Volume 15, Issue 10, 10 2024 Edition - IJSER Journal Publication


Publication for Volume 15, Issue 10, 10 2024 Edition - IJSER Journal Publication

IJSER Research Group https://www.ijser.org/forum/index.php Register for IJSER Research Forum      IJSER Xplore IJSER Xplore Research Paper Database
Pages   [1]
 

Analyzing Speech Impairments: A Machine Learning Approach to Dysarthria Detection []


Dysarthria includes dysfunction in the nerves and muscles controlling speech, leading to unclear spoken words. While many studies have been carried out to examine speech impairment, the variation of this problem among people with a similar dysarthria diagnosis has necessitated the need for more research in this area. The particular type and severity of the impairment are essential to monitor the progress of dysarthria and make effective therapeutic interventions. This project describes a Convolutional Neural Network (CNN) model for dysarthria detection, where several acoustic features are extracted in the form of zero crossing rates, Mel Frequency Cepstral Coefficients (MFCCs), spectral centroids, and spectral roll-off. Using the TORGO database of speech signals, training the model, and testing it for its efficiency has shown much promise in the early diagnosis of dysarthric speech. The numerical results indicate that the model design provides an efficiency of nearly 95%, which is higher than previous model architectures. This model aims to identify the condition early and help improve the management of dysarthria through timely and accurate diagnosis.

Applying SWARA Technique to Assess Risk Factors in PPP Waste Water Treatment Plant Projects in Egypt []


The aims of this study are: 1) to illustrate and cluster the risk factors in accordance with the public private partnership (PPP)waste water treatment plant (WWTP) projects in Egypt, 2) to assess the risk factors’ criticality degrees according to Step-Wise Weight Assessment Ratio Analysis (SWARA) method. A questionnaire survey was conducted on 20 experts in PPP projects to assess the severity of 57 risk factors gathered from literature. SWARA technique was applied to arrange these risk factors. Price change, contract termination, political corruption, political interference and technical risk are the most important risk factors. The originality of this research stems from the new technique SWARA in assessing risk factors in PPPWWTP projects. The major contribution of this research is a message that geared toward the governments and their policy-makers, especially those of the developing markets. The message is that economic and administrative unconventional actions should take as soon as possible in their systems to face these risk factors

Multifaceted Impact Analysis of Economic and Environmental Indicators on Sustainable Development in China []


This detailed analysis looks into the complex relationship between economic growth, environmental impacts, and technological advances in China's quest for sustainable development, as outlined by the United Nations in 2024. The study employs sophisticated statistical techniques such as Lasso regression analysis, OLS (Ordinary Least Squares), Granger causality tests, and Johansen cointegration to identify long-term and consistent relationships between crucial variables influencing China's environmental and economic conditions. This research provides insights into the intricate connections among technology, foreign direct investment, urban expansion, and environmental sustainability, particularly regarding their influence on CO2 emissions (World Bank, 2022; Lin, Lam, Shi, Chen, & Chen, 2023). The results question existing assumptions, providing a more profound comprehension of China's approaches to sustainable progress (United Nations, 2023). These observations benefit academics and decision-makers, aiding them in achieving harmony between environmental preservation and economic advancement

Application of CNN Architecture for Automated Human Activity Recognition In Deep Learning Network []


Convolutional neural networks (CNNs) are unique and produces great results in the image analysis and classification used for Human Activity Recognition (HAR). CNNs which is a subset of deep learning architectures known for their efficacy in processing and analyzing image data. This report explores the investigation of CNN models for automated HAR, leveraging its ability to automatically extract features and patterns from raw input data. This report uses convolutional neural network algorithms in deep learning to automatically extract features of activities related to different human activities and sporting life. The sample images are collected from Kaggle and randomly collected from Google. The network structure of the constructed CNN model consists of an input layer, two convolutional layers with Dropouts and two pooling layers. After comparing the average accuracy of each set of experiments and the test set of the best model obtained from it, the best model is then selected.

Sustainable Water Management in Yen Binh Industrial Park_ A Comprehensive Analysis and Solutions Approach Submit []


This research investigates the critical issue of water quality within Yen Binh Industrial Park in Vietnam, focusing on the environmental impact of wastewater discharge from various companies operating within the park. Industrial parks, while contributing significantly to economic growth, often present environmental challenges, particularly related to water pollution. By analyzing water samples from the park's main water supply and comparing them with the individual wastewater discharges of selected companies, this study aims to identify specific polluters and assess their contributions to the overall pollution profile. The research highlights the importance of understanding which companies contribute to water quality degradation, providing a foundation for targeted regulatory measures. By identifying common pollutants such as ammonium, chemical oxygen demand (COD), total phosphorus (TP), total nitrogen (TN) and total ammonia (TA), the study offers insights into the cumulative effects of industrial wastewater on the surrounding water bodies. Furthermore, the findings emphasize the need for sustainable industrial practices and improved wastewater management to mitigate environmental risks.

Les infrastructures de réseaux d'eau et d'électricité au Maroc : des approches de gestion en évolution []


During the French protectorate era, private companies were responsible for managing Morocco's water and electricity infrastructure. After gaining independence, the country reexamined this approach but didn’t fully discard it. Instead, it established national offices and local municipal authorities to oversee these services. Then, in the 1990s, Morocco turned to foreign private operators for local management, aiming to encourage foreign investment. As early as 1921, in line with its policy of advanced regionalization, the Moroccan state initiated the creation of Regional Multi-Services Companies (SRM, public limited companies) to handle these services. These developments reflect the ongoing evolution of management models over time.

Cloud-Based Deployment and Monitoring of Vision Transformers for Warehouse Automation: A Framework and Case Study Using AWS []


This paper presents a comprehensive case study on deploying and monitoring a Vision Transformer (ViT) model built with PyTorch for real-time inference. It focuses on the challenges associated with handling high request volumes, optimizing inference latency and managing computational resources during deployment. This solution was implemented in a warehouse that processes orders through ecommerce websites, and utilizes real-time videos from the warehouse to make predictions. The paper describes the deployment architecture leveraging AWS services like SageMaker, Lambda, and CodePipeline, and highlights the monitoring strategies employed to ensure optimal performance and reliability. The findings from this paper offer best practices for practitioners aiming to operationalize ViT models effectively in industrial applications.

Adoption of Digital Learning Technology: An Empirical Analysis of the Determinants in Telecom Sector []


Technology has advanced significantly from the analogue period to the digital era. Digital Learning Technology (DLT) is a learning paradigm based on the use of ubiquitous latest technologies, by using smart devices. It can be described as a learning environment that is assisted in daily life by wireless networks, mobile, and embedded computers. It aims to offer content and interaction to students wherever they are, at any time. The learning process has advanced thanks to the technology revolution, which has also fundamentally altered how knowledge is shared and learned. At present, there exist other frameworks too, but they are centered towards different paradigms, and point of view pertaining to DLT with its emphasis on Telecommunication Sector has not been taken into consideration. As, existing frameworks are centered towards different environments hence there exists a need to add dimensions of Empowered Learner, Digital Citizen, Knowledge Curator, Innovative Designer, Computational Thinker and Creator, Communicator & Global Collaborator. These have not been integrated together in existing available research. The study will ascertain level of knowledge of DLT and examine factors which affect the adoption rate, use, and role of DLT in telecoms setups. The results of this research will help create a framework that, if used in any academic or learning setting in a technology-based firm.

Performance Enhancement of 5G Networks: Remodelling Power Domain Scheme Through NOMA-MIMO Technologies Integration []


In 5G mobile systems, Non-Orthogonal Light Acquisition (NOMA) and Multiple End-to-End (MIMO) technologies must overcome numerous obstacles, including space limitations, connectivity restrictions, and the requirement for increased reliability. It is vital to concentrate on enhancing and reconsidering criteria of BER, SE, average power rate and potential for a link transmission error in order to boost performance in 5G networks using MIMO. Phase modulation was accomplished in a few frequency channels by the suggested model, which took into account input power, bandwidth, transmission power, and signal-to-noise ratio. Following an evaluation of the model's efficacy, the results showed superior performance over earlier research. The transmission findings demonstrate that MIMO-NOMA enhances the critical user's bit error rate and transmission power. The average active rate was used to determine link transmission outcomes. Furthermore, in both uplink and downlink scenarios, with and without MIMO, NOMA's BER, SE, average power rate & failure probability was assessed. Study discovered that MIMO-NOMA installation significantly improved performance for all users. KEY WORDS: MIMO, NOMA.

From Waste to Value: Business Strategies for Harnessing Food Waste in Sustainable Product Development []


The challenge of food waste management has grown into a critical global issue, impacting both environmental sustainability and economic viability. This paper explores strategic approaches to valorizing food waste, focusing on its transformation into value-added products within the circular bioeconomy framework. Through advanced technologies such as anaerobic digestion, microbial fermentation, and bioprocessing, food waste can be converted into biofuels, bioplastics, bioactive compounds, and animal feed, contributing to resource conservation and reducing greenhouse gas emissions. Key examples from industries demonstrate how businesses can reduce waste, create new revenue streams, and support sustainable development. Additionally, the study examines the economic implications of these technologies, emphasizing the need for scalable solutions and government incentives to enhance financial feasibility. The paper concludes by identifying critical challenges such as regulatory barriers, consumer perception, and the variability of food waste composition, alongside future research directions aimed at optimizing waste-to-product processes and fostering innovation in food waste valorization.

Typical Values of Institutional Diagnostic Reference Level (DRL) for 16-slice and 128-slice Computed Tomography (CT) Scanner in a Level 3 Regional Hospital in the Philippines []


Currently, the Philippines is still finalizing the guidelines for the establishment of National Diagnostic Reference Level (NDRL). In the absence of NDRL, healthcare institutions consisting of several X-ray rooms or a single facility linked to a new technique may also derive typical values set as the median value of the distribution from a patient survey. This study aims to determine the typical values of Volume Computed Tomography Dose Index (CTDIvol) and the Dose-Length Product (DLP) for the Head, Chest, and Abdomen-Pelvis CT scan using the 16-slice and 128-slice CT scanner installed in the hospital. A retrospective patient survey of adults who underwent CT scan examination from September to December 2021 was done to collect the CTDIvol and DLP values. A total of 391 examinations were included in the survey (296 for Head, 34 for Chest, and 61 for Abdomen-Pelvis). The CTDIvol and DLP for each CT scanner were selected as the median values of the collected data and compared with published values. Results have shown that the typical values of the CTDIvol and DLP for the Head (42 mGy,781 mGy-cm), Chest (11 mGy, 416 mGy-cm), and Abdomen-Pelvis (15 mGy, 814 mGy-cm) using the 16-slice scanner are generally higher than those of the 128-slice scanner with values of (32 mGy, 648 mGy-cm), (6 mGy, 222 mGy-cm), and (11 mGy, 558 mGy-cm), respectively. Comparing the results for both scanners to published values revealed that they are within reasonable range. The recent dose reduction technologies employed in the newly-installed 128-slice CT scanner possibly contributed to the lower values compared with those obtained using the older 16-slice CT scanner.The findings of this study can be a basis for the institutional DRL, which can be contributed to the database for the establishment of NDRL in the Philippines.

Pages   [1]