International Journal of Computer and Information Technology
Not a member yet
138 research outputs found
Sort by
Predicting the Growth of e-Commerce using Trendline Analysis: A Case Study of Ogun State, Nigeria
Get PDFThere is a growing interest from e-commerce planners and other planning agencies in the Information Technology world to measure and forecast the growth of e-commerce in developing countries like Nigeria. The difficulties lie in finding the best forecasting model that can incorporate both the internal and external barriers that influence the full adoption and diffusion of e-commerce. This study attempts to identify the relevant e-commerce tools and its spread in Ogun East Senatorial District as well as formulating a mathematical model for e-commerce adoption and diffusion. A well-structured questionnaire was used to collect data from 126 respondents and analyzed using Trendline, a built-in analysis tool in Microsoft® Office Excel version 2013. The study identified PCs/laptops, ATM cards, e-mail services, mobile money transfer, e-commerce Websites, and point-of-sales (POS) terminals as e-commerce tools used by the respondents. The results of the study show that majority of the e-commerce users/adopters were single female students between the ages of 21 and 30 years, with university education owing to a proportion of 63% of the respondents while the earliest adopted e-commerce tools in descending order were tablets/smartphones, PCs/laptops, ATM cards, and email services. The results further show that the most popularly-used tools were e-commerce websites (98% responses), email services (94% responses), mobile money transfer (94% responses), POS terminals (94% responses), tablets/smartphones (93% responses), PCs/laptops (87% responses) and ATM cards (80% responses). Based on the findings of this study, it is therefore recommended that government should promote the use and development of e-commerce, notably by reducing the costs of access to technology, through the liberation of trade in software and hardware.
Object Tracking in Video Using the TLD and CMT Fusion Model
Get PDFObject tracking has been an attractive study topic in computer vision in recent years, thanks to the development of video monitoring systems. Tracking-Learning Detection (TLD), Compressive Tracking (CT), and Clustering of Static-Adaptive Correspondences for Deformable Object Tracking are some of the state-of-the-art methods for motion object tracking (CMT). We present a fusion model that combines TLD and CMT in this study. To restrict the calculation time of the CMT technique, the fusion TLD CMT model enhanced the TLD benefits of computation time and accuracy on t no deformable objects. The experimental results on the Vojir dataset for three techniques (TLD, CMT, and TLD CMT) demonstrated that our fusion proposal successfully trades off CMT accuracy for computing time
A Survey of Deep Learning Solutions for Anomaly Detection in Surveillance Videos
Get PDFDeep learning has proven to be a landmark computing approach to the computer vision domain. Hence, it has been widely applied to solve complex cognitive tasks like the detection of anomalies in surveillance videos. Anomaly detection in this case is the identification of abnormal events in the surveillance videos which can be deemed as security incidents or threats. Deep learning solutions for anomaly detection has outperformed other traditional machine learning solutions. This review attempts to provide holistic benchmarking of the published deep learning solutions for videos anomaly detection since 2016. The paper identifies, the learning technique, datasets used and the overall model accuracy. Reviewed papers were organised into five deep learning methods namely; autoencoders, continual learning, transfer learning, reinforcement learning and ensemble learning. Current and emerging trends are discussed as well
Parallel Merging and Sorting on Linked List
Get PDFWe study linked list sorting and merging on the PRAM model. In this paper we show that n real numbers can be sorted into a linked list in constant time with n2+e processors or in ) time with n2 processors. We also show that two sorted linked lists of n integers in {0, 1, …, m} can be merged into one sorted linked list in O(log(c)n(loglogm)1/2) time using n/(log(c)n(loglogm)1/2) processors, where c is an arbitrarily large constant
Dhouib-Matrix-TSP1 Method to Optimize Octagonal Fuzzy Travelling Salesman Problem Using α-Cut Technique
Get PDFThis paper proposes the optimization of the fuzzy travel salesman problem by using the α-Cut technique as a ranking function and the Dhouib-Matrix-TSP1 as an approximation method. This method is enhanced by the standard deviation metric and obtains a minimal tour in fuzzy environment where all parameters are octagonal fuzzy numbers.
Fuzzy numbers are converted into a crisp number thanks to the ranking function α-Cut. The proposed approach in details is discussed and illustrated by a numerical example. This method helps in designing successfully the tour to a salesman on navigation through the distance matrix so that it minimizes the total fuzzy distance
Deep Learning Methods In Predicting Indonesia Composite Stock Price Index (IHSG)
Get PDFThe stock price changes at any time within seconds. The stock price is a time series data. Thus, it is necessary to have the best analysis model in predicting the stock price to make decisions to avoid losses in investing. In this research, the method used two models Deep Learning namely Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) in predicting Indonesia Composite Stock Price Index (IHSG). The dataset used is historical data from the Jakarta Composite Index (^JKSE) stock price in 2013-2020 obtained through Yahoo Finance. The results suggest that Deep learning methods with LSTM and GRU models can predict Indonesia Composite Stock Price Index (IHSG). Based on the test results obtained RMSE value of 71.28959454502723 with an accuracy rate of 92.39% for LSTM models and obtained RMSE value of 70.61870739073838 with an accuracy rate of 96.77% on GRU models
Deep Learning Classification of Building Types in Northern Cyprus
Get PDFAmong the areas where AI studies centered on developing models that provide real-time solutions for the real estate industry are real estate price forecasting, building age, and types and design of the building (villa, apartment, floor number). Nevertheless, within the ML sector, DL is an emerging region with an Interest increases every year. As a result, a growing number of DL research are in conferences and papers, models for real estate have begun to emerge. In this study, we present a deep learning method for classification of houses in Northern Cyprus using Convolutional neural network.
This work proposes the use of Convolutional neural networks in the classification of houses images. The classification will be based on the house age, house price, number of floors in the house, house type i.e. Villa and Apartment.
The first category is Villa versus Apartments class; based on the training dataset of 362 images the class result shows the overall accuracy of 96.40%. The second category is split into two classes according to age of the buildings, namely 0 to 5 years Apartments 6 to 10 years Apartments. This class is to classify the building based on their age and the result shows the accuracy of 87.42%. The third category is villa with roof versus Villa without roof apartments class which also shows the overall accuracy of 87.60%. The fourth category is Villa Price from 10,000 euro to 200,000 Versus Villa Price from 200,000 Euro to above and the result shows the accuracy of 81.84%. The last category consists of three classes namely 2 floor Apartment versus 3 floor Apartment, 2 floor Apartment versus 4 floor Apartment and 2 floor Apartment versus 5 floor Apartment which all shows the accuracy of 83.54%, 82.48% and 84.77% respectively.
From the experiments carried out in this thesis and the results obtained we conclude that the main aims and objectives of this thesis which is to used Deep learning in Classification and detection of houses in Northern Cyprus and to test the performance of AlexNet for houses classification was successful. This study will be very significant in creation of smart cities and digitization of real estate sector as the world embrace the used of the vast power of Artificial Intelligence, machine learning and machine vision
Continuous Speech and Time-Frequency Transform Using the Kalman Filter
Get PDFIn this paper, a Radial Basis Function-based Kalman filter has been utilized to in order to extended to the time-frequency transform, also called a spectrogram or spectrograph, and also been applied to simple continuous speech
Torsion, an Information State of Evolutionary Energy and Matter
Get PDFThe torsion field as phenomenon and mechanism, has mainly drawn attention and its deep analysis came to the conclusion that torsion is a subtle phenomenon and the field is the element which contains and generates the state of torsion itself. Often torsional fields, space rotating fields, inter-dimensional ports and vortexes are mentioned in this context. We observed that the torsional field is created by dividing information [16], thus it is a component resulted from the informational dimension [19]
A New Digital Signature Scheme Using Tribonacci Matrices
Get PDFAchieving security is the most important goal for any digital signature scheme. The security of RSA, the most widely used signature is based on the difficulty of factoring of large integers. The minimum key size required for RSA according to current technology is 1024 bits which can be increased with the advancement in technology. Representation of message in the form of matrix can reduce the key size and use of Tribonacci matrices can double the security of RSA. Recently M.Basu et.al introduced a new coding theorycalled Tribonacci coding theory based onTribonacci numbers, that are the generalization ofthe Fibonacci numbers. In this paper we present anew and efficient digital signature scheme usingTribonacci matrices and factoring