Pub Date : 2024-08-08DOI: 10.38124/ijisrt/ijisrt24jul721
Rohini Mehta, Pulicharla Sai Pravalika, Bellamkonda Venkata Naga Durga Sai, B. Kumar. P, Ritendu Bhattacharyya, Bharani Kumar Depuru
Behavior analysis involves the detailed process of identifying, modeling, and comprehending the various nuances and patterns of emotional expressions exhibited by individuals. It poses a significant challenge to accurately detect and predict facial emotions, especially in contexts like remote interviews, which have become increasingly prevalent. Notably, many participants struggle to convey their thoughts to interviewers with a happy expression and good posture, which may unfairly diminish their chances of employment, despite their qualifications. To address this challenge, artificial intelligence techniques such as image classification offer promising solutions. By leveraging AI models, behavior analysis can be applied to perceive and interpret facial reactions, thereby paving the way to anticipate future behaviors based on learned patterns to the participants. Despite existing works on facial emotion recognition (FER) using image classification, there is limited research focused on platforms like remote interviews and online courses. In this paper, our primary focus lies on emotions such as happiness, sadness, anger, surprise, eye contact, neutrality, smile, confusion, and stooped posture. We have curated our dataset, comprising a diverse range of sample interviews captured through participants' video recordings and other images documenting facial expressions and speech during interviews. Additionally, we have integrated existing datasets such as FER 2013 and the Celebrity Emotions dataset. Through our investigation, we explore a variety of AI and deep learning methodologies, including VGG19, ResNet50V2, ResNet152V2, Inception-ResNetV2, Xception, EfficientNet B0, and YOLO V8 to analyze facial patterns and predict emotions. Our results demonstrate an accuracy of 73% using the YOLO v8 model. However, we discovered that the categories of happy and smile, as well as surprised and confused, are not disjoint, leading to potential inaccuracies in classification. Furthermore, we considered stooped posture as a non-essential class since the interviews are conducted via webcam, which does not allow for the observation of posture. By removing these overlapping categories, we achieved a remarkable accuracy increase to around 76.88% using the YOLO v8 model.
{"title":"Advancing Virtual Interviews: AI-Driven Facial Emotion Recognition for Better Recruitment","authors":"Rohini Mehta, Pulicharla Sai Pravalika, Bellamkonda Venkata Naga Durga Sai, B. Kumar. P, Ritendu Bhattacharyya, Bharani Kumar Depuru","doi":"10.38124/ijisrt/ijisrt24jul721","DOIUrl":"https://doi.org/10.38124/ijisrt/ijisrt24jul721","url":null,"abstract":"Behavior analysis involves the detailed process of identifying, modeling, and comprehending the various nuances and patterns of emotional expressions exhibited by individuals. It poses a significant challenge to accurately detect and predict facial emotions, especially in contexts like remote interviews, which have become increasingly prevalent. Notably, many participants struggle to convey their thoughts to interviewers with a happy expression and good posture, which may unfairly diminish their chances of employment, despite their qualifications. To address this challenge, artificial intelligence techniques such as image classification offer promising solutions. By leveraging AI models, behavior analysis can be applied to perceive and interpret facial reactions, thereby paving the way to anticipate future behaviors based on learned patterns to the participants. Despite existing works on facial emotion recognition (FER) using image classification, there is limited research focused on platforms like remote interviews and online courses. In this paper, our primary focus lies on emotions such as happiness, sadness, anger, surprise, eye contact, neutrality, smile, confusion, and stooped posture. We have curated our dataset, comprising a diverse range of sample interviews captured through participants' video recordings and other images documenting facial expressions and speech during interviews. Additionally, we have integrated existing datasets such as FER 2013 and the Celebrity Emotions dataset. Through our investigation, we explore a variety of AI and deep learning methodologies, including VGG19, ResNet50V2, ResNet152V2, Inception-ResNetV2, Xception, EfficientNet B0, and YOLO V8 to analyze facial patterns and predict emotions. Our results demonstrate an accuracy of 73% using the YOLO v8 model. However, we discovered that the categories of happy and smile, as well as surprised and confused, are not disjoint, leading to potential inaccuracies in classification. Furthermore, we considered stooped posture as a non-essential class since the interviews are conducted via webcam, which does not allow for the observation of posture. By removing these overlapping categories, we achieved a remarkable accuracy increase to around 76.88% using the YOLO v8 model.","PeriodicalId":517644,"journal":{"name":"International Journal of Innovative Science and Research Technology (IJISRT)","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141928799","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 : 2024-08-08DOI: 10.38124/ijisrt/ijisrt24jul1320
Durga Nath Regmi
"Unlocking the Power of Cascading Teaching: A Key Strategy for Effective Knowledge Transfer and Professional Development discusses the importance of cascading teaching as a strategy for transferring knowledge and promoting professional development. The paper highlights the benefits of cascading teaching, such as increased engagement, improved retention of information, and enhanced collaboration among colleagues. It is found that cascading teaching is likely a research paper, article, or book that discusses the concept of cascading teaching as a strategy for knowledge transfer and professional development. It may explore how cascading teaching can be used to effectively share knowledge and skills within an organization or educational setting. The abstract also emphasizes the role of leadership in supporting and facilitating cascading teaching initiatives within organizations. Overall, the abstract underscores the value of cascading teaching as a powerful tool for enhancing learning and development in the workplace.
{"title":"Unlocking the Power of Cascading Teaching: A Key Strategy for Effective Knowledge Transfer and Professional Development","authors":"Durga Nath Regmi","doi":"10.38124/ijisrt/ijisrt24jul1320","DOIUrl":"https://doi.org/10.38124/ijisrt/ijisrt24jul1320","url":null,"abstract":"\"Unlocking the Power of Cascading Teaching: A Key Strategy for Effective Knowledge Transfer and Professional Development discusses the importance of cascading teaching as a strategy for transferring knowledge and promoting professional development. The paper highlights the benefits of cascading teaching, such as increased engagement, improved retention of information, and enhanced collaboration among colleagues. It is found that cascading teaching is likely a research paper, article, or book that discusses the concept of cascading teaching as a strategy for knowledge transfer and professional development. It may explore how cascading teaching can be used to effectively share knowledge and skills within an organization or educational setting. The abstract also emphasizes the role of leadership in supporting and facilitating cascading teaching initiatives within organizations. Overall, the abstract underscores the value of cascading teaching as a powerful tool for enhancing learning and development in the workplace.","PeriodicalId":517644,"journal":{"name":"International Journal of Innovative Science and Research Technology (IJISRT)","volume":"26 23","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141927084","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 : 2024-08-08DOI: 10.38124/ijisrt/ijisrt24jul1058
Victor Ojodomo Akoh, Fati Oiza Ochepa
This study employed the stacking of three machine learning techniques: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Logistic Regression algorithms to develop a model for detecting cyberbullying using a post dataset acquired from the X Platform. The proposed model's task is to extract keywords from the post dataset and then classify them as either 1 ("cyberbullying word") or 0 ("not cyberbullying word"). The model generated an accuracy of 85.52%, and it was deployed using a simple Graphical User Interface (GUI) web application. This study recommends that the model be included on social media platforms to help reduce the growing use of cyberbullying phrases.
{"title":"Machine Learning-Based Strategies for Detecting Cyberbullying in Online Chats","authors":"Victor Ojodomo Akoh, Fati Oiza Ochepa","doi":"10.38124/ijisrt/ijisrt24jul1058","DOIUrl":"https://doi.org/10.38124/ijisrt/ijisrt24jul1058","url":null,"abstract":"This study employed the stacking of three machine learning techniques: Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Logistic Regression algorithms to develop a model for detecting cyberbullying using a post dataset acquired from the X Platform. The proposed model's task is to extract keywords from the post dataset and then classify them as either 1 (\"cyberbullying word\") or 0 (\"not cyberbullying word\"). The model generated an accuracy of 85.52%, and it was deployed using a simple Graphical User Interface (GUI) web application. This study recommends that the model be included on social media platforms to help reduce the growing use of cyberbullying phrases.","PeriodicalId":517644,"journal":{"name":"International Journal of Innovative Science and Research Technology (IJISRT)","volume":"21 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141928465","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 : 2024-08-08DOI: 10.38124/ijisrt/ijisrt24jul1663
Hepri Massandi, Adi Fitra, Susan Kustiwan, Tri Ngudi Wiyatno
This research was conducted at a company operating in the construction sector in Cikarang. The researcher conducted direct research on the welding process. The main process of focus in this research is on welding quality defects of the Slag Inclusion type. After knowing the main problem that is the cause of a defect, then carry out an improvement plan using the Root Cause Analysis (RCA) method, which is a method of repairing causal factors by analyzing what, how, and why a factor that causes a defect can occur with the aim of finding the root cause so that There needs to be changes to avoid errors. The RCA method has 2 approaches, namely the Fishbone diagram and 5 whys. Therefore, the author took the title "Increasing the Productivity of the Welding Process in the H-beam Production Line Using the RCA (Root Cause Analysis) Approach at Pt. XYZ” Root Cause Analysis (RCA) is a tool designed to understand the root cause of an event's problems based on causality in a process. The main factor that causes defects is humans who are careless when working, who do not see or observe the material when they want to start work or even underestimate the work. So implementing SOPs is very necessary to regulate workers so they don't work as they please, and outdated machines can hamper production and improve the quality of main raw materials.
{"title":"Increasing Productivity of the Welding Process on the H-Beam Production Line by Approach RCA (Root Cause Analysis) at Pt. XYZ","authors":"Hepri Massandi, Adi Fitra, Susan Kustiwan, Tri Ngudi Wiyatno","doi":"10.38124/ijisrt/ijisrt24jul1663","DOIUrl":"https://doi.org/10.38124/ijisrt/ijisrt24jul1663","url":null,"abstract":"This research was conducted at a company operating in the construction sector in Cikarang. The researcher conducted direct research on the welding process. The main process of focus in this research is on welding quality defects of the Slag Inclusion type. After knowing the main problem that is the cause of a defect, then carry out an improvement plan using the Root Cause Analysis (RCA) method, which is a method of repairing causal factors by analyzing what, how, and why a factor that causes a defect can occur with the aim of finding the root cause so that There needs to be changes to avoid errors. The RCA method has 2 approaches, namely the Fishbone diagram and 5 whys. Therefore, the author took the title \"Increasing the Productivity of the Welding Process in the H-beam Production Line Using the RCA (Root Cause Analysis) Approach at Pt. XYZ” Root Cause Analysis (RCA) is a tool designed to understand the root cause of an event's problems based on causality in a process. The main factor that causes defects is humans who are careless when working, who do not see or observe the material when they want to start work or even underestimate the work. So implementing SOPs is very necessary to regulate workers so they don't work as they please, and outdated machines can hamper production and improve the quality of main raw materials.","PeriodicalId":517644,"journal":{"name":"International Journal of Innovative Science and Research Technology (IJISRT)","volume":"50 15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141928071","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 : 2024-08-08DOI: 10.38124/ijisrt/ijisrt24jul1305
Cariño, Hope A., Rodney Mar Jimenez, Mulleon, Razzil Kate K., Ian C. Abordo, Ma Almira P. Nebres, Raymond M. Salvador
Background and Aim: The Philippines suffers from double-burden malnutrition, and nurses are no exception. This study aimed to investigate the association between the BMI, eating habits, and physical activity among registered nurses in Iligan City, Philippines. Design: The researchers utilized a correlational research design to explore the connections between double burden malnutrition, BMI, physical activity, and eating habits among 81 registered nurses in selected hospitals in Iligan City. Results: Most participants experienced high blood pressure (93.8%), and a minority had diabetes (9.9%). Dietary habits showed median intakes of 2.70 for go- foods (1-3 per month), 3.65 for grow foods (1 per week), and 2.47 for glow foods (1-3 per month). The majority engaged in physical activity for less than thirty minutes daily (96.3%). There was a significant BMI difference between low and moderate activity levels (p = 0.003), indicating an important association with physical activity patterns. However, BMI scores did not significantly correlate with eating habits. Conclusion: No associations were found between the nurses’ BMI and eating habits, but a strong association were found between BMI and physical activity, underscoring the double burden of malnutrition. Future research with larger samples is needed to clarify these relationships. The study also highlights the growing public health concern of overweight/obesity among registered nurses, indicating that their BMI and physical activity patterns may contribute to the double-burden malnutrition.
{"title":"The Prevalence of Double-Burden Malnutrition among Registered Nurses in Iligan City","authors":"Cariño, Hope A., Rodney Mar Jimenez, Mulleon, Razzil Kate K., Ian C. Abordo, Ma Almira P. Nebres, Raymond M. Salvador","doi":"10.38124/ijisrt/ijisrt24jul1305","DOIUrl":"https://doi.org/10.38124/ijisrt/ijisrt24jul1305","url":null,"abstract":"Background and Aim: The Philippines suffers from double-burden malnutrition, and nurses are no exception. This study aimed to investigate the association between the BMI, eating habits, and physical activity among registered nurses in Iligan City, Philippines. Design: The researchers utilized a correlational research design to explore the connections between double burden malnutrition, BMI, physical activity, and eating habits among 81 registered nurses in selected hospitals in Iligan City. Results: Most participants experienced high blood pressure (93.8%), and a minority had diabetes (9.9%). Dietary habits showed median intakes of 2.70 for go- foods (1-3 per month), 3.65 for grow foods (1 per week), and 2.47 for glow foods (1-3 per month). The majority engaged in physical activity for less than thirty minutes daily (96.3%). There was a significant BMI difference between low and moderate activity levels (p = 0.003), indicating an important association with physical activity patterns. However, BMI scores did not significantly correlate with eating habits. Conclusion: No associations were found between the nurses’ BMI and eating habits, but a strong association were found between BMI and physical activity, underscoring the double burden of malnutrition. Future research with larger samples is needed to clarify these relationships. The study also highlights the growing public health concern of overweight/obesity among registered nurses, indicating that their BMI and physical activity patterns may contribute to the double-burden malnutrition.","PeriodicalId":517644,"journal":{"name":"International Journal of Innovative Science and Research Technology (IJISRT)","volume":"19 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141928252","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 : 2024-08-08DOI: 10.38124/ijisrt/ijisrt24jul1745
Aditya Vinesh, Akshai Karthik Prasad, Govind S, Surya S Gowri, S. K. K.
Edutrack introduces an innovative approach to attendance management in educational institutions, integrating state-of-the-art image and voice recognition technologies seamlessly. This advanced solution automates attendance tracking with unmatched precision, utilizing image recognition for data capture and voice recognition for accurate student identification. Edutrack streamlines administrative workflows and provides educators with comprehensive attendance records that seamlessly integrate with existing school management systems. It ensures centralized data management while adhering to stringent data privacy regulations. The intuitive interface empowers educators with efficient attendance monitoring capabilities, marking a significant advancement in educational administration. Edutrack transcends traditional attendance management methods, enriching the educational journey by fostering student engagement and accountability through its innovative real-time feedback system. This encourages students to actively participate in their academic pursuits and take responsibility for their learning outcomes. Moreover, educators can leverage Edutrack to analyze attendance patterns and offer timely interventions to support students facing attendance challenges. With personalized assistance and targeted interventions, Edutrack cultivates an environment that nurtures academic success and student well-being
{"title":"Attendance Management System Using Image andVoice Recognition","authors":"Aditya Vinesh, Akshai Karthik Prasad, Govind S, Surya S Gowri, S. K. K.","doi":"10.38124/ijisrt/ijisrt24jul1745","DOIUrl":"https://doi.org/10.38124/ijisrt/ijisrt24jul1745","url":null,"abstract":"Edutrack introduces an innovative approach to attendance management in educational institutions, integrating state-of-the-art image and voice recognition technologies seamlessly. This advanced solution automates attendance tracking with unmatched precision, utilizing image recognition for data capture and voice recognition for accurate student identification. Edutrack streamlines administrative workflows and provides educators with comprehensive attendance records that seamlessly integrate with existing school management systems. It ensures centralized data management while adhering to stringent data privacy regulations. The intuitive interface empowers educators with efficient attendance monitoring capabilities, marking a significant advancement in educational administration. Edutrack transcends traditional attendance management methods, enriching the educational journey by fostering student engagement and accountability through its innovative real-time feedback system. This encourages students to actively participate in their academic pursuits and take responsibility for their learning outcomes. Moreover, educators can leverage Edutrack to analyze attendance patterns and offer timely interventions to support students facing attendance challenges. With personalized assistance and targeted interventions, Edutrack cultivates an environment that nurtures academic success and student well-being","PeriodicalId":517644,"journal":{"name":"International Journal of Innovative Science and Research Technology (IJISRT)","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141926215","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 : 2024-08-08DOI: 10.38124/ijisrt/ijisrt24jul1317
Samrat S, S. J. Manjunath
The rapid urbanization in Karnataka, characterized by increasing population and infrastructure demands, necessitates innovative solutions to ensure sustainable and efficient urban management. Leveraging the Internet of Things (IoT), Artificial Intelligence (AI), and Machine Learning (ML) offers significant potential to enhance the decision-making capabilities of policy makers in Karnataka’s smart cities. This research paper investigates the effectiveness of these technologies in improving urban governance, focusing on real-time data acquisition, predictive analytics, and informed policy decisions. AI and ML are crucial in the analysis and interpretation of the vast amounts of data generated by IoT devices. AI algorithms process this data to identify patterns, anomalies, and trends, while ML models predict future scenarios based on historical data. For instance, predictive analytics can forecast traffic congestion, energy demand, and potential public health crises, allowing policy makers to deploy preemptive measures. In smart city initiatives, AI-driven insights ensure that resources are allocated efficiently, urban planning is optimized, and public services are enhanced. In conclusion, the integration of IoT, AI, and ML holds transformative potential for enhancing decision-making processes in Karnataka’s smart cities. By providing real-time data, predictive insights, and efficient resource management tools, these technologies enable policy makers to address urban challenges proactively and sustainably.
卡纳塔克邦快速城市化的特点是人口和基础设施需求不断增加，因此需要创新的解决方案来确保可持续和高效的城市管理。利用物联网（IoT）、人工智能（AI）和机器学习（ML）为提高卡纳塔克邦智慧城市决策者的决策能力提供了巨大潜力。本研究论文调查了这些技术在改善城市治理方面的有效性，重点关注实时数据采集、预测分析和知情决策。人工智能和 ML 对于分析和解释物联网设备产生的大量数据至关重要。人工智能算法通过处理这些数据来识别模式、异常和趋势，而 ML 模型则根据历史数据预测未来的情景。例如，预测分析可以预测交通拥堵、能源需求和潜在的公共卫生危机，使决策者能够部署先发制人的措施。在智慧城市计划中，人工智能驱动的洞察力可确保资源得到有效分配，城市规划得到优化，公共服务得到加强。总之，物联网、人工智能和 ML 的整合为卡纳塔克邦智慧城市的决策过程带来了变革潜力。通过提供实时数据、预测性洞察力和高效的资源管理工具，这些技术使决策者能够积极主动、可持续地应对城市挑战。
{"title":"Leveraging IoT, AI, and ML for Enhanced Decision-Making in Karnataka’s Smart Citie","authors":"Samrat S, S. J. Manjunath","doi":"10.38124/ijisrt/ijisrt24jul1317","DOIUrl":"https://doi.org/10.38124/ijisrt/ijisrt24jul1317","url":null,"abstract":"The rapid urbanization in Karnataka, characterized by increasing population and infrastructure demands, necessitates innovative solutions to ensure sustainable and efficient urban management. Leveraging the Internet of Things (IoT), Artificial Intelligence (AI), and Machine Learning (ML) offers significant potential to enhance the decision-making capabilities of policy makers in Karnataka’s smart cities. This research paper investigates the effectiveness of these technologies in improving urban governance, focusing on real-time data acquisition, predictive analytics, and informed policy decisions. AI and ML are crucial in the analysis and interpretation of the vast amounts of data generated by IoT devices. AI algorithms process this data to identify patterns, anomalies, and trends, while ML models predict future scenarios based on historical data. For instance, predictive analytics can forecast traffic congestion, energy demand, and potential public health crises, allowing policy makers to deploy preemptive measures. In smart city initiatives, AI-driven insights ensure that resources are allocated efficiently, urban planning is optimized, and public services are enhanced. In conclusion, the integration of IoT, AI, and ML holds transformative potential for enhancing decision-making processes in Karnataka’s smart cities. By providing real-time data, predictive insights, and efficient resource management tools, these technologies enable policy makers to address urban challenges proactively and sustainably.","PeriodicalId":517644,"journal":{"name":"International Journal of Innovative Science and Research Technology (IJISRT)","volume":"6 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141928794","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 : 2024-08-08DOI: 10.38124/ijisrt/ijisrt24jul830
Kgoshi Kgashane Lucas Pilusa
Local government in the Republic of South Africa is crucial for providing services and fostering development at the grassroots level. However, the sector is plagued by high levels of corruption, undermining its effectiveness and eroding public trust. This paper examines the challenges of professionalizing local government in South Africa amidst pervasive corruption, exploring the current state of local governance, the impacts of corruption, and strategies for fostering professionalism to enhance service delivery and governance. Efforts to professionalize local government are essential for enhancing administrative efficiency, accountability, and transparency. This study employs a qualitative research design to investigate the barriers to professionalization and the measures that can be taken to overcome these challenges. Through interviews, case studies, and document analysis, the study seeks to provide insights into effective strategies for reducing corruption and improving the performance of local governments in South Africa. The findings suggest that while corruption remains a significant hurdle, targeted interventions such as capacity building, stringent oversight mechanisms, and community engagement can foster a culture of professionalism. The study concludes with recommendations for policymakers, practitioners, and stakeholders to support the professionalization of local government as a means to combat corruption and improve service delivery.
{"title":"Professionalizing Local Government in the Republic of South Africa Amidst High Level of Corruption","authors":"Kgoshi Kgashane Lucas Pilusa","doi":"10.38124/ijisrt/ijisrt24jul830","DOIUrl":"https://doi.org/10.38124/ijisrt/ijisrt24jul830","url":null,"abstract":"Local government in the Republic of South Africa is crucial for providing services and fostering development at the grassroots level. However, the sector is plagued by high levels of corruption, undermining its effectiveness and eroding public trust. This paper examines the challenges of professionalizing local government in South Africa amidst pervasive corruption, exploring the current state of local governance, the impacts of corruption, and strategies for fostering professionalism to enhance service delivery and governance. Efforts to professionalize local government are essential for enhancing administrative efficiency, accountability, and transparency. This study employs a qualitative research design to investigate the barriers to professionalization and the measures that can be taken to overcome these challenges. Through interviews, case studies, and document analysis, the study seeks to provide insights into effective strategies for reducing corruption and improving the performance of local governments in South Africa. The findings suggest that while corruption remains a significant hurdle, targeted interventions such as capacity building, stringent oversight mechanisms, and community engagement can foster a culture of professionalism. The study concludes with recommendations for policymakers, practitioners, and stakeholders to support the professionalization of local government as a means to combat corruption and improve service delivery.","PeriodicalId":517644,"journal":{"name":"International Journal of Innovative Science and Research Technology (IJISRT)","volume":"54 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141927915","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 : 2024-08-08DOI: 10.38124/ijisrt/ijisrt24jul1256
Mydell F. Pilo
The study was conducted to understand and describe the experiences of Grade 1 teachers in Asuncion District in enhancing classroom instruction through engaging with learning action cell sessions in the new face to face classes. Qualitative research design was used and considered assumption on selecting participants, ethics, in collecting, analyzing and interpreting data. Respondents were the Grade 1 Teachers who were purposely selected through referrals and using facilitating questions to draw out narratives on their experiences, challenges and coping mechanism and further learning insights given their undertakings as technologically inclined teachers. The teachers found to have experienced and challenged with lecture approach, coaching and workshop techniques. Coping mechanisms have been found to adapt through seeking teaching effectiveness, content knowledge and pedagogy and learning environment. Educational insights were found to have recognized the importance of diversity of learners, curriculum and planning and assessment and reporting. Future direction may provide an opportunity to explore the importance of recognizing and addressing the diverse needs of learners in the classroom. Future research can also underscore the importance of investing in high-quality professional development opportunities, supporting teacher autonomy, and creating inclusive learning environments. By doing so, we can improve the quality of classroom
{"title":"Learning Action Cells Sessions: Enhancing Classroom Instruction in the New Face to Face Classes","authors":"Mydell F. Pilo","doi":"10.38124/ijisrt/ijisrt24jul1256","DOIUrl":"https://doi.org/10.38124/ijisrt/ijisrt24jul1256","url":null,"abstract":"The study was conducted to understand and describe the experiences of Grade 1 teachers in Asuncion District in enhancing classroom instruction through engaging with learning action cell sessions in the new face to face classes. Qualitative research design was used and considered assumption on selecting participants, ethics, in collecting, analyzing and interpreting data. Respondents were the Grade 1 Teachers who were purposely selected through referrals and using facilitating questions to draw out narratives on their experiences, challenges and coping mechanism and further learning insights given their undertakings as technologically inclined teachers. The teachers found to have experienced and challenged with lecture approach, coaching and workshop techniques. Coping mechanisms have been found to adapt through seeking teaching effectiveness, content knowledge and pedagogy and learning environment. Educational insights were found to have recognized the importance of diversity of learners, curriculum and planning and assessment and reporting. Future direction may provide an opportunity to explore the importance of recognizing and addressing the diverse needs of learners in the classroom. Future research can also underscore the importance of investing in high-quality professional development opportunities, supporting teacher autonomy, and creating inclusive learning environments. By doing so, we can improve the quality of classroom","PeriodicalId":517644,"journal":{"name":"International Journal of Innovative Science and Research Technology (IJISRT)","volume":"38 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141928655","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 : 2024-08-08DOI: 10.38124/ijisrt/ijisrt24jul1334
Shekofeh Yaraghi, Farhad Khosravi
Pneumonia is a life threatening disease, which occurs in the lungs caused by either bacterial or viral infection. A person suffering from pneumonia has some symptoms including cough, fever and chills, dyspnea, and low energy and appetite. The symptoms will worsen and it can be life endangering if not acted upon in the right time. Pneumonia can be diagnosed using various methods and devices, such as blood tests, sputum culture , and various types of imaging, but the most common diagnostic method is chest X-ray imaging. According to the progress achieved in the diagnosis of pneumonia, there are some problems such as the low accuracy of the diagnosis. Hence the purpose of this article is to diagnose pneumonia from chest x-ray images using transfer learning and Generative Adversarial Network (GAN) with high accuracy in two groups of normal and Pneumonia and then diagnose the type of disease in three groups: normal, viral pneumonia and bacterial pneumonia. The dataset of the article contains 5856 chest X-ray images, including normal images, viral pneumonia and bacterial pneumonia. Adversarial generator network was used in order to increase the data volume and accuracy of diagnosis. Two different pre-trained deep Convolutional Neural Network (CNN) including DenseNet121 and MobileNet, were used for deep transfer learning. The result obtained in dividing into two classes, normal and pneumonia, using DenseNet121 and MobileNet, reached an accuracy of 0.99, which is improved compared to the previous method. Therefore, the results of proposed study can be useful in faster diagnosing pneumonia by the radiologist and can help in the fast screening of the pneumonia patients.
肺炎是一种威胁生命的疾病，由细菌或病毒感染引起，发生在肺部。肺炎患者会出现一些症状，包括咳嗽、发烧和发冷、呼吸困难、精力和食欲不振。症状会不断加重，如果不及时采取措施，可能会危及生命。肺炎可通过各种方法和设备进行诊断，如验血、痰培养和各种成像，但最常见的诊断方法是胸部 X 光成像。在肺炎诊断取得进展的同时，也存在诊断准确率低等问题。因此，本文的目的是利用迁移学习和生成对抗网络（GAN）从胸部 X 光图像中诊断肺炎，对正常和肺炎两组进行高精度诊断，然后对正常、病毒性肺炎和细菌性肺炎三组进行疾病类型诊断。文章的数据集包含 5856 张胸部 X 光图像，包括正常图像、病毒性肺炎和细菌性肺炎。为了增加数据量和提高诊断的准确性，使用了对抗生成器网络。两种不同的预训练深度卷积神经网络（CNN）（包括 DenseNet121 和 MobileNet）被用于深度迁移学习。使用 DenseNet 121 和 MobileNet 将病例分为正常和肺炎两类的结果显示，准确率达到了 0.99，与之前的方法相比有所提高。因此，本研究的结果有助于放射科医生更快地诊断肺炎，并有助于肺炎患者的快速筛查。
{"title":"Diagnosis of Pneumonia from Chest X-Ray Images using Transfer Learning and Generative Adversarial Network","authors":"Shekofeh Yaraghi, Farhad Khosravi","doi":"10.38124/ijisrt/ijisrt24jul1334","DOIUrl":"https://doi.org/10.38124/ijisrt/ijisrt24jul1334","url":null,"abstract":"Pneumonia is a life threatening disease, which occurs in the lungs caused by either bacterial or viral infection. A person suffering from pneumonia has some symptoms including cough, fever and chills, dyspnea, and low energy and appetite. The symptoms will worsen and it can be life endangering if not acted upon in the right time. Pneumonia can be diagnosed using various methods and devices, such as blood tests, sputum culture , and various types of imaging, but the most common diagnostic method is chest X-ray imaging. According to the progress achieved in the diagnosis of pneumonia, there are some problems such as the low accuracy of the diagnosis. Hence the purpose of this article is to diagnose pneumonia from chest x-ray images using transfer learning and Generative Adversarial Network (GAN) with high accuracy in two groups of normal and Pneumonia and then diagnose the type of disease in three groups: normal, viral pneumonia and bacterial pneumonia. The dataset of the article contains 5856 chest X-ray images, including normal images, viral pneumonia and bacterial pneumonia. Adversarial generator network was used in order to increase the data volume and accuracy of diagnosis. Two different pre-trained deep Convolutional Neural Network (CNN) including DenseNet121 and MobileNet, were used for deep transfer learning. The result obtained in dividing into two classes, normal and pneumonia, using DenseNet121 and MobileNet, reached an accuracy of 0.99, which is improved compared to the previous method. Therefore, the results of proposed study can be useful in faster diagnosing pneumonia by the radiologist and can help in the fast screening of the pneumonia patients.","PeriodicalId":517644,"journal":{"name":"International Journal of Innovative Science and Research Technology (IJISRT)","volume":"57 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141929196","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：