World Academy of Science, Engineering and Technology

Authors: Ishan Dave, Sindhu Ghanta, Hardik Mavdiya

Abstract:

Parkinson's disease ranks as the second most common neurodegenerative disorder, affecting around one million individuals in the United States and resulting in approximately $52 billion in annual healthcare costs. Conventional diagnostic methods for Parkinson's, including MRI and Dopamine Transporter Scans, are both invasive and expensive. This paper presents a automated approach for diagnosis of Parkinson's based on the analysis of spiral drawing patterns using deep learning. We utilized a publicly accessible dataset containing spiral drawings from both healthy subjects and Parkinson's patients. Classification models were developed using MobileNetV2 and ResNet50 architectures. Our experimental results demonstrated that MobileNetV2, with its lighter framework, achieved a test accuracy of 91%, outperforming a more complex ResNet50 model. These findings indicate that CNNs, particularly MobileNetV2, provide a viable and less burdensome method for early detection of Parkinson's disease, potentially alleviating the economic and physical impacts of traditional diagnostic techniques.

Keywords: Parkinson's, machine learning, deep learning, MobileNetV2, ResNet50, transfer learning

Procedia PDF Downloads 6

Authors: Waleed Afandi

Abstract:

Artificial intelligence (AI) has rapidly transformed various sectors, including education. This paper explores the integration of AI in education, emphasizing its potential to revolutionize learning processes, enhance teaching methodologies, and personalize education. We examine the historical context of AI in education, current applications, and the potential challenges and ethical considerations associated with its implementation. By reviewing a wide range of literature, this study aims to provide a comprehensive understanding of how AI can be leveraged to improve educational outcomes and the future directions of AI-driven educational innovations. Additionally, the paper discusses the impact of AI on student engagement, teacher support, and administrative efficiency. Case studies highlighting successful AI applications in diverse educational settings are presented, showcasing the practical benefits and real-world implications. The analysis also addresses potential disparities in access to AI technologies and suggests strategies to ensure equitable implementation. Through a balanced examination of the promises and pitfalls of AI in education, this study seeks to inform educators, policymakers, and technologists about the optimal pathways for integrating AI to foster an inclusive, effective, and innovative educational environment.

Keywords: artificial intelligence, education, personalized learning, teaching methodologies, educational outcomes, AI applications, student engagement, teacher support, administrative efficiency, equity in education

Procedia PDF Downloads 5

Authors: Nur Sahver Uslu, Ali̇ Hakan Büyüklü

Abstract:

Maintenance, Repair, and Overhaul (MRO) costs are significant in the aviation industry. On the other hand, companies that provide MRO services to the aviation industry but are not dominant in the sector, need to determine the right strategies for sustainable profitability in a competitive environment. This study examined the operational real data of a small medium enterprise (SME) MRO company where analytical methods are not widely applied. The company's customers were divided into two categories: airline companies and non-airline companies, and the variables that best explained profitability were analyzed with Logistic Regression for each category and the results were compared. First, data reduction was applied to the transformed variables that went through the data cleaning and preparation stages, and the variables to be included in the model were decided. The misclassification rates for the logistic regression results concerning both customer categories are similar, indicating consistent model performance across different segments. Less profit margin is obtained from airline customers, which can be explained by the variables part description, time to quotation (TTQ), turnaround time (TAT), manager, part cost, and labour cost. The higher profit margin obtained from non-airline customers is explained only by the variables part description, part cost, and labour cost. Based on the two models, it can be stated that it is significantly more challenging for the MRO company, which is the subject of our study, to achieve profitability from Airline customers. While operational processes and organizational structure also affect the profit from airline customers, only the type of parts and costs determine the profit for non-airlines.

Keywords: aircraft, aircraft components, aviation, data analytics, data science, gini index, maintenance, repair, and overhaul, MRO, logistic regression, profit, variable clustering, variable reduction

Procedia PDF Downloads 8

Authors: Essang Anwana Onuntuei, Chinyere Blessing Azunwoke

Abstract:

The study aimed to probe how well cyber law operates worldwide, and then draw a logical conclusion on Nigeria’s experience using a deductive reasoning approach. With a purposive or structured sampling technique, seventy-eight countries (thirteen countries each from six continents of the world) were selected as sample size. The methods used for analysing the data include the Analysis of Variance (ANOVA), Pearson product-moment correlation and regression analysis, and multiple regression analysis methods respectively. At a two-tailed test of 0.05 confidence level, the results of findings established that about 23.74 (F calculated) which is > 2.23 (F critical) claimed the total cyber-attacks and malware types vary significantly. Also, at a two-tailed confidence level test of 0.05, 0.75 (F calculated) is < 1.7 (F critical), and the P-value = 0.73 to establish significantly that cybercrime legislation does not vary statistically. More so, the calculated value (tcalculated) = 7.305 is < table value (tcritical) = 12.05 at a two-tailed test of 0.05 to imply that electronic transactions law does not statistically impact the total number of cyber-attacks. The result also proved that Consumer Privacy and Protection law does not statistically impact the total number of cyber-attacks as the calculated value (tcalculated) = 6.21 < table value (tcritical) = 20.82 at a two-tailed test of 0.05. In addition, the calculated value (tcalculated) = 7.97 < table value (tcritical) = 14.76 at a two-tailed test of 0.05 implied that Privacy and Data Protection law does not statistically impact the total number of cyber-attacks worldwide. The calculated value (tcalculated) = 5.75 < table value (tcritical) = 12.65 at a two-tailed test of 0.05 to prove that cybercrime law does not statistically impact the total number of cyber-attacks. Finally, the calculated value (tcalculated) = 6.21 < table value (tcritical) = 20.82 at a two-tailed test of 0.05 concludes that combined multiple cyber laws do not significantly impact the total number of cyber-attacks worldwide. Recommendations were made based on the results of findings from the study.

Keywords: Cybercrime Legislation, Cyber Attacks, Consumer Privacy and Protection Law, Detection, Electronic Transaction Law, Prevention, Privacy and Data Protection Law, Prohibition, Prosecution

Procedia PDF Downloads 8

Authors: Samhita Mummadi, Sree Divya Nagalli, Harshini Vemuri, Saketh Charan Nakka, Sumesh K. J.

Abstract:

One of the most significant challenges faced by people in today’s digital era is an alarming increase in fraudulent activities on online platforms. The fascination with online shopping to avoid long queues in shopping malls, the availability of a variety of products, and home delivery of goods have paved the way for a rapid increase in vast online shopping platforms. This has had a major impact on increasing fraudulent activities as well. This loop of online shopping and transactions has paved the way for fraudulent users to commit fraud. For instance, consider a store that orders thousands of products all at once, but what’s fishy about this is the massive number of items purchased and their transactions turning out to be fraud, leading to a huge loss for the seller. Considering scenarios like these underscores the urgent need to introduce machine learning approaches to combat fraud in online shopping. By leveraging robust algorithms, namely KNN, Decision Trees, and Random Forest, which are highly effective in generating accurate results, this research endeavors to discern patterns indicative of fraudulent behavior within transactional data. Introducing a comprehensive solution to this problem in order to empower e-commerce administrators in timely fraud detection and prevention is the primary motive and the main focus. In addition to that, sentiment analysis is harnessed in the model so that the e-commerce admin can tailor to the customer’s and consumer’s concerns, feedback, and comments, allowing the admin to improve the user’s experience. The ultimate objective of this study is to ramp up online shopping platforms against fraud and ensure a safer shopping experience. This paper underscores a model accuracy of 84%. All the findings and observations that were noted during our work lay the groundwork for future advancements in the development of more resilient and adaptive fraud detection systems, which will become crucial as technologies continue to evolve.

Keywords: behavior analysis, feature selection, Fraudulent pattern recognition, imbalanced classification, transactional anomalies

Procedia PDF Downloads 7

Authors: Assel Jaxylykova, Alexnder Pak

Abstract:

This study utilized a Self-Organizing Map (SOM) for unsupervised learning on the CONLL-2003 dataset for Named Entity Recognition (NER). The process involved encoding words into 300-dimensional vectors using FastText. These vectors were input into a SOM grid, where training adjusted node weights to minimize distances. The SOM provided a topological representation for identifying and clustering named entities, demonstrating its efficacy without labeled examples. Results showed an F1-measure of 0.86, highlighting SOM's viability. Although some methods achieve higher F1 measures, SOM eliminates the need for labeled data, offering a scalable and efficient alternative. The SOM's ability to uncover hidden patterns provides insights that could enhance existing supervised methods. Further investigation into potential limitations and optimization strategies is suggested to maximize benefits.

Keywords: named entity recognition, natural language processing, self-organizing map, CONLL-2003, semantics

Procedia PDF Downloads 11

Authors: Somoshree Datta, Chithra A. V., Sandeep Nithyanandan, Smitha K. K.

Abstract:

Space exploration has always been at the forefront of technological innovation, pushing the boundaries of human knowledge and capabilities. In recent years, the integration of Artificial Intelligence (AI) has revolutionized the field, offering unprecedented opportunities to enhance the efficiency, autonomy and intelligence of space missions. This survey paper aims to provide a comprehensive overview of the multifaceted applications of AI in space exploration, exploring the evolution of this synergy and its impact on mission success, scientific discovery, and the future of space endeavors. Indian Space Research Organization (ISRO) has achieved great feats in the recent moon mission (Chandrayaan-3) and sun mission (Aditya L1) by using artificial intelligence to enhance moon navigation as well as help young scientists to study the Sun even before the launch by creating AI-generated image visualizations. Throughout this survey, we will review key advancements, challenges and prospects in the intersection of AI and space exploration. As humanity continues its quest to explore the cosmos, the integration of AI promises to unlock new frontiers, reshape mission architectures, and redefine our understanding of the universe. This survey aims to serve as a comprehensive resource for researchers, engineers and enthusiasts interested in the dynamic and evolving landscape of AI applications in space exploration.

Keywords: artificial intelligence, space exploration, space missions, deep learning

Procedia PDF Downloads 8

Authors: Chithra A. V., Somoshree Datta, Sandeep Nithyanandan

Abstract:

Sign Language Recognition (SLR) is the process of interpreting and translating sign language into spoken or written language using technological systems. It involves recognizing hand gestures, facial expressions, and body movements that makeup sign language communication. The primary goal of SLR is to facilitate communication between hearing- and speech-impaired communities and those who do not understand sign language. Due to the increased awareness and greater recognition of the rights and needs of the hearing- and speech-impaired community, sign language recognition has gained significant importance over the past 10 years. Technological advancements in the fields of Artificial Intelligence and Machine Learning have made it more practical and feasible to create accurate SLR systems. This paper presents a distinct approach to SLR by framing it as a video classification problem using Deep Learning (DL), whereby a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) has been used. This research targets the integration of sign language recognition into healthcare settings, aiming to improve communication between medical professionals and patients with hearing impairments. The spatial features from each video frame are extracted using a CNN, which captures essential elements such as hand shapes, movements, and facial expressions. These features are then fed into an RNN network that learns the temporal dependencies and patterns inherent in sign language sequences. The INCLUDE dataset has been enhanced with more videos from the healthcare domain and the model is evaluated on the same. Our model achieves 91% accuracy, representing state-of-the-art performance in this domain. The results highlight the effectiveness of treating SLR as a video classification task with the CNN-RNN architecture. This approach not only improves recognition accuracy but also offers a scalable solution for real-time SLR applications, significantly advancing the field of accessible communication technologies.

Keywords: sign language recognition, deep learning, convolution neural network, recurrent neural network

Procedia PDF Downloads 7

Authors: Mohamed Hamza, Alex Ohoussou

Abstract:

At JAWDA, our primary focus is on ensuring the satisfaction of our clients worldwide. We are committed to delivering new features on our SaaS platform as quickly as possible while maintaining high-quality standards. In this paper, we highlight two key aspects of testing that represent an evolution of current methods and a potential trend for the future, which have enabled us to uphold our commitment effectively. These aspects are: "One Sandbox per Pull Request" (dynamic test environments instead of static ones) and "QA for All.".

Keywords: QA for all, dynamic sandboxes, QAOPS, CICD, continuous testing, all testers, QA matters for all, 1 sandbox per PR, utilization rate, coverage rate

Procedia PDF Downloads 5

Authors: Nisar Ahmad, Xuyi, Ali Akbar

Abstract:

As healthcare systems worldwide strive for improvement, the integration of advanced health information systems (HIS) has emerged as a pivotal strategy. This study aims to investigate the critical role of leadership in the implementation and enhancement of HIS in Chinese hospitals and how such leadership can drive improvements in patient outcomes and overall healthcare satisfaction. We propose a comprehensive study to be conducted across various hospitals in China, targeting healthcare professionals as the primary population. The research will leverage established theories of transformational leadership and technology acceptance to underpin the analysis. In our approach, data will be meticulously gathered through surveys and interviews, focusing on the experiences and perceptions of healthcare professionals regarding HIS implementation and its impact on patient care. The study will utilize SPSS and SmartPLS software for robust data analysis, ensuring precise and comprehensive insights into the correlation between leadership effectiveness and HIS success. We hypothesize that strong, visionary leadership is essential for the successful adoption and optimization of HIS, leading to enhanced patient outcomes and increased satisfaction with healthcare services. By applying advanced statistical methods, we aim to identify key leadership traits and practices that significantly contribute to these improvements. Our research will provide actionable insights for policymakers and healthcare administrators in China, offering evidence-based recommendations to foster leadership that champions HIS and drives continuous improvement in healthcare delivery. This study will contribute to the global discourse on health information systems, emphasizing the future role of leadership in transforming healthcare environments and outcomes.

Keywords: health information systems, leadership, patient outcomes, healthcare satisfaction

Procedia PDF Downloads 9

Authors: Mohammed H. Rasheed, Hussein Nadhem Fadhel, Mohammed M. Siddeq

Abstract:

In this paper we suggested image quality measuring metrics tools that can provide an accurate and close to the perceived quality sense of the tested images. Such tools give metrics that can be used to compare the performance of image compression algorithms. In this paper, two new metrics to measure the quality of decompressed images are proposed. The metric measurement based on combined data (CD) between an originals and decompressed images. Compared with other e.g., PSNR and RMSE, the proposed metrics gives values with the closest reflection of image quality perception by the human eye.

Keywords: RMSE, PSNR, image quality metrics, image compression

Procedia PDF Downloads 4

Authors: Michael Nthabiseng Moeti, Makhulu Relebogile Langa, Joey Jansen van Vuuren

Abstract:

This paper examines the utilization of personal electronic devices like laptops, tablets, and smartphones for professional duties within a financial organization. This phenomenon is known as bring your own device (BYOD). BYOD accords employees the freedom to use their personal devices to access corporate resources from anywhere in the world with Internet access. BYOD arrangements introduce significant security risks for both organizations and users. These setups change the threat landscape for enterprises and demand unique security strategies, as conventional tools tailored for safeguarding managed devices fall short in adequately protecting enterprise assets without active user cooperation. This paper applies protection motivation theory (PMT) to highlight behavioral risks from BYOD users that may impact the security of financial institutions. Thematic analysis was applied to gain a comprehensive understanding of how users perceive this phenomenon. These findings demonstrates that the existence of a security policy does not ensure that all employees will take measures to protect their personal devices. Active promotion of BYOD security policies is crucial for financial institution employees and management. This paper developed a BYOD security model which is useful for understanding compliant behaviors. Given that BYOD security is becoming a major concern across financial sector, it is important. The paper recommends that future research could expand the number of universities from which data is collected.

Keywords: BYOD, information security, protection motivation theory, security risks, thematic analysis

Procedia PDF Downloads 13

Authors: Justyna Żywiołek, Marek Matulewski

Abstract:

The article presents the results of a survey conducted among students from various European countries. The aim of the study was to understand how artificial intelligence (AI) affects educational processes in a digital environment. The survey covered a wide range of topics, including students' understanding and use of AI, its impact on motivation and engagement, interaction and support issues, accessibility and equity, and data security and privacy concerns. Most respondents admitted having difficulties comprehending the advanced functions of AI in educational tools. Many students believe that excessive use of AI in education can decrease their motivation for self-study and active participation in classes. Additionally, students reported that interaction with AI-based tools is often less satisfying compared to direct contact with teachers. Furthermore, the survey highlighted inequalities in access to advanced AI tools, which can widen the educational gap between students from different economic backgrounds. Students also expressed concerns about the security and privacy of their personal data collected and processed by AI systems. The findings suggest that while AI has the potential to support digital education, significant challenges need to be addressed to make these tools more effective and acceptable for students. Recommendations include increasing training for students and teachers on using AI, providing more interactive and engaging forms of education, and implementing stricter regulations on data protection.

Keywords: AI, digital education, education tools, motivation and engagement

Procedia PDF Downloads 11

Authors: Sourabh Yaduvanshi, Varsha Namdeo, Namrata Yaduvanshi

Abstract:

This study delves into the design and development intricacies of crafting detailed 2D bar charts via d3.js, recognizing its limitations in generating 3D visuals within the Document Object Model (DOM). The study combines three.js with d3.js, facilitating a smooth evolution from 2D to immersive 3D representations. This fusion epitomizes the synergy between front-end technologies, expanding horizons in data visualization. Beyond technical expertise, it symbolizes a creative convergence, pushing boundaries in visual representation. The abstract illuminates methodologies, unraveling the intricate integration of this fusion and guiding enthusiasts. It narrates a compelling story of transcending 2D constraints, propelling data visualization into captivating three-dimensional realms, and igniting creativity in front-end visualization endeavors.

Keywords: design, development, front-end technologies, visualization

Procedia PDF Downloads 8

Authors: Abubakar Abdulkareem, Nasir Haruna Soba

Abstract:

This study investigates the non-utilization of AI tools for research and academic writing among academic staff in Nigerian universities using the perceived attribute of innovation theory by Rogers as a theoretical framework to guide the investigation. This study was framed in an interpretative research paradigm. A qualitative methodology and case study research design was adopted. Interviews were conducted with 20 academic staff. The study used a thematic analysis process to identify 115 narratives. The narratives are organized into five major categories and further collapsed into five theoretical constructs explaining the non-use of AI tools for research and academic writing. Findings from this study revealed some of the reasons for the non-utilization of AI tools for research and academic writing as lack of Awareness, perceived Complexity, trust and Reliability Concerns, cost and accessibility, ethical and Privacy concerns and, cultural and institutional factors, etc.

Keywords: non-utilization, AI tools, research and academic writing, academic staff

Procedia PDF Downloads 15

Authors: Innocent Uzougbo Onwuegbuzie

Abstract:

Wireless Sensor Networks (WSNs) are crucial for numerous applications, yet they face significant challenges due to resource constraints such as limited power and memory. Traditional routing algorithms like Dijkstra, Ad hoc On-Demand Distance Vector (AODV), and Bellman-Ford, while effective in path establishment and discovery, are not optimized for the unique demands of WSNs due to their large memory footprint and power consumption. This paper introduces the Adaptive Energy-Aware Routing (AEAR) model, a solution designed to address these limitations. AEAR integrates reactive route discovery, localized decision-making using geographic information, energy-aware metrics, and dynamic adaptation to provide a robust and efficient routing strategy. We present a detailed comparative analysis using a dataset of 50 sensor nodes, evaluating power consumption, memory footprint, and path cost across AEAR, Dijkstra, AODV, and Bellman-Ford algorithms. Our results demonstrate that AEAR significantly reduces power consumption and memory usage while optimizing path weight. This improvement is achieved through adaptive mechanisms that balance energy efficiency and link quality, ensuring prolonged network lifespan and reliable communication. The AEAR model's superior performance underlines its potential as a viable routing solution for energy-constrained WSN environments, paving the way for more sustainable and resilient sensor network deployments.

Keywords: wireless sensor networks (WSNs), adaptive energy-aware routing (AEAR), routing algorithms, energy, efficiency, network lifespan

Procedia PDF Downloads 11

Authors: Innocent Uzougbo Onwuegbuzie

Abstract:

Healthcare delivery in low-income markets is fraught with numerous challenges, including limited access to essential medical resources, inadequate healthcare infrastructure, and a significant shortage of trained healthcare professionals. These constraints lead to suboptimal health outcomes and a higher incidence of preventable diseases. This paper explores the application of Wireless Sensor Networks (WSNs) as a transformative solution to enhance healthcare delivery in these underserved regions. WSNs, comprising spatially distributed sensor nodes that collect and transmit health-related data, present opportunities to address critical healthcare needs. Leveraging WSN technology facilitates real-time health monitoring and remote diagnostics, enabling continuous patient observation and early detection of medical issues, especially in areas with limited healthcare facilities and professionals. The implementation of WSNs can enhance the overall efficiency of healthcare systems by enabling timely interventions, reducing the strain on healthcare facilities, and optimizing resource allocation. This paper highlights the potential benefits of WSNs in low-income markets, such as cost-effectiveness, increased accessibility, and data-driven decision-making. However, deploying WSNs involves significant challenges, including technical barriers like limited internet connectivity and power supply, alongside concerns about data privacy and security. Moreover, robust infrastructure and adequate training for local healthcare providers are essential for successful implementation. It further examines future directions for WSNs, emphasizing innovation, scalable solutions, and public-private partnerships. By addressing these challenges and harnessing the potential of WSNs, it is possible to revolutionize healthcare delivery and improve health outcomes in low-income markets.

Keywords: wireless sensor networks (WSNs), healthcare delivery, low-Income markets, remote patient monitoring, health data security

Procedia PDF Downloads 14

Authors: Innocent Uzougbo Onwuegbuzie, Siene Elizabeth Eke

Abstract:

This study investigates cybersecurity challenges and solutions in managing Information and Communication Technology (ICT) at the Federal Polytechnic, Ado-Ekiti, South-West Nigeria. The rapid evolution of ICT has revolutionized organizational operations and impacted various sectors, including education, healthcare, and finance. While ICT advancements facilitate seamless communication, complex data analytics, and strategic decision-making, they also introduce significant cybersecurity risks such as data breaches, ransomware, and other malicious attacks. These threats jeopardize the confidentiality, integrity, and availability of information systems, necessitating robust cybersecurity measures. The primary aim of this research is to identify prevalent cybersecurity challenges in ICT management, evaluate their impact on the institution's operations, and assess the effectiveness of current cybersecurity solutions. Adopting a quantitative research approach, data was collected through surveys and structured questionnaires from students, staff, and IT professionals at the Federal Polytechnic, Ado-Ekiti. The findings underscore the critical need for continuous investment in cybersecurity technologies, employee and student training, and regulatory compliance to mitigate evolving cyber threats. This research contributes to bridging the knowledge gap in cybersecurity management and provides valuable insights into effective strategies and technologies for safeguarding ICT systems in educational institutions. The study's objectives are to enhance the security posture of the Federal Polytechnic, Ado-Ekiti, in an increasingly digital world by identifying and addressing the cybersecurity challenges faced by its ICT management.

Keywords: cybersecurity challenges, cyber threat mitigation, federal polytechnic Ado-Ekiti, ICT management

Procedia PDF Downloads 17

Authors: Thiago Fabrizio Gavilano Farje, Marcelo Patricio Herrera Malpartida

Abstract:

This study examines the influence of artificial intelligence (AI) on the work efficiency of administrative employees in the financial sector of Metropolitan Lima, Peru, during the year 2024. Focusing on the relationship between AI implementation and work efficiency, it addresses specific variables such as decision-making, motivation, and employee productivity. To accomplish the analysis between AI and work efficiency within the financial sector of Metropolitan Lima, it is necessary to evaluate how AI optimizes time in administrative tasks, examine how AI impacts the agility of the process of making decisions, and investigate the influence of AI on the satisfaction and motivation of employees. The research adopts a correlational and explanatory approach, designed to establish and understand the connections between AI and work efficiency. A survey design adapted from an OECD study is used, applying questionnaires to a representative sample of administrative workers in the financial sector who incorporate AI into their functions. The target population includes administrative workers in the financial sector of Metropolitan Lima, estimated at 73,097 employees based on data from the Censo Nacional de Empresas y Establecimientos and studies by the BCRP. The sample, selected through simple random sampling, comprises 246 workers.

Keywords: business management, artificial intelligence, decision making, labor efficiency, financial sector

Procedia PDF Downloads 12

Authors: Rizwan Rizwan

Abstract:

This paper provides an overview of Federated Learning (FL) and its application in enhancing data security, privacy, and efficiency. FL utilizes three distinct architectures to ensure privacy is never compromised. It involves training individual edge devices and aggregating their models on a server without sharing raw data. This approach not only provides secure models without data sharing but also offers a highly efficient privacy--preserving solution with improved security and data access. Also we discusses various frameworks used in FL and its integration with machine learning, deep learning, and data mining. In order to address the challenges of multi--party collaborative modeling scenarios, a brief review FL scheme combined with an adaptive gradient descent strategy and differential privacy mechanism. The adaptive learning rate algorithm adjusts the gradient descent process to avoid issues such as model overfitting and fluctuations, thereby enhancing modeling efficiency and performance in multi-party computation scenarios. Additionally, to cater to ultra-large-scale distributed secure computing, the research introduces a differential privacy mechanism that defends against various background knowledge attacks.

Keywords: federated learning, differential privacy, gradient descent strategy, convergence, stability, threats

Procedia PDF Downloads 10

Authors: Wudneh Asegedech Ayele

Abstract:

Background: Dietary diversity is strongly related with non-communicable disease (NCDs). Diet plays a key role as a risk factor for hypertension. Diets rich in fruits, vegetables, and low-fat dairy products that include whole grains, poultry, fish, and nuts, that contain only small amounts of red meat, sweets, and sugar-containing beverages, and that contain decreased amounts of total and saturated fat and cholesterol have been found to have a protective effect against hypertension. Methods: hospital based Cross-sectional study design was employed from June 1-June 25, 2021. Sampling technique was Systematic random sampling and data were collected using an interview method. Data were entered into Epi Data version 3.1 and exported to SPSS version 25 for processed and analysis respectively. Descriptive statistics were used to summarize data. Bivariate and multivariate logistic regression will employed to determine dietary diversity among hypertension patients. Results: Adequate dietary diversity score were 96 (24.68%). Most of them cereal, white roots and tubers, dark green leafy vegetables, Vitamin A rich fruits ,meat, egg and coffee or tea more intakes. Hypertensive patients who didn’t consume cereals four times less likely adequate dietary diversity than who consumed cereals [AOR= 4.083, 95%: CI (2.096 -7.352)]. Hypertensive patients who didn’t consume white roots and tubers 14 times less likely adequate dietary diversity than who consumed white roots and tubers [AOR= 13.733, 95% CI: (5.388-34.946)]. Conclusion and recommendation the study showed one of fourth part reported adequate dietary diversity score. Cereals, fruits, vegetables and milk and milk products were statistically associated with dietary diversity practice. Health education about dietary modifications and behavioral change to dietary diversity

Keywords: dietary diversity practice and associated facrors among hypertension patients at tirunesh beijing hospital, hypertension, dietary, diversity and tirunesh beijing hospital, associated facrors among hypertension patient, at tirunesh beijing hospita

Procedia PDF Downloads 15

Authors: Kavita Bodke

Abstract:

Structural health monitoring (SHM) is experiencing growth, necessitating the development of distinct methodologies to address its expanding scope effectively. In this study, we developed automatic structure damage identification, which incorporates three unique types of a building’s structural integrity. The first pertains to the presence of fractures within the structure, the second relates to the issue of dampness within the structure, and the third involves corrosion inside the structure. This study employs image classification techniques to discern between intact and impaired structures within structural data. The aim of this research is to find automatic damage detection with the probability of each damage class being present in one image. Based on this probability, we know which class has a higher probability or is more affected than the other classes. Utilizing photographs captured by a mobile camera serves as the input for an image classification system. Image classification was employed in our study to perform multi-class and multi-label classification. The objective was to categorize structural data based on the presence of cracks, moisture, and corrosion. In the context of multi-class image classification, our study employed three distinct methodologies: Random Forest, Multilayer Perceptron, and CNN. For the task of multi-label image classification, the models employed were Rasnet, Xceptionet, and Inception.

Keywords: SHM, CNN, deep learning, multi-class classification, multi-label classification

Procedia PDF Downloads 17

Authors: Soheila Sadeghi

Abstract:

Infrastructure projects often encounter contract variations that can significantly deviate from the original tender estimates, leading to cost overruns, schedule delays, and financial implications. This research aims to quantitatively assess the impact of changes in contract variations on project performance by conducting an in-depth analysis of a comprehensive dataset from the Regional Airport Car Park project. The dataset includes tender budget, contract quantities, rates, claims, and revenue data, providing a unique opportunity to investigate the effects of variations on project outcomes. The study focuses on 21 specific variations identified in the dataset, which represent changes or additions to the project scope. The research methodology involves establishing a baseline for the project's planned cost and scope by examining the tender budget and contract quantities. Each variation is then analyzed in detail, comparing the actual quantities and rates against the tender estimates to determine their impact on project cost and schedule. The claims data is utilized to track the progress of work and identify deviations from the planned schedule. The study employs statistical analysis using R to examine the dataset, including tender budget, contract quantities, rates, claims, and revenue data. Time series analysis is applied to the claims data to track progress and detect variations from the planned schedule. Regression analysis is utilized to investigate the relationship between variations and project performance indicators, such as cost overruns and schedule delays. The research findings highlight the significance of effective variation management in construction projects. The analysis reveals that variations can have a substantial impact on project cost, schedule, and financial outcomes. The study identifies specific variations that had the most significant influence on the Regional Airport Car Park project's performance, such as PV03 (additional fill, road base gravel, spray seal, and asphalt), PV06 (extension to the commercial car park), and PV07 (additional box out and general fill). These variations contributed to increased costs, schedule delays, and changes in the project's revenue profile. The study also examines the effectiveness of project management practices in managing variations and mitigating their impact. The research suggests that proactive risk management, thorough scope definition, and effective communication among project stakeholders can help minimize the negative consequences of variations. The findings emphasize the importance of establishing clear procedures for identifying, assessing, and managing variations throughout the project lifecycle. The outcomes of this research contribute to the body of knowledge in construction project management by demonstrating the value of analyzing tender, contract, claims, and revenue data in variation impact assessment. However, the research acknowledges the limitations imposed by the dataset, particularly the absence of detailed contract and tender documents. This constraint restricts the depth of analysis possible in investigating the root causes and full extent of variations' impact on the project. Future research could build upon this study by incorporating more comprehensive data sources to further explore the dynamics of variations in construction projects.

Keywords: contract variation impact, quantitative analysis, project performance, claims analysis

Procedia PDF Downloads 18

Authors: Arth J. Shah, Madhu R. Kamble

Abstract:

Voice biometric liveness detection is customized to certify an authentication process of the voice data presented is genuine and not a recording or synthetic voice. With the rise of deepfakes and other equivalently sophisticated spoofing generation techniques, it’s becoming challenging to ensure that the person on the other end is a live speaker or not. Voice Liveness Detection (VLD) system is a group of security measures which detect and prevent voice spoofing attacks. Motivated by the recent development of the Kolmogorov-Arnold Network (KAN) based on the Kolmogorov-Arnold theorem, we proposed KAN for the VLD task. To date, multilayer perceptron (MLP) based classifiers have been used for the classification tasks. We aim to capture not only the compositional structure of the model but also to optimize the values of univariate functions. This study explains the mathematical as well as experimental analysis of KAN for VLD tasks, thereby opening a new perspective for scientists to work on speech and signal processing-based tasks. This study emerges as a combination of traditional signal processing tasks and new deep learning models, which further proved to be a better combination for VLD tasks. The experiments are performed on the POCO and ASVSpoof 2017 V2 database. We used Constant Q-transform, Mel, and short-time Fourier transform (STFT) based front-end features and used CNN, BiLSTM, and KAN as back-end classifiers. The best accuracy is 91.26 % on the POCO database using STFT features with the KAN classifier. In the ASVSpoof 2017 V2 database, the lowest EER we obtained was 26.42 %, using CQT features and KAN as a classifier.

Keywords: Kolmogorov Arnold networks, multilayer perceptron, pop noise, voice liveness detection

Procedia PDF Downloads 19

Authors: Bantie Getnet Yirsaw, Muluken Chanie Agimas, Gebrie Getu Alemu, Tigabu Kidie Tesfie, Nebiyu Mekonnen Derseh, Habtamu Wagnew Abuhay, Meron Asmamaw Alemayehu, Getaneh Awoke Yismaw

Abstract:

Introduction: Hepatitis B virus (HBV) is one of the major public health problems globally and needs an urgent response. It is one of the most responsible causes of mortality among the five hepatitis viruses, and it affects almost every class of individuals. Thus, the main objective of this study was to determine the pooled prevalence and its determinants among pregnant women in East Africa. Methods: We searched studies using PubMed, Scopus, Embase, ScienceDirect, Google Scholar, and grey literature that were published between January 01/2020 to January 30/2024. The studies were assessed using the Newcastle Ottawa Scale (NOS) quality assessment scale. The random-effect (DerSimonian) model was used to determine the pooled prevalence and associated factors of HBV among pregnant women. Heterogeneity was assessed by I² statistic, sub-group analysis, and sensitivity analysis. Publication bias was assessed by the Egger test, and the analysis was done using STATA version 17. Result: A total of 45 studies with 35639 pregnant women were included in this systematic review and meta-analysis. The overall pooled prevalence of HBV among pregnant women in East Africa was 6.0% (95% CI: 6.0%−7.0%, I² = 89.7%). The highest prevalence of 8% ((95% CI: 6%, 10%), I² = 91.08%) was seen in 2021, and the lowest prevalence of 5% ((95% CI: 4%, 6%) I² = 52.52%) was observed in 2022. A pooled meta-analysis showed that history of surgical procedure (OR = 2.14 (95% CI: 1.27, 3.61)), having multiple sexual partners (OR = 3.87 (95% CI: 2.52, 5.95), history of body tattooing (OR = 2.55 (95% CI: 1.62, 4.01)), history of tooth extraction (OR = 2.09 (95% CI: 1.29, 3.39)), abortion history(OR = 2.20(95% CI: 1.38, 3.50)), history of sharing sharp material (OR = 1.88 (95% CI: 1.07, 3.31)), blood transfusion (OR = 2.41 (95% CI: 1.62, 3.57)), family history of HBV (OR = 4.87 (95% CI: 2.95, 8.05)) and history needle injury (OR = 2.62 (95% CI: 1.20, 5.72)) were significant risk factors associated with HBV infection among pregnant women. Conclusions: The pooled prevalence of HBV infection among pregnant women in East Africa was at an intermediate level and different across countries, ranging from 1.5% to 22.2%. The result of this pooled prevalence was an indication of the need for screening, prevention, and control of HBV infection among pregnant women in the region. Therefore, early identification of risk factors, awareness creation of the mode of transmission of HBV, and implementation of preventive measures are essential in reducing the burden of HBV infection among pregnant women.

Keywords: hepatitis B virus, prevalence, determinants, pregnant women, meta-analysis, East Africa

Procedia PDF Downloads 12

Authors: Yaxin Bi

Abstract:

Accurate prediction and understanding of the evolution mechanisms of earthquakes remain challenging in the fields of geology, geophysics, and seismology. This study leverages Long Short-Term Memory (LSTM) networks and Generative Adversarial Networks (GANs), a generative model tailored to time-series data, for generating synthetic time series data based on Swarm satellite data, which will be used for detecting seismic anomalies. LSTMs demonstrated commendable predictive performance in generating synthetic data across multiple countries. In contrast, the GAN models struggled to generate synthetic data, often producing non-informative values, although they were able to capture the data distribution of the time series. These findings highlight both the promise and challenges associated with applying deep learning techniques to generate synthetic data, underscoring the potential of deep learning in generating synthetic electromagnetic satellite data.

Keywords: LSTM, GAN, earthquake, synthetic data, generative AI, seismic precursors

Procedia PDF Downloads 16

Authors: Weichen Chang

Abstract:

To create a guided teaching method for AI generative drawing design, this paper develops a set of teaching models for AI generative drawing (DCAI), which combines learning modes such as problem-solving, thematic inquiry, phenomenon-based, task-oriented, and DFC . Through the information security AI picture book learning guided programs and content, the application of participatory action research (PAR) and interview methods to explore the dual knowledge of Context and ChatGPT (DCAI) for AI to guide the development of students' AI learning skills. In the interviews, the students highlighted five main learning outcomes (self-study, critical thinking, knowledge generation, cognitive development, and presentation of work) as well as the challenges of implementing the model. Through the use of DCAI, students will enhance their consensus awareness of generative mapping analysis and group cooperation, and they will have knowledge that can enhance AI capabilities in DCAI inquiry and future life. From this paper, it is found that the conclusions are (1) The good use of DCAI can assist students in exploring the value of their knowledge through the power of stories and finding the meaning of knowledge communication; (2) Analyze the transformation power of the integrity and coherence of the story through the context so as to achieve the tension of ‘starting and ending’; (3) Use ChatGPT to extract inspiration, arrange story compositions, and make prompts that can communicate with people and convey emotions. Therefore, new knowledge construction methods will be one of the effective methods for AI learning in the face of artificial intelligence, providing new thinking and new expressions for interdisciplinary design and design education practice.

Keywords: artificial intelligence, task-oriented, contextualization, design education

Procedia PDF Downloads 12

Authors: Melkamu A. Zeru, Yamral M. Warkaw, Aweke A. Mitku, Muluwerk Ayele

Abstract:

Introduction: Malaria is a severe health threat in the World, mainly in Africa. It is the major cause of health problems in which the risk of morbidity and mortality associated with malaria cases are characterized by spatial variations across the county. This study aimed to investigate the spatial patterns and predictors of malaria distribution in Ethiopia. Methods: A weighted sample of 15,239 individuals with rapid diagnosis tests was obtained from the Central Statistical Agency and Ethiopia malaria indicator survey of 2015. Global Moran's I and Moran scatter plots were used in determining the distribution of malaria cases, whereas the local Moran's I statistic was used in identifying exposed areas. In data manipulation, machine learning was used for variable reduction and statistical software R, Stata, and Python were used for data management and analysis. The auto logistics spatial binary regression model was used to investigate the predictors of malaria. Results: The final auto logistics regression model reported that male clients had a positive significant effect on malaria cases as compared to female clients [AOR=2.401, 95 % CI: (2.125 - 2.713)]. The distribution of malaria across the regions was different. The highest incidence of malaria was found in Gambela [AOR=52.55, 95%CI: (40.54-68.12)] followed by Beneshangul [AOR=34.95, 95%CI: (27.159 - 44.963)]. Similarly, individuals in Amhara [AOR=0.243, 95% CI:(0.1950.303],Oromiya[AOR=0.197,95%CI:(0.1580.244)],DireDawa[AOR=0.064,95%CI(0.049-0.082)],AddisAbaba[AOR=0.057,95%CI:(0.044-0.075)], Somali[AOR=0.077,95%CI:(0.059-0.097)], SNNPR[OR=0.329, 95%CI: (0.261- 0.413)] and Harari [AOR=0.256, 95%CI:(0.201 - 0.325)] were less likely to had low incidence of malaria as compared with Tigray. Furthermore, for a one-meter increase in altitude, the odds of a positive rapid diagnostic test (RDT) decrease by 1.6% [AOR = 0.984, 95% CI :( 0.984 - 0.984)]. The use of a shared toilet facility was found as a protective factor for malaria in Ethiopia [AOR=1.671, 95% CI: (1.504 - 1.854)]. The spatial autocorrelation variable changes the constant from AOR = 0.471 for logistic regression to AOR = 0.164 for auto logistics regression. Conclusions: This study found that the incidence of malaria in Ethiopia had a spatial pattern that is associated with socio-economic, demographic, and geographic risk factors. Spatial clustering of malaria cases had occurred in all regions, and the risk of clustering was different across the regions. The risk of malaria was found to be higher for those who live in soil floor-type houses as compared to those who live in cement or ceramics floor type. Similarly, households with thatched, metal and thin, and other roof-type houses have a higher risk of malaria than ceramic tiles roof houses. Moreover, using a protected anti-mosquito net reduced the risk of malaria incidence.

Keywords: malaria, Ethiopia, auto logistics, spatial model, spatial clustering

Procedia PDF Downloads 14

Authors: Su Yen Chen

Abstract:

Extensive research on ChatGPT has revealed its capabilities and limitations across various clinical, educational, and research contexts, emphasizing crucial issues such as accuracy, transparency, and ethical usage. Studies applying the Technology Acceptance Model (TAM) and Uses and Gratifications Theory have deepened our understanding of the factors that drive user acceptance and satisfaction of ChatGPT for general use. These insights are particularly valuable for examining healthcare-specific behaviors, trust levels, and perceived risks. Despite these advancements, there remains a notable gap in our understanding of how general user perceptions of AI translate into its practical applications within the healthcare sector. This study focuses on examining the perceptions of ChatGPT's impact among 266 healthcare majors in Taiwan, exploring its implications for their career development and utility in clinical practice, medical education, and research. By employing a structured survey with precisely defined subscales, this research aims to probe the breadth of ChatGPT's applications within healthcare, assessing both the perceived benefits and the challenges it presents. The findings from the survey reveal that perceptions and usage of ChatGPT among healthcare majors vary significantly, influenced by factors such as its perceived utility, risk, novelty, and trustworthiness. Graduate students and those who perceive ChatGPT as more beneficial and less risky are particularly inclined to use it more frequently. This increased usage is closely linked to significant impacts on personal career development. Furthermore, ChatGPT's perceived usefulness contributes to its broader impact within the healthcare domain, suggesting that both innovation and practical utility are key drivers of acceptance and perceived effectiveness in professional healthcare settings. Trust emerges as an important factor, especially in clinical settings where the stakes are high. The trust that healthcare professionals place in ChatGPT significantly affects its integration into clinical practice and influences outcomes in medical education and research. Thus, ChatGPT's reliability and practical value are critical for its successful adoption in these areas. However, an interesting paradox arises with regard to ease of use. While making ChatGPT more user-friendly is generally seen as beneficial, it also raises concerns among users who have lower levels of trust and perceive higher risks associated with its use. This complex interplay between ease of use and safety concerns necessitates a careful balance, highlighting the need for robust security measures and clear, transparent communication about how AI systems work and their limitations. The study suggests several strategic approaches to enhance the adoption and integration of AI in healthcare. These include targeted training programs for healthcare professionals to increase familiarity with AI technologies, reduce perceived risks, and build trust. Ensuring transparency and conducting rigorous testing are also vital to foster trust and reliability. Moreover, comprehensive policy frameworks are needed to guide the implementation of AI technologies, ensuring high standards of patient safety, privacy, and ethical use. These measures are crucial for fostering broader acceptance of AI in healthcare, as the study contributes to enriching the discourse on AI's role by detailing how various factors affect its adoption and impact.

Keywords: ChatGPT, healthcare, survey study, IT adoption, behaviour, applcation, concerns

Procedia PDF Downloads 13

Authors: Kriuk Boris, Kriuk Fedor

Abstract:

This paper presents a comparative study of fundamental similarity functions for Siamese networks in semantic textual similarity (STS) tasks. We evaluate various similarity functions using the STS Benchmark dataset, analyzing their performance and stability. Additionally, we introduce a multi-objective approach for optimal threshold selection. Our findings provide insights into the effectiveness of different similarity functions and offer a straightforward method for threshold selection optimization, contributing to the advancement of Siamese network architectures in STS applications.

Keywords: siamese networks, semantic textual similarity, similarity functions, STS benchmark dataset, threshold selection

Procedia PDF Downloads 15