Particle Swarm Optimization, a population based optimization technique has been used in wide number of application areas to solve optimization problems. This paper presents a new algorithm for initialization of population in standard PSO called Opposition based Particle Swarm Optimization (O-PSO). The performance of proposed initialization algorithm is compared with the existing PSO variants on several benchmark functions and the experimental results reveal that O-PSO outperforms existing approaches to a large extent.

Internet of things (IoT) and machine learning based systems incorporating smart wearable technology are rapidly evolving to monitor and manage healthcare and physical activities. This paper is focused on the proposition of a fog-centric wireless, real-time, smart wearable and IoT-based framework for ubiquitous health and fitness analysis in a smart gym environment. The proposed framework aims to aid in the health and fitness industry based on body vitals, body movement and health related data. The framework is expected to assist athletes, trainers and physicians with the interpretation of multiple physical signs and raise alerts in case of any health hazard. We proposed a method to collect and analyze exercise specific data which can be used to measure exercise intensity and its benefit to athlete's health and serve as recommendation system for upcoming athletes. We determined the validity of the proposed framework by giving a six weeks workout plan with six days a week for workout activity targeting all muscles followed by one day for recovery. We recorded the electrocardiogram, heart rate, heart rate variability, breath rate, and determined athlete's movement using a 3D-acceleration. The collected data in the research is used in two modules. A Health zone module implemented on body vitals data which categorizes athlete's health state into various categories. Hzone module is responsible for health hazards identification and alarming. Outstandingly, the Hzone module is able to identify an athlete's physical state with 97% accuracy. A gym activity recognition (GAR) module is implemented to recognize workout activity in real-time using body movements and body vitals data. The purpose of the GAR module is to collect and analyze exercise specific data. The GAR module achieved an accuracy of above 89% on athlete independent model based on muscle group.

No abstract

This paper presents an evolutionary algorithm based technique to solve multi-objective feature subset selection problem. The data used for classification contains large number of features called attributes. Some of these attributes are not relevant and needs to be eliminated. In classification procedure, each feature has an effect on the accuracy, cost and learning time of the classifier. So, there is a strong requirement to select a subset of the features before building the classifier. This proposed technique treats feature subset selection as multi-objective optimization problem. This research uses one of the latest multi-objective genetic algorithms (NSGA-II). The fitness value of a particular feature subset is measured by using ID3. The testing accuracy acquired is then assigned to the fitness value. This technique is tested on several datasets taken from the UCI machine repository. The experiments demonstrate the feasibility of using NSGA-II for feature subset selection.

No abstract

No abstract

No abstract

Adversaries and anti-social elements have exploited the rapid proliferation of computing technology and online social media in the form of novel security threats, such as fake profiles, hate speech, social bots, and rumors. The hate speech problem on online social networks (OSNs) is also widespread. The existing literature has machine learning approaches for hate speech detection on OSNs. However, the effectiveness of contextual information at different orientations is understudied. This study presents a novel Convolutional, BiGRU, and Capsule network-based deep learning model, HCovBi-Caps, to classify the hate speech. The proposed model is evaluated over two Twitter-based benchmark datasets -DS1(balanced) and DS2(unbalanced) with the best performance of 0.90, 0.80, and 0.84 respectively considering precision, recall, and f-score over unbalanced dataset. In terms of training and validation accuracy, the proposed model shows the best performance of 0.93 and 0.90, respectively, over the unbalanced dataset. In comparative evaluation, HCovBi-Caps demonstrates a significantly better performance than state-of-the-art approaches. In addition, HCovBi-Caps shows comparatively better performance over the unbalanced dataset. We also investigate the impact of different hyperparameters on the efficacy of HCovBi-Caps to ascertain the selection of their values. We observed that a higher value of routing iterations adversely affects the model performance, whereas a higher value of capsule dimension improves the performance.