Global Journal of Computer Science and Technology (GJCST)
Not a member yet
1830 research outputs found
Sort by
Hybrid Fuzzy Medical Expert Systems
Get PDFExpert Systems are intelligent programs of Artificial Intelligence (AI). In many applications, information available to the expert system is incomplete like medical diagnosis. This incomplete information is fuzzy rather than probable. Hybrid fuzzy expert systems (HFMES) combination of different fuzzy expert systems of same type co-ordinate and co-operated. In this paper, Hybrid fuzzy medical expert Systems are studied. Fuzzy inference and fuzzy reasoning are discussed for HFMES Fuzzy knowledge representation is disused for HFMES. Some examples are given for HFMES
Study and Performance Analysis of Different Techniques for Computing Data Cubes
Get PDFData is an integrated form of observable and recordable facts in operational or transactional systems in the data warehouse. Usually, data warehouse stores aggregated and historical data in multi-dimensional schemas. Data only have value to end-users when it is formulated and represented as information. And Information is a composed collection of facts for decision making. Cube computation is the most efficient way for answering this decision making queries and retrieve information from data. Online Analytical Process (OLAP) used in this purpose of the cube computation. There are two types of OLAP: Relational Online Analytical Processing (ROLAP) and Multidimensional Online Analytical Processing (MOLAP). This research worked on ROLAP and MOLAP and then compare both methods to find out the computation times by the data volume. Generally, a large data warehouse produces an extensive output, and it takes a larger space with a huge amount of empty data cells. To solve this problem, data compression is inevitable. Therefore, Compressed Row Storage (CRS) is applied to reduce empty cell overhead
A Genetic-Neural System Diagnosing Hepatitis B
Get PDFHepatitis B is a life threaten disease and if not diagnose early can lead to death of the infected patient. In this paper a genetic neural system for diagnosing hepatitis B was designed. The system was designed to diagnose HBV using clinical symptoms. The dataset used in training the system was gotten from UCI repository. The system incorporated both genetic algorithm and neural network. The genetic algorithm was used to optimize the dataset used in training the neural network. The neural network was trained for 300 iterations and the system had a prediction accuracy of 99.14% on predicting Hepatitis B
Virtual Processor based on Hybrid Processor
Get PDFThis proposal presents a robust method through which virtualization can be optimized by the use of a hybrid processor. The discourse acknowledges that virtualization has become a key constituent of machine processing and efficiency through building virtual machine clusters that can be universally integrated to harness the utilization of hardware computing resources. As observed in low-level computing paradigms, the traditional x86 architecture was only capable of classical trapping to deploy virtualization, yielding para-virtualization. In response, virtual processors based on hybrid processors with hardware-assisted paging enables the handling of foreign Memory Management Unit (MMU) operations and translates the corresponding physical address to actual machine-controlled dynamic addresses, improving memory bound executions as well as the overall output of the HVM. This architecture derives a more powerful utility from the compromised architecture whereby the kernel space while the user space resides in the same privilege ring. Even though myriad hybrid architectures exist, the ultimate objective of this proposal is to satisfy one intrinsic feature: incorporate superiority behavior of the hardwareassisted virtualization
Digital Torque Transformation
Get PDFThe Equipment Installment Plan (EIP) was a game changer in telecom industry and is an integral part of T-Mobile2019;s Un-carrier strategy. The EIP system is a home-grown system based on Java/J2EE and a combination of client-server and SOA architecture principles. The application runs on Bea Web Logic servers with Oracle DB with multiple batch jobs. As the system grew in size, operational challenges surfaced which includes multiple physical server security updates and maintenance cost. (DTT)201D; was the answer to address these challenges. The method employed PaaS Pivotal Container Services (PKS). Enterprise PKS uses the latest stable OSS distribution of Kubernetes2014;with no proprietary extensions. PKS is widely expansible to other applications in T-Mobile ecosystem as PKS can be deployed On-premises as a PaaS
Classification of Image using Convolutional Neural Network (CNN)
Get PDFComputer vision is concerned with the automatic extraction, analysis, and understanding of useful information from a single image or a sequence of images. We have used Convolutional Neural Networks (CNN) in automatic image classification systems. In most cases, we utilize the features from the top layer of the CNN for classification; however, those features may not contain enough useful information to predict an image correctly. In some cases, features from the lower layer carry more discriminative power than those from the top. Therefore, applying features from a specific layer only to classification seems to be a process that does not utilize learned CNN2019;s potential discriminant power to its full extent. Because of this property we are in need of fusion of features from multiple layers. We want to create a model with multiple layers that will be able to recognize and classify the images. We want to complete our model by using the concepts of Convolutional Neural Network and CIFAR-10 dataset. Moreover, we will show how MatConvNet can be used to implement our model with CPU training as well as less training time. The objective of our work is to learn and practically apply the concepts of Convolutional Neural Network
Energy Efficient Mobile Sink Based Routing Model For Maximizing Lifetime of Wireless Sensor Network
Get PDFRecently, wide adoption of wireless sensor networks (WSNs) has been seen for provision real-time and non-real-time application services. Provisioning these application service requires energy efficient routing design for WSN. Clustering technique is an efficient mechanism that plays a major role in minimizing energy dissipation of WSN. However, the existing model are designed considering minimizing energy consumption of sensor device considering homogenous. However, it incurs energy overhead among cluster head. Further, maximizing coverage time is not considered by exiting clustering approach considering heterogeneous network affecting lifetime performance. For overcoming issues of routing data packets in WSN, mobile sink has been used. Here, the sensor device will transmit packet in multihop fashion to the rendezvous and the mobile sink will move towards rendezvous points (RPs) to collect data, as opposed to all nodes. However, the exiting model designed so far incurs packet delay (latency) and energy (storage) overhead among sensor device. For overcoming research challenges, this work present energy efficient mobile sink based routing model for maximizing lifetime of wireless sensor network. Experiment are conducted to evaluate the performance of proposed model shows significant performance in terms of communication, routing overhead and lifetime of sensor network
Modern IT-Infrastructure and IT-Managment in Small and Medium Enterprises
Get PDFSmall and medium enterprises (SMEs) face the same challenges in their IT-departments as their bigger counterparts. In this article, we will take a quick look at existing best practices to deal with those challenges. In addition we will discuss a generic approach to introduce IT-Structure and IT-Management in an actual SMEs using these best practice methods
A Survey on Natural Inspired Computing (NIC): Algorithms and Challenges
Get PDFNature employs interactive images to incorporate end users2019; awareness and implication aptitude form inspirations into statistical/algorithmic information investigation procedures. Nature-inspired Computing (NIC) is an energetic research exploration field that has appliances in various areas, like as optimization, computational intelligence, evolutionary computation, multi-objective optimization, data mining, resource management, robotics, transportation and vehicle routing. The promising playing field of NIC focal point on managing substantial, assorted and self-motivated dimensions of information all the way through the incorporation of individual opinion by means of inspiration as well as communication methods in the study practices. In addition, it is the permutation of correlated study parts together with Bio-inspired computing, Artificial Intelligence and Machine learning that revolves efficient diagnostics interested in a competent pasture of study. This article intend at given that a summary of Nature-inspired Computing, its capacity and concepts and particulars the most significant scientific study algorithms in the field
Research Study on basic Understanding of Artificial Neural Networks
Get PDFArtificial neural networks are a computing system inspired by human neuron, designed to simulate the way human brain analyzes and processes information. They are the foundation of artificial intelligence and machine learning technology. This research paper focuses on the basic understanding of Artificial neural networks. ANN create a lots of excitement in Machine learning research and that results a huge development on many AI and machine learning systems like text processing, speech recognition, image processing. Neural networks consist of input and output layers, in many cases hidden layer consisting of units that transform the input into something that the output layer can use. They are essential tools for finding patterns which are far too complex or numerous for a human programmer to extract and teach the machine to recognize