Open Access Original Research Article

Data Mining Classification Algorithms for Analyzing Soil Data

Kazheen Ismael Taher, Adnan Mohsin Abdulazeez, Dilovan Asaad Zebari

Asian Journal of Research in Computer Science, Page 17-28
DOI: 10.9734/ajrcos/2021/v8i230196

Rapid changes are occurring in our global ecosystem, and stresses on human well-being, such as climate regulation and food production, are increasing, soil is a critical component of agriculture. The project aims to use Data Mining (DM) classification techniques to predict soil data. Analysis DM classification strategies such as k-Nearest-Neighbors (k-NN), Random-Forest (RF), Decision-Tree (DT) and Naïve-Bayes (NB) are used to predict soil type. These classifier algorithms are used to extract information from soil data. The main purpose of using these classifiers is to find the optimal machine learning classifier in the soil classification. in this paper we are applying some algorithms of DM and machine learning on the data set that we collected by using Weka program, then we compare the experimental result with other papers that worked like our work.  According to the experimental results, the highest accuracy is k-NN has of 84 % when compared to the NB (69.23%), DT and RF (53.85 %). As a result, it outperforms the other classifiers. The findings imply that k-NN could be useful for accurate soil type classification in the agricultural domain.

Open Access Original Research Article

Constructivist Approach for E-Learning Effectiveness in African Higher Education Contexts

Mohamed Elfateeh Alobeed A Ismail, T. Gnana Sambanthan

Asian Journal of Research in Computer Science, Page 29-41
DOI: 10.9734/ajrcos/2021/v8i230197

There is a spurt in online learning worldwide, particularly in Asian and African countries, after the COVID-19 pandemic. Outcomes Based Education (OBE), the new paradigm in Africa, India and elsewhere in the world promotes e-Learning as part of its Lifelong learning attribute. Design of such e-Learning system should incorporate features of autonomous learner’s characteristics (like African higher education students) for their preparedness and progression phases of e-Learning. This is due to the fact that the learning environment and learner characteristics, may differ from place to place and cultures. As per literature, principles of constructivist theory have been successfully adapted for e-Learning. Meta-cognition is a new addition to the OBE paradigm besides cognitive, affective and psychomotor domains, that plays important role in e-Learning. This paper attempts to construct metrics for meta-cognition using constructivist’s learning parameters, for analyzing three phases of e-Learning. Literatures are limited on meta-cognitive studies of e-Learner characteristics. The novelty of the paper is the adaptation of certain principles of ecological system on meta-cognition with literature support. Inductive research with appropriate methodology is applied for studying the effectiveness of e-Learning. Ecological factors in the meta-cognition aspects of the constructivist’s theory have been considered. Two parts are treated by the paper: i. Comparative study between Indian and African scenario; ii. Detailed study of selective African countries on the preparedness and progression phases of e-Learning. Survey methods have been chosen for obtaining feedbacks on scientifically designed questionnaire. Three hypotheses on the meta-cognitive aspects of self-regulation and a null hypothesis for the comparative study, have been constructed. Observations on the three phases of e-Learning have been documented and inferences drawn. Conclusions made out our research study along with the results presented will be of immense use to e-Learning system designers, particularly for the African scenario.

Open Access Original Research Article

Utilization of Eight-Variable Karnaugh Maps in the Exploration of Problems of Qualitative Comparative Analysis

Ali Muhammad Ali Rushdi, Raid Salih Badawi

Asian Journal of Research in Computer Science, Page 57-84
DOI: 10.9734/ajrcos/2021/v8i230199

Qualitative Comparative Analysis (QCA) is an emergent methodology of diverse applications in many disciplines. However, its premises and techniques are continuously subject to discussion, debate, and (even) dispute. We use a regular and modular Karnaugh map to explore a prominent recently-posed eight-variable QCA problem. This problem involves a partially-defined Boolean function (PDBF), that is dominantly unspecified. Without using the algorithmic integer-programming approach, we devise a simple heuristic map procedure to discover minimal sets of supporting variables. The eight-variable problem studied herein is shown to have at least two distinct such sets, with cardinalities of 4 and 3, respectively. For these two sets, the pertinent function is still a partially-defined Boolean function (PDBF), equivalent to 210 = 1024 completely-specified Boolean functions (CSBFs) in the first case, and to four CSBFs only in the second case. We obtained formulas for the four functions of the second case, and a formula for a sample fifth function in the first case. Although only this fifth function is unate, each of the five functions studied does not have any non-essential prime implicant, and hence each of them enjoys the desirable feature of having a single IDF that is both a unique minimal sum and the complete sum. According  to our scheme of first identifying a minimal set of supporting variables, we avoided the task of drawing prime-implicant loops on the initial eight-variable map, and  postponed this task till the map became dramatically reduced in size. Our map techniques and results are hopefully of significant utility in future QCA applications.

Open Access Review Article

Comprehensive Survey for Cloud Computing Based Nature-Inspired Algorithms Optimization Scheduling

Hazha Saeed Yahia, Subhi R. M. Zeebaree, Mohammed A. M. Sadeeq, Nareen O. M. Salim, Shakir Fattah Kak, Adel AL-Zebari, Azar Abid Salih, Helat Ahmed Hussein

Asian Journal of Research in Computer Science, Page 1-16
DOI: 10.9734/ajrcos/2021/v8i230195

Many applications in the real world include optimizing specific targets, such as cost minimization, energy conservation, climate, and maximizing production, efficiency, and sustainability. The optimization problem is strongly non-linear with multifunctional landscapes under several dynamic, non-linear constraints in some instances. It is challenging to address those issues. Also, with the increasing strength of modern computers, simplistic brute force methods are still inefficient and unwanted. Practical algorithms are also vital for these implementations whenever possible.

Cloud computing has become an essential and popular emerging computing environment that supports on-demand services and provides internet-based services. Cloud computing allows a range of services and tools to be easily accessed from anywhere in the world. Since cloud computing has global access to its services, there will always be threats and challenges facing its servers and services, such as; task scheduling, security, energy efficiency, network load, and other challenges. In the research area, many algorithms have been addressed to solve these problems. This paper investigates relevant analysis and surveys on the above topics, threats, and outlooks. This paper offers an overview of nature-inspired algorithms, their applications, and valuation, emphasizing cloud computing problems. Many problems in science and engineering can be viewed as optimization problems with complex non-linear constraints. Highly nonlinear solutions typically need advanced optimization algorithms, and conventional algorithms can have difficulty addressing these issues. Because of its simplicity and usefulness, nature-inspired algorithms are currently being used. There are nevertheless some significant concerns with computing and swarming intelligence influenced by evolution.

Open Access Review Article

IoT and ICT based Smart Water Management, Monitoring and Controlling System: A Review

Hajar Maseeh Yasin, Subhi R. M. Zeebaree, Mohammed A. M. Sadeeq, Siddeeq Y. Ameen, Ibrahim Mahmood Ibrahim, Rizgar R. Zebari, Rowaida Khalil Ibrahim, Amira B. Sallow

Asian Journal of Research in Computer Science, Page 42-56
DOI: 10.9734/ajrcos/2021/v8i230198

Water is a basic human need in all economic operations. Farmland, renewable energy, the industrial industry, and mining are all critical economic areas. Water supplies are under severe strain. With the population increase, the requirement for water from competing economic sectors is increased. So, there is not enough water left to meet human needs and maintain environmental flows that maintain the integrity of our ecosystems. Underground water is becoming depleted in many sectors, making now and future generations near the point of being deprived of protection from the increasing climate variability. Therefore, the critical role that information technology methods and internet communication technologies (ICT) play in water resources managing to limit the excessive waste of fresh water and to control and monitor water pollution. In this paper, we have to review research that uses the internet of things (IoT) as a communication technology that controls the preservation of the available amount of water and not wastes it by homeowners and farmers. In contrast, they use water, and we have also reviewed some researches that preserve water quality and reduce its pollution.