Foundation University Journal of Engineering and Applied Sciences
Not a member yet
56 research outputs found
Sort by
Sentiment Analysis of COVID-19 Tweets using Neural Network in Pakistan
Get PDFCovid-19 is a respiratory infectious disease that spreads from person to person. World Health Organization declared it a pandemic in March 2020. Social distancing and lockdowns during the pandemic affected the lives, sentiments, and mental health of people. They are mentally, physically, and emotionally disturbed. It was observed that the verification of the very first Covid case increased the precariousness and fear in Pakistan because people had no information about the state policies. In this paper, Covid-related tweets from Pakistan for the year 2021 are collected. Pakistan faced two Covid waves in 2021. Dataset is preprocessed and a neural network-based model is applied to analyze the sentiment of the tweet. Sentiments of people are analyzed separately for each Covid wave, moreover, a comparative analysis is presented to discuss the change in people's sentiments with the passage of time. Results show a reduction in the number of tweets from third to fourth wave. Moreover, the %decrease in negative and positive sentiments are 6 and 1 respectively which show that by the passage of time, people started living with the environment and time healed the wounds of fears and uncertainty in their lives
Benchmarking Travelling Reviews using Opinion Mining
Get PDFOnline travel reviews offer valuable data, yet it remains uncertain if those most influenced by these reviews actually read them. This research aims to uncover consistent patterns and explain variations in online travel ratings, comments, and reviews. To accomplish this, millions of reviews were collected from Pakistan's top online travel companies, Uber and Careem. Utilizing semantic affiliation analysis, subject terms were extracted, forming a semantic affiliation structure. The findings highlight significant differences among channels concerning topical vocabulary, subject distribution, structural traits, and community links. The network visualization results are particularly noteworthy, as they illustrate connections between key concepts and words within each topic, making them easily understandable. With the proposed logical method, we can better understand the strategic snafus in the travel sector and gain fresh insights into how to dig up popular assessments to better serve tourists, lodging establishments, and trade groups
COVID-19 Lungs CT Scan Lesion Segmentation
Get PDFThe outburst of the novel coronavirus 2019 has caused a multinational pandemic that has impacted a huge number of individuals around the globe. One of the primary indications of COVID-19 is the formation of lesions in the lungs, which can cause severe harm to the respiratory system and lead to death. In the following study, we submitted a novel strategy for making lung window CT scans and mediastinal window CT scans similar, to input it into a customized U-Net based model to achieve a decent degree of accuracy in segmenting these lung lesions. The method suggested in this research study is based on specialized image processing algorithms to normalize the CT scans' pixel intensity level and uniform the mediastinal and lung window CT scans. This allows us to accurately segment the lung lesions using a UNet model with a single channel input. We were able to achieve an IOU score of 82.4%, which is a significant addition to the existing Medical World. Additionally, the suggested approach is on par with cutting-edge methods
Potential of Large Language Models (LLMs) as Supplementary Tools for Historical Learning: Users’ Interaction and Knowledge Acquisition
Get PDFThis study explores the strengths and limits of large language models (LLMs) in exploring the information on history, an area unexplored in the existing literature. ChatGPT and Gemini, as LLMs, have demonstrated superior performance in education, healthcare, and business. This study proposes utilizing the ChatGPT (ver. 3.5) and Gemini applications to acquire information on historical figures like Sher Shah Suri and Mughal Emperors and Sikhs in the subcontinent. To evaluate the proposed study, this study used two data sets: the first data set comprised a set of questions (n = 26) and the second data set contained questions (n = 35). The results indicate that ChatGPT provides concise answers to the questions of both datasets compared to the Gemini application. However, Gemini exhibited a higher accuracy (92.30%) than ChatGPT with accuracy (76.92%) for dataset 1. For the dataset 2, ChatGPT showed better accuracy (68.57%) than Gemini with accuracy (65.71%). Further research could expand on this study by employing additional artificial intelligence (AI) tools on large-scale datasets from diverse domains
Glaucoma Detection using Fundus Images by Extracting Localized Disc Features
Get PDFGlaucoma is one of the leading causes of blindness worldwide. It occurs due to high pressure in the eyes and other factors such as family history, age, ethnicity, etc. It damages the optic nervous system which is irreversible damage. That's why regular screening for glaucoma is crucial and recommended. Researchers are continuously searching for better methods to identify glaucoma at early stages before it becomes worse and incurable. Significant work has been conducted on it, but there is still room for improvement. The main goal of this study is to propose a reliable system for glaucoma detection that considers the key factors contributing to glaucoma development, in accordance with the decisions made by clinical experts. In this work, the U-net model is used with EfficentNetb3 as a backbone model for optic disc and optical cup segmentation. In addition, a general deep learning model that has 1D convolution layers and other basic layers is used for glaucoma classification. Features extracted from optical disc and optical cup are used to train the deep learning model and overall 95% classification accuracy and 0.92 AUC are achieved for glaucoma classification on the RIGA dataset
Multiple Eye Disease Detection Using Deep Learning
Get PDFHuman eyes are susceptible to various abnormalities due to aging, trauma, and diseases like diabetes. Glaucoma, cataracts, macular degeneration, and diabetic retinopathy are the leading causes of blindness worldwide. It is crucial to detect and diagnose these eye diseases early to provide timely treatment and prevent vision loss. Multiple eye disease detection through the analysis of medical images can aid in this process. The steps involved in the detection of multiple eye diseases using deep learning include image acquisition, region of interest extraction, feature extraction, and disease classification or detection. In this study, we proposed a model using deep learning algorithms, ResNetand VGG16, to detect eye diseases such as uveitis, glaucoma, crossed eyes, bulging eyes, and cataracts. We achieved a 92% accuracy rate using ResNet50 and 79% accuracy using the VGG16 model. By automating the detection process, we can save time for doctors and increase the accuracy and detection rate. The proposed model can be integrated into the healthcare system to assist in early diagnosis and effective treatment of eye diseases
Behavioral Authentication for Smartphones backed by "Something you Process"
Get PDFAuthentication of smartphone devices has been never so important nowadays. Machine learning techniques are not far behind to touch the new milestones of the latest and ever updating world. However, totally depending on machine learning will give you the scenarios of false user being accepted as true one and a true user being rejected as the false one, which can be devastating in some cases. Fifth factor of authentication “Something You Process” eradicates most of the cases of the false acceptance and false rejection, if used with the mentioned techniques. The novel approach applied here is the fifth factor combined with machine learning system and Behavioral authentication. The fifth factor is anti-shoulder surfing since the arithmetic operation is hidden by hand placed on the screen. After placing hand on the screen in such a way that it hides the code from others, the system shows the arithmetic operation and the processed calculation is performed in user’s mind. The pattern which is shown to the user is public, but machine learns the touch dynamics of the user along with his different postures including lying posture. The focus has been on the aspect of something that can be another layer or line of defense which can save the user’s authentication process. It results in decrement of false acceptance or false rejection upon unlocking of a smartphone device. This study deals with the postures of standing, sitting, and lying. The data is collected and the features are extracted in all of these positions
A Comparative Analysis of Fruits and Vegetables Quality Using AI-Assisted Technologies: A Review
No full textFood quality is a major issue for society since it is a crucial guarantee not only for human health but also for society's progress and stability. The planting, harvesting, and storage through preparation and consumption, all aspects of food processing should be considered. One of the most important methods for managing fruit and vegetable quality is by using AI food quality evaluation techniques. Emerging technologies such as computer vision and artificial intelligence (AI) are thought to profit from the availability of massive data for active training and the generation of intelligent and operational equipment in real-time and predictably. The review helps provide an overview of leading-edge artificial intelligence and computer vision technologies that can help farmers in agriculture and food processing. In addition, the review presents some implications for the challenges and recommendations regarding the inclusion of technologies in real-time agriculture, policies, and substantial global investments. In addition, the fourth industrial revolution technologies of profound learning and computer vision robotics which are key to sustainability for food production is also addressed in it
Country Level Social Aggression Using Computational Modelling
Get PDFComputational modelling is emerging field to model the cognitive as well as social interactions between individual and society. Aggression is social evil which is instance response and its impact last for long time. Different societies have different norms and values based on ecological, environmental and cultural attributes so aggression level also varies among individuals and societies. Current study is based on psychological and temporal aggressive behaviour different individuals and societies in same habitat. In this paper we have proposed a frame work to model human social and psychological behaviors. Results are based on simulation which are according to our assumptions
Heart Diseases Prediction and Diagnosis using Supervised Learning
Get PDFThe existing data for clinical diagnosis are often enlarged, but available tools are not efficient enough for decision making. Data mining techniques provide a user-oriented approach for clinical diagnosis and reduce risk factors. To improve clinical diagnosis, particularly for heart diseases, nine different data mining techniques have been applied for classification and clustering. We compare all these techniques for better prediction. Despite all recent research efforts, the literature lacks the application of multiple techniques on multiple data sets for heart disease prediction; which helps in decision making. In particular, this study is the augmentation of techniques for multiple data analysis by comparing four datasets with 14 attributes and a different number of instances. Another challenge is how to increase the accuracy of the decision-making process. Our research findings predict the better accuracy by using SMO and classification via regression for all data sets which shows the significant difference. Consequently, this research further helps to integrate the clinical decision support, thereby reducing medical errors, enhance patient safety, decrease unwanted practice variation, and improve patient recovery