The number of studies on the development of indoor positioning systems has increased recently due to the growing demands of the various location-based services. Inertial sensors available in commercial smartphones play an important role in indoor localization and navigation owing to their highly accurate localization performance. In this study, the inertial sensors of a smartphone, which generate distinct patterns for physical activities and action units (AUs), are employed to localize a target in an indoor environment. These AUs, (such as a left turn, right turn, normal step, short step, or long step), help to accurately estimate the indoor location of a target. By taking advantage of sophisticated deep learning algorithms, we propose a novel approach for indoor navigation based on long short-term memory (LSTM). The LSTM accurately recognizes physical activities and related AUs by automatically extracting the efficient features from the distinct patterns of the input data. Experiment results show that LSTM provides a significant improvement in the indoor positioning performance through the recognition task. The proposed system achieves a better localization performance than the trivial fingerprinting method, with an average error of 0.782 m in an indoor area of 128.6 m². Additionally, the proposed system exhibited robust performance by excluding the abnormal activity from the pedestrian activities.

Recent developments in the field of preventive healthcare have received considerable attention due to the effective management of various chronic diseases including diabetes, heart stroke, obesity, and cancer. Various automated systems are being used for activity and food recognition in preventive healthcare. The automated systems lack sophisticated segmentation techniques and contain multiple sensors, which are inconvenient to be worn in real-life settings. To monitor activity and food together, our work presents a novel wearable system that employs the motion sensors in a smartwatch together with a piezoelectric sensor embedded in a necklace. The motion sensor generates distinct patterns for eight different physical activities including eating activity. The piezoelectric sensor generates different signal patterns for six different food types as the ingestion of each food is different from the others owing to their different characteristics: hardness, crunchiness, and tackiness. For effective representation of the signal patterns of the activities and foods, we employ dynamic segmentation. A novel algorithm called event similarity search (ESS) is developed to choose a segment with dynamic length, which represents signal patterns with different complexities equally well. Amplitude-based features and spectrogram-generated images from the segments of activity and food are fed to convolutional neural network (CNN)-based activity and food recognition networks, respectively. Extensive experimentation showed that the proposed system performs better than the state of the art methods for recognizing eight activity types and six food categories with an accuracy of 94.3% and 91.9% using support vector machine (SVM) and CNN, respectively.

Unintentional islanding is a problem in electrical distribution networks; it happens when the central utility is unintentionally separated from the rest of the distributed power system. The islanding detection problem becomes severe in non-detection zones. We propose an intelligent islanding detection technique with zero non-detection zone for a hybrid distributed generation system. It is based on the computation of frequency spectrum variations over time using short-term Fourier transform and convolutional neural networks. For various islanding and non-islanding occurrences, the three-phase voltage at the point of common coupling is monitored, and time-series data is collected. Then computations for a set of multiple frequencies on scaled time-series data are carried out, and complex numbers are split into magnitude and phase values. To detect islanding and non-islanding occurrences, a modified convolutional neural network with forward propagation was utilized. For the IEC 61850-7-420 test system, several islanding and non-islanding scenarios are created and deployed to train the convolutional neural network for the proposed approach. The efficacy of the proposed islanding detection learning model is assessed using 5-fold cross-validation. The findings reveal that under normal and noisy conditions, the proposed methodology has zero non-detection zone with original dataset, excellent accuracy, selectivity, and sensitivity.

Tactile perception enables people with visual impairments (PVI) to engage with artworks and real-life objects at a deeper abstraction level. The development of tactile and multi-sensory assistive technologies has expanded their opportunities to appreciate visual arts. We have developed a tactile interface based on the proposed concept design under considerations of PVI tactile actuation, color perception, and learnability. The proposed interface automatically translates reference colors into spatial tactile patterns. A range of achromatic colors and six prominent basic colors with three levels of chroma and values are considered for the cross-modular association. In addition, an analog tactile color watch design has been proposed. This scheme enables PVI to explore artwork or real-life object color by identifying the reference colors through a color sensor and translating them to the tactile interface. The color identification tests using this scheme on the developed prototype exhibit good recognition accuracy. The workload assessment and usability evaluation for PVI demonstrate promising results. This suggest that the proposed scheme is appropriate for tactile color exploration.