured by the KFold cross-validation accuracy.
{"title":"Machine Learning Model for Multiclass Lesion Diagnoses","authors":"Karim E. Ismail, Mohamed A. AbouRizka, F. Maghraby","doi":"10.1109/NILES50944.2020.9257976","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257976","url":null,"abstract":"Cancer detection is one of the most important research fields in the area of intelligent computing. Skin lesion diagnosis is a challenging topic, and several models have experimented on different datasets. Researchers proposed classification models that classify the lesion type if it is malignant or benign. The aim of this research is to propose a multiclass machine learning model that detect the lesion diagnosis rather than its type. The used dataset was retrieved from the International Skin Imaging Collaboration datasets archive since it is a benchmark that has thousands of dermoscopic images of different diagnoses. Melanoma, Nevus, and Seborrheic keratosis were the used lesion diagnosis. The proposed model consists of sequential phases, that start with the filtering and end with the classification. Kernel Support Vector Machine and Random Forest were the classifiers of the proposed model and their performance was measured by the KFold cross-validation accuracy.","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":"130187314","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/NILES50944.2020.9257946
Mohamed Esmail Abed, Mo'men Aly, H. Ammar, R. Shalaby
In this paper we implement and evaluate two ways of controlling the steering angle of an autonomous vehicle, PID control with manual tuning followed by gradient descent algorithm tuning-which is able to enhance the performance through self-adjusting the controller parameters-and using supervised machine learning through the end-to-end deep learning for self-driving car which implement Convolutional Neural Network (CNN) to predict the steering angle for a given instance of a track. The verification testing went through two phases: software simulation using python for first run testing and C++ for simulation followed by track testing with a vehicle prototype. The proposed PID steering control system exhibits more stable steering commands-less oscillations-which makes it better than CNN Behavioral cloning control model. However, CNN Behavioral Cloning model may show better results after many several hours of training.
{"title":"Steering Control for Autonomous Vehicles Using PID Control with Gradient Descent Tuning and Behavioral Cloning","authors":"Mohamed Esmail Abed, Mo'men Aly, H. Ammar, R. Shalaby","doi":"10.1109/NILES50944.2020.9257946","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257946","url":null,"abstract":"In this paper we implement and evaluate two ways of controlling the steering angle of an autonomous vehicle, PID control with manual tuning followed by gradient descent algorithm tuning-which is able to enhance the performance through self-adjusting the controller parameters-and using supervised machine learning through the end-to-end deep learning for self-driving car which implement Convolutional Neural Network (CNN) to predict the steering angle for a given instance of a track. The verification testing went through two phases: software simulation using python for first run testing and C++ for simulation followed by track testing with a vehicle prototype. The proposed PID steering control system exhibits more stable steering commands-less oscillations-which makes it better than CNN Behavioral cloning control model. However, CNN Behavioral Cloning model may show better results after many several hours of training.","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":"130284457","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/NILES50944.2020.9257888
A. Mohammed, Helmy M. El Zoghby, M. M. Elmesalawy
The worldwide outbreak due to COVID-19 pandemic lead to a major change in the life style in general and in the education system in specific. To help contain the impacts of COVID-19, universities and schools need to strongly shift to various electronic education models such as online learning, distance learning and blended learning. One of the crucial models that support the success of distance learning especially in engineering education is the remote-controlled experimentations, which allow students to execute the required practical work in a similar way as it conducted in the physical laboratories if it is appropriately designed. This paper introduces an integrated solution for improving the remotely controlled working on the educational laboratory experiments for electrical engineering sector. The proposed solution consists of four main components: Internet of remote-controlled things that represent the required experimentation devices, cloud platform, TCP/IP Internet communication connection, and finally the control and monitoring application. A complete experiment for phasor measurement unit (PMU) system as an example is deployed in the university laboratory with its all components which is completely controlled and managed remotely from the home through Internet. PMU is installed in a prototype of electrical substation with different types of loads. All required experimental data and results are successfully obtained and controlled through the developed system with the required accuracy and performance.
{"title":"Remote Controlled Laboratory Experiments for Engineering Education in the Post-COVID-19 Era: Concept and Example","authors":"A. Mohammed, Helmy M. El Zoghby, M. M. Elmesalawy","doi":"10.1109/NILES50944.2020.9257888","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257888","url":null,"abstract":"The worldwide outbreak due to COVID-19 pandemic lead to a major change in the life style in general and in the education system in specific. To help contain the impacts of COVID-19, universities and schools need to strongly shift to various electronic education models such as online learning, distance learning and blended learning. One of the crucial models that support the success of distance learning especially in engineering education is the remote-controlled experimentations, which allow students to execute the required practical work in a similar way as it conducted in the physical laboratories if it is appropriately designed. This paper introduces an integrated solution for improving the remotely controlled working on the educational laboratory experiments for electrical engineering sector. The proposed solution consists of four main components: Internet of remote-controlled things that represent the required experimentation devices, cloud platform, TCP/IP Internet communication connection, and finally the control and monitoring application. A complete experiment for phasor measurement unit (PMU) system as an example is deployed in the university laboratory with its all components which is completely controlled and managed remotely from the home through Internet. PMU is installed in a prototype of electrical substation with different types of loads. All required experimental data and results are successfully obtained and controlled through the developed system with the required accuracy and performance.","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":"131535352","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/NILES50944.2020.9257915
M. M. Elmesalawy, Abdullah Ibrahim Salama, M. Anany
The unprecedented spread of COVID-19 pandemic has become the main challenge for several countries around the world. One of the crucial measures taken to control and manage the diffusion of COVID-19 pandemic is contact tracing. The approach is based on tracing and identifying people who have been exposed to an infected individual to prevent onward transmission by alerting those who came in contact with the positive case; thus, isolation measures and suitable precautions can be taken. By using the communication and localization technologies embedded on the smartphones, those who made contact can be effectively traced by continuously collecting the timestamped locations and contacts of the owners. In this paper, an innovative privacy preserving smartphone-based contact tracing solution named ‘Tracy’ is proposed to help the health facilities to limit and control the spread of COVID-19 especially with the upcoming second wave of the virus. The proposed system consists of three main components: an intelligent application installed on smartphones, a data processing platform, and a website on which the different functions of those parts are integrated to provide the required services for the contact tracing solution. The system is designed to allow individuals to investigate the possibility of them contacting a person infected with the emerging coronavirus. A novel algorithm is designed to determine the effective location points in the individual's routes in which possible contacts can happen and based on these effective points, the prior contacts are decided. The system is also designed to provide an effective communication method with the local health facilities to receive medical advice and precautionary measures required for those who have discovered the possibility of contact with COVID-19. The reliability and scalability of the proposed solution is recognized by the usage of effective contact location points to determine the point of contact with the infected rather than using all the points of the individual's route.
{"title":"Tracy: Smartphone-based Contact Tracing Solution that Supports Self-investigation to Limit the Spread of COVID-19","authors":"M. M. Elmesalawy, Abdullah Ibrahim Salama, M. Anany","doi":"10.1109/NILES50944.2020.9257915","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257915","url":null,"abstract":"The unprecedented spread of COVID-19 pandemic has become the main challenge for several countries around the world. One of the crucial measures taken to control and manage the diffusion of COVID-19 pandemic is contact tracing. The approach is based on tracing and identifying people who have been exposed to an infected individual to prevent onward transmission by alerting those who came in contact with the positive case; thus, isolation measures and suitable precautions can be taken. By using the communication and localization technologies embedded on the smartphones, those who made contact can be effectively traced by continuously collecting the timestamped locations and contacts of the owners. In this paper, an innovative privacy preserving smartphone-based contact tracing solution named ‘Tracy’ is proposed to help the health facilities to limit and control the spread of COVID-19 especially with the upcoming second wave of the virus. The proposed system consists of three main components: an intelligent application installed on smartphones, a data processing platform, and a website on which the different functions of those parts are integrated to provide the required services for the contact tracing solution. The system is designed to allow individuals to investigate the possibility of them contacting a person infected with the emerging coronavirus. A novel algorithm is designed to determine the effective location points in the individual's routes in which possible contacts can happen and based on these effective points, the prior contacts are decided. The system is also designed to provide an effective communication method with the local health facilities to receive medical advice and precautionary measures required for those who have discovered the possibility of contact with COVID-19. The reliability and scalability of the proposed solution is recognized by the usage of effective contact location points to determine the point of contact with the infected rather than using all the points of the individual's route.","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":"133687585","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/NILES50944.2020.9257875
A. Boluwade
The COVID-19 event was unexpected and has had shocking impacts such as widespread economic losses and tens of thousands of deaths. The COVID-19 infection rate is relatively low in Africa compared to other continents, but the number of cases is rising. As of July 12, 2020, in Africa, there are a total of 13,194 deaths and 591,153 reported cases. The dynamics of this pandemic spread are relatively unknown; however, previous studies have established a relationship between poor air quality standards due to nitrogen dioxide (NO2) and fine particulate matter (PM2.5) and COVID-19 deaths and cases. Meanwhile, other studies have linked preexisting health conditions from cardiovascular diseases with COVID-19 fatalities. However, none of these studies have examined these indicators from socio-economic and strategic planning perspectives. The primary aim of this paper is to combine and cluster these two air qualities indicators, preexisting heart conditions due to morbidity and mortality from cardiovascular disease (MMDC), the probability from dying from four main (cardiovascular diseases, cancer, chronic respiratory diseases, and diabetes) non-communicable diseases (NCDs) using a self-organizing map (SOM) and the hierarchical clustering method (HCM). Using SOM and HCM, all the variables mentioned above were partitioned into five clusters that did not follow the geographical boundaries of five regions in Africa. The results show that the countries with the highest COVID-19 deaths and cases as of 12 July 2020 are Egypt (3769 and 81,158) and South Africa (3971 and 264,184). The SOM technique was successfully used to combine these two countries into a single cluster. Notably, these two countries also have high rates of pre-existing health conditions (MMDC, NCDs), poor air quality indicators (NO2 and PM2.5) and pollution levels. Since no single country can manage this pandemic alone, a concerted effort is needed to mitigate and combat this virus. Therefore, relating these indicators together at the continental level would help improve state-of-the-art planning and management of the COVID-19 pandemic in Africa.
{"title":"Regionalizing & Partitioning Africa’s Coronavirus (COVID-19) Fatalities Using Environmental Factors and Underlying Health Conditions for Social-economic Impacts","authors":"A. Boluwade","doi":"10.1109/NILES50944.2020.9257875","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257875","url":null,"abstract":"The COVID-19 event was unexpected and has had shocking impacts such as widespread economic losses and tens of thousands of deaths. The COVID-19 infection rate is relatively low in Africa compared to other continents, but the number of cases is rising. As of July 12, 2020, in Africa, there are a total of 13,194 deaths and 591,153 reported cases. The dynamics of this pandemic spread are relatively unknown; however, previous studies have established a relationship between poor air quality standards due to nitrogen dioxide (NO2) and fine particulate matter (PM2.5) and COVID-19 deaths and cases. Meanwhile, other studies have linked preexisting health conditions from cardiovascular diseases with COVID-19 fatalities. However, none of these studies have examined these indicators from socio-economic and strategic planning perspectives. The primary aim of this paper is to combine and cluster these two air qualities indicators, preexisting heart conditions due to morbidity and mortality from cardiovascular disease (MMDC), the probability from dying from four main (cardiovascular diseases, cancer, chronic respiratory diseases, and diabetes) non-communicable diseases (NCDs) using a self-organizing map (SOM) and the hierarchical clustering method (HCM). Using SOM and HCM, all the variables mentioned above were partitioned into five clusters that did not follow the geographical boundaries of five regions in Africa. The results show that the countries with the highest COVID-19 deaths and cases as of 12 July 2020 are Egypt (3769 and 81,158) and South Africa (3971 and 264,184). The SOM technique was successfully used to combine these two countries into a single cluster. Notably, these two countries also have high rates of pre-existing health conditions (MMDC, NCDs), poor air quality indicators (NO2 and PM2.5) and pollution levels. Since no single country can manage this pandemic alone, a concerted effort is needed to mitigate and combat this virus. Therefore, relating these indicators together at the continental level would help improve state-of-the-art planning and management of the COVID-19 pandemic in Africa.","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":"129373710","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/NILES50944.2020.9257952
Mourad A. Kenk, M. Hassaballah, Mohamed Abdel Hameed, Saddam Bekhet
Poor weather conditions such as the presence of heavy snow, fog, rain and dust storm are considered as dangerous restrictions of the functionality of cameras via reducing clear visibility. Thus, they have bad effect on computer vision algorithms used in traffic scene understanding, such as object detection, tracking, and recognition which are vital for traffic monitoring. Current methods for image enhancement can not be utilized under the influence of weather variability from foggy to dusty situations. This paper proposes an adaptive technique for visibility enhancement based on the bright balance and Laplace filtering. The overall visibility enhancement process is composed of three main parts: color and illumination improvement, reflection and component details enhancement, and linear weighted fusion. First, the contrast of an image is enhanced by auto white balance and Gamma correction for each color channel (Red, Green, Blue) individually to achieve color enhancement and outperform the illumination. Second, the detail enhancement is achieved by the Laplace pyramid filter to process the reflection component. Third, the detail enhanced layer is added back to the corrected color layer to reconstruct the clear image. The quantitative results and visual analysis demonstrate the efficacy of the proposed technique. Comparing with the state-of-the-art image enhancement methods, the evaluation of the objective metrics have shown that the contrast of unclear images can be effectively improved by the proposed method and with well effects on both foggy and dusty situations.
{"title":"Visibility Enhancer: Adaptable for Distorted Traffic Scenes by Dusty Weather","authors":"Mourad A. Kenk, M. Hassaballah, Mohamed Abdel Hameed, Saddam Bekhet","doi":"10.1109/NILES50944.2020.9257952","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257952","url":null,"abstract":"Poor weather conditions such as the presence of heavy snow, fog, rain and dust storm are considered as dangerous restrictions of the functionality of cameras via reducing clear visibility. Thus, they have bad effect on computer vision algorithms used in traffic scene understanding, such as object detection, tracking, and recognition which are vital for traffic monitoring. Current methods for image enhancement can not be utilized under the influence of weather variability from foggy to dusty situations. This paper proposes an adaptive technique for visibility enhancement based on the bright balance and Laplace filtering. The overall visibility enhancement process is composed of three main parts: color and illumination improvement, reflection and component details enhancement, and linear weighted fusion. First, the contrast of an image is enhanced by auto white balance and Gamma correction for each color channel (Red, Green, Blue) individually to achieve color enhancement and outperform the illumination. Second, the detail enhancement is achieved by the Laplace pyramid filter to process the reflection component. Third, the detail enhanced layer is added back to the corrected color layer to reconstruct the clear image. The quantitative results and visual analysis demonstrate the efficacy of the proposed technique. Comparing with the state-of-the-art image enhancement methods, the evaluation of the objective metrics have shown that the contrast of unclear images can be effectively improved by the proposed method and with well effects on both foggy and dusty situations.","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":"132954815","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/NILES50944.2020.9257965
Mema M. Eshak, Mohamed A. Khafagy, P. Makeen, S. Abdellatif
This paper introduces an improved gray-wolf optimization technique (EGWO) for a photovoltaic (PV) stand-alone system. The fundamental objective is to study non-uniform solar irradiance power mismatches in PV modules through modelling maximum power point tracker (MPPT) for increasing PV power output. An EGWO-MPPT detection algorithm for promoting the global peak between the multiple peaks is implemented, seeking for the optimum maximum energy from the PV system. Furthermore, a neural network-based MPPT optimizer has been modeled as a benchmark for our proposed system, showing the trade-off between time response and accuracy under a non-uniform irradiance profile.
{"title":"Optimizing the performance of a stand-alone PV system under non-uniform irradiance using Gray-Wolf and hybrid neural network AI-MPPT algorithms","authors":"Mema M. Eshak, Mohamed A. Khafagy, P. Makeen, S. Abdellatif","doi":"10.1109/NILES50944.2020.9257965","DOIUrl":"https://doi.org/10.1109/NILES50944.2020.9257965","url":null,"abstract":"This paper introduces an improved gray-wolf optimization technique (EGWO) for a photovoltaic (PV) stand-alone system. The fundamental objective is to study non-uniform solar irradiance power mismatches in PV modules through modelling maximum power point tracker (MPPT) for increasing PV power output. An EGWO-MPPT detection algorithm for promoting the global peak between the multiple peaks is implemented, seeking for the optimum maximum energy from the PV system. Furthermore, a neural network-based MPPT optimizer has been modeled as a benchmark for our proposed system, showing the trade-off between time response and accuracy under a non-uniform irradiance profile.","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":"125468595","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：