This study embarks on a comprehensive analysis to evaluate the efficiency and scalability of in-memory computing (IMC) compared to traditional disk-based processing for big data analytics. Utilising the "New York City Taxi Trip Duration" dataset from Kaggle, we designed an experiment focusing on three critical analytical tasks: aggregation, sorting, and filtering. Our objective was to quantify the performance improvements offered by IMC, as facilitated by Apache Spark, against conventional SQL queries executed on a disk-based system. The findings reveal that IMC consistently outperforms disk-based processing in execution time, with significant reductions observed across all tasks. Specifically, the aggregation task highlighted the stark contrast in data retrieval speed, demonstrating IMC's superior efficiency with a completion time of 47.3 seconds, compared to 138.7 seconds for disk-based processing. Similar disparities were noted in sorting and filtering tasks, further accentuating IMC's performance advantage. Resource utilisation analysis, focusing on CPU and RAM consumption, indicated higher demands associated with IMC, underscoring the trade-off between enhanced speed and increased resource usage. The investigation provides a nuanced understanding of the practical implications of adopting IMC for big data analytics, especially considering the resource constraints of home computing environments. By juxtaposing theoretical advantages with empirical data, this paper contributes to the ongoing discourse on optimising data processing methodologies in the era of big data, offering insights into the balance between computational efficiency and resource management. Keywords: in-memory computing, big data analytics, disk-based processing, data processing efficiency, resource utilisation, Apache Spark, data analytics performance DOI: 10.7176/CEIS/15-1-05 Publication date: April 30 th 2024
This study examined effects of credit reference system on the right to privacy of customers of financial institutions. The credit reference system being a medium for the exchange of personal information of customers of financial institutions taking part therein; aims at facilitating credit market efficiency and stability. The right to privacy on other hand tries to keep to the minimum the intrusion to private domain of persons, customers of financial institutions being one of them. This article critically examined how these two seemingly conflicting interests have been compromised under the Ethiopian laws. A doctrinal research approach was employed in the analysis of the Ethiopian laws on the right to privacy and laws governing the credit reference system . The review of literature and analysis of legal instruments of both national and international character have been used to substantiate the arguments set forth in this work.This work concluded that even though violation of the right to privacy of the customers of financial institutions can be justified on the ground of voluntary relinquishment such rights; the Ethiopian credit reference system still needs reconsideration in light of principles recognized internationally for the protection of the right to privacy of persons. This work recommends for the revision of the Ethiopian credit reference system for better protection of the right to privacy of customers of financial institutions. Keywords: rights, privacy, credit reference system, financial institutions, Ethiopia DOI: 10.7176/CEIS/15-1-03 Publication date: January 31 st 2024
Artificial Intelligence (AI), advanced alternative to human mind, created by human mind, to simulate human intelligence in machines to think, perform and mimic human cognitive functions. Like humans, it uses various techniques like visual perception, speech recognition, decision-making, and language translation. One of growing security treats in country is with sleeper cells, a groups of individuals or agents operating undercover, within a society as normal people, until activated for a specific purpose, but identifying sleeper cells among community is a complex task that involves various intelligence and security measures. Artificial Intelligence (AI) can play a role in enhancing some aspects of this process, but it is important to note that AI alone may not be a panacea for such challenges due to ethical, legal, and technical considerations. This paper describes how AI help to identify sleeper cells. Keywords: Sleeper cells, Behavioural analysis, Artificial Intelligence, Defence, Security threats DOI: 10.7176/CEIS/15-1-02 Publication date: January 31 st 2024
This study embarks on a comprehensive analysis to evaluate the efficiency and scalability of in-memory computing (IMC) compared to traditional disk-based processing for big data analytics. Utilising the "New York City Taxi Trip Duration" dataset from Kaggle, we designed an experiment focusing on three critical analytical tasks: aggregation, sorting, and filtering. Our objective was to quantify the performance improvements offered by IMC, as facilitated by Apache Spark, against conventional SQL queries executed on a disk-based system. The findings reveal that IMC consistently outperforms disk-based processing in execution time, with significant reductions observed across all tasks. Specifically, the aggregation task highlighted the stark contrast in data retrieval speed, demonstrating IMC's superior efficiency with a completion time of 47.3 seconds, compared to 138.7 seconds for disk-based processing. Similar disparities were noted in sorting and filtering tasks, further accentuating IMC's performance advantage. Resource utilisation analysis, focusing on CPU and RAM consumption, indicated higher demands associated with IMC, underscoring the trade-off between enhanced speed and increased resource usage. The investigation provides a nuanced understanding of the practical implications of adopting IMC for big data analytics, especially considering the resource constraints of home computing environments. By juxtaposing theoretical advantages with empirical data, this paper contributes to the ongoing discourse on optimising data processing methodologies in the era of big data, offering insights into the balance between computational efficiency and resource management. Keywords: in-memory computing, big data analytics, disk-based processing, data processing efficiency, resource utilisation, Apache Spark, data analytics performance DOI: 10.7176/CEIS/15-1-06 Publication date: April 30 th 2024
Lung cancer is a major contributor to cancer-related mortality globally, and timely identification is essential for enhancing patient prognosis. Recently, deep learning methods, specifically Convolutional Neural Networks (CNN), have demonstrated encouraging outcomes in image-based medical diagnosis. The paper suggests utilising a CNN-based method to diagnose lung cancer from a healthcare image dataset, with a specific focus on histopathological image data. The proposed CNN approach utilises the natural hierarchical characteristics found in healthcare imagery to autonomously acquire distinctive features that indicate lung cancer. Transfer learning from extensive image datasets and improving models that have been trained are used to tackle the limitations of limited healthcare image datasets successfully. The CNN model utilising the VGG-19 architecture is developed and tested on a comprehensive dataset of lung cancer patients. Following extensive testing and evaluation, the model demonstrates high accuracy as well as precision and recall in diagnosing lung cancer using medical imaging. Interpretability techniques are utilised to get insights into the model's decision-making process, hence increasing its transparency and therapeutic relevance. The proposed CNN-based technology has the potential to help radiologists and clinicians discover and diagnose lung cancer earlier, leading to better patient care and treatment outcomes. Keywords: Lung Cancer, Histopathological image, Convolutional Neural Networks, VGG-19, Deep Learning DOI: 10.7176/CEIS/15-1-04 Publication date: March 31 st 2024
The study was conducted at Dangila district, Amhara region, Ethiopia. The concept of linkage in this study is communication and work together to develop and disseminate improved agricultural technologies to farmers. Researchers and development agents are the main actors in the process of technology release and transfer and their achievement depends on strong linkages with each other. The lack of integration and coordination between agricultural research and extension has resulted in confusion as to who should undertake on-farm verifications and pre-extension trials before making technologies directly available to farmers. The objective of this study was to identify and describe the factors that influence farmers’ participation on the technology demonstration. Simple random and purposive sampling techniques were used for selecting respondents and study area for this study. The data collection tools also included interview schedules and check lists. The data were analyzed through binary logistic regression model. The binary logistic regression model analysis result indicated that, Sex, education, extension advisory service and land ownership factors were significantly influence the farmers’ participation on the technology demonstration. In general perspective role of linkages in the process of technology transfer in Ethiopia were weak. The major reasons were non/little involvement of farmers in the research system, top-down approach, poor use of linkage mechanisms and strategies.
Weeds constitute a serious problem to wheat crops and cause a great loss to the yield. Manual weeding is labor-intensive and time-consuming. Chemical weed control has a negative impact on both the environment and humans. To overcome these problems, an engine-operated weeder was designed and developed at Asella Agricultural Engineering Research Center (AAERC). The developed weeder was designed on the basis of agronomic and machine parameters. The developed prototype weeder consists of the mainframe, weeder blade, ground wheel, and power transmission system. The rated engine speed of 2800 rpm was reduced to 46 rpm of the ground wheels by using bevel gear, chain, and sprocket mechanism in three stages. The overall dimension of prototype weeder was 1650 mm in length, 800 mm in width and 1050 mm in height. The total production cost of the engine-operated weeder was 11,409.92 ETB. This paper is focused on machine design analysis and fabrication of prototype. Performance evaluation of propototype would be addressed in the next coming paper.
Classification tasks are difficult and challenging in the bioinformatics field, that used to predict or diagnose patients at an early stage of disease by utilizing DNA microarray technology. However, crucial characteristics of DNA microarray technology are a large number of features and small sample sizes, which means the technology confronts a "dimensional curse" in its classification tasks because of the high computational execution needed and the discovery of biomarkers difficult. To reduce the dimensionality of features to find the significant features that can employ feature selection algorithms and not affect the performance of classification tasks. Feature selection helps decrease computational time by removing irrelevant and redundant features from the data. The study aims to briefly survey popular feature selection methods for classifying DNA microarray technology, such as filters, wrappers, embedded, and hybrid approaches. Furthermore, this study describes the steps of the feature selection process used to accomplish classification tasks and their relationships to other components such as datasets, cross-validation, and classifier algorithms. In the case study, we chose four different methods of feature selection on two-DNA microarray datasets to evaluate and discuss their performances, namely classification accuracy, stability, and the subset size of selected features. Keywords: Brief survey; DNA microarray data; feature selection; filter methods; wrapper methods; embedded methods; and hybrid methods. DOI: 10.7176/CEIS/14-2-01 Publication date: March 31 st 2023
The goal of this look at turned into to appear on the practices and demanding situations of cooperative getting to know in the selected authorities well-known secondary schools of Sidama Zone. The individual of technological know-how turned into used descriptive survey fashion and blended evaluation approach. The pattern of the look at turned into 385, forty five teachers, 324 student’s 8 school principals and 8 supervisors had been enclosed as a pattern thru sincere random and purposive sampling method severally. Instruments used at some stage in this look at enclosed shape, semi-established interview and commentary. For shape a five cause Likert scale turned into adopted. Frequencies and share turned into accustomed examine the information. Data generated from interview and room commentary turned into delineated qualitatively. The findings suggest that teachers and college students have advantageous attitudes toward cooperative getting to know which they prefer it to lecture-fashion. Consequently the subsequent findings had been obtained: lecturer’s loss of information and schooling on cooperative getting to know; college students’ loss of hobby to take part in cooperative getting to know and passive shape of getting to know; loss of sufficient guide from frame and inaccessibility of tutorial substances had been some of the demanding situations that prevent the implementation of cooperative getting to know. Consequently, lecturer’s unit lively historical coaching strategies. Similarly, college students indicated that they may be now no longer inclined to take part in phrase while the individual of technological know-how ascertained in the real room. The mission for teachers is to increase abilities to facilitate advantageous cooperation know-how amongst their college students World Health Organization must act with each other’s. Its advocate, presenting good enough frame guide, making ready supplementary substances, making ready cooperative getting to know education for teachers and inviting experts to proportion know-how concerning cooperative getting to know. Keywords: cooperative, Frequencies, implementation, supplementary &education DOI: 10.7176/CEIS/14-1-02 Publication date: January 31 st 2023
The most commonly used sampling techniques in research are probability and nonprobability methods. While probability sampling is based on the principle of random selection of participants in a particular study, non-random selection is the basis of probability sampling. The random and non-random classifications appear to have some potential flaws and are insufficient to represent all sampling procedures involving human participants. Similarly, most authors believe that they use random sampling techniques, although in reality, they do not use true random sampling. Therefore, the objective of this paper is to highlight that sampling techniques can be characterized as true-random, quasi-random, or nonrandom, rather than merely random and nonrandom. Attempts have been made to show how inadequate random and non-random sampling methods are, the characteristics of true-random, quasi-random, and nonrandom sampling procedures, and when each sampling procedure is appropriate. Since each unit of the population is randomly selected and the chance of selecting the unit is equal, a real random sample is used to estimate the characteristics of the population directly from the sample. With quasi-random sampling, it is not possible to directly estimate population characteristics, but only indirectly. However, population characteristics cannot be directly or indirectly estimated by using non-random sampling techniques. Keywords: True-random; quasi-random; non-random; sampling techniques DOI: 10.7176/CEIS/14-1-03 Publication date: January 31 st 2023
Ransomware is a collection of malicious software used by cyber security criminals to extort victims to pay a specified ransom at a specific time. In addition, ransomware attacks represent a modern challenge for all countries, companies, and organizations.A part of the results in this paper includes the timeline for the most ransomware that appeared in 2020, such that the paper listed eight ransomware this year, started by (Ragnar Locker) which appeared in January 2020, and ended by (Egregor) which appeared in September from the same year. In addition, the study found that: most ransomware uses a combination of three algorithms, like Nefilim and RansomExx, which use (RSA-2048, RSA-4096, and AES-256) algorithms, while most of the ransomware jointly uses the RSA & AES algorithms. In addition, the paper pointed out that: Egregor and Conti have the largest amount of ransoms, which is ($35 and $25) million respectively, instead (ProLock) which has the lowest ransom which is ($40000). Also, the amount ransoms of Nefilim and RansomExx is not determined. While Avaddon, Conti, and Nefilim are the most dangerous ransomware in 2020, because of their wide separation and attacks in many countries and companies. Keywords: Cyberattack, Ransomware, Ransom, Encryption, AES, RSA, RC4 DOI: 10.7176/CEIS/14-3-02 Publication date: August 31 st 2023
Purpose: Given the proper implementation of Artificial Intelligence (AI) technology, administrative and medical processes in the health sector of countries with low incomes can change quickly. This modification highlights the crucial influence of AI on a variety of health sector processes. Previous research indicates that AI may improve the standard of medical treatments. According to reports, AI technologies make life better for people by making it simpler, safer, and more productive. This study sought to identify the most significant potential and difficulties related to the application of AI in the health sector of emerging economies. Method: A thorough systematic literature review analysis was conducted using a total of 6 databases (Web of Science, ACM Digital, Science Direct, Emerald, IEEE, and Scopus). The selection was narrowed down to 49 articles after careful consideration in order to complete the review on potential AI possibilities and challenges that the health sector of developing economies need to be aware of. Results: The study found five major obstacles connected with AI adoption that requires attention in developing nations' health sectors: a lack of infrastructure, a lack of AI capabilities and skills, data integration, security, privacy, and legal concerns, as well as patient safety. The research also revealed six AI potentials that can aid the developing economy's health sector, including data exchange and availability, workflow management, cost reduction, resource management, professional training, and autonomous decision-making. It was discovered that AI has the ability to significantly outperform humans in terms of accuracy, efficiency, and timeliness of medical and associated administrative activities. Keywords: Artificial Intelligence, Opportunities, Challenges, Health Sector, Developing Economies, PRISMA DOI: 10.7176/CEIS/14-3-03 Publication date: August 31 st 2023
The use of computer vision to support and automate agriculture and viticulture is increasing. Therefore, it is important to continuously test new technologies and equipment. Management of pests and diseases in viticulture is a labour-intensive task. This study aims to investigate current technologies in computer vision that could be applied to disease and pest detection in viticulture and the application of transfer learning on segmentation networks. This study also implements a case study and applies computer vision for disease and pest detection. Observation of limitations in the network's performance on testing images, after training on the limited data set, suggests that careful control is needed over lighting conditions in the image capture environment. Although initial results are positive, a larger training dataset is recommended to achieve a greater level of accuracy. Keywords: Artificial Intelligence, Computer Visions, Viticulture, Sensors DOI: 10.7176/CEIS/14-3-01 Publication date: August 31 st 2023
This study explores all viable methods and techniques for the production of a responsive humanoid robot which would be both practically feasible and economically efficient. In the past few decades, scientists have been highly interested in the development of life-like humanoid robots. Some of these robots were used mostly in transporting heavy objects of accessing regions that were unreachable by humans. Between 1980’s and the 1990’s, engineers and scientists shifted their interest to the development of humanoid robots. These types of robots were able to stand, walk, and even pick up objects with mechanical hands. The introduction of humanoid robots greatly increased the interests of ordinary people in humanoid robots in particular. However, with the interest in these robots came the issue of communication. Majority of these robot have little or no recognizable facial features and would have to communicate with an external user by the use of audible sounds or visual symbols. This issue brought up the idea of creating robots that have recognizable facial features and are capable of carrying a conversation with humans. This project will develop a responsive and controllable humanoid robot head which would be capable of recreating basic movements of the human neck (such as rotate and pitch) as well as some basic and widely recognizable human facial expressions. This project focuses on developing a cost efficient, and practical process of creating animatronic robotic protype which will serve as a springboard for researcher, students, academia, and robot developers. The study further conducts a biomechanical analysis of the human head with specific emphasis on facial features including skeletal and muscular tissue structure to assist readers to learn and replicate the process. Above all, the project will enable researchers, scholars, students, and robot making companies to produce an animatronic humanoid robot head which can recreate basic human facial expressions that are easily recognizable to the average human such as happiness, anger, fear, sadness etc. to assist smooth communication, and business transaction. Also, the robot would be capable of recreating basic human neck and head movements like tilting of the head upwards and downwards and rotating of the head from side to side to follow human instructions. Keywords: Robots, Humans, Interactions, Humanoids, Robotic, Production, Automated, Facial-Expression, Skin, Animatronic, Skeletal, Artificial- Intelligence (AI) DOI: 10.7176/CEIS/14-2-02 Publication date: March 31 st 2023
This article utilizes Information Communication Technology (ICT) frameworks to investigate the impactful effect of Information Communication Technology (ICT) such as enterprise resource planning (ERP) and electronic commerce (e-commerce) on businesses in general. A narrative literature review analysis (or type) of research has been adopted, while a Boolean search of 24 articles met the criteria for inclusion. As part of the literature search, the data collection procedure took into account the first and second authors of the completed simultaneous electronic and ancestral searches for peer-reviewed articles by using the online database, Association of Computing Machinery (ACM), and five databases from A Database Management System (DBMS): Oracle Database Software (ODS), A Relational Database Management System (RDMS), Journal Data Mining and Knowledge Discovery (JDMKD) as well as Google scholar and advanced Google scholar. As part of the findings for the study utilized for the article, many scholars made specific inferences to the ICT applications in firms and businesses. Out of the twenty-four articles, six of the researchers, thus 24%, underscored and also perceived that e-commerce has become a widely accepted method for business operation. Researchers of 4 articles—thus 17% -- explicitly stated in their research that the use of e-commerce in the business world has benefited companies greatly. A total of 7 (29.5%) researchers –provide detailed discussion in the literature about labor productivity and ICT applications in businesses, mass communications, firms, and organizations, as well as the effective implementation of ERP in firms, businesses, and organizations. Above all, the article has unearthed implications as well as made cogent suggestion for future research in order to contribute to overall educational policy of society. Toward this end, three (12.5%) researchers provide a discussion about Supply Chain Management (SCM) performance and the components of an ERP system as well as ERP successful implementation emphasizing on the application and importance of ICT to businesses. Keywords: ICT, Enterprise, Resource, Planning, Businesses, Firms, E-commerce, Computers, Database DOI: 10.7176/CEIS/14-2-04 Publication date: March 31 st 2023
In today's highly interconnected world, network security has become a critical aspect of protecting organizations from cyber-attacks. The increasing sophistication of attackers and their ability to exploit software and firmware vulnerabilities pose significant dangers to the security of networks. However, many organizations often neglect the essential steps required to secure their networks, leading to an increased risk of security breaches. In this research article, we aim to address this issue by investigating network security concepts, potential dangers, and practical defense strategies. We begin by exploring the different types of cyber-attacks and their sources, highlighting the various ways attackers exploit network vulnerabilities. We also examine the reasons why organizations often overlook network security and the consequences of not prioritizing it. To better understand the complexity of network security, we categorize the different security concerns using the CIA (confidentiality, integrity, and availability) triangle. This approach allows us to identify the various areas of vulnerability and their potential impact on network security. Next, we focus on the most crucial basic concepts and steps involved in various network security operations. We outline the best practices and practical approaches organizations can take to improve their network security, including implementing security policies and procedures, using encryption and authentication methods, and conducting regular security assessments. By highlighting the importance of network security and providing practical guidance on how organizations can defend against cyber-attacks, we hope to raise awareness and help prevent security breaches. Keywords: Network, Internet, Security, Security Threats, IP Address, Network Attack, Attackers DOI: 10.7176/CEIS/14-2-03 Publication date: March 31 st 2023
The data that matters to executives in the United States industry includes machine performance data, maintenance and service data, and production data. This data improves machine performance, reduces downtime, and increases efficiency. The individuals who need this data include executives, maintenance and service personnel, and production managers. The methods of ensuring that the critical data reaches the users have industrial big data analytics, implementing a robust data management system, and training personnel. The use of big data analytics in various industries has been growing rapidly over the past few years. The industrial sector has seen significant benefits from implementing big data analytics. This research paper explores the potential of future maintenance and service innovation in the United States industrial sector using big data analytics, the benefits of being data-driven, and implementing a data-driven process strategy in the United States industrial sector. The paper explains the key data sources, storage, and processing techniques currently used in the industry to gather and analyze data. The paper also identifies the challenges and methodologies in leveraging big data analytics to drive maintenance and service operations innovation. The study will focus on identifying the data that matters most to executives in the industry, determining who needs it, and exploring methods for ensuring the critical data is effectively communicated to its intended users. Additionally, the paper will examine recent advances and terminologies in big data analytics, the methodology for designing innovation-based industries, presents the theoretical background and hypotheses, and examine limitations and future research opportunities in the field. KEYWORDS - Maintenance, Innovation, Big Data, Analytics, Industry, United States, Data, Organization DOI: 10.7176/CEIS/14-1-04 Publication date: February 28 th 2023
Handwriting recognition is the ability of a computer to receive and interpret intelligible handwritten input from sources such as paper documents, photographs, touch-screens and other devices. The purpose of the research is to design develops, construct, deploy, and test a convolutional neural network (CNN) for handwriting recognition. The CNN for handwriting recognition was developed with Python and MNIST dataset was used. CNN was evaluated together with Simple Neural Network (SNN) and it was found that a CNN operating on well-tuned hardware with GPU and adequate training data can recognize numbers with an accuracy of up to 98.7 percent. The accuracy and speed of the model can be improved by expanding the dataset, increasing the number of epoch runs, and executing it on parallel hardware. Using these strategies, an accuracy of up to 99.89 percent, can be achieved. Keywords: CNN, SNN, Tensor Flow, Neural Network Architecture, Confusion matrix DOI: 10.7176/CEIS/14-1-05 Publication date: February 28 th 2023
Ransomware has become a form of electronic warfare and cybercrime, which is increasing day by day due to the large revenue of money it has generated, which estimated at millions of dollars. The act of paying or refusing it also poses another challenge to the countries and organizations, as their laws and regulations say not to pay the extortionists, but in return, to the needs of these organizations for their data, it will respond to the blackmailers and pay the ransom, which encouraged the extortionists to produce much dangerous ransomware.A part of the results in this paper includes the timeline for the most ransomware that appeared in 2019, such that the paper listed nine ransomware this year, started by (Mega Cortex) which appeared in January 2019, and ended by (Double Extortion) which appeared in November from the same year. In addition, the study found that: most of the ransomware uses a combination of three algorithms, like REvil and NetWalker, which use (RSA-2048, ECDH, and Chacha20) algorithms, while most of the ransomware jointly uses the RSA & AES algorithms. In addition, the paper pointed out that: REvil and LockBit2.0 have the largest amounts of ransoms, which is ($50) million for each one, instead (DoppelPaymer) has the lowest ransom which is ($1.2) million. While CLOP, REvil, and LockBit2.0 are the most dangerous ransomware in 2019, because of their wide separation and attacks in many countries in Europe, Asia, and USA. Keywords: Cyberattack, Ransomware, Ransom, Encryption, AES, RSA, RC4 DOI: 10.7176/CEIS/10-1-02 Publication date: September 30 th 2023
This research work studies the performance of the internet services of institution of higher learning in Nigeria. Data was collated from Lagos State University of Science and Technology (LASUSTECH) as case study of this research work. The problem of Internet Bandwidth optimization in the institution of higher learning in Nigeria was extensively addressed in this paper. The operation of the Link-Load balancer which provides an efficient cost-effective and easy-to-use solution to maximize utilization and availability of Internet access is discussed. In this research work, the Lagrange’s method of interpolation was used to predict effective internet data bandwidth for significantly increasing number of internet users. The linear Lagrange’s interpolation model (LILAGRINT model) was proposed for LASUSTECH. The predictions allow us to view the effective internet data bandwidth with respect to the corresponding acceptable number of internet users as the number of user’s increases. The integrity of the model was examined, verified and validated at the ICT department of the institution. The LILAGRINT model was integrated into the management of ICT and tested. The result showed that the proposed LILAGRINT model proved to be highly effective and innovative in the area of internet data bandwidth predictability. Keywords: Internet Data Bandwidth, Optimization, Link-load balancer, Lagrange’s interpolation, Predictions, Management of ICT DOI: 10.7176/CEIS/10-1-04 Publication date: September 30 th 2023
