Abhijit Bhowmik, N. Mohd, M. Noor, Saef Ullah, M. Miah, Mazid-Ul-Haque Debajyoti, Karmaker
Teacher performance evaluation is an essential task in the field of education. In recent years, aspect-based sentiment analysis (ABSA) has emerged as a promising technique for evaluating teaching performance by providing a more nuanced analysis of student evaluations. This article presents a novel approach for creating a large-scale dataset for ABSA of teacher performance evaluation. The dataset was constructed by collecting student feedback from American International University-Bangladesh and then labeled by undergraduate-level students into three sentiment classes: positive, negative, and neutral. The dataset was carefully cleaned and preprocessed to ensure data quality and consistency. The final dataset contains over 2,000,000 student feedback instances related to teacher performance, making it one of the largest datasets for ABSA of teacher performance evaluation. This dataset can be used to develop and evaluate ABSA models for teacher performance evaluation, ultimately leading to better feedback and improvement for educators. The results of this study demonstrate the usefulness and effectiveness of ABSA in evaluating teacher performance and highlight the importance of creating high-quality datasets for this task.
{"title":"A comprehensive dataset for aspect-based sentiment analysis in evaluating teacher performance","authors":"Abhijit Bhowmik, N. Mohd, M. Noor, Saef Ullah, M. Miah, Mazid-Ul-Haque Debajyoti, Karmaker","doi":"10.53799/ajse.v22i2.862","DOIUrl":"https://doi.org/10.53799/ajse.v22i2.862","url":null,"abstract":"Teacher performance evaluation is an essential task in the field of education. In recent years, aspect-based sentiment analysis (ABSA) has emerged as a promising technique for evaluating teaching performance by providing a more nuanced analysis of student evaluations. This article presents a novel approach for creating a large-scale dataset for ABSA of teacher performance evaluation. The dataset was constructed by collecting student feedback from American International University-Bangladesh and then labeled by undergraduate-level students into three sentiment classes: positive, negative, and neutral. The dataset was carefully cleaned and preprocessed to ensure data quality and consistency. The final dataset contains over 2,000,000 student feedback instances related to teacher performance, making it one of the largest datasets for ABSA of teacher performance evaluation. This dataset can be used to develop and evaluate ABSA models for teacher performance evaluation, ultimately leading to better feedback and improvement for educators. The results of this study demonstrate the usefulness and effectiveness of ABSA in evaluating teacher performance and highlight the importance of creating high-quality datasets for this task.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125784017","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}
Task scheduling determines the order of mapping tasks to virtual machines to meet objectives. In this paper, a batch mode heuristic method that is centralized, dynamic, and multi-objective has been presented for scheduling independent tasks with a deadline and belonging to several user levels, using the cloud elasticity in the public cloud environment. In this method, it has been intended to improve the objectives of makespan, deadline violation, total execution cost, and load balancing by considering the tasks’ prioritization based on the criteria of user level, deadline, task length, and selection of heterogeneous virtual machines according to processing power, workload and usage cost. The proposed method was simulated using the CloudSim tool. Besides, the method’s ability to achieve the mentioned goals has been evaluated in comparison with similar methods. The evaluation results, established on standard test data, show that the proposed method has a good performance in improving its objectives.
{"title":"A Centralized Multi-Criteria Method for Scheduling Tasks in a Cloud Computing Environment","authors":"Ehsan Shojaeian, M. Mohsenzadeh, M. Sahrapour","doi":"10.53799/ajse.v22i2.506","DOIUrl":"https://doi.org/10.53799/ajse.v22i2.506","url":null,"abstract":"Task scheduling determines the order of mapping tasks to virtual machines to meet objectives. In this paper, a batch mode heuristic method that is centralized, dynamic, and multi-objective has been presented for scheduling independent tasks with a deadline and belonging to several user levels, using the cloud elasticity in the public cloud environment. In this method, it has been intended to improve the objectives of makespan, deadline violation, total execution cost, and load balancing by considering the tasks’ prioritization based on the criteria of user level, deadline, task length, and selection of heterogeneous virtual machines according to processing power, workload and usage cost. The proposed method was simulated using the CloudSim tool. Besides, the method’s ability to achieve the mentioned goals has been evaluated in comparison with similar methods. The evaluation results, established on standard test data, show that the proposed method has a good performance in improving its objectives.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125240279","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}
Md. Jahid Hasan, Oussama Haddad, I. C. Ijeh, Md. Abdur Rahman
The transfer of data from multiple internet of things (IoT) devices requires the use of a robust and efficient multiple access (MA) solution. This paper considers the orthogonal frequency division MA (OFDMA) technique for the light-fidelity (LiFi)-based IoT uplink using infrared to transmit data from multiple mobile users to a fixed access point. The conventional schemes based on orthogonal frequency allocate distinct subcarriers to each user sharing the same time slot. We consider a new approach by allocating distinct time slots to a group of OFDMA users. Taking into account realistic opto-electronic components, we study the performance of the conventional and proposed optical-OFDMA schemes. We show that asymmetrically clipped optical-OFDMA signaling scheme outperforms direct current biased signaling in terms of electrical power efficiency. Focusing on the asymmetrically clipped signaling, We demonstrate the robustness of our proposed time multiplexed optical-OFDMA scheme against MA interference caused by signal clipping. We also show the advantages of our scheme in reducing computational complexity by a factor of 2 compared to the conventional optical-OFDMA schemes.
{"title":"Time Multiplexed Optical-OFDMA for Uplink Transmission in LiFi-based IoT Networks","authors":"Md. Jahid Hasan, Oussama Haddad, I. C. Ijeh, Md. Abdur Rahman","doi":"10.53799/ajse.v22i2.522","DOIUrl":"https://doi.org/10.53799/ajse.v22i2.522","url":null,"abstract":"The transfer of data from multiple internet of things (IoT) devices requires the use of a robust and efficient multiple access (MA) solution. This paper considers the orthogonal frequency division MA (OFDMA) technique for the light-fidelity (LiFi)-based IoT uplink using infrared to transmit data from multiple mobile users to a fixed access point. The conventional schemes based on orthogonal frequency allocate distinct subcarriers to each user sharing the same time slot. We consider a new approach by allocating distinct time slots to a group of OFDMA users. Taking into account realistic opto-electronic components, we study the performance of the conventional and proposed optical-OFDMA schemes. We show that asymmetrically clipped optical-OFDMA signaling scheme outperforms direct current biased signaling in terms of electrical power efficiency. Focusing on the asymmetrically clipped signaling, We demonstrate the robustness of our proposed time multiplexed optical-OFDMA scheme against MA interference caused by signal clipping. We also show the advantages of our scheme in reducing computational complexity by a factor of 2 compared to the conventional optical-OFDMA schemes. \u0000 ","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129998712","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}
Fuzzy differential equation models are suitable where uncertainty exists for real-world phenomena. Numerical techniques are used to provide an approximate solution to these models in the absence of an exact solution. However, existing studies that have developed numerical techniques for solving FIVPs possess an absolute error accuracy that could be improved. This is as a result of the low order and non-self-starting properties of the developed numerical techniques by previous studies. For this reason, this study, develops an Obrechkoff-type two-step implicit block method with the presence of second and third derivative for the numerical solution of first-order nonlinear fuzzy initial value problems. The convergence properties for the proposed block method are described in detail. Then the proposed method is adopted to solve first-order nonlinear fuzzy initial value problems with triangular and trapezoidal fuzzy numbers. The obtained results indicates that the proposed method effectively solves first-order nonlinear fuzzy initial value problems with better accuracy.
{"title":"Solving First-Order Nonlinear Fuzzy Initial Value Problems Using Two-Step Block Method with Presence of Higher Derivatives","authors":"Kashif Hussain, O. Adeyeye, N. Ahmad","doi":"10.53799/ajse.v22i2.337","DOIUrl":"https://doi.org/10.53799/ajse.v22i2.337","url":null,"abstract":"Fuzzy differential equation models are suitable where uncertainty exists for real-world phenomena. Numerical techniques are used to provide an approximate solution to these models in the absence of an exact solution. However, existing studies that have developed numerical techniques for solving FIVPs possess an absolute error accuracy that could be improved. This is as a result of the low order and non-self-starting properties of the developed numerical techniques by previous studies. For this reason, this study, develops an Obrechkoff-type two-step implicit block method with the presence of second and third derivative for the numerical solution of first-order nonlinear fuzzy initial value problems. The convergence properties for the proposed block method are described in detail. Then the proposed method is adopted to solve first-order nonlinear fuzzy initial value problems with triangular and trapezoidal fuzzy numbers. The obtained results indicates that the proposed method effectively solves first-order nonlinear fuzzy initial value problems with better accuracy.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126061341","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 study focuses on predicting the adoption intention of ChatGPT among Professionals in Bangladesh. ChatGPT, powered by natural language processing and artificial intelligence, has the potential to revolutionize communication and enhance productivity in professional settings. The Unified Theory of Acceptance and Use of Technology (UTAUT) is used as a theoretical framework to examine the variables that affect the adoption intention of ChatGPT. The study aims to understand the impact of attitude towards AI, performance expectancy, effort expectancy, social influence, facilitating conditions, hedonic motivation, trust, behavioral intention to use, and actual use of ChatGPT among Professionals in Bangladesh. The research questions explore the relationships between these variables. The objectives of the study are to examine the relationship between attitude towards AI and behavioral intention to use ChatGPT, investigate the impact of performance expectancy and effort expectancy on behavioral intention to use, explore the effect of social influence and facilitating conditions on behavioral intention to use, assess the relationship between hedonic motivation and behavioral intention to use, investigate the influence of trust on behavioral intention to use, and analyze the relationship between behavioral intention to use and actual use of ChatGPT. The findings provide valuable insights into the factors influencing the adoption intention and actual use of ChatGPT. The study highlights the significance of strengthening behavioral intentions, emphasizing performance benefits and building trust, and creating facilitating conditions to promote adoption and utilization. The research contributes to the understanding of factors influencing the adoption and usage behavior of ChatGPT and offers practical implications for organizations and policymakers to maximize the benefits of artificial intelligence applications in the context of Bangladeshi Professionals.
{"title":"Predicting Adoption Intention of Artificial Intelligence ChatGPT","authors":"Mehedi Hasan Emon, Farheen Hassan, Md. Mehzabul Hoque Nahid, Vichayanan Rattanawiboonsom","doi":"10.53799/ajse.v22i2.797","DOIUrl":"https://doi.org/10.53799/ajse.v22i2.797","url":null,"abstract":"This study focuses on predicting the adoption intention of ChatGPT among Professionals in Bangladesh. ChatGPT, powered by natural language processing and artificial intelligence, has the potential to revolutionize communication and enhance productivity in professional settings. The Unified Theory of Acceptance and Use of Technology (UTAUT) is used as a theoretical framework to examine the variables that affect the adoption intention of ChatGPT. The study aims to understand the impact of attitude towards AI, performance expectancy, effort expectancy, social influence, facilitating conditions, hedonic motivation, trust, behavioral intention to use, and actual use of ChatGPT among Professionals in Bangladesh. The research questions explore the relationships between these variables. The objectives of the study are to examine the relationship between attitude towards AI and behavioral intention to use ChatGPT, investigate the impact of performance expectancy and effort expectancy on behavioral intention to use, explore the effect of social influence and facilitating conditions on behavioral intention to use, assess the relationship between hedonic motivation and behavioral intention to use, investigate the influence of trust on behavioral intention to use, and analyze the relationship between behavioral intention to use and actual use of ChatGPT. The findings provide valuable insights into the factors influencing the adoption intention and actual use of ChatGPT. The study highlights the significance of strengthening behavioral intentions, emphasizing performance benefits and building trust, and creating facilitating conditions to promote adoption and utilization. The research contributes to the understanding of factors influencing the adoption and usage behavior of ChatGPT and offers practical implications for organizations and policymakers to maximize the benefits of artificial intelligence applications in the context of Bangladeshi Professionals.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123630314","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}
Speech Emotion Recognition (SER) plays a predominant role in human-machine interaction. SER is a challenging task because of number of complexities involved in it. For an accurate emotion classification system, feature extraction is the first and important step carried out on speech signals. And after the features are extracted, it is very important to select the best features out of all and reject the redundant and least important features. Feature selection methods play an important role in SER performance. The classifier gets the selected features, so as to reduce the unnecessary overload and perform better to classify the emotions. In this study, a good combination of features is selected from Punjabi Emotional Speech Database. Then a number of feature selection algorithms are explored and experimented upon, to select the best features. 1D-CNN is used for classification purpose. The results are shown and compared on the basis of number of performance metrics. LASSO has shown the best performance results as compared to other feature selection methods.
{"title":"Comparison of Various Feature Selection Algorithms in Speech Emotion Recognition","authors":"K. Kaur, Parminder Singh","doi":"10.53799/ajse.v22i2.357","DOIUrl":"https://doi.org/10.53799/ajse.v22i2.357","url":null,"abstract":"Speech Emotion Recognition (SER) plays a predominant role in human-machine interaction. SER is a challenging task because of number of complexities involved in it. For an accurate emotion classification system, feature extraction is the first and important step carried out on speech signals. And after the features are extracted, it is very important to select the best features out of all and reject the redundant and least important features. Feature selection methods play an important role in SER performance. The classifier gets the selected features, so as to reduce the unnecessary overload and perform better to classify the emotions. In this study, a good combination of features is selected from Punjabi Emotional Speech Database. Then a number of feature selection algorithms are explored and experimented upon, to select the best features. 1D-CNN is used for classification purpose. The results are shown and compared on the basis of number of performance metrics. LASSO has shown the best performance results as compared to other feature selection methods.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121547021","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}
Mohammad Tawhidul Alam, M. Mahbubur Rahman, Q. Ahsan
Conversion of existing high voltage long AC transmission line into combined AC-DC system can bring the benefit of stability improvement. Of late, most of the developments in stability analysis are simulation based. Sometimes it is difficult to draw a generalized conclusion through simulation result. In this case, an analytical model can be a perfect tool to analyze the fault and get concrete decision about the future planning. This paper presents a stability model for the analysis of all types of fault. Primarily, the stability model is established for the fault at the transmission line and then introducing simple logical modification it can be applicable for the development of analytical models of all kinds of faults, such as; Fault at the load terminal, sustained fault at the line, fault very close to the generator bus. To expose the efficacy of the developed stability model two different ways of validation process is followed and optimistic results are found
{"title":"A Novel Stability Model for AC-DC Combined Simultaneous Power Flow","authors":"Mohammad Tawhidul Alam, M. Mahbubur Rahman, Q. Ahsan","doi":"10.53799/ajse.v22i2.682","DOIUrl":"https://doi.org/10.53799/ajse.v22i2.682","url":null,"abstract":"Conversion of existing high voltage long AC transmission line into combined AC-DC system can bring the benefit of stability improvement. Of late, most of the developments in stability analysis are simulation based. Sometimes it is difficult to draw a generalized conclusion through simulation result. In this case, an analytical model can be a perfect tool to analyze the fault and get concrete decision about the future planning. This paper presents a stability model for the analysis of all types of fault. Primarily, the stability model is established for the fault at the transmission line and then introducing simple logical modification it can be applicable for the development of analytical models of all kinds of faults, such as; Fault at the load terminal, sustained fault at the line, fault very close to the generator bus. To expose the efficacy of the developed stability model two different ways of validation process is followed and optimistic results are found","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115753706","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}
Khaleque Insi̇a, Abir Ahmed, Effat Jahan, S. Ahmad, Sreejon Barua, Imran Ali, Md. Rifat Hazari, M. Mannan
The growing popularity of electric vehicles on a worldwide scale leads to further research to monitor their performance. The use of Internet of Things (IoT) technology will make it easier to integrate the automated real-time monitoring system with the current electric vehicle technology. The great majority of electric vehicles use rechargeable lithium-ion batteries. Use of lithium-ion batteries creates an overcharging situation in the battery, which significantly decreases battery life. It also increases the possibility of disastrous safety risks due to fire. This paper develops an IoT-based battery management system to minimize hazardous situations. The battery monitoring system (BMS) notifies the user about the condition of the battery in real time.
{"title":"IoT-Based Smart Battery Management and Monitoring System for Electric Vehicles","authors":"Khaleque Insi̇a, Abir Ahmed, Effat Jahan, S. Ahmad, Sreejon Barua, Imran Ali, Md. Rifat Hazari, M. Mannan","doi":"10.53799/ajse.v22i2.731","DOIUrl":"https://doi.org/10.53799/ajse.v22i2.731","url":null,"abstract":"The growing popularity of electric vehicles on a worldwide scale leads to further research to monitor their performance. The use of Internet of Things (IoT) technology will make it easier to integrate the automated real-time monitoring system with the current electric vehicle technology. The great majority of electric vehicles use rechargeable lithium-ion batteries. Use of lithium-ion batteries creates an overcharging situation in the battery, which significantly decreases battery life. It also increases the possibility of disastrous safety risks due to fire. This paper develops an IoT-based battery management system to minimize hazardous situations. The battery monitoring system (BMS) notifies the user about the condition of the battery in real time.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114553076","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The paper aims to analyze the effects of various Prandtl number and different nanoparticles for heat transfer and entropy generation of free convection laminar fluid flow in an L-shaped cavity filled by nanofluid. To investigate the second law characteristics of free convective flow and heat transfer from an L- shaped geometry filled by water and nanofluids (Cu-water, Ag-water, Al2O3-water), the effects of Prandtl number and various nanoparticles on the average Nusselt number, total entropy generation and Bejan number has been numerically analyzed. Isotherms, stream function and entropy generation caused by heat transfer are also presented for various Prandtl numbers and various nanoparticles. The governing equations are solved using penalty finite element method with Galerkins weighted residual technique. The results reveal that Ag-water nanofluid with highest Prandtl number gives the highest amount of irreversibility as well as rate of heat transfer. Cu-water and Ag-water nanofluid produces more irreversibilities than Al2O3-water nanofluid and base fluid. Also the results show that the Nusselt number and Bejan number increase with the increase of Prandtl number. Therefore, Prandtl number may be an important parameter for desired heat transfer increment with decreasing entropy generation in the given geometry.
{"title":"Second Law Analysis for Free Convection in an L-Shaped Cavity Filled with Nanofluid","authors":"A. Nahar, Salma Parvin, Md. Hasanuzzaman","doi":"10.53799/ajse.v22i2.438","DOIUrl":"https://doi.org/10.53799/ajse.v22i2.438","url":null,"abstract":"The paper aims to analyze the effects of various Prandtl number and different nanoparticles for heat transfer and entropy generation of free convection laminar fluid flow in an L-shaped cavity filled by nanofluid. To investigate the second law characteristics of free convective flow and heat transfer from an L- shaped geometry filled by water and nanofluids (Cu-water, Ag-water, Al2O3-water), the effects of Prandtl number and various nanoparticles on the average Nusselt number, total entropy generation and Bejan number has been numerically analyzed. Isotherms, stream function and entropy generation caused by heat transfer are also presented for various Prandtl numbers and various nanoparticles. The governing equations are solved using penalty finite element method with Galerkins weighted residual technique. The results reveal that Ag-water nanofluid with highest Prandtl number gives the highest amount of irreversibility as well as rate of heat transfer. Cu-water and Ag-water nanofluid produces more irreversibilities than Al2O3-water nanofluid and base fluid. Also the results show that the Nusselt number and Bejan number increase with the increase of Prandtl number. Therefore, Prandtl number may be an important parameter for desired heat transfer increment with decreasing entropy generation in the given geometry.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123121000","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}
Lama Mansour, Zainab H. Omran, Ghaydaa Mnsoor Kaddoura, M. Dakkak, Yasser Rahhal
IPTV delivers television content over Internet Protocol (IP) networks. Videos On Demand (VOD) is the most popular IPTV, allowing users to freely select from a vast pool of program genres. Therefore, it is necessary to introduce innovative features to attract new users and retain existing ones. For this purpose, IPTV systems typically use VOD recommendation engines. The primary purpose of recommendation systems is to suggest user-relevant items from various items by producing a list of recommendations for each user. In this paper, we introduce an approach to recommendation systems in IPTV. We developed this approach on implicit feedback derived from users’ interaction with movies/series sets, such as how many times they watched a movie and how long they have spent watching specific movies/series. For the previous factors, we tested a variety of recommendation algorithms, content-based, collaborative-based, and hybrid. Then applied the previously mentioned algorithms on real-life big data sets after introducing some modifications to the algorithms, then benchmarked the results on multiple performance metrics. We noticed that the applied changes achieved promising results.
{"title":"A Recommendation System Based on Implicit Data for Internet Protocol Television (IPTV)","authors":"Lama Mansour, Zainab H. Omran, Ghaydaa Mnsoor Kaddoura, M. Dakkak, Yasser Rahhal","doi":"10.53799/ajse.v22i2.491","DOIUrl":"https://doi.org/10.53799/ajse.v22i2.491","url":null,"abstract":"IPTV delivers television content over Internet Protocol (IP) networks. Videos On Demand (VOD) is the most popular IPTV, allowing users to freely select from a vast pool of program genres. Therefore, it is necessary to introduce innovative features to attract new users and retain existing ones. For this purpose, IPTV systems typically use VOD recommendation engines. The primary purpose of recommendation systems is to suggest user-relevant items from various items by producing a list of recommendations for each user. In this paper, we introduce an approach to recommendation systems in IPTV. We developed this approach on implicit feedback derived from users’ interaction with movies/series sets, such as how many times they watched a movie and how long they have spent watching specific movies/series. For the previous factors, we tested a variety of recommendation algorithms, content-based, collaborative-based, and hybrid. Then applied the previously mentioned algorithms on real-life big data sets after introducing some modifications to the algorithms, then benchmarked the results on multiple performance metrics. We noticed that the applied changes achieved promising results.","PeriodicalId":224436,"journal":{"name":"AIUB Journal of Science and Engineering (AJSE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115390662","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：