Global Journal of Computer Science and Technology (GJCST)
Not a member yet
1830 research outputs found
Sort by
A Review on Human Gait Detection
Get PDFThe human gait is the identification of human locomotive based on limbs position or action The tracking of human gait can help in various applications like normal and abnormal gait fall detection gender detection age detection biometrics and in some terrorist and criminal activity detection The present work carried out is a review of various methodologies employed in human gait detection The analysis describes that the different feature extraction and machine learning techniques to be adopted for the identification of human gait based on the purpose of the applicatio
Improved Hybrid Algorithm Approach based Load Balancing Technique in Cloud Computing
Get PDFThe routine life of modern citizens is completely dominated by the computer aided services The computer aided services depends on information and communication technologies The success behind this cloud computing are data centers with virtualization technology equipped with fastest internet and the wide acceptance of the users due to its affordable price to the common people Effective services can be provided to the end user only when proper scheduling of tasks are done in peak hours when heterogeneous collection of requests are coming to the data cente
Review of Various Encryption Algorithms
Get PDFAdvancement in technology dictates that information security, user data integrity and security be paramount to protect user information and data from vulnerabilities from malicious intruders- third parties. Need is therefore a factor for information systems to secure user data and information. The concept data encryption ensures that user data is unreadable to third parties keeping their information more safe and secure while using the internet. A lot information on security has been provided by both the physical security and operating system security but neither of these methods have successfully and sufficiently provided a secure mechanism and support on storing and processing of user data and information. This paper reviews the various encryption algorithms that are employed to protect user information and data against various vulnerabilities
Simulation and Design of University Area Network Scenario(UANS) using Cisco Packet Tracer
Get PDFComputer network has become the most significant issue in our day to day life. Networking companies depend on the proper functioning and analysis of their networks for education, administration, communication, e-library, automation, etc. Mainly interfacing with the network is induced by one of the other user/users to share some data with them. So, this paper is about communication among users present at remote sites, sharing this same network UANS. UANS stands for the University Area Network Scenario. So in this work the network is designed using Cisco Packet Tracer. The paper describes how the tool can be used to develop a simulation model of the Pabna University of Science and Technology, Pabna, Bangladesh. The study provides into various concepts such as topology design, IP address configuration and how to send information in the form of packets in a single network and the use of virtual Local Area Network (VLANs) to separate the traffic generated by a different department
An Integration of Deep Learning and Neuroscience for Machine Consciousness
Get PDFConscious processing is a useful aspect of brain function that can be used as a model to design artificial-intelligence devices There are still certain computational features that our conscious brains possess and which machines currently fail to perform those This paper discusses the necessary elements needed to make the device conscious and suggests if those implemented the resulting machine would likely to be considered conscious Consciousness mainly presented as a computational tool that evolved to connect the modular organization of the brain Specialized modules of the brain process information unconsciously and what we subjectively experience as consciousness is the global availability of data which is made possible by a non modular global workspace During conscious perception the global neuronal work space at parieto-frontal part of the brain selectively amplifies relevant pieces of information Supported by large neurons with long axons which makes the long-distance connectivity possible the selected portions of information stabilized and transmitted to all other brain modules The brain areas that have structuring ability seem to match to a specific computational problem The global workspace maintains this information in an active state for as long as it is needed In this paper a broad range of theories and specific problems have been discussed which need to be solved to make the machine conscious Later particular implications of these hypotheses for research approach in neuroscience and machine learning are debate
Recognition of Handwritten Digit using Convolutional Neural Network (CNN)
No full textHumans can see and visually sense the world around them by using their eyes and brains Computer vision works on enabling computers to see and process images in the same way that human vision does Several algorithms developed in the area of computer vision to recognize images The goal of our work will be to create a model that will be able to identify and determine the handwritten digit from its image with better accuracy We aim to complete this by using the concepts of Convolutional Neural Network and MNIST dataset We will also show how MatConvNet can be used to implement our model with CPU training as well as less training time Though the goal is to create a model which can recognize the digits we can extend it for letters and then a person s handwriting Through this work we aim to learn and practically apply the concepts of Convolutional Neural Network
Algorithm and Design Techniques 2013; A Survey
No full textAlgorithm design plays a significant role in development of any application that is concerned with engineering and technology Advancement in implementation levels of algorithms made a good impact with the model developed Meanwhile the time and space complexity of the execution of the algorithm varies with regard to the input to the algorithm upon fixation of various parametric levels This paper summarizes a survey on various algorithm design techniques and its applications The applicability of the algorithms varies with regard to the problem and the nature of computation level
Security Solution for the IOT Devices
Get PDFAs the internet is available widely with low cost to connect with the devices day by day. Almost all electronic devices are coming to the market with wi-fi capabilities and sensors built into them, even technology costs also coming down. All of these devices are forming Network by accessing the internet through their wi-fi capabilities. These are creating a perfect IOT storm like smart phones are becoming rocks and penetrating everywhere so the sky is the limit for them. As these all are in the hands of everybody, there is obviously security threats. In this paper, all the possible threats are addressing with possible solutions occurring in these IoT devices. Suggested the Homomorphic Encryption scheme for security in IoT devices
Data Migration from Relational Database to MongoDB
Get PDFMongoDB is a document-oriented database which helps us group data more logically. This paper demonstrates the conversion of data from a native tabular form to unstructured documents. The document and collections within it needs not to be well defined prior to the creation of unstructured data in MongoDB. The MongoDB has lots of extensive built-in-features and is highly compatible with other software systems, with extensive and flexible ways of accessing data beyond JSON query, its highly compatible Business Intelligence Connector is highly compatible which makes it compatible with existing databases. High scalability is making it remarkable and popular in the World and hence made me think about writing a paper demonstrating the data conversion. This conversion has helped me in making the most of modern data to be compatible with MongoDB. Data is stored on the cloud as cloud-based storage is an excellent and most cost-effective solution. My solution is highly scalable as the built-in shading solution for data handling makes it one of the best big data handling tool. The data that i have used, is location based in MongoDB that can directly yeild document ACID transactions to maintain data integrity
An Optimized Recursive General Regression Neural Network Oracle for the Prediction and Diagnosis of Diabetes
Get PDFDiabetes is a serious, chronic disease that has been seeing a rise in the number of cases and prevalence over the past few decades. It can lead to serious complications and can increase the overall risk of dying prematurely. Data-oriented prediction models have become effective tools that help medical decision-making and diagnoses in which the use of machine learning in medicine has increased substantially. This research introduces the Recursive General Regression Neural Network Oracle (R-GRNN Oracle) and is applied on the Pima Indians Diabetes dataset for the prediction and diagnosis of diabetes. The R-GRNN Oracle (Bani-Hani, 2017) is an enhancement to the GRNN Oracle developed by Masters et al. in 1998, in which the recursive model is created of two oracles: one within the other. Several classifiers, along with the R-GRNN Oracle and the GRNN Oracle, are applied to the dataset, they are: Support Vector Machine (SVM), Multilayer Perceptron (MLP), Probabilistic Neural Network (PNN), Gaussian NaEF;ve Bayes (GNB), K-Nearest Neighbor (KNN), and Random Forest (RF). Genetic Algorithm (GA) was used for feature selection as well as the hyperparameter optimization of SVM and MLP, and Grid Search (GS) was used to optimize the hyperparameters of KNN and RF. The performance metrics accuracy, AUC, sensitivity, and specificity were recorded for each classifier. The R-GRNN Oracle was able to achieve the highest accuracy, AUC, and sensitivity (81.14%, 86.03%, and 63.80%, respectively), while the optimized MLP had the highest specificity (89.71%)