Rapid developments in technology around the world require continuous efforts in academia to develop innovative solutions to enhance the learning of basic and advanced programming concepts. Educators understand the value of preparing highly skilled programmers to join the industry, and this puts a responsibility to develop and enhance teaching techniques in order to get better results, especially in introductory courses where novice programmers face difficulties in understanding basic programming concepts. Serious games were proven to be effective, motivational and beneficial for novice programmers to support them during their learning journey. In this paper, we investigate the issues that students face when learning arrays and based on that, we design and implement Space Geeks, a serious game targeted at teaching arrays for novice programmers. We discuss the design principles used to develop Space Geeks, and we test and evaluate the game in an educational environment. Our findings show that Space Geeks, our developed serious game, is promising to help novice programmers improve in learning basic programming concepts, due to its ease of use and ease of understanding.

Predicting defect-prone software components can play a significant role in allocating relevant testing resources to fault-prone modules and hence increasing the business value of software projects. Most of the current software defect prediction studies utilize traditional supervised machine learning algorithms to predict defects in software applications. The software datasets utilized in such studies are imbalanced and therefore the reported results cannot be reliably used to judge their performance. Moreover, it is important to explain the output of machine learning models employed in fault-predication techniques to determine the contribution of each utilized feature to the model output. In this paper, we propose a new framework for predicting software defects utilizing eleven machine learning classifiers over twelve different datasets. For feature selection, we employ four different nature-inspired search algorithms, namely, particle swarm optimization, genetic algorithm, harmony algorithm, and ant colony optimization. Moreover, we make use of the synthetic minority oversampling technique (SMOTE) to address the problem of data imbalance. Furthermore, we utilize the Shapley additive explanation model for highlighting the highest determinative features. The obtained results demonstrate that gradient boosting, stochastic gradient boosting, decision trees, and categorical boosting outperform others tested model with over 90% accuracy and ROC-AUC. Additionally, we found that the ant colony optimization technique outperforms the other tested feature extraction techniques.

Developing an effective classification model in the medical field is challenging due to limited datasets. To address this issue, this study proposes using a generative adversarial network (GAN) as a data-augmentation technique. The research aims to enhance the classifier's generalization performance, stability, and precision through the generation of synthetic data that closely resemble real data. We employed feature selection and applied five classification algorithms to thirteen benchmark medical datasets, augmented using the least-square GAN (LS-GAN). Evaluation of the generated samples using different ratios of augmented data showed that the support vector machine model outperforms other methods with larger samples. The proposed data augmentation approach using a GAN presents a promising solution for enhancing the performance of classification models in the healthcare field.

: The failure rates in introductory programming courses still shows that there is a continuous need in research to investigate and propose new methods and techniques of teaching introductory to programming courses to attract more people to the information technology field and build more skilled programmers from their first course. This study investigates students levels in multiple topics in introduction to programming, then, proposes a new science fiction themed game called Space Geeks. The game is initially designed to target arrays, and is extendable to cover more programming concepts. The design of this games helps students enhance their coding skills, gives motivation using game features, and helps them understand the arrays concept by visualisation and graphics. This work will open more insights to focus on further introductory topics such as arrays since that there has been other work to focus on other topics such as variables, input/output, and problem solving.

Breast cancer is one of the leading causes of death among women worldwide. Many methods have been proposed for automatic breast cancer diagnosis. One popular technique utilizes a classification-based association called Association Classification (AC). However, most AC algorithms suffer from considerable numbers of generated rules. In addition, irrelevant and redundant features may affect the measures used in the rule evaluation process. As such, they could severely affect the accuracy rates in rule mining. Feature selection identifies the optimal subset of features representing a problem in almost the same context as the original features. Feature selection is a critical preprocessing step for data mining as it tends to increase the prediction speed and accuracy of the classification model and thereby increase performance. In this research, an ensemble filter feature selection method and a wrapper feature selection algorithm in conjunction with the AC approach are proposed for undertaking breast cancer classification. The proposed approach employs optimal discriminative feature subsets for breast cancer prediction. Specifically, it first utilizes a new bootstrapping search strategy that effectively selects the most optimal feature subset that considers the overall weighted average of the relative frequency-based evaluation criteria function. We employ a Weighted Average of Relative Frequency (WARF)-based filter method to compute discriminative features from the ensemble results. The adopted filter algorithms utilize the prioritization ranking technique for selecting a subset of informative features that are used for subsequent AC-based disease classification. Another wrapper feature selection method, namely a hybrid Particle Swarm Optimization (PSO)-WARF filter-based wrapper method, is also proposed for feature selection. Two classification models, i.e., WARF-Predictive Classification Based on Associations (PCBA) and hybrid PSO-WARF-PCBA, are subsequently constructed based on the above filter and wrapper-based feature selection methods for breast cancer prediction. The proposed approach of the two models is evaluated using UCI breast cancer datasets. The empirical results indicate that our models achieve impressive performance and outperform a variety of well-known benchmark AC algorithms consistently for breast cancer diagnosis.

Nowadays, smartphones are an essential part of people’s lives and a sign of a contemporary world. Even that smartphones bring numerous facilities, but they form a wide gate into personal and financial information. In recent years, a substantial increasing rate of malicious efforts to attack smartphone vulnerabilities has been noticed. A serious common threat is the ransomware attack, which locks the system or users’ data and demands a ransom for the purpose of decrypting or unlocking them. In this article, a framework based on metaheuristic and machine learning is proposed for the detection of Android ransomware. Raw sequences of the applications API calls and permissions were extracted to capture the ransomware pattern of behaviors and build the detection framework. Then, a hybrid of the Salp Swarm Algorithm (SSA) and Kernel Extreme Learning Machine (KELM) is modeled, where the SSA is used to search for the best subset of features and optimize the KELM hyperparameters. Meanwhile, the KELM algorithm is utilized for the identification and classification of the apps into benign or ransomware. The performance of the proposed (SSA-KELM) exhibits noteworthy advantages based on several evaluation measures, including accuracy, recall, true negative rate, precision, g-mean, and area under the curve of a value of 98%, and a ratio of 2% of false positive rate. In addition, it has a competitive convergence ability. Hence, the proposed SSA-KELM algorithm represents a promising approach for efficient ransomware detection.

Extreme Learning Machine (ELM) is a learning algorithm proposed recently to train single hidden layer feed forward networks (SLFN). It has many attractive properties that include better generalization performance and very fast learning. ELM starts by assigning random values to the input weights and hidden biases and then in one step it determines the output weights using Moore-Penrose generalized inverse. Despite the aforementioned advantages, ELM performance might be affected by the random initialization of weights and biases or by the large generated network which might contain unnecessary number of neurons. In order to increase the generalization performance and to produce more compact networks, a hybrid model that combines ELM with competitive swarm optimizer (CSO) is proposed in this paper. The proposed model (CSONN-ELM) optimizes the weights and biases and dynamically determines the most appropriate number of neurons. To evaluate the effectiveness of the CSONN-ELM, it is experimented using 23 benchmark datasets, and compared to a set of static rules extracted from literature that are used to determine the number of neurons of SLFN. Moreover, it is compared to two dynamic methods that are used to enhance the performance of ELM, that are Optimally pruned ELM (OP-ELM) and metaheuristic based ELMs (Particle Swarm Optimization-ELM and Differential Evolution-ELM). The obtained results show that the proposed method enhances the generalization performance of ELM and overcomes the static and dynamic methods.

A class decomposition is one of the possible solutions and the most important factors of success for the improvement of classification performance. The idea is to transform a dataset by categorizing each class label into groups or clusters. Thus, the transformation is done concerning data characteristics and similarities. This paper proposed a hybrid model for a class decomposition by the integration of gap statistic, k-means clustering algorithm, and Naive Bayes classifier. The model is based on clustering validity using gap statistic for enhancing the classifier performance. The model works by dividing each dataset into several subsets regarding its class labels. After that, the clustering validity using gap statistic is employed for estimating the optimal number of clusters for each subset that belong to a particular class label. The estimated number of clusters is used then as an input parameter for the k-means clustering algorithm for relabeling the data objects with a new class label in each subset. Every data object is allocated to each of the clusters generated by the k-means clustering algorithm, which consider it as the new class label. The proposed model integrates the class decomposition approach with Naive Bayes classifier to compare the performance of the proposed model under several classification measures. The model is validated and evaluated by employing different real-world datasets collected from the UCI machine learning repository. The experimental results show that a significant improvement in classification accuracy and F-measure when the class decomposition is applied. Also, the experiments indicate that using a class decomposition is not appropriate for all datasets.

Software defect prediction is a promising approach aiming to improve software quality and testing efficiency by providing timely identification of defect-prone software modules before the actual testing process begins. These prediction results help software developers to effectively allocate their limited resources to the modules that are more prone to defects. In this paper, a hybrid heterogeneous ensemble approach is proposed for the purpose of software defect prediction. Heterogeneous ensembles consist of set of classifiers of different learning base methods in which each of them has its own strengths and weaknesses. The main idea of the proposed approach is to develop expert and robust heterogeneous classification models. Two versions of the proposed approach are developed and experimented. The first is based on simple classifiers, and the second is based on ensemble ones. For evaluation, 21 publicly available benchmark datasets are selected to conduct the experiments and benchmark the proposed approach. The evaluation results show the superiority of the ensemble version over other well-regarded basic and ensemble classifiers.

Random Weight Networks have been extensively used in many applications in the last decade because it has many strong features such as fast learning and good generalization performance. Most of the traditional training techniques for Random Weight Networks randomly select the connection weights and hidden biases and thus suffer from local optima stagnation and degraded convergence. The literature shows that stochastic population-based optimization techniques are well regarded and reliable alternative for Random Weight Networks optimization because of high local optima avoidance and flexibility. In addition, many practitioners and non-expert users find it difficult to set the other parameters of the network like the number of hidden neurons, the activation function, and the regularization factor. In this paper, an approach for training Random Weight Networks is proposed based on a recent variant of particle swarm optimization called competitive swarm optimization. Unlike most of Random Weight Networks training techniques, which are used to optimize only the input weights and hidden biases, the proposed approach will automatically tune the weights, biases, the number of hidden neurons, and regularization factor as well as the embedded activation function in the network, simultaneously. The goal is to help users to effectively identify a proper structure and hyperparameter values to their applications while obtaining reasonable prediction results. Twenty benchmark classification datasets are used to compare the proposed approach with different types of basic and hybrid Random Weight Network-based models. The experimental results on the benchmark datasets show that the reasonable classification results can be obtained by automatically tuning the hyperparameters using the proposed approach.

Extreme learning machine (ELM) is a novel and recent machine learning algorithm which was first proposed by Huang et al. (Proceedings of 2004 IEEE international joint conference on, pp 985–990, 2004). Over the last decade, ELM has gained a remarkable research interest with tremendous audiences from different domains in a short period of time due to its impressive characteristics over other single hidden-layer feedforward neural networks. Although ELM enjoys powerful advantages, it still has some potential weaknesses like performance sensitivity to the initial condition of the input weights, number of hidden neurons, and the selection of activation functions. In order to overcome the limitations of classical ELM, many metaheuristic algorithms including the evolutionary algorithms, swarm intelligence, memetic and trajectory algorithms have been proposed for optimizing the different components of ELM by researchers aiming to improve the generalization performance of ELM networks for different types of complex problems and applications. Therefore our review paper intent to conduct a deep study of the important aspects of applying metaheuristic algorithms for optimizing ELM networks. Three main streams of research lines are identified: the optimization of input weights and hidden biases, selection of hidden neurons, and optimization of activation functions. Furthermore, this paper will discuss a wide spectrum of applications of metaheuristic-based ELM models. We will highlight the strengths of these models and the improvements that are suggested in the literature to overcome their weaknesses. We touch upon several interesting and challenging open issues in optimizing ELM using metaheuristics.

NoSQL database systems have emerged and developed at an accelerating rate in the last years. Attractive properties such as scalability and performance, which are needed by many applications today, contributed to their increasing popularity. Time is very important aspect in many applications. Many NoSQL database systems do not offer built in management for temporal properties. In this paper, we discuss how we can embed temporal properties in NoSQL databases. We review and differentiate between the most popular NoSQL stores. Moreover, we propose various solutions to modify data models for embedding bitemporal properties in two of the most popular categories of NoSQL databases (Key-value stores and Column stores). In addition, we give examples of how to represent bitemporal properties using Redis Key-value store and Cassandra column oriented store. This work can be used as basis for designing and implementing temporal operators and temporal data management in NoSQL databases.

Feature selection (FS) is considered as one of the most common and challenging tasks in Machine Learning. FS can be considered as an optimization problem that requires an efficient optimization algorithm to find its optimal set of features. This paper proposes a wrapper FS method that combines a time-varying number of leaders and followers binary Salp Swarm Algorithm (called TVBSSA) with Random Weight Network (RWN). In this approach, the TVBSSA is used as a search strategy, while RWN is utilized as an induction algorithm. The objective function is formulated in a manner to aggregate three objectives: maximizing the classification accuracy, maximizing the reduction rate of the selected features, and minimizing the complexity of generated RWN models. To assess the performance of the proposed approach, 20 well-known UCI datasets and a number of existing FS methods are employed. The comparative results show the ability of the proposed approach in outperforming similar algorithms in the literature and its merits to be used in systems that require FS. (C) 2019 Elsevier Ltd. All rights reserved.

Extreme Learning Machine (ELM) is swiftly gaining popularity as a way to train Single hidden Layer Feed forward Networks (SLFN) for its attractive properties. ELM is a fast learning network with remarkable generalization performance. Although ELM generally can outperform traditional gradient descent-based algorithms such as Backpropagation, its performance can be highly affected by the random selection of the input weights and hidden biases of SLFN. Moreover, ELM networks tend to have more hidden neurons due to this random selection. In this paper, we propose a new model that uses Competitive Swarm Optimizer (CSO) to optimize the values of the input weights and hidden neurons of ELM. Two versions of ELM are considered: the classical ELM and the regularized version. The goal of the model is to increase the generalization performance, stabilize the classifier, and to produce more compact networks by reducing the number of neurons in the hidden layer. The proposed model is experimented based on 15 medical classification problems. Experimental results demonstrate that the proposed model can achieve better generalization performance with smaller number of hidden neurons and with higher stability. In addition, it requires much less training time compared to other metaheuristic based ELMs. (C) 2018 Elsevier Ltd. All rights reserved.

The huge growth of the usage of internet increases the need to transfer and save multimedia files. Mammogram images are part of these files that have large image size with high resolution. The compression of these images is used to reduce the size of the files without degrading the quality especially the suspicious regions in the mammogram images. Reduction of the size of these images gives more chance to store more images and minimize the cost of transmission in the case of exchanging information between radiologists. Many techniques exists in the literature to solve the loss of information in images. In this paper, two types of compression transformations are used which are Singular Value Decomposition (SVD) that transforms the image into series of Eigen vectors that depends on the dimensions of the image and Discrete Cosine Transform (DCT) that covert the image from spatial domain into frequency domain. In this paper, the Computer Aided Diagnosis (CAD) system is implemented to evaluate the microcalcification appearance in mammogram images after using the two transformation compressions. The performance of both transformations SVD and DCT is subjectively compared by a radiologist. As a result, the DCT algorithm can effectively reduce the size of the mammogram images by 65% with high quality microcalcification appearance regions.

Minimum vertex cover (MVC) is a well-known NP-Complete optimization problem. The importance of MVC in theory and practical comes from the wide range of its applications. This paper describes a polynomial time greedy algorithm to find near optimal solutions for MVC. The new algorithm NMVAS is a modification of already existed algorithm called MVAS which uses the same principle of selecting candidate from the neighborhood of the vertex with a modification in the selection procedure. A comparative study is conducted between the NMVAS and MVAS which shows that the proposed algorithm NMVSA provides better or equal results in the most cases of the underlying data sets which leads to a better average approximation ratio of NMVAS. NMVAS inherits the simplicity of the original algorithm.