International Journal of Computer and Information Technology
Not a member yet
138 research outputs found
Sort by
Comparative Analysis of the Performance of Single Sign-On Authentication Systems with OpenID and OAuth Protocols: Application of Single Sign-On (SSO) in Information Systems at the University of Technology Yogyakarta
Get PDFA vast number of people use the internet on a regular basis. The growing number of users will inadvertently bring new issues for both users and administrators as user managers. Users forget their user accounts and passwords when they have too many accounts to surf the internet. Web-based application services at University of Technology Yogyakarta include the Academic Information System (SIA) and E-Learning without exception. Both have the same issue: figuring out how to establish an authentication mechanism that will prevent users from forgetting their accounts on the system. The goal of this research is to create a prototype using Single Sign On (SSO) and compare the performance of the two SSO protocols utilized, OpenID and OAuth. The Explicate Problem, Define Requirements, Design and Develop Artifact, Demonstrate Artifact, Evaluate Artifact, and Communication processes are all part of this study. The results of prototype testing are obtained by attempting to log in using an academic service system account, and users are not required to login/authenticate again while accessing the e-learning page. Performance studies on both protocols revealed that the highest number of users who could login to the system at the same time was 1230 (OpenID) and 1219 (OAuth). In comparison to the OpenID protocol, the OAuth protocol is more consistent in terms of average response time for handling user requests. A greater specification is also required to suit the demands of additional users
Feature Extraction using Histogram of Oriented Gradients for Image Classification in Maize Leaf Diseases
Get PDFThe paper presents feature extraction methods and classification algorithms used to classify maize leaf disease images. From maize disease images, features are extracted and passed to the machine learning classification algorithm to identify the possible disease based on the features detected using the feature extraction method. The maize disease images used include images of common rust, leaf spot, and northern leaf blight and healthy images. An evaluation was done for the feature extraction method to see which feature extraction method performs best with image classification algorithms. Based on the evaluation, the outcomes revealed Histogram of Oriented Gradients performed best with classifiers compared to KAZE and Oriented FAST and rotated BRIEF. The random forest classifier emerged the best in terms of image classification, based on four performance metrics which are accuracy, precision, recall, and F1-score. The experimental outcome indicated that the random forest had 0.74 accuracy, 0.77 precision, 0.77 recall, and 0.75 F1-score
A Discrete Mathematical Model of the Variable State of the Pandemic
Get PDFThe paper describes and analyzes a discrete mathematical model of the variable state of the pandemic, which is important for determining production quantities of vaccines and antiviral drugs, predicting the number of infected persons, and the intensity of the process of disseminating information or new ideas to the public. According to the system of differential equations of the pandemic, a discrete mathematical model in vector-matrix form was developed and the equilibrium of the model in the space state was proved. As a result of the implementation of the pandemic model, the discrete dynamic curves of the variable state were obtained in a Matlab package
Analysis of the Convolutional Neural Network Model in Detecting Brain Tumor
Get PDFDetecting brain tumors is an active area of research in brain image processing. This paper proposes a methodology to segment and classify brain tumors using magnetic resonance images (MRI). Convolutional Neural Networks (CNN) are one of the effective detection methods and have been employed for tumor segmentation. We optimized the total number of layers and epochs in the model. First, we run the CNN with 1000 epochs to see its best-optimized number. Then we consider six models, increasing the number of layers from one to six. It allows seeing the overfitting according to the number of layers
Comparative Evaluation for Effectiveness Analysis of Policy Based Deep Reinforcement Learning Approaches
Get PDFDeep Reinforcement Learning (DRL) has proven to be a very strong technique with results in various applications in recent years. Especially the achievements in the studies in the field of robotics show that much more progress will be made in this field. Undoubtedly, policy choices and parameter settings play an active role in the success of DRL. In this study, an analysis has been made on the policies used by examining the DRL studies conducted in recent years. Policies used in the literature are grouped under three different headings: value-based, policy-based and actor-critic. However, the problem of moving a common target using Newton\u27s law of motion of collaborative agents is presented. Trainings are carried out in a frictionless environment with two agents and one object using four different policies. Agents try to force an object in the environment by colliding it and try to move it out of the area it is in. Two-dimensional surface is used during the training phase. As a result of the training, each policy is reported separately and its success is observed. Test results are discussed in section 5. Thus, policies are tested together with an application by providing information about the policies used in deep reinforcement learning approaches
Automated Chronic Kidney Disease Detection Model with Knearest Neighbor
Get PDFChronic kidney disease is one of the most common disease in the world today. Kidney disease causes death if the patient is not threated at early stage. One of the challenge in kidney disease treatment is accurate identification of kidney disease at an early stage. Moreover, detecting kidney disease requires experienced nephrologist. However, in developing nations lack of medical specialist or nephrologist for identifying chronic kidney disease makes the problem more challenging. As alternative solution to kidney disease identification, researchers have developed many intelligent models using K-nearest Neighbors (KNN) algorithm. However, the accuracy of the existing KNN model has scope for improvement. Thus, this study proposed KNN based model for accurate identification of kidney disease at early stage. To develop optimized KNN model, we have employed error plot to find most favorable K value to obtain more accurate result than the existing models. To conduct experiments, study employed kidney disease dataset collected form publically available Kaggle data repository for training and testing the proposed model. Finally, we have evaluated the proposed model against predictive accuracy. The experimental result on the proposed model appears to prove that the predictive accuracy of the model is 99.86%
Digital Video Watermarking for Copyright Labelling
Get PDFPenggunaan konten multimedia di internet kini semakin berkembang, terutama dalam video digital. Pemalsuan, penipuan, dan penjarahan konten video menyebabkan masalah karena pasokan sumber daya untuk berbagi konten. Hak cipta menjadi hal yang krusial dalam video digital untuk menghindari manipulasi dari pihak yang tidak bertanggung jawab. Ada banyak cara yang bisa dilakukan untuk melabeli hak cipta ke dalam sebuah video. Salah satunya adalah digital watermarking. Pembuatan air digital digunakan untuk mencegah replikasi ilegal atau eksploitasi konten digital, melindungi konten digital, dan menghindari manipulasi multimedia secara ilegal. Penggunaan beberapa metode seperti Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT), dan Discrete Fourier Transform (DFT) untuk pelabelan hak cipta video akan dibandingkan berdasarkan imperceptibility dan robustness setelah beberapa manipulasi diterapkan ke dalam video yang disisipkan-watermark. Dari segi imperceptibility, metode DWT menghasilkan nilai PSNR sebesar 45,62435 dB, metode DCT menghasilkan nilai PSNR sebesar 45.89422 dB, dan metode DFT menghasilkan nilai PSNR sebesar 45.77747 dB. Rerata PSNR dari ketiga metode tersebut adalah 45.76535 dB. Artinya, video yang disisipkan tanda air tampak mirip dengan yang disisipkan. Dengan demikian, dari percobaan dapat disimpulkan bahwa metode DWT, DCT, dan DFT yang diterapkan menunjukkan bahwa video yang diberi watermark masih dalam kualitas yang baik yaitu wajar dan memenuhi imperceptibility. Dari segi kekokohan, NC mean metode DCT adalah 0,63974, metode DCT adalah 0,755839, dan metode DFT adalah 0,745442. Hal ini menunjukkan bahwa hasil ekstraksi watermark dari ketiga metode tersebut sama dengan hasil watermark aslinya. Dengan kata lain, semua tanda air pada ketiga metode ini dapat diekstraksi dengan baik meskipun serangan dikirimkan kepada mereka. Dari tingkat uji imperceptibility dan robustness pada metode DWT, DCT, dan DFT, dapat dikatakan bahwa metode DCT lebih baik daripada metode DWT dan DFT karena performansinya yang tinggi pada PSNR dan NC
A Vision of the Internet of Things: A Review of Critical Challenges
Get PDFToday, Information Communication Technology has brought many benefits to have a better life. Meanwhile, the concept of the Internet of Things (IoT), which has transformed the traditional lifestyle into a modern lifestyle and is growing rapidly, is of great importance. This research deals with the critical challenges of IoT. Although not much time has passed since the advent of the concept of the IoT, today the Internet of Things has faced a great deal of complexity in the industry, which requires in-depth studies to realise its potential and challenges. This study introduces and examines IoT challenges including security and privacy, scalability, interoperability, mobility, protocol & standardisation, and energy consumption. In this study, the relationship between these challenges has been clearly defined. Finally, based on the research, some main challenges or sub-challenges considered for these challenges
A Computer Model of the Spread of the Pandemic and its Analysis
Get PDFThe paper describes and analyzes a mathematical model of the variable state of the incidence of epidemic diseases, which is of great importance for determining the quantity of vaccines and antiviral drugs to be produced. The information model according to the system of differential equations of the spread of the pandemic is illustrated in a structural diagram. The model is presented in a vector-matrix form and the state of equilibrium of the model in the spatial state is proved.The model of the spread of the pandemic was developed, whose implementation with a Matlab software package resulted in obtaining the curves of variation of the state. The developed computer model of the incidence of epidemic diseases can be used to make a projection of the number of infected people, as well as intensity of the process of disseminating information and ideas in the community
Software-Defined Networking in Cloud Computing
Get PDFThrough network programmability, we may simplify network management and bring innovation, cloud computing introduced some of its network concepts. One of the most prominent cloud models for minimizing maintenance obligations and simplifying network infrastructure administration is the SDN (Software Defined Network) architecture. SDN stands out because it provides separation of the control plane and programmability for developing network applications. As a result, SDN is expected to enable more efficient configuration, higher performance, and increased flexibility to support new network architectures. This article is aimed to demonstrates the importance of the SDN and the major role it plays in the organization and how SDNs can be profitable to many organizations that remain in the archaic or a traditional cloud environment and how SDN can restructure the cloud architecture with more security enhancement and also to investigate SDN related issues and challenges to provide insight into the obstacles that this revolutionary network paradigm will face in the future, from both a protocol and architecture standpoint. In this study, systematic literature was conducted and descriptive was used to analyze data. When it comes to SDN, the following challenges and issues stand out: All of these phrases are used to characterize the properties of a system: scalability, high availability, reliability, elasticity, security, performance, resilience, and dependability