International Journal of Computational Intelligence and Applications

In this modern world, mobile devices have been paired with the cloud environment to scale the voluminous amount of generated data. The implementation comes at the cost of privacy as proprietary data can be stolen in transit to the cloud, or victims’ phones can be seized along with synced data from cloud. The attacker can gain access to the phone through shoulder surfing, or even spoofing attacks. Our approach is to mitigate this issue by proposing an active cloud authentication framework using touch biometric pattern. To the best of our knowledge, active cloud authentication using touch dynamics for mobile cloud computing has not been explored in the literature. This research creates a proof of concept that will lead into a simulated cloud framework for active authentication. Given the amount of data captured by the mobile device from user activity, it can be a computationally intensive process for the mobile device to handle with such limited resources. To solve this, we simulated a post-transmission process of data to the cloud so that we could implement the authentication process within the cloud. We evaluated the touch data using traditional machine learning algorithms, such as Random Forest (RF), Support Vector Machine (SVM), and also using a deep learning classifier, the Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) algorithms. The novelty of this work is two-fold. First, we develop a distributed tensorflow framework for cloud authentication using touch biometric pattern. This framework helps alleviate the drawback of the computationally intensive recognition of the substantial amount of raw data from the user. Second, we apply the RF, SVM, and a deep learning classifier, the LSTM-RNN, on the touch data to evaluate the performance of the proposed authentication scheme. The proposed approach shows a promising performance with an accuracy of 99.0361% using RF on the distributed tensorflow framework.

The ubiquitous presence of smart phones and other hand-held computing devices has resulted in a growing feasibility to utilize them as computing resources. However, these mobile devices are constrained in battery and may not possess adequate capability for computationally intensive tasks. Cloud computing allows mobile devices to address their inherent challenges by making it possible to offload computation, completely or partially, to powerful cloud servers. This enables mobile devices to act as compute resources; though, it also results in cost of using cloud servers as well as communication cost involved in offloading. The paper models the computation offloading problem as an optimization problem and makes use of nature-inspired algorithms for deciding whether a task should be executed locally on a mobile device or offloaded to the cloud. The study was performed over four algorithms, namely Genetic Algorithm (GA), Differential Evolution (DE), Particle Swarm Optimization (PSO) and Shuffled Frog Leaping Algorithm (SFLA). Experimental analysis revealed that these algorithms outperform exhaustive search technique by providing a near optimal solution in a reasonable time even for large workflows. Results also establish that GA outperforms DE, PSO and SFLA by around 45%, 65% and 42%, respectively by reducing an application’s overall execution cost.

Cloud computing is the advancing technology that aims at providing services to the customers with the available resources in the cloud environment. When the multiple users request service from the cloud server, there is a need of the proper scheduling of the resources to attain good customer satisfaction. Therefore, this paper proposes the Regressive Whale Optimization (RWO) algorithm for workflow scheduling in the cloud computing environment. RWO is the meta-heuristic algorithm, which schedules the task depending on a fitness function. Here, the fitness function is defined based on three major constraints, such as resource utilization, energy, and the Quality of Service (QoS). Therefore, the proposed task scheduling requires minimum time and cost for executing the task in the virtual machines. The performance of the proposed method is analyzed using the four experimental setups, and the results of the analysis prove that the proposed multi-objective task scheduling method performs well than the existing methods. The evaluation metrics considered for analyzing the performance of the proposed workflow scheduling method are resource utilization, energy, cost, and time. Resource utilization is the process of making the most of the resources available for performing tasks. Energy is the quantitative property of the resource to perform tasks. The proposed method attains the maximum resource utilization at a rate of 0.0334, minimal rate of energy, scheduling cost, and time as 0.2291, 0.0181, and 0.0007, respectively.

Movement data can be collected and used to add new security features and functionality to users’ mobile devices. Measuring a user’s movement using mobile devices allows for the use of behavioral biometrics. This assessment could introduce a shift in our current methods for securing mobile devices: instead of physical attributes like fingerprints or our face, the use of behavioral attributes like the way we walk or perform some personal activity. In this paper, an empirical evaluation of different classification techniques is conducted on user movement data. The datasets used in this empirical evaluation contain accelerometer data that were collected during various experiments from several mobile devices, including smartphones, smart watches, and other accelerometer sensors. We aggregated the user movement data and provided them as input into five traditional machine learning algorithms. The classification performances of the data were compared with a deep learning technique, the Long Short-Term Memory-Recurrent Neural Network (LSTM-RNN). The LSTM-RNN achieved its highest accuracy at 89% compared to 97% from a traditional machine learning algorithm, specifically the k-Nearest Neighbor (k-NN) algorithm on wrist-worn accelerometer data, thus showing the LSTM to be a less viable option.

Model Transformation (MT) has led the researchers to concentrate more in the field of software engineering. MT focuses mainly on transforming the input model to the target model to make it easily understandable. For the transformation, using optimal rules among a set of rules makes the design simpler. This paper proposes an algorithm, namely Whale Optimization integrated Adaptive Dragonfly (WOADF) algorithm, which integrates Adaptive Dragonfly (ADF) algorithm and Whale Optimization Algorithm (WOA), for transforming class diagrams (CLDs) to Relational Schema (RS). Further, the UML CLD is transformed into the RS model based on specific rules incorporated by the proposed WOADF algorithm. The fitness function of the proposed model is evaluated to select the optimal rule, by including the test cases to evaluate the optimal blocks. Then, the optimal blocks obtained from the proposed WOADF algorithm are used for achieving the transformation from CLD to the RS model. The effectiveness of the proposed WOADF algorithm is checked with Automatic Correctness (AC) and fitness values and is evaluated to be the best when compared to other existing techniques with maximum AC value measured to be 0.812 and fitness value to be 0.897, respectively.

Diversity is a key component for building a successful ensemble classifier. One approach to diversifying the base classifiers in an ensemble classifier is to diversify the data they are trained on. While sampling approaches such as bagging have been used for this task in the past, we argue that since they maintain the global distribution, they do not create diversity. Instead, we make a principled argument for the use of $k$-means clustering to create diversity. Expanding on previous work, we observe that when creating multiple clusterings with multiple $k$ values, there is a risk of different clusterings discovering the same clusters, which would in turn train the same base classifiers. This would bias the ensemble voting process. We propose a new approach that uses the Jaccard Index to detect and remove similar clusters before training the base classifiers, not only saving computation time, but also reducing classification error by removing repeated votes. We empirically demonstrate the effectiveness of the proposed approach compared to the state of the art on 19 UCI benchmark datasets.