Pub Date : 2024-01-28DOI: 10.1109/ICETSIS61505.2024.10459633
Hamed H. Aly
Renewable energy forecasting is crucially important because of its fluctuation and stochastic characteristics. In this paper, a hybrid model for wind speed and power forecasting using neuro wavelet and long short-term memory (LSTM) is proposed. The architecture of the proposed forecasting model involves two steps; the first step is to employ a time-based neuro wavelet for the wind speed or power forecasting. The second step is to subtract the forecasted wind speed or power from the actual ones to calculate the error (residuals). This error is then fed as an input to the LSTM to determine the forecasted wind speed or power error. The forecasted wind speed will be equal to that from the first step and the forecasted wind error from the second step. The same procedures are repeated for the forecasted wind power. In this paper, a simulated model for wind power is used. The results demonstrate the effectiveness of the proposed model for wind speed and power forecasting.
{"title":"A Proposed Hybrid Deep Learning Model for Wind Power Forecasting","authors":"Hamed H. Aly","doi":"10.1109/ICETSIS61505.2024.10459633","DOIUrl":"https://doi.org/10.1109/ICETSIS61505.2024.10459633","url":null,"abstract":"Renewable energy forecasting is crucially important because of its fluctuation and stochastic characteristics. In this paper, a hybrid model for wind speed and power forecasting using neuro wavelet and long short-term memory (LSTM) is proposed. The architecture of the proposed forecasting model involves two steps; the first step is to employ a time-based neuro wavelet for the wind speed or power forecasting. The second step is to subtract the forecasted wind speed or power from the actual ones to calculate the error (residuals). This error is then fed as an input to the LSTM to determine the forecasted wind speed or power error. The forecasted wind speed will be equal to that from the first step and the forecasted wind error from the second step. The same procedures are repeated for the forecasted wind power. In this paper, a simulated model for wind power is used. The results demonstrate the effectiveness of the proposed model for wind speed and power forecasting.","PeriodicalId":518932,"journal":{"name":"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)","volume":"411 1","pages":"1011-1014"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530407","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 : 2024-01-28DOI: 10.1109/ICETSIS61505.2024.10459491
Ishaq Ibrahim, Ali Nasser Altahitah, Kalsom Ali, A. Ateeq, M. Alaghbari
This study aims to explore the outcomes of Chat GPT on the education and learning process in the Malaysian undergraduate students. The influence of Chat GPT on the Malaysian undergraduate students predicted to impact the human capital development. This is a qualitative study conducting ethnography design approach, established an interview's questions and examined the reliability of the instruments, containing four interviewees from different four universities enrolled in undergraduate programs. The study resulted as there is a huge impact of Chat GPT on Malaysian undergraduate students, found that Chat GPT known by all the students and frequently used in their assignments and learning process. In addition, this research finds that Chat GPT impacts the undergraduate students all over the world positively by enforcing further monitoring and prepare a space for the students and lecturers to communicate and discuss the ideas to avoid the absence of innovation and creativity amongst the Malaysian undergraduate students.
{"title":"How Does Chat GPT Influence Human Capital Development Amongst Malaysian Undergraduate Students?","authors":"Ishaq Ibrahim, Ali Nasser Altahitah, Kalsom Ali, A. Ateeq, M. Alaghbari","doi":"10.1109/ICETSIS61505.2024.10459491","DOIUrl":"https://doi.org/10.1109/ICETSIS61505.2024.10459491","url":null,"abstract":"This study aims to explore the outcomes of Chat GPT on the education and learning process in the Malaysian undergraduate students. The influence of Chat GPT on the Malaysian undergraduate students predicted to impact the human capital development. This is a qualitative study conducting ethnography design approach, established an interview's questions and examined the reliability of the instruments, containing four interviewees from different four universities enrolled in undergraduate programs. The study resulted as there is a huge impact of Chat GPT on Malaysian undergraduate students, found that Chat GPT known by all the students and frequently used in their assignments and learning process. In addition, this research finds that Chat GPT impacts the undergraduate students all over the world positively by enforcing further monitoring and prepare a space for the students and lecturers to communicate and discuss the ideas to avoid the absence of innovation and creativity amongst the Malaysian undergraduate students.","PeriodicalId":518932,"journal":{"name":"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)","volume":"191 2","pages":"213-219"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530246","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 : 2024-01-28DOI: 10.1109/ICETSIS61505.2024.10459380
Rania Hamami, Narima Zermi, L. Boubchir, Amine Khaldi
This paper presents an innovative technique to safeguard sensitive medical images like X-rays, MRIs, and CT scans from unauthorized access and dissemination. The proposed approach leverages a combination of wavelet and discrete cosine transforms to embed hospital logos and patient information directly within the images. To enhance security and resilience against tampering, the embedded data is first hashed using the robust SHA-256 algorithm. Experimental results demonstrate remarkable performance, achieving a peak signal-to-noise ratio exceeding 50 dB, indicating minimal image distortion, and impressive resistance against various attacks. This approach can potentially revolutionize medical image management, safeguarding sensitive information and fostering a more secure healthcare network.
本文提出了一种创新技术，用于保护 X 光片、核磁共振成像和 CT 扫描等敏感医疗图像免遭未经授权的访问和传播。所提出的方法结合了小波变换和离散余弦变换，可直接在图像中嵌入医院标识和患者信息。为提高安全性和防篡改能力，嵌入数据首先使用稳健的 SHA-256 算法进行哈希处理。实验结果表明，该方法性能卓越，峰值信噪比超过 50 dB，图像失真极小，并能有效抵御各种攻击。这种方法有可能彻底改变医学图像管理，保护敏感信息，促进更安全的医疗保健网络。
{"title":"Enhancing Shared Image Security in Networked Environments: A Digital Watermarking Approach","authors":"Rania Hamami, Narima Zermi, L. Boubchir, Amine Khaldi","doi":"10.1109/ICETSIS61505.2024.10459380","DOIUrl":"https://doi.org/10.1109/ICETSIS61505.2024.10459380","url":null,"abstract":"This paper presents an innovative technique to safeguard sensitive medical images like X-rays, MRIs, and CT scans from unauthorized access and dissemination. The proposed approach leverages a combination of wavelet and discrete cosine transforms to embed hospital logos and patient information directly within the images. To enhance security and resilience against tampering, the embedded data is first hashed using the robust SHA-256 algorithm. Experimental results demonstrate remarkable performance, achieving a peak signal-to-noise ratio exceeding 50 dB, indicating minimal image distortion, and impressive resistance against various attacks. This approach can potentially revolutionize medical image management, safeguarding sensitive information and fostering a more secure healthcare network.","PeriodicalId":518932,"journal":{"name":"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)","volume":"182 3","pages":"1434-1438"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530252","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 : 2024-01-28DOI: 10.1109/ICETSIS61505.2024.10459533
Madala Guru Brahmam, Vijay Anand R, Veena Grover, Saikat Gochhait
There is a growing need for firms, organizations, and industries to prioritize requirements, which emphasizes the need for an efficient method to satisfy customers. When combined with the Vertical Binary Search approach, the Majority Voting Goal Based (MVGB) prioritization strategy provides a complete solution for arranging needs in order of importance. In this paper, the MVGB and Vertical Binary Search technique are explained in detail, along with a 4-step methodical approach that is in line with the principles of Binary Search. Stakeholder decisions and their allocated votes for each requirement are the basis for the approach, which yields computed values. The superiority of MVGB in terms of speed, fault tolerance, reliability, and other crucial criteria is revealed by a comparative analysis of the approach against alternative demand prioritizing methods, particularly Multi-voting and Binary Search.
{"title":"Optimizing Requirements Prioritization: Majority Voting Goal-Based Approach with Vertical Binary Search","authors":"Madala Guru Brahmam, Vijay Anand R, Veena Grover, Saikat Gochhait","doi":"10.1109/ICETSIS61505.2024.10459533","DOIUrl":"https://doi.org/10.1109/ICETSIS61505.2024.10459533","url":null,"abstract":"There is a growing need for firms, organizations, and industries to prioritize requirements, which emphasizes the need for an efficient method to satisfy customers. When combined with the Vertical Binary Search approach, the Majority Voting Goal Based (MVGB) prioritization strategy provides a complete solution for arranging needs in order of importance. In this paper, the MVGB and Vertical Binary Search technique are explained in detail, along with a 4-step methodical approach that is in line with the principles of Binary Search. Stakeholder decisions and their allocated votes for each requirement are the basis for the approach, which yields computed values. The superiority of MVGB in terms of speed, fault tolerance, reliability, and other crucial criteria is revealed by a comparative analysis of the approach against alternative demand prioritizing methods, particularly Multi-voting and Binary Search.","PeriodicalId":518932,"journal":{"name":"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)","volume":"394 7","pages":"1283-1288"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530037","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 : 2024-01-28DOI: 10.1109/ICETSIS61505.2024.10459531
Faisal Faisal, M. Shabri, Abd. Majid, A. Sakir
This article examines the impact of ownership structure, type of ownership structure namely market investor, financing decision, dividend decision, and COVID-19 on the value of 158 selected firms over the 2010-2022 period. Using a Panel Least Square Technique (EGLS), the study documented that the ownership structure (the first largest shareholder, the second largest shareholder, the type of ownership structure or market investor), and dividend decision affect positively the firm value, while the financing decision and COVID-19 pandemic affect negatively the corporate value. Our result findings stress the significance of the ownership structure, type of ownership structure by the market investor, financing decision, and dividend decision to be taken into consideration by the manager of the firms to improve the firm value and for investors when designing the investment decision in the Indonesian stock market.
{"title":"Do Ownership, Financing and Dividend Decisions, and COVID-19 Matter for Firm Value? Evidence from Indonesia","authors":"Faisal Faisal, M. Shabri, Abd. Majid, A. Sakir","doi":"10.1109/ICETSIS61505.2024.10459531","DOIUrl":"https://doi.org/10.1109/ICETSIS61505.2024.10459531","url":null,"abstract":"This article examines the impact of ownership structure, type of ownership structure namely market investor, financing decision, dividend decision, and COVID-19 on the value of 158 selected firms over the 2010-2022 period. Using a Panel Least Square Technique (EGLS), the study documented that the ownership structure (the first largest shareholder, the second largest shareholder, the type of ownership structure or market investor), and dividend decision affect positively the firm value, while the financing decision and COVID-19 pandemic affect negatively the corporate value. Our result findings stress the significance of the ownership structure, type of ownership structure by the market investor, financing decision, and dividend decision to be taken into consideration by the manager of the firms to improve the firm value and for investors when designing the investment decision in the Indonesian stock market.","PeriodicalId":518932,"journal":{"name":"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)","volume":"268 2","pages":"1159-1163"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530054","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 : 2024-01-28DOI: 10.1109/ICETSIS61505.2024.10459599
Abdallah Shatat, Mariam Altahoo, Munira Almannaei
Business Intelligence (BI) is critical in enhancing decision-making processes, operational efficiency, and positive outcomes such as improved customer service, stronger customer relationships, increased profitability, and lower failure rates. This study investigates and analyses the impact of Business intelligence on decision-making and customer service. The secondary data collection methodology employed in this paper involves a systematic review of existing knowledge by researchers about Business Intelligence. Several keywords were used, such as “Business Intelligence,” “BI in customer service and decision-making process”, and “BI Tools”. The collected research was published between 2018 and 2023 to ensure up-to-date information. This method facilitated the detection of the effect of business intelligence on decision-making and customer service by presenting its tools and challenges of implementation and examining its impact on Uber as a case study. Finally, the results have shown a positive effect on the decision-making and customer service level at Uber after using business intelligence and its tools efficiently.
{"title":"The Impact of Business Intelligence on Decision-Making Process and Customer Service","authors":"Abdallah Shatat, Mariam Altahoo, Munira Almannaei","doi":"10.1109/ICETSIS61505.2024.10459599","DOIUrl":"https://doi.org/10.1109/ICETSIS61505.2024.10459599","url":null,"abstract":"Business Intelligence (BI) is critical in enhancing decision-making processes, operational efficiency, and positive outcomes such as improved customer service, stronger customer relationships, increased profitability, and lower failure rates. This study investigates and analyses the impact of Business intelligence on decision-making and customer service. The secondary data collection methodology employed in this paper involves a systematic review of existing knowledge by researchers about Business Intelligence. Several keywords were used, such as “Business Intelligence,” “BI in customer service and decision-making process”, and “BI Tools”. The collected research was published between 2018 and 2023 to ensure up-to-date information. This method facilitated the detection of the effect of business intelligence on decision-making and customer service by presenting its tools and challenges of implementation and examining its impact on Uber as a case study. Finally, the results have shown a positive effect on the decision-making and customer service level at Uber after using business intelligence and its tools efficiently.","PeriodicalId":518932,"journal":{"name":"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)","volume":"44 7","pages":"355-360"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530396","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 : 2024-01-28DOI: 10.1109/ICETSIS61505.2024.10459626
Mudasir Ali Rind, Mohammad Ali Al Qudah, Pirali Aliyev
In recent years, there has been significant progress in the field of Artificial Intelligence, both in terms of technological advancements and knowledge acquisition. These advancements have led to the development of unorthodox learning methodologies in Artificial Intelligence applications. Artificial Intelligence is the field of study focused on developing advanced systems that can effectively learn and teach, providing learners with the most relevant information based on their own learning requirements and preferences. AI applications have made significant contributions to the education industry, particularly in higher education, where they play a crucial role in facilitating learning. This research examined the motivation and efficacy of learners in relation to the artificial intelligence learning strategy for learning applications. Data were gathered from a total of 121 respondents who were selected from five higher education colleges in the Sindh region of Pakistan. This study revealed that most learners expressed satisfaction with the utilization of artificial intelligence (AI) applications in various aspects. Specifically, they acknowledged that AI applications enhance learning capabilities and productivity. Moreover, they recognized the usefulness of AI applications in augmenting knowledge and facilitating the learning process by providing easily understandable content. What is your opinion on the potential of AI applications in these areas? Most learners expressed good motivation for the questions and expressed optimism about the usefulness of artificial intelligence applications. In conclusion, more engagement between learners and AI learning applications will provide positive outcomes in comprehending the material of the relevant topic. This paper proposes the implementation of training programs for learners specifically focused on AI learning applications.
{"title":"Determining the Impact Artificial Intelligence on Development of Higher Education","authors":"Mudasir Ali Rind, Mohammad Ali Al Qudah, Pirali Aliyev","doi":"10.1109/ICETSIS61505.2024.10459626","DOIUrl":"https://doi.org/10.1109/ICETSIS61505.2024.10459626","url":null,"abstract":"In recent years, there has been significant progress in the field of Artificial Intelligence, both in terms of technological advancements and knowledge acquisition. These advancements have led to the development of unorthodox learning methodologies in Artificial Intelligence applications. Artificial Intelligence is the field of study focused on developing advanced systems that can effectively learn and teach, providing learners with the most relevant information based on their own learning requirements and preferences. AI applications have made significant contributions to the education industry, particularly in higher education, where they play a crucial role in facilitating learning. This research examined the motivation and efficacy of learners in relation to the artificial intelligence learning strategy for learning applications. Data were gathered from a total of 121 respondents who were selected from five higher education colleges in the Sindh region of Pakistan. This study revealed that most learners expressed satisfaction with the utilization of artificial intelligence (AI) applications in various aspects. Specifically, they acknowledged that AI applications enhance learning capabilities and productivity. Moreover, they recognized the usefulness of AI applications in augmenting knowledge and facilitating the learning process by providing easily understandable content. What is your opinion on the potential of AI applications in these areas? Most learners expressed good motivation for the questions and expressed optimism about the usefulness of artificial intelligence applications. In conclusion, more engagement between learners and AI learning applications will provide positive outcomes in comprehending the material of the relevant topic. This paper proposes the implementation of training programs for learners specifically focused on AI learning applications.","PeriodicalId":518932,"journal":{"name":"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)","volume":"409 18","pages":"1486-1489"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530412","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 : 2024-01-28DOI: 10.1109/ICETSIS61505.2024.10459496
Pagolu Meghana, Visalakshi Annepu, M. Jweeg, Kalapraveen Bagadi, H. Aljibori, M. N. Mohammed, O. Abdullah, S. Aldulaimi, M. Alfiras
Regression analysis, a stalwart in statistical methodology, offers a robust framework for predicting outcomes based on historical data. It hinges on the premise that by scrutinizing past input data, one can discern the relationships between independent and dependent variables, enabling the forecasting of final results. In the dynamic landscape of Machine Learning, a multitude of regression techniques exists. Nevertheless, many real-world companies grapple with optimizing their return on investment due to the perplexing task of selecting the most apt model for their specific datasets. This research endeavor seeks to bridge this knowledge gap by conducting a comprehensive comparative analysis of three widely used and highly proficient regression algorithms: Multiple Linear Regression (MLR), Random Forest (RF), and Neural Networks (NNs). MLR offers a simple and interpretable linear model, while RF harnesses ensemble learning to handle complex relationships, and NN s employ intricate, nonlinear modeling capabilities. The study subjects two distinct datasets, Crop Yield, and Cardiovascular Disease, to scrutiny. The former addresses agricultural productivity forecasting, while the latter explores healthcare applications. By evaluating these datasets using the three regression models, the research aims to determine the most suitable model for each dataset's unique characteristics, enabling data-driven decision-making and enhancing the efficacy of regression analysis in practical, real-world scenarios.
{"title":"Analysis of Neural Network Algorithm in Comparison to Multiple Linear Regression and Random Forest Algorithm","authors":"Pagolu Meghana, Visalakshi Annepu, M. Jweeg, Kalapraveen Bagadi, H. Aljibori, M. N. Mohammed, O. Abdullah, S. Aldulaimi, M. Alfiras","doi":"10.1109/ICETSIS61505.2024.10459496","DOIUrl":"https://doi.org/10.1109/ICETSIS61505.2024.10459496","url":null,"abstract":"Regression analysis, a stalwart in statistical methodology, offers a robust framework for predicting outcomes based on historical data. It hinges on the premise that by scrutinizing past input data, one can discern the relationships between independent and dependent variables, enabling the forecasting of final results. In the dynamic landscape of Machine Learning, a multitude of regression techniques exists. Nevertheless, many real-world companies grapple with optimizing their return on investment due to the perplexing task of selecting the most apt model for their specific datasets. This research endeavor seeks to bridge this knowledge gap by conducting a comprehensive comparative analysis of three widely used and highly proficient regression algorithms: Multiple Linear Regression (MLR), Random Forest (RF), and Neural Networks (NNs). MLR offers a simple and interpretable linear model, while RF harnesses ensemble learning to handle complex relationships, and NN s employ intricate, nonlinear modeling capabilities. The study subjects two distinct datasets, Crop Yield, and Cardiovascular Disease, to scrutiny. The former addresses agricultural productivity forecasting, while the latter explores healthcare applications. By evaluating these datasets using the three regression models, the research aims to determine the most suitable model for each dataset's unique characteristics, enabling data-driven decision-making and enhancing the efficacy of regression analysis in practical, real-world scenarios.","PeriodicalId":518932,"journal":{"name":"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)","volume":"238 1","pages":"437-443"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530240","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 : 2024-01-28DOI: 10.1109/ICETSIS61505.2024.10459374
Loubna Bougheloum, M. B. Salah, M. Bettayeb
Obstacle detection is a crucial factor in ensuring the safety and mobility of visually impaired individuals. This paper introduces a comprehensive system designed to support individuals with visual impairments in outdoor environments, employing recent advancements in artificial intelligence (AI). The core of the system involves the use of YOLOv5 for efficient object recognition and Google Text-to-Speech (GTTS) for the conversion of detection results into clear and informative audio feedback. The model is trained on a customized dataset encompassing 10 specific outdoor object categories, in addition with the widely used MS COCO dataset. This strategic combination allows the system to attain heigh accuracy in obstacle detection, surpassing the performance of previous techniques. The model's ability to accurately identify and classify outdoor objects contributes to its efficacy in real-world scenarios. To ensure user accessibility, the system transforms output labels into text, which is then converted into an audio format. This audio feedback is seamlessly delivered to visually impaired users via earphones, providing real-time information about their surroundings. This approach represents a significant advancement in AI-driven outdoor obstacle detection, promising not only improved accuracy but also enhanced usability for individuals with visual impairments. By addressing the challenges of outdoor navigation, this new approach has the capacity to significantly enhance the autonomy and well-being of people with visual impairments in their everyday activities.
障碍物检测是确保视障人士安全和行动能力的关键因素。本文介绍了一个综合系统，该系统旨在利用人工智能（AI）的最新进展，为户外环境中的视障人士提供支持。该系统的核心包括使用 YOLOv5 进行高效的物体识别，以及使用谷歌文本到语音（GTTS）将检测结果转换为清晰翔实的音频反馈。除广泛使用的 MS COCO 数据集外，该模型还在包含 10 个特定户外物体类别的定制数据集上进行了训练。这种策略性组合使系统在障碍物检测方面达到了很高的精度，超越了以往技术的性能。该模型能够准确识别和分类室外物体，因此在实际应用中非常有效。为确保用户无障碍使用，该系统将输出标签转换为文本，然后再转换为音频格式。这种音频反馈可通过耳机无缝传送给视障用户，为他们提供周围环境的实时信息。这种方法代表了人工智能驱动的户外障碍物检测技术的重大进步，不仅有望提高准确性，还能增强视障人士的可用性。通过应对户外导航的挑战，这种新方法能够显著提高视障人士在日常活动中的自主性和幸福感。
{"title":"Outdoor Obstacle Detection for Visually Impaired using AI Technique","authors":"Loubna Bougheloum, M. B. Salah, M. Bettayeb","doi":"10.1109/ICETSIS61505.2024.10459374","DOIUrl":"https://doi.org/10.1109/ICETSIS61505.2024.10459374","url":null,"abstract":"Obstacle detection is a crucial factor in ensuring the safety and mobility of visually impaired individuals. This paper introduces a comprehensive system designed to support individuals with visual impairments in outdoor environments, employing recent advancements in artificial intelligence (AI). The core of the system involves the use of YOLOv5 for efficient object recognition and Google Text-to-Speech (GTTS) for the conversion of detection results into clear and informative audio feedback. The model is trained on a customized dataset encompassing 10 specific outdoor object categories, in addition with the widely used MS COCO dataset. This strategic combination allows the system to attain heigh accuracy in obstacle detection, surpassing the performance of previous techniques. The model's ability to accurately identify and classify outdoor objects contributes to its efficacy in real-world scenarios. To ensure user accessibility, the system transforms output labels into text, which is then converted into an audio format. This audio feedback is seamlessly delivered to visually impaired users via earphones, providing real-time information about their surroundings. This approach represents a significant advancement in AI-driven outdoor obstacle detection, promising not only improved accuracy but also enhanced usability for individuals with visual impairments. By addressing the challenges of outdoor navigation, this new approach has the capacity to significantly enhance the autonomy and well-being of people with visual impairments in their everyday activities.","PeriodicalId":518932,"journal":{"name":"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)","volume":"354 7-8","pages":"628-633"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530483","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 : 2024-01-28DOI: 10.1109/ICETSIS61505.2024.10459487
Ahmad Shatat, Abdallah Saleh, Islam Nassar, Rifat Hussain
This research seeks to develop an internship management system (ISM) at the university level that plays a crucial role as an intermediary platform between internship stakeholders, which are interns, academic supervisors, and field supervisors. The system development life cycle methodology was followed to develop the internship system, which consists of four phases, i.e., planning, analysis, design, and implementation. This study shows only one phase, which is the planning phase.
{"title":"Internship Management System (Planning Phase)","authors":"Ahmad Shatat, Abdallah Saleh, Islam Nassar, Rifat Hussain","doi":"10.1109/ICETSIS61505.2024.10459487","DOIUrl":"https://doi.org/10.1109/ICETSIS61505.2024.10459487","url":null,"abstract":"This research seeks to develop an internship management system (ISM) at the university level that plays a crucial role as an intermediary platform between internship stakeholders, which are interns, academic supervisors, and field supervisors. The system development life cycle methodology was followed to develop the internship system, which consists of four phases, i.e., planning, analysis, design, and implementation. This study shows only one phase, which is the planning phase.","PeriodicalId":518932,"journal":{"name":"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)","volume":"354 2","pages":"66-72"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530484","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：