Mohanad Salih Farhan Al-Jadiri, Abdul Muttalib I. Said
This study investigated the effect of high-temperature fire flame on reinforced concrete columns coated with a layer of gypsum insulation. Six samples were cast and cured in a hot water bath at 67°C, covered on one side by 10 and 20 mm thick layers of gypsum plaster. The samples were exposed to a 900°C fire flame in a hydrocarbon fire furnace for one and two hours. The results showed that the gypsum plaster layer prevented a high-temperature rise within the core of the column. The differences between all gypsum-coated columns varied compared to those of the reference samples. The gypsum-coated columns had reduced axial displacements and no spalling and visible cracks on their faces. The improvement in the compressive strength of concrete will be discussed in a future paper. This study was carried out following ACI-318 and ASTM C1529.
{"title":"Reinforced Concrete Columns Insulated by Different Gypsum Layers Exposed to 900°C One Side Fire Flame","authors":"Mohanad Salih Farhan Al-Jadiri, Abdul Muttalib I. Said","doi":"10.48084/etasr.6083","DOIUrl":"https://doi.org/10.48084/etasr.6083","url":null,"abstract":"This study investigated the effect of high-temperature fire flame on reinforced concrete columns coated with a layer of gypsum insulation. Six samples were cast and cured in a hot water bath at 67°C, covered on one side by 10 and 20 mm thick layers of gypsum plaster. The samples were exposed to a 900°C fire flame in a hydrocarbon fire furnace for one and two hours. The results showed that the gypsum plaster layer prevented a high-temperature rise within the core of the column. The differences between all gypsum-coated columns varied compared to those of the reference samples. The gypsum-coated columns had reduced axial displacements and no spalling and visible cracks on their faces. The improvement in the compressive strength of concrete will be discussed in a future paper. This study was carried out following ACI-318 and ASTM C1529.","PeriodicalId":11826,"journal":{"name":"Engineering, Technology & Applied Science Research","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135918301","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}
Tuan Anh Bui, Duc-Do Le, Duc-Toan Tran, Manh-Toan Nguyen, Van-Thuc Tran, Ngoc-Tam Bui
Preventing surface damage is crucial for optimal machine performance, with lubricants and additives playing a vital role in achieving this objective. This study specifically focuses on evaluating the influence of fly-ash additives on the wear resistance of machine components when incorporated into lubricant oil. The experiments were conducted following ASTM standard operating conditions, utilizing the four-ball wear test to measure the scratch width and weight loss of balls using different lubricant oil formulations, including 0, 0.1%, 0.5%, 0.75%, and 1% additive. The findings demonstrate that the inclusion of 0.5% fly ash additive in the lubricant oil results in a significant reduction in both scratch width and weight loss of the balls. However, it should be noted that higher additive ratios may lead to increased scratch width and weight loss due to the agglomeration of the fly ash particles on the sliding surfaces. To achieve optimal effectiveness in reducing friction and wear, it is recommended to carefully control the content of fly ash within an appropriate range. Furthermore, this study highlights the width of scratches on balls as a reliable indicator for assessing the anti-wear properties of oils. The insights gained from this research offer valuable guidance to manufacturers in the selection of suitable anti-wear oils for specific applications. Further investigations could explore the impact of different lubricants and additive ratios to identify the most appropriate lubrication parameters. Overall, this study contributes to a better understanding of the effects of fly ash additives on the performance of lubricant oil and provides practical guidance for optimizing lubrication strategies in diverse industrial contexts.
{"title":"Analyzing the Impact of Fly Ash Additive Ratio on Lubricant Properties","authors":"Tuan Anh Bui, Duc-Do Le, Duc-Toan Tran, Manh-Toan Nguyen, Van-Thuc Tran, Ngoc-Tam Bui","doi":"10.48084/etasr.6114","DOIUrl":"https://doi.org/10.48084/etasr.6114","url":null,"abstract":"Preventing surface damage is crucial for optimal machine performance, with lubricants and additives playing a vital role in achieving this objective. This study specifically focuses on evaluating the influence of fly-ash additives on the wear resistance of machine components when incorporated into lubricant oil. The experiments were conducted following ASTM standard operating conditions, utilizing the four-ball wear test to measure the scratch width and weight loss of balls using different lubricant oil formulations, including 0, 0.1%, 0.5%, 0.75%, and 1% additive. The findings demonstrate that the inclusion of 0.5% fly ash additive in the lubricant oil results in a significant reduction in both scratch width and weight loss of the balls. However, it should be noted that higher additive ratios may lead to increased scratch width and weight loss due to the agglomeration of the fly ash particles on the sliding surfaces. To achieve optimal effectiveness in reducing friction and wear, it is recommended to carefully control the content of fly ash within an appropriate range. Furthermore, this study highlights the width of scratches on balls as a reliable indicator for assessing the anti-wear properties of oils. The insights gained from this research offer valuable guidance to manufacturers in the selection of suitable anti-wear oils for specific applications. Further investigations could explore the impact of different lubricants and additive ratios to identify the most appropriate lubrication parameters. Overall, this study contributes to a better understanding of the effects of fly ash additives on the performance of lubricant oil and provides practical guidance for optimizing lubrication strategies in diverse industrial contexts.","PeriodicalId":11826,"journal":{"name":"Engineering, Technology & Applied Science Research","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135918456","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}
Predicting stock markets remains a critical and challenging task due to many factors, such as the enormous volume of generated price data, instant price data changes, and sensitivity to human sentiments, wars, and natural disasters. Since the previous three years of the COVID-19 pandemic, forecasting stock markets is more difficult, complex, and problematic for stock market analysts. However, technical analysts of the stock market and academic researchers are continuously trying to develop innovative and modern methods for forecasting stock market prices, using statistical techniques, machine learning, and deep learning-based algorithms. This study investigated a Transformer sequential-based approach to forecast the closing price for the next day. Ten sliding window timesteps were used to forecast next-day stock closing prices. This study aimed to investigate reliable techniques based on stock input features. The proposed Transformer-based method was compared with ARIMA, Long-Short Term Memory (LSTM), and Random Forest (RF) algorithms, showing its outstanding results on Yahoo Finance data, Facebook Intra data, and JPMorgan's Intra data. Each model was evaluated using Mean Absolute Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE).
{"title":"Evaluation of Stock Closing Prices using Transformer Learning","authors":"Tariq Saeed Mian","doi":"10.48084/etasr.6017","DOIUrl":"https://doi.org/10.48084/etasr.6017","url":null,"abstract":"Predicting stock markets remains a critical and challenging task due to many factors, such as the enormous volume of generated price data, instant price data changes, and sensitivity to human sentiments, wars, and natural disasters. Since the previous three years of the COVID-19 pandemic, forecasting stock markets is more difficult, complex, and problematic for stock market analysts. However, technical analysts of the stock market and academic researchers are continuously trying to develop innovative and modern methods for forecasting stock market prices, using statistical techniques, machine learning, and deep learning-based algorithms. This study investigated a Transformer sequential-based approach to forecast the closing price for the next day. Ten sliding window timesteps were used to forecast next-day stock closing prices. This study aimed to investigate reliable techniques based on stock input features. The proposed Transformer-based method was compared with ARIMA, Long-Short Term Memory (LSTM), and Random Forest (RF) algorithms, showing its outstanding results on Yahoo Finance data, Facebook Intra data, and JPMorgan's Intra data. Each model was evaluated using Mean Absolute Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE).","PeriodicalId":11826,"journal":{"name":"Engineering, Technology & Applied Science Research","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135918146","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}
A typical 5G Ultra-Dense Network (UDN) comprises different types of Base Stations (BSs) in its structure. Dense deployment of small-cell BSs within a macrocell BS's coverage offers significant benefits, as the distance between a User Equipment (UE) and its small-cell BS is shorter with robust signals. Thus, the network capacity will increase dramatically. However, selecting an appropriate small-cell BS for a particular UE becomes a challenge in 5G UDNs. This study proposed a mechanism to address the cell selection problem and maximize fairness among UEs when making the cell selection decision. The proposed mechanism considered different parameters. The load balance for each small-cell BS was considered to fairly distribute UEs and avoid traffic congestion. Moreover, the signal strength was considered with the achievable data rate for all small-cell BSs to stimulate idle small-cell BSs to be in operating mode. A simulation was carried out in MATLAB to evaluate the proposed mechanism. Signal-to-Interference-Ratio (SINR) and Signal Strength (SS) -based strategies were also simulated for comparison. The proposed solution outperformed the other schemes in terms of fairness, as the UEs attached to the system were fairly distributed among small-cell BSs. Furthermore, the proposed mechanism achieved the best radio resource distribution in terms of fairness compared to the two other schemes.
{"title":"A Fairness-based Cell Selection Mechanism for Ultra-Dense Networks (UDNs)","authors":"Sultan Alotaibi","doi":"10.48084/etasr.6106","DOIUrl":"https://doi.org/10.48084/etasr.6106","url":null,"abstract":"A typical 5G Ultra-Dense Network (UDN) comprises different types of Base Stations (BSs) in its structure. Dense deployment of small-cell BSs within a macrocell BS's coverage offers significant benefits, as the distance between a User Equipment (UE) and its small-cell BS is shorter with robust signals. Thus, the network capacity will increase dramatically. However, selecting an appropriate small-cell BS for a particular UE becomes a challenge in 5G UDNs. This study proposed a mechanism to address the cell selection problem and maximize fairness among UEs when making the cell selection decision. The proposed mechanism considered different parameters. The load balance for each small-cell BS was considered to fairly distribute UEs and avoid traffic congestion. Moreover, the signal strength was considered with the achievable data rate for all small-cell BSs to stimulate idle small-cell BSs to be in operating mode. A simulation was carried out in MATLAB to evaluate the proposed mechanism. Signal-to-Interference-Ratio (SINR) and Signal Strength (SS) -based strategies were also simulated for comparison. The proposed solution outperformed the other schemes in terms of fairness, as the UEs attached to the system were fairly distributed among small-cell BSs. Furthermore, the proposed mechanism achieved the best radio resource distribution in terms of fairness compared to the two other schemes.","PeriodicalId":11826,"journal":{"name":"Engineering, Technology & Applied Science Research","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135918440","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 growing concern about the energy crisis and environmental protection has caused a growing interest in wind power generation systems. Researchers and engineers urgently need to create new multiphase induction machines for the production of wind energy, since they are essential parts of wind turbines. This study offers control and stability analysis of a multiphase induction machine based on the entropy stability requirements for its linearized model. The generated model was used to assess the on-load properties of the multiphase induction machine and calculate its steady-state parameters under each operating circumstance. According to the analysis, the eigenvalues depend on the machine parameters, with the excitation capacitance and speed variation being the most important. Stabilization of the multiphase induction machine is the main focus of the singular values, which vary according to its variables. The simulated results include an examination of a multiphase induction machine steady state for voltage build-up at various types of load.
{"title":"Persistent Voltage Control of a Wind Turbine-Driven Isolated Multiphase Induction Machine","authors":"Marwa Ben Sliemene, Mohamed Arbi Khlifi","doi":"10.48084/etasr.6330","DOIUrl":"https://doi.org/10.48084/etasr.6330","url":null,"abstract":"The growing concern about the energy crisis and environmental protection has caused a growing interest in wind power generation systems. Researchers and engineers urgently need to create new multiphase induction machines for the production of wind energy, since they are essential parts of wind turbines. This study offers control and stability analysis of a multiphase induction machine based on the entropy stability requirements for its linearized model. The generated model was used to assess the on-load properties of the multiphase induction machine and calculate its steady-state parameters under each operating circumstance. According to the analysis, the eigenvalues depend on the machine parameters, with the excitation capacitance and speed variation being the most important. Stabilization of the multiphase induction machine is the main focus of the singular values, which vary according to its variables. The simulated results include an examination of a multiphase induction machine steady state for voltage build-up at various types of load.","PeriodicalId":11826,"journal":{"name":"Engineering, Technology & Applied Science Research","volume":"259 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135918004","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}
Huda Alamoudi, Nahla Aljojo, Asmaa Munshi, Abdullah Alghoson, Ameen Banjar, Araek Tashkandi, Anas Al-Tirawi, Iqbal Alsaleh
Recently, Sentiment Analysis (SA) has become a crucial area of research as it enables us to gauge people's opinions from various sources such as student evaluations, social media posts, product reviews, etc. This paper aims to create an Arabic dataset derived from student satisfaction surveys conducted at the University of Jeddah regarding their subjects and instructors. In addition, this study presents an evaluation of classical machine learning models such as Naive Bayes, Support Vector Machine, Logistic Regression, Decision Tree, and Random Forest classifier for Arabic SA, whereas the results are compared using various metrics. Furthermore, AraBERT was used for the pre-trained transformer to improve the performance, achieving an accuracy of 78%. The paper fills the lack of SA research in the education domain in the Arabic language.
{"title":"Arabic Sentiment Analysis for Student Evaluation using Machine Learning and the AraBERT Transformer","authors":"Huda Alamoudi, Nahla Aljojo, Asmaa Munshi, Abdullah Alghoson, Ameen Banjar, Araek Tashkandi, Anas Al-Tirawi, Iqbal Alsaleh","doi":"10.48084/etasr.6347","DOIUrl":"https://doi.org/10.48084/etasr.6347","url":null,"abstract":"Recently, Sentiment Analysis (SA) has become a crucial area of research as it enables us to gauge people's opinions from various sources such as student evaluations, social media posts, product reviews, etc. This paper aims to create an Arabic dataset derived from student satisfaction surveys conducted at the University of Jeddah regarding their subjects and instructors. In addition, this study presents an evaluation of classical machine learning models such as Naive Bayes, Support Vector Machine, Logistic Regression, Decision Tree, and Random Forest classifier for Arabic SA, whereas the results are compared using various metrics. Furthermore, AraBERT was used for the pre-trained transformer to improve the performance, achieving an accuracy of 78%. The paper fills the lack of SA research in the education domain in the Arabic language.","PeriodicalId":11826,"journal":{"name":"Engineering, Technology & Applied Science Research","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135918477","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}
Faizah Alshammari, Nahla Aljojo, Araek Tashkandi, Abdullah Alghoson, Ameen Banjar, Nidhal K. El Abbadi
Riyadh is the most populous city in Saudi Arabia, with a population of over five million people. The governmental and economic centers of Saudi Arabia are located in the city. Due to the fact that the metropolitan region that surrounds Riyadh is continuously growing and expanding, appropriate planning is essential. To be able to formulate efficient plans, one needs access to trustworthy facts and information. Failing to have a clear picture of the future renders planning inefficient. Along with a hybrid time-series prediction of the expansion of the wider Riyadh metropolitan area, an urban growth forecasting model was constructed for the Riyadh region as part of this study. This model was used to make projections about the city's future population. This prediction was conducted with the application of Linear Regression (LR), Seasonal Auto-Regressive Integrated Moving Average (SARIMAX), and Auto-Regressive Integrated Moving Average (ARIMA). The dataset for this study consisted of satellite images of the region surrounding Riyadh that were acquired between 1992 and 2022. Mean Absolute Percentage Error (MAPE) was applied to measure the performance of the proposed hybrid models. The calculated MAPE vales are 2.0% for SARIMAX, 12% for LR, and 22% for ARIMA. As a consequence, the hybrid model's forecast for the future of the region suggests that the projections made regarding the expansion are keeping pace.
{"title":"A Hybrid Time-Series Prediction of the Greater Riyadh's Metropolitan Area Expansion","authors":"Faizah Alshammari, Nahla Aljojo, Araek Tashkandi, Abdullah Alghoson, Ameen Banjar, Nidhal K. El Abbadi","doi":"10.48084/etasr.6350","DOIUrl":"https://doi.org/10.48084/etasr.6350","url":null,"abstract":"Riyadh is the most populous city in Saudi Arabia, with a population of over five million people. The governmental and economic centers of Saudi Arabia are located in the city. Due to the fact that the metropolitan region that surrounds Riyadh is continuously growing and expanding, appropriate planning is essential. To be able to formulate efficient plans, one needs access to trustworthy facts and information. Failing to have a clear picture of the future renders planning inefficient. Along with a hybrid time-series prediction of the expansion of the wider Riyadh metropolitan area, an urban growth forecasting model was constructed for the Riyadh region as part of this study. This model was used to make projections about the city's future population. This prediction was conducted with the application of Linear Regression (LR), Seasonal Auto-Regressive Integrated Moving Average (SARIMAX), and Auto-Regressive Integrated Moving Average (ARIMA). The dataset for this study consisted of satellite images of the region surrounding Riyadh that were acquired between 1992 and 2022. Mean Absolute Percentage Error (MAPE) was applied to measure the performance of the proposed hybrid models. The calculated MAPE vales are 2.0% for SARIMAX, 12% for LR, and 22% for ARIMA. As a consequence, the hybrid model's forecast for the future of the region suggests that the projections made regarding the expansion are keeping pace.","PeriodicalId":11826,"journal":{"name":"Engineering, Technology & Applied Science Research","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135918775","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 aims to investigate experimentally the flexural behavior of lightweight Self-Compacted Concrete (SCC) beams made by Expanded Polystyrene (EPS) concrete and reinforced with rebars and steel fibers. To achieve the aims of this study, seven simply supported EPS lightweight fiber-reinforced concrete beams were fabricated and tested up to failure to study the effects of EPS content and the volume fraction of the steel fibers on their flexural behavior. The tested specimens were divided into two groups with one additional reference beam to be cast without using EPS or steel fibers. In the first group, three lightweight specimens were constructed using 25% EPS beads and were reinforced with 0%, 0.75%, and 1.5% steel fiber volume fractions. The second group is similar to the first group but was fabricated using 50% EPS beads. The test results showed that the mechanical properties of the hardened concrete were significantly reduced due to polystyrene EPS beads with some enhancement when steel fibers were added to the concrete mix. The flexure strength of EPS-LWT concrete beams was significantly reduced due to the polystyrene EPS beads. Furthermore, the results revealed remarkable enhancement in the flexure strength of the tested beams due to the steel fiber reinforcement.
{"title":"Structural Performance of Lightweight Fiber Reinforced Polystyrene Aggregate Self-Compacted Concrete Beams","authors":"Rafaa Mahmood Abbas, Rawah Khalid Rakaa","doi":"10.48084/etasr.6217","DOIUrl":"https://doi.org/10.48084/etasr.6217","url":null,"abstract":"This study aims to investigate experimentally the flexural behavior of lightweight Self-Compacted Concrete (SCC) beams made by Expanded Polystyrene (EPS) concrete and reinforced with rebars and steel fibers. To achieve the aims of this study, seven simply supported EPS lightweight fiber-reinforced concrete beams were fabricated and tested up to failure to study the effects of EPS content and the volume fraction of the steel fibers on their flexural behavior. The tested specimens were divided into two groups with one additional reference beam to be cast without using EPS or steel fibers. In the first group, three lightweight specimens were constructed using 25% EPS beads and were reinforced with 0%, 0.75%, and 1.5% steel fiber volume fractions. The second group is similar to the first group but was fabricated using 50% EPS beads. The test results showed that the mechanical properties of the hardened concrete were significantly reduced due to polystyrene EPS beads with some enhancement when steel fibers were added to the concrete mix. The flexure strength of EPS-LWT concrete beams was significantly reduced due to the polystyrene EPS beads. Furthermore, the results revealed remarkable enhancement in the flexure strength of the tested beams due to the steel fiber reinforcement.","PeriodicalId":11826,"journal":{"name":"Engineering, Technology & Applied Science Research","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135918449","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}
Existing recommender system algorithms often find it difficult to interpret and, as a result, to extract meaningful recommendations from social media. Because of this, there is a growing demand for more powerful algorithms that are able to extract information from low-dimensional spaces. One such approach would be the cutting-edge matrix factorization technique. Facebook is one of the most widely used social networking platforms. It has more than one billion monthly active users who engage with each other on the platform by sharing status updates, images, events, and other types of content. Facebook's mission includes fostering stronger connections between individuals, and to that end, the platform employs techniques from recommender systems in an effort to better comprehend the actions and patterns of its users, after which it suggests forming new connections with other users. However, relatively little study has been done in this area to investigate the low-dimensional spaces included within the black box system by employing methods such as matrix factorization. Using a probabilistic matrix factorization approach, the interactions that users have with the posts of other users, such as liking, commenting, and other similar activities, were utilized in an effort to generate a list of potential friends that the user who is the focus of this work may not yet be familiar with. The proposed model performed better in terms of suggestion accuracy in comparison to the original matrix factorization, which resulted in the creation of a recommendation list that contained more correct information.
{"title":"A Recommendation Engine Model for Giant Social Media Platforms using a Probabilistic Approach","authors":"Aadil Alshammari, Mohammed Alshammari","doi":"10.48084/etasr.6325","DOIUrl":"https://doi.org/10.48084/etasr.6325","url":null,"abstract":"Existing recommender system algorithms often find it difficult to interpret and, as a result, to extract meaningful recommendations from social media. Because of this, there is a growing demand for more powerful algorithms that are able to extract information from low-dimensional spaces. One such approach would be the cutting-edge matrix factorization technique. Facebook is one of the most widely used social networking platforms. It has more than one billion monthly active users who engage with each other on the platform by sharing status updates, images, events, and other types of content. Facebook's mission includes fostering stronger connections between individuals, and to that end, the platform employs techniques from recommender systems in an effort to better comprehend the actions and patterns of its users, after which it suggests forming new connections with other users. However, relatively little study has been done in this area to investigate the low-dimensional spaces included within the black box system by employing methods such as matrix factorization. Using a probabilistic matrix factorization approach, the interactions that users have with the posts of other users, such as liking, commenting, and other similar activities, were utilized in an effort to generate a list of potential friends that the user who is the focus of this work may not yet be familiar with. The proposed model performed better in terms of suggestion accuracy in comparison to the original matrix factorization, which resulted in the creation of a recommendation list that contained more correct information.","PeriodicalId":11826,"journal":{"name":"Engineering, Technology & Applied Science Research","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135918772","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}
Sidi Mohamed Ahmed Ghaly, Mohammad Obaidullah Khan, Mohamed Shalaby, Khalid A. Alsnaie, Majdi Oraiqat
Accurate and real-time measurement of fluid flow velocity is crucial in various industrial processes, especially when dealing with multiple phase fluids. Traditional flow measurement methods often struggle to accurately quantify the velocity of complex multiphase flows within pipes. This challenge necessitates the exploration of innovative techniques capable of providing reliable measurements. This paper proposes the utilization of Electrical Capacitance Tomography (ECT) as a promising approach for measuring the velocity of multiple phase fluids in pipes. The ECT technique involves the non-intrusive imaging of the electrical capacitance distribution within the pipe. By utilizing an array of electrodes placed around the pipe circumference, the capacitance distribution can be reconstructed, offering insight into the fluid flow patterns. By analyzing the temporal changes in the capacitance distribution, the velocity of different phases within the pipe can be estimated. To achieve accurate velocity measurements, an ECT system needs to account for the complexities introduced by multiphase flows. Various image reconstruction algorithms, such as linear back-projection and iterative algorithms like Gauss-Newton and Levenberg-Marquardt, are employed to reconstruct the capacitance distribution. Additionally, advanced signal processing techniques, such as cross-correlation analysis and time-difference methods, are used to extract velocity information from the reconstructed images. This paper presents an experimental investigation of measuring the velocity of multiple-phase fluids in pipes using the ECT technique. The study aims to address the challenges associated with different flow regimes, fluid properties, and pipe geometries by exploring advancements in electrode design, system calibration, and data processing techniques to enhance the accuracy and robustness of ECT-based velocity measurements.
{"title":"Real Time Measurement of Multiphase Flow Velocity using Electrical Capacitance Tomography","authors":"Sidi Mohamed Ahmed Ghaly, Mohammad Obaidullah Khan, Mohamed Shalaby, Khalid A. Alsnaie, Majdi Oraiqat","doi":"10.48084/etasr.6130","DOIUrl":"https://doi.org/10.48084/etasr.6130","url":null,"abstract":"Accurate and real-time measurement of fluid flow velocity is crucial in various industrial processes, especially when dealing with multiple phase fluids. Traditional flow measurement methods often struggle to accurately quantify the velocity of complex multiphase flows within pipes. This challenge necessitates the exploration of innovative techniques capable of providing reliable measurements. This paper proposes the utilization of Electrical Capacitance Tomography (ECT) as a promising approach for measuring the velocity of multiple phase fluids in pipes. The ECT technique involves the non-intrusive imaging of the electrical capacitance distribution within the pipe. By utilizing an array of electrodes placed around the pipe circumference, the capacitance distribution can be reconstructed, offering insight into the fluid flow patterns. By analyzing the temporal changes in the capacitance distribution, the velocity of different phases within the pipe can be estimated. To achieve accurate velocity measurements, an ECT system needs to account for the complexities introduced by multiphase flows. Various image reconstruction algorithms, such as linear back-projection and iterative algorithms like Gauss-Newton and Levenberg-Marquardt, are employed to reconstruct the capacitance distribution. Additionally, advanced signal processing techniques, such as cross-correlation analysis and time-difference methods, are used to extract velocity information from the reconstructed images. This paper presents an experimental investigation of measuring the velocity of multiple-phase fluids in pipes using the ECT technique. The study aims to address the challenges associated with different flow regimes, fluid properties, and pipe geometries by exploring advancements in electrode design, system calibration, and data processing techniques to enhance the accuracy and robustness of ECT-based velocity measurements.","PeriodicalId":11826,"journal":{"name":"Engineering, Technology & Applied Science Research","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135918324","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：