Journal of Applied Artificial Intelligence <p>Journal of Applied Artificial Intelligence (JAAI) is an international and interdisciplinary scholarly peer reviewed journal on artificial intelligence published by Saba Publishing.<br />JAAI devoted entirely to Artificial Intelligence and welcomes papers in the overall field including, but not limited to, machine learning and cognition, deep learning, supervised learning, unsupervised learning, classification, regression, clustering, big and streaming data, optimization algorithms, feature selection and extraction, pattern recognition, bio-informatics, uncertain information processes, recommender systems, E-service personalization, distributed and parallel processing, computer vision, neural networks, natural language processing, heuristic search, multi-objective optimization, multi-agent systems, advances in social network systems, reasoning under uncertainty, forecasting and predication models as well as other hot topics.</p> <p><strong>Editor in Chief: <a href="" target="_blank" rel="noopener">Dr Nibras Abdullah</a></strong><br /><strong>ISSN (online)</strong>: <a href="" target="_blank" rel="noopener">2709-5908</a><br /><strong>Frequency:</strong> Semiannual</p> en-US Tue, 13 Sep 2022 14:48:50 +0000 OJS 60 E2IDS: An Enhanced Intelligent Intrusion Detection System Based On Decision Tree Algorithm <p>Due to the increased usage of the Internet of Things and heterogeneous distributed devices, the development of effective and reliable intrusion detection systems (IDS) has become more critical. The massive volume of data with various dimensions and security features, on the other hand, can influence detection accuracy and raise the computation complexity of these systems. Fortunately, Artificial Intelligence (AI) has recently attracted a lot of attention, and it is now a principal component of these systems. This work presents an enhanced intelligent intrusion detection model (E2IDS) to detect state of the art known cyberattacks. The model design is Decision Tree (DT) algorithm-based, with an approach to data balancing since the data set used is highly unbalanced and one more approach for feature selection. Furthermore, accuracy, recall and F-score are selected as the performance evaluation metrics. The experimental results show that our E2IDS not only overcomes the benchmark work but also reduces the complexity of the computing process.</p> Mohamed Aly Bouke, Azizol Abdullah, Sameer Hamoud ALshatebi, Mohd Taufik Abdullah Copyright (c) 2022 Journal of Applied Artificial Intelligence Thu, 30 Jun 2022 00:00:00 +0000 The Classification of Flower Features using Artificial Intelligence from Ganga Choti Bagh Azad Kashmir <p>This research utilized surface and shading highlights for blossom grouping. Standard data set of blossoms have utilized for tests. The pre-handling like clamor expulsion and division for end of foundation are applied on input pictures. Surface and shading highlights are separated from the portioned pictures. Surface component is removed utilizing GLCM (Gray Level Co-event Matrix) technique and shading highlight is separated utilizing Color second. For arrangement, neural organization classifier is utilized. The general precision of the framework is 96.0%.</p> Sajid Ali Khan, Ishtiaq Afzal Copyright (c) 2022 Journal of Applied Artificial Intelligence Thu, 30 Jun 2022 00:00:00 +0000 Obesity prediction using machine learning techniques <p>Currently, safeguarding the community is vital in terms of finding solution to health related problems which can be achieved through medical research using the advent of technology. Obesity has become worldwide health concern as it is becoming a threat to the future. It is the most common health problems all over the world. Thousands of diseases as well as risks and death are associated to it. An early prediction of a disease will help both doctors and patients to act and minimize if not total eradication of the root cause or work on preventing the disease symptom from further deterioration. Going through patient’s medical history is one of the methods of identifying a disease which most time consuming as processing manually and it comes with an error-prone analyses and expense. Therefore, there is need to scientifically develop a predicting model of the occurrence of the disease or its existence using an automated technique as it is becoming a need of the day. In this research work, we used machine learning techniques on a public clinical available dataset to predict obesity status using different machine learning algorithms. Five machine learning algorithms were applied. Gboost Classifier, Random Forest Classifier, Decision Tree Classifier, K-Nearest Neighbor and Support Vector Machine and the model has shown promising results with as Gboost classifier achieves the highest accuracy of 99.05% as compared to other classifiers. Meanwhile, the K-Nearest Neighbor gave the relatively strong accuracy of 95.74%.</p> Fati Musa, Dr., Professor Copyright (c) 2022 Journal of Applied Artificial Intelligence Thu, 30 Jun 2022 00:00:00 +0000 An Access Control System for Covid19 Using Computer Vision and Deep Learning Techniques: A Aystematic Review <p><em>After the emergence of the Coronavirus disease (Covid19) in December, 2019 the virus was confirmed by the World Health Organization (WHO) to be a dangerous virus that spread through airborne and droplets. One of the most effective way of preventing the spread of this virus is the use of facemask in public places such as banks, shopping mall, schools, offices and the likes. For this reasons people are advised to use facemask whenever they go out for their daily activities. However, some people have refused to wear the facemask in public places, thereby increasing the rate at which the virus spreads. Hence, there is a need to design an access control system for use in public places to grant access to people complying with the facemask regulations or deny access to those faulting them. Literature has shown that the use of computer vision and deep learning technology can play important role in the deployment of such access control system for face detection and facemask detection. The computer vision and deep learning techniques used in face recognition and facemask detection are describes in this systematic literature review.<br></em></p> Taiwo Abiodun, Emeka Ogbuju, Francisca Oladipo Copyright (c) 2022 Journal of Applied Artificial Intelligence Thu, 30 Jun 2022 00:00:00 +0000 Developing a Model for Predicting Lung Cancer Using Variational Quantum-Classical Algorithm: A Survey <p>There are real life problems that currently proved hard for classical computers (even the best of supercomputers) to solve-the so called computationally intractable problems. Computers and computing devices are limited, by virtue of the fact that they cannot perform certain complex problems. For example, modern cryptography assumes that it is impossible to factorize a large number as the complexity of solving this problem increases exponentially. Even the best supercomputers of today cannot sufficiently find the prime factors of a number with 700-1,000 digits. With quantum computing, however, Shor’s algorithm proved that in principle, a quantum computer can be used to break the security of conventional cryptosystems. Quantum computing also promises exponential improvements for many optimization problems. Lov Grover algorithm was also designed to search for an element in unstructured database. Effort is currently on to leverage quantum computing and quantum mechanical phenomena to tackle complex machine learning problems. Using machine learning algorithm to solve problems is common place. What is however new is using quantum machine learning algorithm to solve problems such as detecting, classifying and predicting disease such as lung cancer. In this work, we highlight the limitations of classical computers to solve certain problems and then propose a hybrid model called the variational quantum-classical algorithm to predict the possibility of a patient developing lung cancer given a set of features which are spelt out in the dataset. The dataset is initially pre-processed, and made to pass through a Parameterized Quantum Circuit (PQC) and then post-processed. Finally, the output of the post-processing phase is used for prediction of lung cancer.</p> Philip Adebayo; Frederick Basaky , Edgar Osaghae Copyright (c) 2022 Journal of Applied Artificial Intelligence Thu, 30 Jun 2022 00:00:00 +0000 A Deep Learning Approach-FDNN: Forest Deep Neural Network to Predict Cow’s Parturition Date <p>In this prospective study, we integrate neural network architecture with a supervised random forest feature detector to develop a new model named Forest Deep Neural Network (FDNN) to predict daily and hourly calving time of cattle. To overcome challenges of prediction problems like data sparsity along with unknown correlation structures, we incorporate the benefits of random forest (RF) with a deep neural network (DNN) to predict the daily and hourly calving time of cattle, which is nobody done yet. For this study, we take a total of 45 Holstein-Friesian cows (27 primiparous and 18 multiparous) for collecting physical activities. Using IceQube and HR Tag technologies, we record daily and hourly lying time, the number of stand-ups, ruminating time, the number of steps, and the number of head moves of cattle from 15 days before the actual calving time. Different statistical analysis has been carried out over the daily and hourly-captured data, and we have found that these monitored physical activities change very significantly over time. We have applied five classifiers such as FDNN, DNN, RF, decision tree (DT), and support vector machine (SVM) over the daily and hourly datasets. Hyperparameter optimization has been conducted over the classifiers using Grid Search approach to filter out the optimal parameter configurations. With optimal parameters, our developed model overpowered the other four classifiers in terms of accuracy, sensitivity, specificity, and ROC score (ACC= 98.38, SN=88.19, SP=98.41, and ROC=99 of predicting daily calving time; ACC=97.93, SN=97.40, SP=89.42, and ROC=98 of predicting hourly calving time).</p> Md Motiur Rahman, Eaftekhar Ahmed Rana, Nafisa Nawar Tamzi, Indrajit Saha, Fazlul Hasan Siddiqui Copyright (c) 2022 Journal of Applied Artificial Intelligence Thu, 30 Jun 2022 00:00:00 +0000 The Cancer Detection using Deep Learning: A Survey <p>Cancer refers to a group of diseases that are defined by abnormal cell proliferation and can spread to other parts of the body. Pancreatic cancer originates in the organ behind the lower stomach called the pancreas. The pancreas secretes digestive enzymes as well as hormones that help regulate sugar metabolism. Pancreas cancer is usually discovered late, spreads quickly, and has a poor prognosis. Cancer-specific symptoms may not appear until later stages<em>, </em>and there are no reliable screening techniques to identify high-risk patients. The manual method of checking whether a patient has Pancreatic cancer or not can be time-consuming and it can be tedious because it required experience in Radiologist interpretation; to avoid poor decisions by giving wrong diagnoses to patients. One of the leading causes of cancer death is pancreatic cancer; however, if found early enough, it can be treated<em>. </em>To solve this issue, an Artificial Neural Network (ANN) has been developed, trained, and tested using an abdominal Computed Tomography (CT) scan images dataset to detect pancreatic tumors by many authors. To detect the tumor, it employs image processing techniques of a convolution neural network to detect the tumorous area in the image after it has been pre-processed. It was observed that the technique gives better accuracy in tumor detection.</p> <p>&nbsp;</p> Ibrahim Shuaib Odunlami, Dr. Edgar Osaghae, Dr. Basaky Frederick Copyright (c) 2022 Journal of Applied Artificial Intelligence Thu, 30 Jun 2022 00:00:00 +0000