The Simple Human Learning Optimization (SHLO) algorithm, drawing inspiration from human learning mechanisms, is a robust metaheuristic. This study introduces three tailored variations of the SHLO algorithm for optimizing the 0/1 Knapsack Problem. While these variants utilize the same SHLO operators for learning, their distinctiveness lies in how they generate new solutions, specifically in the selection of learning operators and bits for updating. To assess their efficacy, comprehensive tests were conducted using four benchmark datasets for the 0/1 Knapsack Problem. The results, encompassing 42 instances from three datasets, reveal that both SHLO and its proposed variations yield optimal solutions for small instances of the problem. Notably, for datasets 2 and 3, the performance of SHLO variations 2 and 3 outpaces that of the Harmony Search Algorithm and the Flower Pollination Algorithm. In particular, Variation 3 demonstrates superior performance compared to SHLO and variations 1 and 2 concerning optimal solution quality, success rate, convergence speed, and execution time. This makes Variation 3 notably more efficient than other approaches for both small and large instances of the 0/1 Knapsack Problem. Impressively, Variation 3 exhibits a remarkable 14x speed improvement over SHLO for large datasets.

Static analysis and detection of malware is a crucial phase for handling security threats. Most researchers stated that the problem with the static analysis is an imbalance in the dataset, causing invalid result metrics. It requires more time for extracting features from the raw binaries, and methods like neural networks require more time for the training. Considering these problems, we proposed a model capable of building a feature set from the dataset and classifying static PE files efficiently.  The research work was conducted to emphasize the importance of feature extraction rather than focusing on model building. The well-extracted features help to provide better results when fed to neural networks with minimal numbers of layers. Using minimum layers will enhance the performance of the model and take fewer resources and time for the processing and evaluation. In this research work, EMBER datasets published by Endgame Inc. containing PE file information are used. Feature extraction, data standardization, and data cleaning techniques are performed to handle the imbalance and impurities from the dataset. Later the extracted features were scaled into a standard form to avoid the problems related to range variations. A total of 2381 features are extracted and pre-processed from both the 2017 and 2018 datasets, respectively. 

The pre-processed data is then given to a deep learning model for training. The deep learning model created using dense and dropout layers to minimize the resource strain on the model and deliver more accurate results in less amount of time. The results obtained during experimentation for EMBER v2017 and v2018 datasets are 97.53% and 94.09%, respectively. The model is trained for ten epochs with a learning rate of 0.01, and it took 4 minutes/epoch, which is one minute lesser than the Decision Tree model. In terms of precision metrics, our model achieved 98.85%, which is 1.85% more as compared to the existing models. 

Predicting academic performance of the student is crucial task as it depends on various factors. To perform such predictions the machine learning and data mining algorithms are useful. This paper presents investigation of application of C5.0, J48, CART, Naïve Bayes (NB), K-Nearest Neighbour (KNN), Random Forest and Support Vector Machine for prediction of students’ performance. Three datasets from school level, college level and e-learning platform with varying input parameters are considered for comparison between C5.0, NB, J48, Multilayer Perceptron (MLP), PART, Random Forest, BayesNet, and Artificial Neural Network (ANN). Paper presents comparative results of C5.0, J48, CART, NB, KNN, Random forest and SVM on changing tuning parameters. The performance of these techniques is tested on three different datasets. Results show that the performances of Random forest and C5.0 are better than J48, CART, NB, KNN, and SVM.

Malware is a threat to people in the cyber world. It steals personal information and harms computer systems. Various developers and information security specialists around the globe continuously work on strategies for detecting malware. From the last few years, machine learning has been investigated by many researchers for malware classification. The existing solutions require more computing resources and are not efficient for datasets with large numbers of samples. Using existing feature extractors for extracting features of images consumes more resources. This paper presents a Convolutional Neural Network model with pre-processing and augmentation techniques for the classification of malware gray-scale images. An investigation is conducted on the Malimg dataset, which contains 9339 gray-scale images. The dataset created from binaries of malware belongs to 25 different families. To create a precise approach and considering the success of deep learning techniques for the classification of raising the volume of newly created malware, we proposed CNN and Hybrid CNN+SVM model. The CNN is used as an automatic feature extractor that uses less resource and time as compared to the existing methods. Proposed CNN model shows (98.03%) accuracy which is better than other existing CNN models namely VGG16 (96.96%), ResNet50 (97.11%) InceptionV3 (97.22%), Xception (97.56%). The execution time of the proposed CNN model is significantly reduced than other existing CNN models. The proposed CNN model is hybridized with a support vector machine. Instead of using Softmax as activation function, SVM performs the task of classifying the malware based on features extracted by the CNN model. The proposed fine-tuned model of CNN produces a well-selected features vector of 256 Neurons with the FC layer, which is input to SVM. Linear SVC kernel transforms the binary SVM classifier into multi-class SVM, which classifies the malware samples using the one-against-one method and delivers the accuracy of 99.59%.

This paper presents an investigation of the convolutional neural network (CNN) with Word2Vec word embedding technique for text classification. Performance of CNN is tested on seven benchmark datasets with a different number of classes, training and testing samples. Test classification results obtained from proposed CNN are compared with results of CNN models and other classifiers reported in the literature. Investigation shows that CNN models are better suitable for text classification than other techniques. The main objective of the paper is to identify best-fitted parameter values batch size, epochs, activation function, dropout rates and feature maps values. Results of proposed CNN are better than many other classification techniques reported in the literature for Yelp Review Polarity dataset and Amazon Review Polarity dataset. For all the seven datasets, accuracy obtained by proposed CNN is close to the best-known results from the literature.

Primary concern of any cloud provider is to improve resource utilization and minimize cost of service. Different mapping relations among virtual machines and physical machines effect on resource utilization, load balancing and cost for cloud data center. Paper addresses the virtual machine placement as optimization problem with resource constraints on CPU, memory and bandwidth. In experimentations, datasets are formed using random data generator. Paper presents random fit algorithm, best fit algorithm based on resource wastage and an evolutionary algorithm- Differential Evolution. Paper presents results of Differential Evolution algorithm with three different mutation approaches. Results show that Differential Evolution algorithm with DE/best/2 mutation operator works efficient than basic DE, best fit and random fit algorithms.

With increasing use of computers, information and communication technologies, some software technologies products become part of everyday life. Many reports shows that use of desktop and mobile operating systems, search engines, web browsers, web servers and programming languages are increasing rapidly. This paper focuses on forecasting growth pattern of selected software technology product families using market share as indicator. Results of four growth curve methods namely Logistic, Gompertz, Log Logistic and Mono-Molecular are compared using MAD and RMSE error measures. For the period under consideration, majority software product families follow increasing / decreasing growth pattern. Results indicate that industry of respective technology product remain dominated by few providers for year 2025. Monopoly or oligopoly market structure will lead to long increasing period for the top providers.

Computational paradigm has been revolving round cloud computing and its offshoots for some time and till we see a breakout resulting in a breakthrough technology driven by advances in microelectronics and material technology. Till we experience a radically efficient technology for computation it is worth juxtaposing the virtues of cloud computing and market’s longing for offering cost and quality arbitrage to the marketplace. Integration of cloud computing in enterprises has the potential to influence the way business gets carried out by them in the market place. Different reports show that demand for cloud computing products and processes is in an upward growth trajectory. This paper identified the characteristics, drivers and constraints of cloud computing which influence its adaptation and integration in enterprises. We are also examining India specific opportunities and threats of cloud computing tools and cloud driven practices in the context of fierce competition among enterprises to remain competitive in the marketplace by reducing software licensing fees, cost of capital to acquire digital systems and cost of maintenances.
New directions in cloud computing are analyzed by using Gartner strategic technologies and trend in research publications. Paper focuses on exploring the research issues which are categorized into technical and business in nature for understanding the evolving fortunes of cloud computing. Number of papers published in IEEE is an indication of the popularity and relevance of the continued research initiatives happening in the area. It is also noticed that that very few researchers are attempting to understand the possibility of remodeling business processes leveraging the new found computational paradigm.