Human activity recognition (HAR) has gained significant attention in computer vision and human‐computer interaction. This paper investigates the difficulties encountered in human activity recognition (HAR), precisely differentiating between various activities by extracting spatial and temporal features from sequential data. Traditional machine learning approaches necessitate manual feature extraction, hindering their effectiveness. For temporal features, RNNs have been widely used for HAR; however, they need help processing long sequences, leading to information bottlenecks. This work introduces a framework that effectively integrates spatial and temporal features by utilizing a series of layers that incorporate a self‐attention mechanism to overcome these problems. Here, spatial characteristics are derived using 1D convolutions coupled with pooling layers to capture essential spatial information. After that, GRUs are used to make it possible to effectively represent the temporal dynamics that are inherent in sequential data. Furthermore, the utilization of an attention mechanism serves the purpose of dynamically selecting the significant segments within the sequence, thereby improving the model’s comprehension of context and enhancing the efficacy of deep neural networks (DNNs) in the domain of human activity recognition (HAR). Three different optimizers, namely, Adam, SGD, and RMSprop, were employed to train the model. Each optimizer was tested with three distinct learning rates of 0.1, 0.001, and 0.0001. Experiments on the UCI‐HAR dataset have shown that the model works well, with an impressive 97% accuracy rate when using the Adam optimizer with a learning rate of 0.001.
1 May 2012 in Journal of Advances in Information Technology
Location Based Services are becoming an integral part of the wider telecommunication scenario. However, the approaches to provide Location Based Services and the research issues in this area are diverse and broad. In this paper, the present state of the Location Based Service systems has been analyzed. The analysis confirmed the heterogeneity of the research problems associated with Location Based Services as well as the array of solutions to address these problems. On one hand, the study carried out will enable one to get some idea about essential features for the implementation of a Location Based Service system. On the other hand, it is strongly believed that this study will assist researchers and the industry to get a sense of the multidimensional research space of Location Based Services which will be helpful for later exploration of this field.
A large number of smart devices (things) are being deployed with the swift development of Internet of Things (IOT). These devices, owned by different organizations, have a wide variety of services to offer over the web. During a natural disaster or emergency (i.e., a situation), for example, relevant IOT services can be found and put to use. However, appropriate service matching methods are required to find the relevant services. Organizations that manage situation responses and organizations that provide IOT services are likely to be independent of each other, and therefore it is difficult for them to adopt a common ontological model to facilitate the service matching. Moreover, there exists a large conceptual gap between the domain of discourse for situations and the domain of discourse for services, which cannot be adequately bridged by existing techniques. In this paper, we address these issues and propose a new method, WikiServe, to identify IOT services that are functionally relevant to a given situation. Using concepts (terms) from situation and service descriptions, WikiServe employs Wikipedia as a knowledge source to bridge the conceptual gap between situation and service descriptions and match functionally relevant IOT services for a situation. It uses situation terms to retrieve situation related articles from Wikipedia. Then it creates a ranked list of services for the situation using the weighted occurrences of service terms in weighted situation articles. WikiServe performs better than a commonly used baseline method in terms of Precision, Recall and F measure for service matching.
18 August 2025 in Journal of Computational Social Science