Lahore Garrison University Research Journal of Computer Science and Information Technology
Not a member yet
227 research outputs found
Sort by
An ONTOLOGY BASED APPROACH FOR TRAFFIC DENSITY ESTIMATION IN INTELLIGENT TRANSPORTATION SYSTEMS
Full text linkIntelligent transportation systems are a group of smart technologies which are intended to make road journey more efficient. The ability of vehicles to share data with all aspects of the road infrastructure via diverse applications is critical to the success of these systems. In this paper, an ontology has been integrated for every vehicle to give them the ability to perceive for themselves. A framework of intelligent transportation system which enables complexity is required for the success of this traffic information exchange and representation of knowledge using the protégé. Proposed and implemented methodology for traffic density estimation is being used to create an ontology in the ITS domain
A systematic review A Conversational interface agent for the export business acceleration
No full textConversational agents, which understand, respond to, and learn from each interaction using Automatic Speech Recognition (ASR), Natural Language Processing (NLP), Advanced Dialog Management, and Machine Learning (ML), have become more common in recent years. Conversational agents, also referred to as chatbots, are used to have real-time conversations with individuals. As a result, conversational agents are now being used in a variety of sectors, including those in education, healthcare, marketing, customer assistance, and entertainment. Conversational agents, which are frequently used as chatbots and virtual or AI helpers, show how computational linguistics is used in everyday life. It can be challenging to pinpoint the variables that affect the use of conversational agents for business acceleration and to defend their utility in order to enhance export company. This paper provides a summary of the evolution of conversational agents from a straightforward model to a sophisticated intelligent system, as well as how they are applied in various practical contexts. This study contributes to the body of literature on information systems by contrasting the different conversational agent types based on the export business acceleration interface. This paper also identifies the challenges conversational applications experience today and makes recommendations for further research
Priority Based Technique and Vehicle Location in VANET Using Google Maps
Full text linkGoogle Maps is becoming popular in digital maps because of its user friendly human computerinteraction and easy to use Application Programming Interface (API) as a plugin to onlineapplications. Vehicular Ad-hoc Network (VANET) is conceptualizing moving cars as nodes ina dynamic road network. VANETs help manage the traffic through communication messagesamong the vehicles. In huge traffic loads too many messages create network congestion andstarvation. The basic objective of this research is to augment conventional VANET by addingmessage prioritization methodology, i.e. messages for top priority vehicles will be transmittedprior to the ones with lower priority. To this end, an algorithm has been developed andimplemented in a web application that incorporates Google maps for getting and displayingvehicle information. The proposed algorithm has been evaluated using experiments forthroughput and congestion avoidance in the network
Identifying Optimal Parameters And Their Impact For Predicting Credit Card Defaulters Using Machine-Learning Algorithms
Full text linkData mining and Machine learning are the emerging technologies that are rapidly spreading in every field of life due to their beneficial aspects. The financial sector also makes use of these technologies. Many research studies regarding banking data analysis have been performed using machine learning techniques. These research studies also have many Problems as the main focus of these studies was to achieve high accuracy and some of them only perform comparative analysis of different classifier's performance. Another major drawback of these studies was that they do not identify any optimal parameters and their impact. In this research, we have identified optimal parameters. These parameters are valuable for performing the credit scoring process and might also be used to predict credit card defaulters. We also find their impact on the results. We have used feature selection and classification techniques to identify optimal parameters and their impact on credit card defaulters identification. We have introduced three classifiers which are Kstar, SMO and Multilayer perceptron and repeat the process of classification and feature selection for every classifier. First, we apply feature selection techniques to our dataset with each classifier to find out possible optimal parameters and In the next phase, we use classification to find the impact of possible optimal parameters and proved our findings. In each round of classification, we have used different parameters available in the dataset every time we include and exclude some parameters and noted the results of each run of classification with each classifier and in this way, we identify the optimal parameters and their impact on the results Whereas we also analyze the performance of classifiers. To perform this research study, we use the “credit card defaults” dataset which we obtained from UCI Machine learning online repository. We use two feature selection techniques that include ranker approach and evolutionary search method and after that, we also apply classification techniques on the dataset. This research can help to reduce the complexities of the credit scoring process. Through this study, we identify up to six optimal parameters and also find their impact on the performance of classifiers. Further We also identify that multilayer perceptron was the best performing classifier out of three. This research work can also be extended to other fields in the future where we use this mechanism to find out optimal parameters and their impact can help us to predict the results.
 
An Intelligent Healthcare system for detecting diabetes using machine learning algorithms
Full text linkThe human disease prediction is specifically a struggling piece of work for an accurate and on time treatment. Around the world, diabetes is a hazardous disease. It affects the various essential organs of the human body, for example, nerves, retinas, and eventually heart. By using models of machine learning algorithms, we can recommend and predict diabetes on various healthcare datasets more accurately with the assistance of an intelligent healthcare recommendation system. Not long ago, for the prediction of diabetes, numerous models and methods of machine learning have been introduced. But despite that, enormous multi-featured healthcare datasets cannot be handled by those systems appropriately. By using Machine Learning, an intelligent healthcare recommendation system is introduced for the prediction of diabetes. Ultimately, the model of machine learning is trained to predict this disease along with K-Fold Cross validation testing. The evaluation of this intelligent and smart recommendation system is depending on datasets of diabetes and its execution is differentiated from the latest development of previous literatures. Our system accomplished 99.0% of efficiency with the shortest time of 12 Milliseconds, which is highly analyzed by the previous existing models of machine learning. Consequently, this recommendation system is superior for the prediction of diabetes than the previous ones. This system enhances the performance of automatic diagnosis of this disease. Code is available at (https://github.com/RaoHassanKaleem/Diebetes-Detection-using-Machine-Learning-Algorithms).
 
A Survey Paper on Blockchain and its Implementation to reduce Security Risks in various domains
Full text linkEvery technology with its powerful uses has issues connected to it and security is at the top of it. As for the changing environment, the world has been shifting to Virtual Reality, the new coming world seems to be the internet and blockchain technology which is more powerful than others and has its applications in every field, be it quantum computing, internet of things, security or others. This survey paper covers the blockchain and its security in different fields of sciences and technology. We begin with the introduction of blockchain and then discuss its structure. After that security issues have been highlighted which include attacks and their behavior in quantum computing, internet of things, cloud computing. Furthermore, we have discussed the most common types of attacks and the SRM model of blockchain followed by the conclusion
Smart Detection of Cardiovascular Disease Using Gradient Descent Optimization
Full text linkThe Internet of Medical Things (IoMT) is the networking of health things or equipment that communicate data over the internet without the need for human involvement in the healthcare field. A large quantity of data is collected from numerous sensors in the health field, and it is all transferred and stored on the cloud. This data is growing bigger here all time, and it's becoming increasingly challenging to secure it on the cloud with real-time storage and computing. Data security problem can be addressed with the aid of machine algorithms and fog computing. For data security in IoMT gadgets correspondence in an intelligent fashion, an intelligent encryption algorithm (IEA) is proposed using blockchain technology in cloud based system framework (CBSF). It is applied on patient’s database to provide immutable security, tampering prevention and transaction transparency at the fog layer in IoMT. The suggested expert system's results indicate that it is suitable for use in for the security. In the fog model, the blockchain technology approach also helps to address latency, centralization, and scalability difficulties
Compute Depression and Anxiety among Students in Pakistan, using Machine Learning
Full text linkThe worldwide mechanical advancement in medical services digitizes the copious information, empowering the guide of the different types of human science all the more precisely than conventional estimating strategies. AI (ML) has been certified as a productive approach for dissecting the enormous measure of information in the medical services area. ML strategies are being used in emotional well-being to anticipate the probabilities of mental problems and, subsequently, execute potential treatment results.
In the speedy present-day world, mental medical problems like depression and anxiety have become exceptionally normal among the majority. In this paper, forecasts of depression and anxieties were made utilizing AI calculations. Depression and anxiety have become emergent hindrances in the lives of human beings. It not only disturbs their daily decorum but has also become a prominent cause for their downfall in health. All around the world people are getting affected by this mental disorder yet the majority of such cases lie between ages 18-25 making university-going students a prime target for such mental diseases.
Though the mental health of university students is known globally as a momentous public health matter. Academicals, social depression, and anxieties are playing quite a negative role in university student’s life, especially in forms of mental illness like depression and anxiety. These mental health issues are becoming a major constraint on their studies and career. Hence, this research is being conducted to develop a technological solution for mentally distorted students.
This paper analyzes depression and anxiety amongst university students by effectively utilizing the k-nn algorithm (a conspicuous technique for detecting and analyzing mental depression and anxiety) and providing a technical solution for this mental hindrance. The experimental results show up to 76.5% accuracy in results after using k-nn without PCA while the accuracy was increased up to 76.6% when the results were generated with PCA
Development of an efficient Computational Model for classification of Tissue remodeling
Full text linkTissue remodeling is one of the most important and crucial biological process. Process in which tissue reorganization and renovation takes place is called tissue remodeling. Mean of recovery in human beings is tissue remodeling in which damaged tissue are replaced completely with new tissue or through tissue repairmen types physiological and pathological tissue remodeling are two derivatives of Tissue remodeling. Normal Tissue remodeling is referred to as Physiological tissue remodeling, however abnormal process which may lead to a disease is known as pathological tissue remodeling.
From past till now different techniques like histopathology and chemicals were being used to identify abnormality in tissues. Which is a time taking and costly processes. There is no such computational method which can be used for the identification of the physiological and pathological tissue remodeling. The current article aims to develop a classification model which has ability to classify weather the given sequence is physiological or pathological process. Three classifiers RF, ANN and SVM will be used for practice and evaluation of proposed classification model
Lung Cancer Detection using Supervised Machine Learning Techniques
Full text linkIn recent times, Lung cancer is the most common cause of mortality in both men and women around the world. Lung cancer is the second most well-known disease after heart disease. Although lung cancer prevention is impossible, early detection of lung cancer can effectively treat lung cancer at an early stage. The possibility of a patient's survival rate increasing if lung cancer is identified early. To detect and diagnose lung cancer in its early stages, a variety of data analysis and machine learning techniques have been applied. In this paper, we applied supervised machine learning algorithms like SVM (Support vector machine), ANN (Artificial neural networks), MLR (Multiple linear regression), and RF (random forest), to detect the early stages of lung tumors. The main purpose of this study is to examine the success of machine learning algorithms in detecting lung cancer at an early stage. When compared to all other supervised machine learning algorithms, the Random forest model produces a high result, with a 99.99% accuracy rat