International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Quantifying Similarities: Oncology Documents from Google Bard and ChatGPT
Get PDFLarge language models hold immense promise for the future of text generation. Google Bard and ChatGPT, two prominent large language models originating from different research laboratories, have been subjects of various studies since their introduction. Despite numerous perspectives explored in the studies, none has specifically delved into the analysis of the similarity between texts generated by these models within the same category. This study addresses this gap by comparing the document generation capabilities of Google Bard and ChatGPT. The analysis focuses on topic-wise comparable documents related to oncology. In this study, 50 oncology-related documents generated by Google Bard are juxtaposed with equivalent topic-wise documents produced by ChatGPT, utilizing both cosine similarity and Jaccard similarity for comparison. The analysis employed statistical tests including the Kolmogorov-Smirnov test, Shapiro-Wilk test, and the one-sample Wilcoxon signed-rank test. The findings revealed a significant level of resemblance among the documents generated by both models: cosine similarity (mean = 0.66, std. dev. = 0.11, min = 0.23, max = 0.80) and Jaccard similarity (mean = 0.88, std. dev. = 0.06, min = 0.7, max = 1.0). This suggests a probable commonality in their training datasets or sources of oncology-related information. The study also posited that the observed similarity could be attributed to the probabilistic nature of language models and the potential for overfitting during their training processes. This study stands out for offering a unique direction and outcomes that pave the way for further exploration in the domain of large language models
Effective Model for CoAP Inspired Trust Aware Scheme in Internet of Things with AES Algorithm
Get PDFIOT networks have been developed in the realm of technology to make connectivity among the things around us. Networks could only connect computer devices before the Internet of Things (IoT) became a reality. Security is the key issue with these devices. There are significant risks of data loss or hacker assault because these gadgets communicate their data via internet. Challenges from the start have accompanied IoT adoption. In this paper, some of the major difficulties on the way to communicate between gadgets are explored. IoT networks protect user privacy with various types of personal data that are made available for these IoT-based connected devices. To protect IoT-based systems, a trust-aware approach utilizing the CoAP and AES algorithms has been proposed in this paper. The AES method has very robust security, shielding the data and architecture in comparison to others. The utilization of AES coupled with CoAP will enhance the efficacy of the system
An Optimal Feature Extraction Technique for Glioma Tumor Detection from Brain MRI
Get PDFA brain tumor is defined by the uncontrolled proliferation of brain tissue cells, defying the typical cellular regulation mechanisms governing growth. The most significant challenge associated with brain tumors lies in their timely diagnosis and accurate stage determination. Accurate detection of tumors from MRI scans can not only assist doctors in their examination but also provide crucial information for appropriate and timely treatment decisions. In this paper, a comprehensive analysis is presented based on comparisons between state-of-the-art dimensionality reduction and classification algorithms. We used a dataset containing brain MRI scans, including both tumor and non-tumor cases, which was split into training and testing sets. After preprocessing the data, we implemented four feature extraction algorithms to obtain different sets of features. Consequently, these sets of features were used to train five classifiers to analyze the accuracy. Based on these results, optimal feature extraction and brain tumor classification technique is selected. The results indicate that the Linear Discriminant Analysis (LDA) technique extracted highly informative features, leading to an impressive accuracy of 92.84%. This highlights the effectiveness of LDA in significantly enhancing the performance of the brain tumor classification process, making it the prime choice for feature extraction that aligns seamlessly with the research\u27s intuition. It has higher accuracy with all the classifiers
Urban Green Spaces and Subjective Well-being: Exploring the Impact on Overall Life Satisfaction Through ML Techniques
Get PDFThe existence of green infrastructure plays a pivotal role within an urban setting, actively contributing to various facets of life. Urban greenness has positive association between increased utilization and higher levels of life satisfaction. But Lahore, a city experiencing rapid growth, is facing a significant challenge as its expansion leads to a reduction in green infrastructure. This decline in green spaces raises serious concerns about the city\u27s long-term sustainability. Therefore, the study aimed to investigate the connection between urban green spaces and subjective well-being, specifically overall life satisfaction. In response to this challenge, this study employs advanced computer science algorithms, including Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), k-Nearest Neighbors (KNN), and Artificial Intelligence (AI), to investigate the connection between urban green spaces and subjective well-being, with a specific focus on overall life satisfaction. For this, primary data was collected an online survey and 1050 respondents were analyzed. The results found that the accessibility of urban green spaces within convenient distances and frequent visits to these areas play a vital role in human life satisfaction, the overall effect of urban green spaces on subjective well-being was found positive (beta = 0.781, R2 = 0.610, at p < 0.000). Therefore, it is concluded that UGSs in an accessible range are essential for high-level subjective well-being
Applications of AI in Health Services
Get PDFThe effects of artificial intelligence (AI)-based technologies on the healthcare sector are explored in this study. This research examined numerous practical uses of AI in healthcare, in addition to a comprehensive literature evaluation. Based on these findings, it appears that large hospitals are currently utilizing AI-enabled technologies to assist with patient diagnostic and treatment activities across a wide variety of ailments. Additionally, AI technologies are affecting the effectiveness of nursing and hospital management. Although AI is generally welcomed by the healthcare industry, its implementations present both utopian (new possibilities) and dystopian (overcoming obstacles) scenarios. To present a well-rounded picture of the usefulness of AI applications in healthcare, we address the specifics of these potential obstacles. The rapid development of AI and associated technologies will aid in the improvement of operational efficiency and the creation of new value for patients. However, to gain the benefits of technology like AI, comprehensive service transformation and operations planning are essential
Unveiling Inefficiencies in Open-Source Code Using Multistage Analysis with Software Metrics
Get PDFSoftware development is challenging due to its technical complexity and time-consuming nature. To overcome these difficulties, various technical solutions have been introduced. In commercial software development, code repositories serve as valuable resources, reducing the time and cost involved in the process. The utilization of pre-developed open code repositories has proven to reduce development time. However, ample amount of work has not determined whether these repositories are testable, maintainable, free of dead code, and have a concise implementation of equivalent algorithms. The objective of this article is to address this gap by thoroughly analyzing the complexity and maintainability of code repositories, determining the impact of removing dead code on size, complexity, and maintainability. For this study, a total of 200 Python open-source code were analyzed using RADON, a widely-used metric tool for assessing cyclomatic complexity, size, volume, and maintainability. The identification of dead code within the repositories was accomplished using Vulture, supplemented by expert evaluation. It has been revealed that the majority of the examined code included dead code, and the removal of this code led to a significant reduction in cyclomatic complexity, volume, and size, while improving code maintainability, as observed by the Mann Whitney U test. The study concludes that the blind use of open-source code is not safe. It strongly recommends the community to thoroughly explore and examine such code from different perspectives before actual implementation. The novelty of this study lies in the use of multiple software metrics in a multi-stage analysis to examine the impact of removing dead code on program complexity, size, and maintainability
Enhancing Teacher Resilience: Innovative Coping Strategies for Flood Vulnerabilities
Get PDFFlood disasters have the potential to inflict substantial damage on infrastructure, homes and agricultural fields, leading to economic and societal vulnerabilities in the less affluent regions of Punjab, Pakistan. These floods also can displace communities, resulting in emotional distress and community disruption. During such challenging circumstances, educators play a pivotal role by providing education, solace, and guidance to farmers and students grappling with floods and potential mitigation measures. In 2022, flood disasters in Tehsil Taunsa Sharif, Punjab, Pakistan, caused significant harm to infrastructure, housing, and crops, exacerbating economic and social vulnerabilities within low-income communities. This study aimed to explore the effectiveness of teacher\u27s coping strategies in flood-prone areas of Tehsil Taunsa Sharif in addressing these social vulnerabilities. For this research, a total of 25 high and higher secondary schools in Tehsil Taunsa Sharif were identified, from which a convenient sample of 10 schools were selected. The population consisted of 150 teachers and the sample included 85 school teachers, chosen using a confidence level of 95% and a confidence interval of 7%. Schools were selected through a convenient sampling technique, while respondents were randomly selected to ensure an unbiased sample. The findings revealed that the majority of teachers acknowledged using various coping strategies in flood-prone areas including efforts to establish a safe and inclusive learning environment (mean = 4.26), assisting students in developing problem-solving skills (mean = 4.26), encouraging students to express their feelings (mean = 4.25) and providing moral support (mean = 4.22). Furthermore, teachers employed various techniques to enhance the effectiveness of coping mechanisms, such as collaborating with local authorities (mean = 4.32), identifying student needs (mean = 4.28), and promoting mental well-being (mean = 4.28). Additionally, the study found that most teachers believed that flooding had a significant impact on the educational level (mean = 4.38). Public-private partnerships were perceived to enhance the well-being of the community (mean = 4.32). The flood\u27s effects on student access to education (mean = 4.31) and mental health (mean = 4.28) were also evident. In light of these findings, the government needs to develop and implement effective early warning systems to alert communities about impending floods. This proactive approach can aid schools and families in preparing for potential disasters and taking necessary actions to minimize disruptions. Furthermore, the incorporation of flood-resistant features in the design of educational infrastructure, including schools, colleges, and universities is crucial for ensuring educational continuity during flood events
ML/AI Based Flood Mapping in Swat Watershed Using Sentinel-I and Sentinel-II Data
Get PDFThis research uses Sentinel-1 and Sentinel-2 data for flood monitoring and mapping, with a focus on the accuracy and reliability of these remote sensing techniques in identifying flood inundation areas. The objectives of this study revolved around the accuracy and reliability of these techniques in detecting and mapping floodwaters. Water indices, namely NDWI and WRI, were utilized to extract floodwater areas and generate flood inundation maps. Additionally, flood extent maps were generated using Sentinel-1 data to complement the findings from Sentinel-2 data. The study implemented a multi-sensor and multi-index approach, considering both optical and radar data, to provide a comprehensive analysis of flood events. Image selection based on low cloud cover was employed to ensure high-quality and cloud-free imagery for accurate flood extent estimation. The selected images were processed using water indices, NDWI and WRI, which effectively captured the spatial distribution of floodwaters. The results revealed insights into the temporal variation and spatial distribution of flood extents, allowing for the identification of most affected areas. The analysis of Sentinel-2 imagery for July 2022 showcased a progressive intensification of the flood event, with the most affected regions being Charbagh, Mangora, Saidu Sharif, and Chakdara. The flood extents increased in August 2022, affecting areas such as Mangora, Saidu Sharif, Charbagh, Manglor, Barikot, and Chakdara. Furthermore, the flood extent in September 2022 indicated the persistence of floodwaters in areas with relatively fewer sloping surfaces. The integration of Sentinel-1 data provided enhanced comprehension into flood extents, particularly in challenging conditions such as high cloud cover or dense vegetation. The flood inundation maps generated from Sentinel-1 data complemented the findings from Sentinel-2 data, enhancing the accuracy and reliability of flood extent assessments. It is important to note that the high areas observed in the Sentinel-1 flood inundation maps are due to the mosaic of all the images acquired during the respective months. This approach includes all the water detected by Sentinel-1 from the 15 images, resulting in a larger affected area being shown. The flood inundation areas derived from Sentinel-1 data for July, August, and September were 129 km², 431 km², and 66 km², respectively. The analysis of Sentinel-1 data reveals that Kalam, Bahrain, and Madyan are highly vulnerable to intense flooding, as indicated by the high flood levels observed in these regions. The steep terrain, narrow valleys, and high rainfall intensity contribute to the heightened flood risk in these areas. The flood extents in Mangora, Saidu Sharif, and Barikot also reached significant levels, indicating widespread inundation in these regions. Overall, the study demonstrated the effectiveness of Sentinel-1 and Sentinel-2 data in flood monitoring and mapping. The multi-sensor and multi-index approach enhanced the reliability and robustness of the flood extent assessments, enabling better-informed decision-making processes for emergency response planning, resource allocation, and the implementation of effective flood mitigation strategies. The findings highlighted the importance of considering multiple indices and satellite data sources to obtain a comprehensive understanding of flood dynamics, while acknowledging the influence of cloud cover and other factors on the accuracy of the results
Comparative Analysis of Lossless Image Compression Algorithms
Get PDFThis research paper conducts a comprehensive analysis of three key lossless image compression algorithms: Run-Length Encoding (RLE), Burrows-Wheeler Transform (BWT) and Differential Pulse Code Modulation (DPCM). The increasing demand for efficient image storage and transmission necessitates a thorough examination of these algorithms. Lossless compression plays a crucial role in diminishing data redundancy while safeguarding the integrity and quality of images. The study encompasses data collection, performance metrics, and algorithm evaluation. Results reveal the strengths and weaknesses of each algorithm. RLE excels in image quality preservation but may not achieve the highest compression ratios. DPCM provides a compromise between resource-efficient compression and image fidelity. BWT offers a competitive balance between compression efficiency and image quality. Based on the comprehensive analysis of three key lossless image compression algorithms, it was observed that BWT emerges as a versatile choice that offers competitive compression while maintaining reasonable image quality. However, when choosing the most suitable algorithm, it is essential to consider specific application requirements, including the desired level of image quality preservation and the availability of computational resource
An Enhanced Authentication Scheme for Ensuring Network Devices Security and Performance Optimization
Get PDFIn the technology world, the wireless network is more flexible and adaptable compared to the wired network. Because it is easy to install and does not require cables. Also, there have been many recent advances in the area of WNs (Wireless Networks), which have undergone rapid development. WNs have emerged as a prevailing technology due to their wide range of applications in every field of life. The WNs are easily prone to security attacks since once deployed these networks are unattended and unprotected. In networks, authentication is a well-explored research area. Recent advancements in networks and ubiquitous devices have meant that there is a need to explore the area of authentication with a new perspective. This study explores authentication schemes and their adoption in network-connected devices. The research will study how a wide variety of devices like those in IoT, WSN, industrial IoT, and wearable healthcare devices establish authentication. The focus of the study will be on high levels of security with an algorithm that has a small footprint. The scheme will be studying the design of a lightweight and secure authentication framework for network-connected devices. The proposed scheme provides extended security features while minimizing wireless communication security challenges. The final results will validate the authenticity of this scheme