Optimization plays a vital role in cloud computing. The process of optimization can be effectively implemented using replica replacement and scheduling policy. The major challenge in virtualization is equal sharing of...
详细信息
In the rapidly evolving landscape of technology, the need for swift and efficient deployment of software and applications has never been more critical. Due to the rapid and constant evolution of innovation, there is a...
详细信息
Advanced Driver Assistance Systems (ADAS) enhance driver safety through various technologies. In high-end cars, ADAS typically uses computer vision-based solutions, such as eye-tracking, to monitor driver attention, m...
详细信息
ISBN:
(纸本)9798350387278
Advanced Driver Assistance Systems (ADAS) enhance driver safety through various technologies. In high-end cars, ADAS typically uses computer vision-based solutions, such as eye-tracking, to monitor driver attention, mood, and drowsiness. However, these ADAS solutions are challenging to implement for two-wheeler (2W) drivers, who constitute about 80% of drivers population in India, mainly due to helmet usage and the unique dynamics of 2W vehicles. This paper investigates improving 2W driver safety through integrating mobility and physiological sensors for ADAS. Experimental studies evaluated a novel ADAS framework combining mobility sensor data (e.g., speed, acceleration, position) with physiological parameters (e.g., heart rate, etc.). This fusion of sensors data approach enables monitoring vehicle dynamics and driver conditions for providing adaptive safety interventions by identifying aggressive/non-aggressive and stress/non-stress patterns. To facilitate the collection of mobility and physiological sensors data a mobile application was developed using Flutter. The physiological parameters were captured from the smart-watch paired with the smart-phone and the mobility parameters were captured from the mobility sensors that were in-built in the smart-phone. The data was collected in Navi-Mumbai area of India. Preliminary experiments conducted using these integrated sensors data show promising results. To incorporate supervised approach for Driver Behaviour Analysis (DBA) requires a tedious task of manual tagging and each driver reacts differently to the different situations that arise while driving. So, an un-supervised learning approach has been incorporated and clustering techniques like k-Means, Gaussian Mixture Model (GMM), Hierarchical Clustering, and k-Means with Dynamic Time Wrapping (DTW) analysed the sensor data to identify patterns indicating potential hazards or driver impairment. The findings based on the preliminary experimental studies done indicate t
It has been associated with converters and inverters. The system has been found to be feasible in efficiently utilizing Photovoltaic energy and integrating it with the electrical grid without any disturbances. The suc...
详细信息
Image captioning is the task of analyzing an image and expressing its content using natural language. It involves computer vision, image analytics, object recognition and natural language processing. This field has be...
详细信息
Supply chain management Constantly encounters challenges for instance service duplication, Indigent Collaboration among various Divisions, and absence of formal procedures, leading to lucidity issues. The prevalence o...
详细信息
Link prediction stands as a crucial network challenge, garnering attention over the past decade, with its significance heightened by the escalating volume of network data. In response to the pressing need for swift re...
详细信息
Link prediction stands as a crucial network challenge, garnering attention over the past decade, with its significance heightened by the escalating volume of network data. In response to the pressing need for swift research focus, this study introduces an innovative approach—the Anchor-aware Graph Autoencoder integrated with the Gini Index (AGA-GI)—aimed at gathering data on the global placements of link nodes within the link prediction framework. The proposed methodology encompasses three key components: anchor points, node-to-anchor paths, and node embedding. Anchor points within the network are identified by leveraging the graph structure as an input. The determination of anchor positions involves computing the Gini indexes (GI) of nodes, leading to the generation of a candidate set of anchors. Typically, these anchor points are distributed across the network structure, facilitating substantial informational exchanges with other nodes. The location-based similarity approach computes the paths between anchor points and nodes. It identifies the shortest path, creating a node path information function that incorporates feature details and location similarity. The ultimate embedding representation of the node is then formed by amalgamating attributes, global location data, and neighbourhood structure through an auto-encoder learning methodology. The Residual Capsule Network (RCN) model acquires these node embeddings as input to learn the feature representation of nodes and transforms the link prediction problem into a classification task. The suggested (AGA-GI) model undergoes comparison with various existing models in the realm of link prediction. These models include Attributes for Link Prediction (SEAL), Embeddings, Subgraphs, Dual-Encoder graph embedding with Alignment (DEAL), Embeddings and Spectral Clustering (SC), Deep Walk (DW), Graph Auto-encoder (GAE), Variational Graph Autoencoders (VGAE), Graph Attention Network (GAT), and Graph Conversion Capsule Link (G
The research project on 'Deep Learning-Based Text Summarization System using T5 small and gTTS' introduces a method to automatically extract and understand information from PDFs. The first step is to extract t...
详细信息
The Industrial Internet of Things (IIoT) has revolutionized industrial operations by enhancing connectivity and automation. However, this interconnectivity also introduces significant vulnerabilities, particularly to ...
详细信息
Twitter is the best source for sentiment analysis, product reviews, current issues, etc. Sentiment analysis extracts positive and negative opinions from the Twitter data set, and R studio provides the best environment...
详细信息
暂无评论