Oriental Journal of Computer Science and Technology An International research journal of Computer Science and Technology

A bijection f from the vertex set V of a graph G to {1,2, …, |V|} is called a prime cordial labeling of G if each edge uv is assigned the label 1 if gcd (f(u), f(v)) = 1 and 0 if gcd (f(u), f(v)) > 1, where the number of edges labeled with 0 and the number of edges labeled with 1 differ at most by one. In this paper I have proved four new results admitting Prime cordial labeling.

Hide Abstract

The significance of medical diagnosis in directing treatment options and improving patient outcomes is critical. With the rapid growth of machine learning, there has been an increase in interest in leveraging its potential to improve diagnostic capabilities. The aim of this research was to conduct a survey on current improvements in medical diagnosis and telemedicine using machine learning techniques, Machine learning and deep learning has shown exceptional success in analyzing medical images in a variety of modalities, including radiology, pathology, dermatology, ophthalmology, Neuro-science, Neuro-computing and Neuro-imaging. Machine learning algorithms have outperformed human specialists in tasks such as tumor identification, segmentation, and disease categorization in some circumstances. The incorporation of machine learning in telemedicine and remote monitoring has allowed for remote access to healthcare services as well as continuous patient monitoring. These advances have resulted in greater accuracy and fewer diagnostic errors in medical diagnosis. Machine learning algorithms have shown excellent sensitivity in diagnosing diseases such diabetic retinopathy, skin cancer, breast cancer metastases, and lung nodules. The successful creation, validation, and implementation of machine learning models in medical diagnostics requires collaboration between machine learning experts and medical professionals. This partnership brings together subject expertise, clinical competence and technical capabilities, resulting in more accurate, reliable, and clinically useful diagnostic tools. We can continue to uncover the full potential of machine learning in medical diagnostics and achieve transformative advances in healthcare by tackling the difficulties and fostering collaboration.

Hide Abstract

The emergence of ChatGPT, a cutting-edge language model based on the GPT-3.5 architecture, has had a transformative impact on natural language processing and human-computer interaction. This study delves into the capabilities, limitations, and ethical considerations associated with ChatGPT. It explores the model's underlying structure and training techniques, highlighting its remarkable ability to generate coherent and contextually appropriate responses spanning diverse subjects. The paper addresses the challenges presented by biases, misinformation, and safety concerns, emphasizing the ongoing efforts to tackle these issues through research. Additionally, it investigates potential applications of ChatGPT in fields like customer service, education, and content creation. Finally, the paper concludes by discussing future directions and key research questions in the advancement of conversational AI through the utilization of ChatGPT.          

Hide Abstract

COVID-19 is an ongoing pandemic and dangerous of coronavirus disease 2019. It caused by the transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). COVID-19 spreads most often when people are physically close. And, it spreads very easily and sustainably through the air, primarily via small droplets or aerosols, as an infected person breaths, coughs, sneezes, sings or speaks. The recommended preventive measures include hand washing, covering one’s mouth when sneezing or coughing, physical distancing, wearing a face mask in public, ventilation and air-filtering, disinfecting surfaces, and monitoring and self-isolation for people exposed or symptomatic. Hence, this paper proposed the architecture of physical distancing detection system with distance sensor which deployed on UAV System with the help of BTS (2G/3G/4G/5G) to enrich the COVID-19 preventive measures, as well as I have also developed a few algorithms for distance sensor (on UAV System) operations which sensing, tagging and disseminating the current distance, position and waiting time of resident’s information, and forwarding schemes to respective infrastructures and suspected residents including the security forces.

Hide Abstract

Wearable tracking gadget that school-age children can wear is the topic of this paper. It doesn't need any pricy technology to operate.. This technology is usable by persons of all educational levels. It has got two buttons one is alert button and another is panic button The major objective of this gadget is to ensure that the youngster may contact their parents in an emergency. The alert button allows the child to notify their parents of an emergency and provide their current location. For communication, the current technology includes Bluetooth, WI-FI, and RFID. It is hard to communicate across a great distance with these technologies because they only have a narrow range of coverage. Also they are not that accurate. This device solves the issue by utilizing GSM technology. Parents do not need to submit any special code to the device to determine the child's location's latitude and longitude. If a child is in any emergency situation and wants his/her parents to know their current exact location. If a child feels uneasy, there are two methods to let the parents know. The cell phone of the parents or guardian receives the alarm message via SMS by pressing alert button and if the child wants to communicate to parents immediately, a call can also be made via this device using the panic button and the child can talk to the parent in real time.

Hide Abstract

System security is very important, especially in the age that we live in. One of the ways to secure data is by creating a password that makes it difficult for unauthorized user to gain access to the system. However, what makes it difficult for the system to be attacked is directly dependent on approach used to create it, and how secured it is. Text based approach is the oldest authentication approach. It requires that the user supplies textual password in order to gain access to the system. However, this approach has shown a significant drawback and several vulnerabilities, one of which is the difficulty in recalling or remembering textual passwords. Several other attacks that textual passwords are vulnerable to include brute force attacks, shoulder spying, dictionary attacks etc. The introduction of graphical schemes made things a lot better. Graphical passwords make use of images. However, most graphical schemes are vulnerable to shoulder surfing attacks. In this research work, we developed two systems; A position-based multi-layer graphical user authentication system and an Image-based multi-layer graphical user authentication system. The reason behind this research work is to compare the two systems, and evaluate them based on three major performance metrics: (1) Security, (2) Reliability (3) Individual preference.

Hide Abstract

Reinforcement learning (RL) is a type of ML, which involves learning from interactions with the environment to accomplish certain long-term objectives connected to the environmental condition. RL takes place when action sequences, observations, and rewards are used as inputs, and is hypothesis-based and goal-oriented. The key asynchronous RL algorithms are Asynchronous one-step Q learning, Asynchronous one-step SARSA, Asynchronous n-step Q-learning and Asynchronous Advantage Actor-Critic (A3C). The paper ascertains the Reinforcement Learning (RL) paradigm for cybersecurity education and training. The research was conducted using a largely positivism research philosophy, which focuses on quantitative approaches of determining the RL paradigm for cybersecurity education and training. The research design was an experiment that focused on implementing the RL Q-Learning and A3C algorithms using Python. The Asynchronous Advantage Actor-Critic (A3C) Algorithm is much faster, simpler, and scores higher on Deep Reinforcement Learning task. The research was descriptive, exploratory and explanatory in nature. A survey was conducted on the cybersecurity education and training as exemplified by Zimbabwean commercial banks. The study population encompassed employees and customers from five commercial banks in Zimbabwe, where the sample size was 370. Deep reinforcement learning (DRL) has been used to address a variety of issues in the Internet of Things. DRL heavily utilizes A3C algorithm with some Q-Learning, and this can be used to fight against intrusions into host computers or networks and fake data in IoT devices.

Hide Abstract

This paper aims at building the causal relations and event structures [13] to study the complex and evolving cyber – physical systems with illustrations of the reasoning based on Robotics [24] and Policy Analysis [25] for Communication Systems. An empirical analysis points to the realism that network security is also a geometric theory with safety and authentication tending to geometric formulae that make the larger structures. Security is very much a matter of perception too. The proposed approach also factors the perceptual aspects of the human mind. This paper includes several interesting possibilities for using linear algebra, discrete mathematics, analysis, and topology in the domains such as economics, game theory, robotics and biology to mention a few.

Hide Abstract

 E-libraries is also known and referred by various authors as either Virtual libraries or Digital libraries. Our society is currently witnessing a quick and continues transformation powered by ICT revolution which has find its way in all other field of human endeavors. The use of information and communication technology (ICT) is becoming an integral part of education in all parts of the globe. Nigeria which Ebonyi is one among the 36 states is not left behind as ICT gradually finds its way into her educational systems regardless of persistent restrictions caused by our low economic status, the increasing numbers of E-libraries even in the young state like Ebonyi stands so encouraging. The advancement of E-libraries has ensured the emergence of global networked environment that has dramatically changed the face and operation of the old traditional libraries’ functions, services including their storage and delivery systems.This paper after reviewing related literature works concerning libraries and its advantages,highlighted several challenges of E-library services in Tertiary institutions in Ebonyi state.Finally,it concludes that if E-libraries in tertiary institutions in the state are to survive, drastic and progressive action needs to be taken by Governments and sponsoring bodies to overcome some of the mentioned challenges.

Hide Abstract

The purpose of this study is to provide new insights into the factors that influence cancellation behaviour with respect to hotel bookings. Cancellations of bookings are one of the most common concerns in the hotel sector. Before the specified arrival date, the client would cancel their reservation. The cancellation has had a major impact on hotel operations as well. The researchers developed a prototype system called Automated Hotel Booking Cancellation that can assist a hotel in better anticipating consumer cancellations and booking transactions. The researchers utilized a survey questionnaire following the ISO 25010 Software Quality Standard to assess the system's usefulness, functionality, accuracy, security, reliability, and maintainability. The results show "strongly agree" in all the domains with an overall mean = 3.46. IT Experts and respondents evaluated the proposed prototype and gained a "Strongly Agree" rating in all the domains under the survey. The domain on the usefulness of the system gained the highest mean = 3.89 with an interpretation of "strongly agree," and the lowest was the domain of security with a mean = 3.15 or "strongly agree," which ranked 6 in summary.

The researchers concluded based on the findings that the developed prototype web-based system was useful and functional to the needs of the target users/beneficiaries. The user interface of the web-based system was user-friendly, representing an object-oriented user interface for the users. An improvement recommended on the cancellation to automatically predict cancellations that can be incorporated into the system using Machine Learning Algorithms to ease the process of cancellation were recommended for future researchers who want to pursue advanced studies about the topic.

Hide Abstract

The flexible architecture offered by cloud computing allows for the dispersion of resources and data over numerous places, making it possible to access them from a variety of industrial settings.  The use, storage, and sharing of resources such as data, services, and industrial applications have all changed as a result of cloud computing. In the past ten years, companies have quickly shifted to cloud computing in order to benefit from increased performance, lower costs, and more extensive access. Additionally, the internet of things (IoT) has significantly improved when cloud computing was incorporated. However, this quick shift to the cloud brought up a number of security concerns and challenges. Traditional security measures don't immediately apply to cloud-based systems and are occasionally inadequate. Despite the widespread use and proliferation of various cyber weapons, cloud platform issues and security concerns have been addressed over the last three years. Deep learning's (DL) quick development in the field of artificial intelligence (AI) has produced a number of advantages that can be used to cloud-based industrial security concerns. The following are some of the research's findings: We provide a detailed evaluation of the structure, services, configurations, and security fashions that enable cloud-primarily based IoT. We additionally classify cloud protection dangers in IoT into four foremost areas (records, network and carrier, programs, and gadgets). We discuss the technological issues raised in the literature before identifying key research gaps. In each class, describe the boundaries using a popular, artificial intelligence, and in-depth studying attitude. and security concerns relating to individuals), which are fully covered; we find and analyze the most recent cloud-primarily based IoT attack innovations; we identify, talk, and verify key safety challenges show the regulations from a standard, synthetic intelligence, and deep learning perspective in every class angle; we first present the technological difficulties identified in the literature before identifying IoT-based cloud infrastructure has significant research gaps which should be highlighted for future research orientations. Cloud computing and cyber security.

Hide Abstract

Altera SDK for OpenCL allows programmers to write a simple code in OpenCL and abstracts all Field programmable gate array (FPGA) design complexity. The kernels are synthesized to equivalent circuits using the FPGA hardware recourses: Adaptive logic modules (ALMs), DSPs and Memory blocks. In this study, we developed a set of fifteen different benchmarks, each of which has its own characteristics. Benchmarks include with/without loop unrolling, have/have not atomic operations, have one/multiple kernels per single file, and in addition to one/more of these characteristics are combined.  Altera OpenCL v14.0 adds more features compared with previous versions. A set of parameters chosen to compare the two OpenCL SDK versions: Logic utilization (in ALMs), total registers, RAM Blocks, total block memory bits, and clock frequency.

Hide Abstract

Quality of queuing service management is the aim of any organization providing its services to customers. The purpose of this paper is to evaluate the factors affecting the quality of service provided by the public sector depending on waiting lines. For this purpose, a questionnaire survey was conducted on a sample of 394 to collect data relating to customer satisfaction. The questionnaire consists of five factors: process, tangible, responsiveness, reliability, and empathy. The results showed that the degree of agreement of the factors; process, tangible, reliability, responsiveness, empathy, and service quality gain a neutral category, and all the factors have statistically significant effects on quality of service except the empathy factor. For the demographic information, the results showed that there are statistically significant differences for most of the demographic information. This paper extends the previous research that investigates factors affecting e-recruitment. The author extends the results of previous research related to the transparency of e-recruitment. The study recommended the service departments should make more effort in the way of providing services to improve the level of service quality management.

Hide Abstract

The SBM Robot is a manually operated robot focused on the Internet of Things and the robot operating system. The system is focused on washing and maintenance. The robot is controlled by an android app that uses the Google Real Time Firebase database to control the robot. HVAC duct is small in size and cleaning and repairing the duct is a very difficult task for humans, but it's easy to robot, robot goes inside the duct, and inspects and cleans the duct. Like similar, ships use fuel, oils, sludge, sewage, water and other fluids stored in tanks.

Hide Abstract

Cloud computing provides multiple services to users through the internet and these services include cloud storage, applications, servers, security and large network access. Virtual Machine allows the user to emulate multiple operating systems on a single computer; with the help of virtual machine migration users can transfer operating system instances from one computer to multiple computer machines. In this paper we will be discussing VM migration in cloud and also I will explain the whole procedure of VM migration. The two methods through which we can perform VM migration are Live VM migration and NON-live VM migration.VM migration also helps in managing the loads of the multiple machines and with VM we can save power consumption. People have written about cloud computing and virtual machines in previous studies, but in this research, we'll speak about virtual machine migration in cloud computing, as well as the techniques that are used in the VM migration process. I have used table to show the differences between VM migration techniques.

Hide Abstract

The term information electronic library it’s need and importance and takes a stock of some notable efforts being made to initiate information electronic library activities in different parts the world.

The aim of electronic library is to explorer and to collect useful knowledge over above faster coping. Search and to distribute. So present paper discuses in electronic library services. It’s meaning, feature, feature, roll of librarians, services of e-libraries, advantages, disadvantages, and objective etc..

Hide Abstract

Agriculture is the backbone of any country and India is blessed to have agriculture as the main occupation of a large population. The varied geographical terrain of India provides an opportunity for yearlong production of crops. With the onset of technical revolution in all the areas of life, all over the world, agriculture is not untouched. The developments in ICT has revolutionized agricultural operations many folds. Be it the meteorological information, soil health, seed health, fertilizer application or even the insect attack on the crops, all are being regulated by the ICT applications in one form or other. Our today’s farmer is well informed about the use of new technologies in agriculture and is very efficiently utilizing the information in an intelligent way. All these are irrespective of the region, season, crop, place or the location. The use of Information Technology has made our farmers SMART, i.e., they are Self Monitoring, Analyzing and Reporting through the use of adequate Technology. The use of proper IT tools has given both the scientists and farmers a suitable platform to interact more frequently and on time. The scientists are using ICT tools to reach the farmers on their fields and our farmers has brought their knowledge to the labs for further growth and development in the field of agriculture. The present paper is a review on the current ICT applications which is making our farmers SMARTER and self reliant. There are many initiatives of government and private organizations to bring our farmers closer to the technologies developed for their benefit. The current paper is an attempt to visualize the efforts made by scientists and technologists in the field of information and Technology for the benefit of farmers and towards the end it conceptualizes the application of ICT and its use by our farmers.

Hide Abstract

Cybersecurity is a combination of technologies, processes and operations that are designed to protect information systems, computers, devices, programs, data and networks from internal or external threats, harm, damage, attacks or unauthorized access¹.The research was purposed to develop a cybersecurity culture framework which ensures that grassroot users of cyberspace are secured from cyber threats. Literature review showed that in Zimbabwe, no research had attempted to come up with a cybersecurity culture framework for grassroot users of cyberspace.The research was guided by the interpretivist paradigm and employed a qualitative methodology. A descriptive research design was used to answer the research questions and unstructured interviews were done to ascertain the cybersecurity needs and challenges of grassroot users of cyberspace. A cybersecurity culture framework was then crafted based on the research findings. The researchers recommended that Zimbabwe should have a cybersecurity vision and strategy that cascades to the grassroot users of cyberspace. Furthermore, the education curricula should be revised so that it incorporates cybersecurity courses at primary and secondary school level .This will then ensure that ICT adoption is matched with cyber hygiene and responsible use of cyberspace.

Hide Abstract

Designed for multiple device-to-device clusters (D2DC) multicast communications is proposed in this research which is an efficient resource allocation scheme. To maximize the sum effective throughput the transmit power and the channel are apportioned to D2DC. Given that the nature of administration is rationed for cellular communications at a specific degree. Our examination details a channel assignment conspire utilizing fractional data of gadget areas. For this situation, we acquire the disturbance likelihood and viable throughput of D2DC communications incomparative outline. This process is carried by increasing the cluster size, code words and subcarriers. we proposed the algorithm here is a sensible channel allocation (CA) conspire utilizing partial information of device locations (CA-PIL). Consequently planned methodology can naturally lessen the measure of required framework overhead contrasted and the Channel Allocation (CA) conspire utilizing full information of device locations (CA-FIL).The forthcoming CA-PIL strategy accomplishes the close ideal aggregate Effective Throughput got by CA-FIL when an enormous number of D2D devices work in the clusters.

Hide Abstract

In the medical field computer-aided diagnosis systems (CADs) are an active area of research as CADs serve to aid medical professionals in simplifying the diagnosis of a patients condition. In this paper we propose a machine learning based method for classifying lumbar disc herniation.  The automation of herniated disc diagnosis decreases the enormous weight on radiologists who need to analyse several cases every day manually. Automation will also help to decrease inter and intra rater variability. Hence his work focuses on the classification of lumber disc herniation based on sagittal view Magnetic Resonance Images (MRIs). The dataset used in this work comprises of 32 images from 32 patients of which 10 patients are healthy while 22 of them have herniated discs. This data is processed through various image processing techniques to obtain three sets of features: the binary image; shape, height and width measurements of discs; and full attribute images. The proposed approach consists of four stages: region extraction, image segmentation, feature extraction and classification. The classification process is performed through support vector machines (SVMs) and K-nearest neighbor (KNNs) of which the KNN with k=5 produced the best results with 78.6% accuracy, F1 score of 66.7%, precision and recall rate of 60% and 75% respectively.

Hide Abstract