Depression is an ordinary mental health-related disorder that hampers people’s daily activities, and sometimes, it destroys an individual’s life. It is one of the major social issues at present. Since depressed people use various social networking sites for sharing their thoughts and feelings, many scholars have tried to identify depression texts in highly resourced languages like English; however, only a small quantity of papers are detected in the resource-constrained Bengali language. This paper focuses on developing a depression intensity detection system from Bengali text data. In this regard, this study experiments on a 2,596 sample-sized dataset with four levels of depression by utilizing five state-of-the-art transformer models, including multilingual Bidirectional Encoder Representations from Transformers, DistilmBERT, XLM-RoBERTa, Bangla-BERT-Base, and BanglaBERT, and suggests a new ensemble method called MaxOfAvgProb. This method goes beyond the performance of the previous work on the same dataset, scoring 63.47% F1-score and 62.90% accuracy. To increase the reliability of the proposed method, we utilize this approach on another available dataset with 4,897 entries. In this case, our recommended method also surpasses the performance of the existing work on the same dataset, with accuracy at 86.45% and F1-score at 86.35%. Identifying the intensity of depression, depressed people may get proper counseling or treatment from their respected guardians or psychologists according to the victims’ level of depression.
{"title":"Depression Intensity Identification using Transformer Ensemble Technique for the Resource-constrained Bengali Language","authors":"Md. Nesarul Hoque, Umme Salma, Md. Jamal Uddin, Sadia Afrin Shampa","doi":"10.38032/jea.2024.02.001","DOIUrl":"https://doi.org/10.38032/jea.2024.02.001","url":null,"abstract":"Depression is an ordinary mental health-related disorder that hampers people’s daily activities, and sometimes, it destroys an individual’s life. It is one of the major social issues at present. Since depressed people use various social networking sites for sharing their thoughts and feelings, many scholars have tried to identify depression texts in highly resourced languages like English; however, only a small quantity of papers are detected in the resource-constrained Bengali language. This paper focuses on developing a depression intensity detection system from Bengali text data. In this regard, this study experiments on a 2,596 sample-sized dataset with four levels of depression by utilizing five state-of-the-art transformer models, including multilingual Bidirectional Encoder Representations from Transformers, DistilmBERT, XLM-RoBERTa, Bangla-BERT-Base, and BanglaBERT, and suggests a new ensemble method called MaxOfAvgProb. This method goes beyond the performance of the previous work on the same dataset, scoring 63.47% F1-score and 62.90% accuracy. To increase the reliability of the proposed method, we utilize this approach on another available dataset with 4,897 entries. In this case, our recommended method also surpasses the performance of the existing work on the same dataset, with accuracy at 86.45% and F1-score at 86.35%. Identifying the intensity of depression, depressed people may get proper counseling or treatment from their respected guardians or psychologists according to the victims’ level of depression.","PeriodicalId":292407,"journal":{"name":"Journal of Engineering Advancements","volume":" 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140992496","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 : 2024-01-19DOI: 10.38032/jea.2024.01.001
Mohammad Sultan Mahmud, Md. Mahbubur Rahman, Md Nahid Zaman Liton
The effects of cavity shape by inclination angle on laminar natural convection inside trapezoidal and square-shaped cavities have been numerically investigated in this work. Several simulations had been conducted for various inclinations of the trapezoidal cavity at Rayleigh numbers (Ra) =105 to 106 in a laminar flow regime. The walls at the left and right sides of the cavities were heated isothermally, while the walls at the top and bottom sides were adiabatic. The problem was assumed to be 2-D and solved using the software package ANSYS Fluent 16.2. Cavity filled with air is examined in two distinct instances; varying boundary layers and the flow generated for the natural convection. This numerical study analyzed the flow characteristics, temperature distribution, and Nusselt number. The analysis reveals that as the Rayleigh number increases, the Nusselt number also increases, with a more pronounced effect at higher Rayleigh numbers. It has been observed that there is a substantial effect of cavity shapes on the Nusselt number. The presence of an angled wall inhibits convection resulting in stronger flow in the squared cavity compared to the trapezoidal cavity. From numerical results, it is also found that the temperature distribution at Ra = 105 is wider than the temperature distribution at Ra= 106.
{"title":"Numerical Analysis of Laminar Natural Convection Inside Enclosed Squared and Trapezoidal Cavities at Different Inclination Angles","authors":"Mohammad Sultan Mahmud, Md. Mahbubur Rahman, Md Nahid Zaman Liton","doi":"10.38032/jea.2024.01.001","DOIUrl":"https://doi.org/10.38032/jea.2024.01.001","url":null,"abstract":"The effects of cavity shape by inclination angle on laminar natural convection inside trapezoidal and square-shaped cavities have been numerically investigated in this work. Several simulations had been conducted for various inclinations of the trapezoidal cavity at Rayleigh numbers (Ra) =105 to 106 in a laminar flow regime. The walls at the left and right sides of the cavities were heated isothermally, while the walls at the top and bottom sides were adiabatic. The problem was assumed to be 2-D and solved using the software package ANSYS Fluent 16.2. Cavity filled with air is examined in two distinct instances; varying boundary layers and the flow generated for the natural convection. This numerical study analyzed the flow characteristics, temperature distribution, and Nusselt number. The analysis reveals that as the Rayleigh number increases, the Nusselt number also increases, with a more pronounced effect at higher Rayleigh numbers. It has been observed that there is a substantial effect of cavity shapes on the Nusselt number. The presence of an angled wall inhibits convection resulting in stronger flow in the squared cavity compared to the trapezoidal cavity. From numerical results, it is also found that the temperature distribution at Ra = 105 is wider than the temperature distribution at Ra= 106.","PeriodicalId":292407,"journal":{"name":"Journal of Engineering Advancements","volume":"49 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139612054","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}
Recently, there have been notable advancements in wireless communication systems to address the deficiencies of fourth generation (4G) wireless technology, such as insufficient spectrum bandwidth, slow data transfer rates, and constrained network capacity. These issues may be addressed in fifth generation (5G) wireless technology, which is no longer stand-alone. This article proposes and designs a defected ground slotted patch antenna (DGSPA) for 5G (Sub-6 GHz band) applications. It can work at 3.5 GHz in the 5G N77 band, Sub-6 GHz 5G, LTE Band 42, and WiMAX. The suggested antenna has an overall dimension of 38×38×1.575 mm3 and is built on the Rogers RT5880 substrate material, whose dielectric permittivity is 2.2. The CST software is used as the simulation tool to analyze the designed antenna’s performance. The novelty of the recommended antenna is in terms of its small size with defective ground structure (DGS), high antenna gain, perfect impedance matching, and improved impedance bandwidth. The role of the DGS is evaluated by comparing the antenna’s performance with and without the DGS. It has been noticed that the DGS-backed antenna had an impedance bandwidth improvement of more than 11MHz, whereas the impedance profile is (50.086−????0.179) Ω, which denotes 50 Ω pure resistivity. It will operate within the frequency range of (3.4828 - 3.522) GHz with an impedance bandwidth of 69.2 MHz. The proposed antenna’s reflection coefficient (|????1,1|) is obtained as -54.028 dB at the resonating frequency of 3.5176 GHz, whereas the radiation gain and efficiency are observed as 6.463 dB and 93.475%, respectively. Thus, due to its promising performance based on radiation pattern, optimum efficiency, and higher bandwidth, the recommended defected ground slotted patch antenna can efficiently be used for the application of Sub-6 GHz 5G services.
{"title":"Design and Performance Analysis of Defected Ground Slotted Patch Antenna for Sub-6 GHz 5G Applications","authors":"Md. Najmul Hossain, Al Amin Islam, Md. Abdur Rahim, Md. Imran Hossain, Md. Arifour Rahman","doi":"10.38032/jea.2023.04.004","DOIUrl":"https://doi.org/10.38032/jea.2023.04.004","url":null,"abstract":"Recently, there have been notable advancements in wireless communication systems to address the deficiencies of fourth generation (4G) wireless technology, such as insufficient spectrum bandwidth, slow data transfer rates, and constrained network capacity. These issues may be addressed in fifth generation (5G) wireless technology, which is no longer stand-alone. This article proposes and designs a defected ground slotted patch antenna (DGSPA) for 5G (Sub-6 GHz band) applications. It can work at 3.5 GHz in the 5G N77 band, Sub-6 GHz 5G, LTE Band 42, and WiMAX. The suggested antenna has an overall dimension of 38×38×1.575 mm3 and is built on the Rogers RT5880 substrate material, whose dielectric permittivity is 2.2. The CST software is used as the simulation tool to analyze the designed antenna’s performance. The novelty of the recommended antenna is in terms of its small size with defective ground structure (DGS), high antenna gain, perfect impedance matching, and improved impedance bandwidth. The role of the DGS is evaluated by comparing the antenna’s performance with and without the DGS. It has been noticed that the DGS-backed antenna had an impedance bandwidth improvement of more than 11MHz, whereas the impedance profile is (50.086−????0.179) Ω, which denotes 50 Ω pure resistivity. It will operate within the frequency range of (3.4828 - 3.522) GHz with an impedance bandwidth of 69.2 MHz. The proposed antenna’s reflection coefficient (|????1,1|) is obtained as -54.028 dB at the resonating frequency of 3.5176 GHz, whereas the radiation gain and efficiency are observed as 6.463 dB and 93.475%, respectively. Thus, due to its promising performance based on radiation pattern, optimum efficiency, and higher bandwidth, the recommended defected ground slotted patch antenna can efficiently be used for the application of Sub-6 GHz 5G services.","PeriodicalId":292407,"journal":{"name":"Journal of Engineering Advancements","volume":"123 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139132704","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 : 2023-12-12DOI: 10.38032/jea.2023.04.003
B. Kareem, A. S. Ilori, A. S. Lawal
In this paper, the data collected from a food processing industry was used to calculate the total productivity. It presents a comprehensive model and methodology for defining and measuring productivity attributes in the food processing industry. The proposed productivity model encompasses seven key factor groups, namely labor, capital, material, energy, machines, facility maintenance, and worker stress levels. Each group is further disaggregated into individual factors, which are assigned specific weights. The mathematical expression of the productivity index model involves summing the weighted individual factors and dividing the result by the total number of group factors. In the case study conducted at a Nigerian food processing company, the developed model was applied to measure the productivity levels. The findings revealed that the current productivity of the company stands at approximately 90%. By utilizing the model, the parameters of productivity were measured, and the results were set as baseline values for future assessments. The study outcomes shed light on the perceived importance and weight values of factors within each group, highlighting their significance in influencing productivity within a technologically advanced food processing corporation. This research contributes valuable insights into the measurement and enhancement of productivity in the food processing industry, offering a structured framework for evaluating process outcomes and optimizing operations to enhance competitiveness. Incorporating the current productivity level of 90% and setting it as the baseline value provides a reference point by allowing comparisons and analysis of productivity improvements over time.
{"title":"Development of a Weighted Productivity Model for a Food Processing Industry","authors":"B. Kareem, A. S. Ilori, A. S. Lawal","doi":"10.38032/jea.2023.04.003","DOIUrl":"https://doi.org/10.38032/jea.2023.04.003","url":null,"abstract":"In this paper, the data collected from a food processing industry was used to calculate the total productivity. It presents a comprehensive model and methodology for defining and measuring productivity attributes in the food processing industry. The proposed productivity model encompasses seven key factor groups, namely labor, capital, material, energy, machines, facility maintenance, and worker stress levels. Each group is further disaggregated into individual factors, which are assigned specific weights. The mathematical expression of the productivity index model involves summing the weighted individual factors and dividing the result by the total number of group factors. In the case study conducted at a Nigerian food processing company, the developed model was applied to measure the productivity levels. The findings revealed that the current productivity of the company stands at approximately 90%. By utilizing the model, the parameters of productivity were measured, and the results were set as baseline values for future assessments. The study outcomes shed light on the perceived importance and weight values of factors within each group, highlighting their significance in influencing productivity within a technologically advanced food processing corporation. This research contributes valuable insights into the measurement and enhancement of productivity in the food processing industry, offering a structured framework for evaluating process outcomes and optimizing operations to enhance competitiveness. Incorporating the current productivity level of 90% and setting it as the baseline value provides a reference point by allowing comparisons and analysis of productivity improvements over time.","PeriodicalId":292407,"journal":{"name":"Journal of Engineering Advancements","volume":"17 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139009500","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 : 2023-11-22DOI: 10.38032/jea.2023.04.002
Oghenenyoreme Emakpo Agbroko, E. Ogunti
A key factor in the design of a car is the comfort and safety of its passengers. The quarter-car suspension system is a feature of the car that ensures load-carrying capacity as well as comfort and safety. It comprises links, springs, and shock absorbers (dampers). Due to its significance, several research has been conducted, to increase its road handling and holding capability while trying to keep its cost moderate. To enhance customer comfort and load carrying, the road holding capacity of an active quarter car suspension was improved/controlled in this study, using the Global Best Inertia Weight Modified Particle Swarm Optimization Algorithm. The observation of the closed loop and open loop systems after designing and simulating on MATLAB reveals a significant improvement in the closed loop system's road holding ability compared to the open loop, in that, when the system was subjected to pothole, the deflection of sprung mass reached steady state in 37.37 seconds as opposed to 7000 seconds for the open loop.
{"title":"Optimal Tuning of a LQR Controlled Active Quarter Car System Using Global Best Inertia Weight Modified Particle Swarm Optimization Algorithm","authors":"Oghenenyoreme Emakpo Agbroko, E. Ogunti","doi":"10.38032/jea.2023.04.002","DOIUrl":"https://doi.org/10.38032/jea.2023.04.002","url":null,"abstract":"A key factor in the design of a car is the comfort and safety of its passengers. The quarter-car suspension system is a feature of the car that ensures load-carrying capacity as well as comfort and safety. It comprises links, springs, and shock absorbers (dampers). Due to its significance, several research has been conducted, to increase its road handling and holding capability while trying to keep its cost moderate. To enhance customer comfort and load carrying, the road holding capacity of an active quarter car suspension was improved/controlled in this study, using the Global Best Inertia Weight Modified Particle Swarm Optimization Algorithm. The observation of the closed loop and open loop systems after designing and simulating on MATLAB reveals a significant improvement in the closed loop system's road holding ability compared to the open loop, in that, when the system was subjected to pothole, the deflection of sprung mass reached steady state in 37.37 seconds as opposed to 7000 seconds for the open loop.","PeriodicalId":292407,"journal":{"name":"Journal of Engineering Advancements","volume":"53 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139246381","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 : 2023-09-05DOI: 10.38032/jea.2023.03.003
Safqut Sanwar, Md. Imteaz Ahmed
This work represents an industrial sorting system where image processing is accompanied using a pick-and-place robotic gripper. The sorting of objects is done based on their shape and color. Here the color and shape of different objects are identified using image processing. For this, a webcam is used to capture images of the object in real-time and then process them via a digital computer. Python programming language is used for image processing in this work. After successfully identifying the color and shape of an object, the object is picked and placed at the desired position using the robotic gripper. Controlling the gripper mechanism is also executed using the Python programming language. It is controlled using the Arduino Uno microcontroller and a few DC servo motors. The gripper can move from 0° to 180°. The objects are brought in front of the camera using a belt conveyor system. After the complete fabrication and assembly, 4 objects of different shapes and colors are used to sort objects at 4 different angles. The objects are picked from 90° and is sorted in either 0°, 45°, 135°, or 180° position. This research work not only gives information about robotics but also can help industries sort complex objects automatically without any human interaction.
{"title":"Automated Object Sorting System with Real-Time Image Processing and Robotic Gripper Mechanism Control","authors":"Safqut Sanwar, Md. Imteaz Ahmed","doi":"10.38032/jea.2023.03.003","DOIUrl":"https://doi.org/10.38032/jea.2023.03.003","url":null,"abstract":"This work represents an industrial sorting system where image processing is accompanied using a pick-and-place robotic gripper. The sorting of objects is done based on their shape and color. Here the color and shape of different objects are identified using image processing. For this, a webcam is used to capture images of the object in real-time and then process them via a digital computer. Python programming language is used for image processing in this work. After successfully identifying the color and shape of an object, the object is picked and placed at the desired position using the robotic gripper. Controlling the gripper mechanism is also executed using the Python programming language. It is controlled using the Arduino Uno microcontroller and a few DC servo motors. The gripper can move from 0° to 180°. The objects are brought in front of the camera using a belt conveyor system. After the complete fabrication and assembly, 4 objects of different shapes and colors are used to sort objects at 4 different angles. The objects are picked from 90° and is sorted in either 0°, 45°, 135°, or 180° position. This research work not only gives information about robotics but also can help industries sort complex objects automatically without any human interaction.","PeriodicalId":292407,"journal":{"name":"Journal of Engineering Advancements","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127539216","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 purpose of this study is to forecast electricity demand by using the best-selected method which untangles all the factors that affect electricity demand. Three different methods traditional methods (Multiple Regression Model), modified-traditional methods (ARMA), and soft computing method (Fuzzy Linear Regression Model) are selected for prediction. Environmental parameters like temperature, humidity, and wind speed are included as variables as Rajshahi has very impactful weather. The impact of each variable was calculated from their standardized values to know the effect of environmental parameters. The accuracy of the three forecasting models is compared by different statistical measures of errors. Using Mean Absolute Percentage Error (MAPE), the errors of the Multiple Regression Model, ARMA, and Fuzzy Linear Regression (FLR) Model are 6.85%, 22.24%, and 4.45%. The other three measures of error also give the FLR gives the best results. Finally, the electricity demand of Rajshahi City for the next five years is forecasted using the Fuzzy Linear Regression Model.
{"title":"Forecasting Model Selection with Variables Impact to Predict Electricity Demand at Rajshahi City of Bangladesh","authors":"Md. Rasel Sarkar, Lafifa Margia Orpa, Rifat Afroz Orpe","doi":"10.38032/jea.2023.03.002","DOIUrl":"https://doi.org/10.38032/jea.2023.03.002","url":null,"abstract":"The purpose of this study is to forecast electricity demand by using the best-selected method which untangles all the factors that affect electricity demand. Three different methods traditional methods (Multiple Regression Model), modified-traditional methods (ARMA), and soft computing method (Fuzzy Linear Regression Model) are selected for prediction. Environmental parameters like temperature, humidity, and wind speed are included as variables as Rajshahi has very impactful weather. The impact of each variable was calculated from their standardized values to know the effect of environmental parameters. The accuracy of the three forecasting models is compared by different statistical measures of errors. Using Mean Absolute Percentage Error (MAPE), the errors of the Multiple Regression Model, ARMA, and Fuzzy Linear Regression (FLR) Model are 6.85%, 22.24%, and 4.45%. The other three measures of error also give the FLR gives the best results. Finally, the electricity demand of Rajshahi City for the next five years is forecasted using the Fuzzy Linear Regression Model.","PeriodicalId":292407,"journal":{"name":"Journal of Engineering Advancements","volume":"12 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125641108","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 : 2023-08-14DOI: 10.38032/jea.2023.03.001
A. Adesanya, Julius Jide Popoola
The daily increasing desire for the right information at any place, anytime, and anywhere by people has made broadcast media indispensable media for disseminating information to the public. Propagation models are deployed in planning and designing wireless communication systems. Different environments do require a unique propagation model. In this paper, least squares regression analysis was utilized to create the path loss models for the in-leaf and out-of-leaf conditions of a teak (Tectona grandis) plantation. The developed model was found to be more suitable compared to the existing Weissberger’s and COST235 models because it gives the least difference in root mean square error of 3.9 dB in the two scenarios compared to COST 234 and Weissberger, which stand at 11.2 dB and 10.8 dB, respectively, and the developed model was closer to the assessed path loss obtained from the measurement carried out. The results of the study establish a standard model that can be deployed in the effective planning and design of wireless communication links for very high bands within the radial distance in the tropical rain forest of 30m to 45m foliage depth. This study confirms the need for distinctive models for radio signals at different locations under different conditions.
{"title":"An Investigation on Effects of In-Leaf and Out-of-Leaf Conditions on Propagated Radio Broadcast FM Signal","authors":"A. Adesanya, Julius Jide Popoola","doi":"10.38032/jea.2023.03.001","DOIUrl":"https://doi.org/10.38032/jea.2023.03.001","url":null,"abstract":"The daily increasing desire for the right information at any place, anytime, and anywhere by people has made broadcast media indispensable media for disseminating information to the public. Propagation models are deployed in planning and designing wireless communication systems. Different environments do require a unique propagation model. In this paper, least squares regression analysis was utilized to create the path loss models for the in-leaf and out-of-leaf conditions of a teak (Tectona grandis) plantation. The developed model was found to be more suitable compared to the existing Weissberger’s and COST235 models because it gives the least difference in root mean square error of 3.9 dB in the two scenarios compared to COST 234 and Weissberger, which stand at 11.2 dB and 10.8 dB, respectively, and the developed model was closer to the assessed path loss obtained from the measurement carried out. The results of the study establish a standard model that can be deployed in the effective planning and design of wireless communication links for very high bands within the radial distance in the tropical rain forest of 30m to 45m foliage depth. This study confirms the need for distinctive models for radio signals at different locations under different conditions.","PeriodicalId":292407,"journal":{"name":"Journal of Engineering Advancements","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129051382","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 : 2023-06-28DOI: 10.38032/jea.2023.02.003
Md. Nesarul Hoque, Umme Salma
Depression is a mental illness that suffers people in their thoughts and daily activities. In extreme cases, sometimes it leads to self-destruction or commit to suicide. Besides an individual, depression harms the victim's family, society, and working environment. Therefore, before physiological treatment, it is essential to identify depressed people first. As various social media platforms like Facebook overwhelm our everyday life, depressed people share their personal feelings and opinions through these platforms by sending posts or comments. We have detected many research work that experiment on those text messages in English and other highly-resourced languages. Limited works we have identified in low-resource languages like Bengali. In addition, most of these works deal with a binary classification problem. We classify the Bengali depression text into four classes: non-depressive, mild, moderate, and severe in this investigation. At first, we developed a depression dataset of 2,598 entries. Then, we apply pre-processing tasks, feature selection techniques, and three types of machine learning (ML) models: classical ML, deep-learning (DL), and transformer-based pre-trained models. The XLM-RoBERTa-based pre-trained model outperforms with 61.11% F1-score and 60.89% accuracy the existing works for the four levels of the depression-class classification problem. Our proposed machine learning-based automatic detection system can recognize the various stages of depression, from low to high. It may assist the psychologist or others in providing level-wise counseling to depressed people to return to their ordinary life.
{"title":"Detecting Level of Depression from Social Media Posts for the Low-resource Bengali Language","authors":"Md. Nesarul Hoque, Umme Salma","doi":"10.38032/jea.2023.02.003","DOIUrl":"https://doi.org/10.38032/jea.2023.02.003","url":null,"abstract":"Depression is a mental illness that suffers people in their thoughts and daily activities. In extreme cases, sometimes it leads to self-destruction or commit to suicide. Besides an individual, depression harms the victim's family, society, and working environment. Therefore, before physiological treatment, it is essential to identify depressed people first. As various social media platforms like Facebook overwhelm our everyday life, depressed people share their personal feelings and opinions through these platforms by sending posts or comments. We have detected many research work that experiment on those text messages in English and other highly-resourced languages. Limited works we have identified in low-resource languages like Bengali. In addition, most of these works deal with a binary classification problem. We classify the Bengali depression text into four classes: non-depressive, mild, moderate, and severe in this investigation. At first, we developed a depression dataset of 2,598 entries. Then, we apply pre-processing tasks, feature selection techniques, and three types of machine learning (ML) models: classical ML, deep-learning (DL), and transformer-based pre-trained models. The XLM-RoBERTa-based pre-trained model outperforms with 61.11% F1-score and 60.89% accuracy the existing works for the four levels of the depression-class classification problem. Our proposed machine learning-based automatic detection system can recognize the various stages of depression, from low to high. It may assist the psychologist or others in providing level-wise counseling to depressed people to return to their ordinary life.","PeriodicalId":292407,"journal":{"name":"Journal of Engineering Advancements","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132749140","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 : 2023-06-27DOI: 10.38032/jea.2023.02.002
Yakubu Anakobe, B. Kareem, B. Akinnuli
Production system effectiveness determine to measure the sustainability of the established industries demands the development of a model for resolving global sustainable productivity challenges. The attributes (internal and external) of industrial failure were determined using questionnaire administration and oral interviews of industry experts in five (5) selected production companies in Nigeria: (Company A); (Company B); (Company C); (Company D) and (Company E). Production System Effectiveness (PSE) factors: Availability A, Performance P, and Quality Q were determined to arrive at manageable decision-making criteria under uncertainty, risk, or competition. Initial measures of PSE were based on the input internal factors (manpower, machine, material, energy, management, information/communication, money, and marketing), while sustainability decisions were determined using globally acceptable standards. The model was tested using data (weighted and normal) from the stated companies to determine their sustainability performances, while paired t-test statistic was used to test the levels of significant difference between weighted (WPSE) and normal (PSE) at 5%. The results indicated varying optimum decisions which were influenced by the nature/types of competition, risk, and standard of measure. The statistical result showed that there was a significant difference between the PSE and WPSE. These differences had little or no effect on optimum decision-making in all companies investigated.
{"title":"Determination of Production System Effectiveness Based on Sustainable Global Standards","authors":"Yakubu Anakobe, B. Kareem, B. Akinnuli","doi":"10.38032/jea.2023.02.002","DOIUrl":"https://doi.org/10.38032/jea.2023.02.002","url":null,"abstract":"Production system effectiveness determine to measure the sustainability of the established industries demands the development of a model for resolving global sustainable productivity challenges. The attributes (internal and external) of industrial failure were determined using questionnaire administration and oral interviews of industry experts in five (5) selected production companies in Nigeria: (Company A); (Company B); (Company C); (Company D) and (Company E). Production System Effectiveness (PSE) factors: Availability A, Performance P, and Quality Q were determined to arrive at manageable decision-making criteria under uncertainty, risk, or competition. Initial measures of PSE were based on the input internal factors (manpower, machine, material, energy, management, information/communication, money, and marketing), while sustainability decisions were determined using globally acceptable standards. The model was tested using data (weighted and normal) from the stated companies to determine their sustainability performances, while paired t-test statistic was used to test the levels of significant difference between weighted (WPSE) and normal (PSE) at 5%. The results indicated varying optimum decisions which were influenced by the nature/types of competition, risk, and standard of measure. The statistical result showed that there was a significant difference between the PSE and WPSE. These differences had little or no effect on optimum decision-making in all companies investigated.","PeriodicalId":292407,"journal":{"name":"Journal of Engineering Advancements","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116246981","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：