No abstract

Residential power consumption and the increasing environmental pollution emitted from the electric generators have lead to the energy management focus. To minimize the power consumption, the overall efficiency of electrical networks must have to be improved. Smart Grid concept has played an important role in moving towards better energy management. The current technologies and projects fail to address the energy waste issue and has given less afford on standby power management and energy monitoring. In this paper, we focus on the energy waste issue and proposed a wireless sensor network for gathering contextual information and controlling the domestic power consumption. Our proposed wireless sensor network consists of multi-modal multi-sensor nodes which is used to monitor different activities and movements, environmental factors and the power consumption of the appliances. Then it controls the operation of the appliances and manages their power consumption according to the gathered contextual information from the nodes thereby it prevents power consumption on unused or unnecessary services. Index Terms-Domestic Power Management, DomesticPower Saving, Wireless Sensor Network.

No abstract

The muscular activities gathered by real-time myoelectric interfaces of surface electromyography (sEMG) can be used to develop myoelectric prosthetic hands for physically disabled people. However, the acquired myoelectric signals must be accurately classified in real time to properly control the operation of the external devices. In this study, we propose methods for detecting and classifying muscular activities using sEMG signals. These methods include outlier removal, data manipulation, data preprocessing, dimensionality reduction, and classification. We use the Ninapro database 1 (DB1) containing sEMG signals from 27 intact subjects while performing 53 hand movements repeatedly. We apply the Principle Component Analysis (PCA), Independent Component Analysis (ICA), and t-distributed Stochastic Neighbor Embedding (t-SNE) feature extraction methods for dimensionality reduction. Five machine learning (ML) algorithms and deep learning artificial neural networks (ANN) are applied for the classification of muscular movements. It is observed that for the recognition of 53 muscular movements of 27 subjects with preprocessed raw data, ANN obtains the highest accuracy of 93.92% for inter-subject and 97.73% for intra-subject movement recognition. Among the ML algorithms, K-Nearest Neighbors (KNN) performs the best with both t-SNE features and the preprocessed raw data in least computational time. With the preprocessed raw data, KNN obtains 93.174% and 97.458% for inter-subject and intra-subject movement classification, respectively while with the t-SNE features, KNN obtains 89.844% accuracy for inter-subject and 95.04% accuracy for intra-subject in reduced computational time. INDEX TERMS Gesture recognition, Computational and artificial intelligence, Biomedical signal processing I. INTRODUCTIONT HE myoelectric interfaces of the surface electromyography gather muscular activity information for different movements. The sEMG signals of different muscular activities can be used to control the operation of external prosthetic devices that are used to make the life of physically disable people easy and comfortable. The external devices may be wearable or not wearable depending on the requirements of the disable people. To ensure the quality and proper operation of the external devices, the muscular activities for different movements are required to be classified accurately in realtime to control the operation of the external devices.There are many works in the literature on muscular movement recognition based on the EMG signals [1]. In [2], the authors consider feature extraction using the mean absolute value (MAV), the variance (VAR), the waveform length (WL), sEMG histogram (HIST), cepstral coefficients (CC), short-time Fourier transform, marginal discrete wavelet transform (mDWT) and classification using linear discriminant analysis (LDA), k-nearest neighbors (KNN), support

No abstract