Lahore Garrison University Research Journal of Computer Science and Information Technology
Not a member yet
227 research outputs found
Sort by
Optimized Yolo with Dropout
No full textThe goal is to recognize different objects by applying the YOLO (You Only Look Once) technique. This technique has a few benefits in contrast to any other techniques for object detection and tracking. In some codes as Fast Convolutional Neural Network (FCNN) and Convolutional Neural Network (CNN) the code will not focus at the picture entirely but for the case of YOLO, the code focuses the entire image by concluding the detection boxes utilizing a convolutional neural framework and the probability of classes for the bounding boxes and finds the image immediately in contrast to some different codes. The dropout layer is also programed at the end to avoid over fitting issues. It is seen that using dropout the results have improved much
Generalized Multi-manifold Graph Ensemble Embedding for Multi-View Dimensionality Reduction
Get PDFIn this paper, we propose a new dimension reduction (DR) algorithm called ensemble graph-based locality preserving projections (EGLPP); to overcome the neighborhood size k sensitivity in locally preserving projections (LPP). EGLPP constructs a homogeneous ensemble of adjacency graphs by varying neighborhood size k and finally uses the integrated embedded graph to optimize the low-dimensional projections. Furthermore, to appropriately handle the intrinsic geometrical structure of the multi-view data and overcome the dimensionality curse, we propose a generalized multi-manifold graph ensemble embedding framework (MLGEE). MLGEE aims to utilize multi-manifold graphs for the adjacency estimation with automatically weight each manifold to derive the integrated heterogeneous graph. Experimental results on various computer vision databases verify the effectiveness of proposed EGLPP and MLGEE over existing comparative DR methods
Operating Systems for the Internet of Things:A Survey
No full textMachine-to-Machine (M2M) is an ecosystem that is used to describe any technology deploying and creating a network of devices to perform actions and exchange information. This new class of communicating devices have very diverse traffic characteristics and pose unique challenges. This paper surveys the state-of-the-art operating system technologies, architectures and available networking stack protocols on it, and explore their potential to support the growth of related applications. Moreover, the diversity of applications and the Internet of Things (IoT) devices also necessitate the investigation of middleware framework and specifications to cater to the currently existing challenges. Therefore, we also discuss different challenges and issues in developing rich applications by using available operating systems. The paper concludes after providing recommendations for future enhancement in existing operating systems
Domain-Independent Natural Language Processing of text using Unsupervised Translation
Get PDFNLP is one of the very important domains of artificial intelligence. Nowadays, advancements are being made and NLP is one of the most developing fields. In this paper, we offer a mutual use of unsupervised translation with n-grams and Natural Language Processing techniques to challenge the difficulty of unsupervised translation extraction from textual data. To build a Text Meaning Extraction System, we have to deliver one important element which is input text. This studypresented a different algorithm to work out resemblances between natural languages, by using sequence package analysis and changing them into n-grams. Whenever the sentences that are grammatically difficult and quite lengthy are applied to see the results of the presented algorithm, there are quite efficient results in a semantic reaction. To enhance the experience in the field of AI and search engines, this research paper shows how to improve the handling capability of fuzzy concepts within computers. For example, when search jobs are executed in search engines small textual concepts or sentences might be semantically formed to switch the keyword-based queries. This ability may be functional to intelligent agents to even the procedure of communication between humans and machinery
Applications of Internet of Vehicle(IoV): A Survey
No full textDue to the fast advancement in the field of communication and computation technology, the Internet of Vehicle (IoV) attracts most of the researchers to contribute in this area of research. In the recent research on the Internet of Vehicle (IoV) technology, IoV becomes one of the major active and famous research areas in the technology of networks, especially in transportation. It provides an Intelligent Transportation System (ITS)and it resolves traffic and driving problems by using advanced communication and information technology. Inthe implementation of IoV, the different actuators, sensors, personal gadgets are required so that the vehicles communicate with each other. In this paper, it will provide the comprehensive survey on applications of IoV and also discuss in detail IoVnetwork model, the required technologies for the creation of IoV, the various applications which are based on existing technologies and the features of research in IoV area and Vehicular Sensor Network (VSN's) based effective and security-oriented applications. The key objective of these applications is to reduce fuel consumption and furthermore to provide a supportin saving the life of drivers andpedestrians
Performance Analysis of Search Algorithms on Workstation system
No full textSearching is a common issue in computer science. It is defined as a process in which elements are to be found from a given list. Search algorithms used in daily life for finding values in array or list, data retrieving, finding passwords and combinations, etc.In the past, many search algorithms have been introduced and existing ones have been improved keeping a view of performance in terms of time and space complexity.Search algorithms are defined based on their framework. Well-known types of search algorithms are binary, linear, jump, and interpolation search.Binary search (interval, logarithmic search) is defined as a search algorithm, which finds the position of an element or target value within a sorted array;linearsearch (sequential search) is a search over the list of items in a sequential way (step-by-step process). Jump search focuses on fewer elements by jumping (skipping) to the next elements in fixed steps while Interpolation search is an improvement over binary search may go to different locations according to the value of the key being searched.In this paper, we have performed a comparative analysis of these search algorithms on the workstation system. Lenovo S-20 workstation with windows as an operating system is used forexperimentation and analysis. Finding out which search algorithm is best in an associated scenario with a comparison of a single-core processor to a workstation of a six-core processor
Flow-Based Rules Generation for Intrusion Detection System using Machine Learning Approach
Get PDFRapid increase in internet users also brought new ways of privacy and security exploitation. Intrusion is one of such attacks in which an authorized user can access system resources and is major concern for cyber security community. Although AV and firewall companies work hard to cope with this kind of attacks and generate signatures for such exploits but still, they are lagging behind badly in this race. This research proposes an approach to ease the task of rules generationby making use of machine learning for this purpose. We used 17 network features to train a random forest classifier and this trained classifier is then translated into rules which can easily be integrated with most commonly used firewalls like snort and suricata etc. This work targets five kind of attacks: brute force, denial of service, HTTP DoS, infiltrate from inside and SSH brute force. Separate rules are generated for each kind of attack. As not every generated rule contributes toward detection that's why an evaluation mechanism is also used which selects the best rule on the basis of precision and f-measure values. Generated rules for some attacks have 100% precision with detection rate of more than 99% which represents effectiveness of this approach on traditional firewalls. As our proposed system translates trained classifier model into set of rules for firewalls so it is not only effective for rules generation but also give machine learning characteristics to traditional firewall to some extent. 
Usability Analysis of University Websites in Pakistan
No full textUsability analysis of a website determines how easy it is for the user to navigate between the pages, find information of interest, and his overall experience of the usage. Good website design is focused on the user experience. Usability is one of the major factors deciding the product's value. It can decide what value the product holds for its user hence the importance of website usability cannot be ignored. In this research, we have used different, manual, and automated heuristic evaluation methods to determine the usability of different Pakistani University websites. Our main goal is to provide some insight on the usability of these University websites as no such work has been done in the past on this. We evaluate a system based on heuristic evaluation and usability standards to measure its score. We also conducted an online survey on University students to get their feedback on their University website. We concluded that the user experience of most of the University websites in Pakistan fails from the usability perspective and students usually have to face a hard time finding the relevantinformation
Application of Internet of Things for Smart City and Environmental Solutions
No full textInternet of Things (IoT) is the latest concept and considered the essential infrastructure for smart cities. However, IoT is allowing smart cities to take the initiative of starting different projects and its deployment all over the world. For Information & Communication Technologies (ICT) solutions, IoT is a compatible way to combine the numerous sensors. Communication of the Internet of Things is the soul of the smart cities. The scopeof IoT in smart cities is connected and deployed with over 50 billion objects this year and more in the future too. This paper deals with concern regarding IoT globally and a detailed review of the idea of IoT with the smart city encouragement and its applications. Furthermore, the paper presents the main gap, instability, and challenges of implementing the IoT with smart cities on technological standards
Cognitive Modelling for User Interface Design in HCI: A Comparative Analysis on Cognitive Models
No full textThis research aims to elaborate the cognition in the field of human-computer interaction, also acknowledges the cognitive modeling and human behavior processes. Cognitive modeling is a field of Human-Computer Interaction (HCI) which is used to design more efficient human interactive systems. It is used to model the interactive system in such a way that analysts can determine methods that users will interact with the system and also be used to understand the different processes of cognitive human behaviors. Hierarchal task analysis is a task to goal-based model, in which analyst selects the actions and tasks to perform. GOMS is a cognitive knowledge of the human information processing model in HCI that describes the user's cognitive architecture based on four components. The linguistic and grammatical model is a syntactical model in which languages and syntax are designed for the user for system communication in an interactive system. Cognitive human behavior processes are also described to understand the mutual coordination of cognition processes and cognitivemodels in designing an interactive system. Problem-solving is a cognitive process of the human mind to search for a problem and explore the possible solutions for that problem. Decision making is also a cognitive process of human behaviour in which human chooses an action from other alternatives based on certain criteria