We consider a wireless networked control system (WNCS) with imperfect bidirectional links for real-time applications such as smart grids. To maintain the stability of WNCS, captured by the probability that plant state...
详细信息
Human activity recognition (HAR) based on sensor data plays a vital role in various fields. Therefore, it is important to improve the recognition performance of different types of actions. In this work, we propose a T...
详细信息
Human activity recognition (HAR) based on sensor data plays a vital role in various fields. Therefore, it is important to improve the recognition performance of different types of actions. In this work, we propose a Temporal Convolutional Network (TCN) combined with a Bidirectional Long Short-Term Memory (Bi-LSTM) architecture to address the issues of insufficient time-varying feature extraction and gradient explosion caused by too many network layers. This architecture effectively recognizes and emphasizes key feature information. The TCN enhances temporal feature extraction (TFE) with an appropriately sized receptive field, while the BiLSTM captures information from both past and future time steps, making it well-suited for tasks requiring bidirectional temporal context. This integration enables the architecture to learn and identify human activities more effectively. The performance of the proposed architecture is evaluated on three benchmark datasets: UCI-HAR, PAMAP2, and WISDM, achieving significant accuracies of 99.1%, 94.8%, and 98.3%, respectively, outperforming other state-of-the-art architectures.
Polyvinyl alcohol (PVA)/Carboxymethylcellulose (CMC)/Carbon fiber (CF) is a well-known composite for various applications like automobile, EMI shielding, and industrial heating. In this study, the effect of Ti3C2 MXen...
详细信息
With the rapid development of headmounted devices, eye tracking as an emerging human-computer interaction technology, has gained increasing importance. However, pupil detection, the core algorithm in eye tracking, suf...
详细信息
Visible-Infrared Person Re-identification (VI-ReID) would effectively improve the recognition performance in weak-lighting and nighttime scenes, which is an important research direction in pattern recognition and comp...
详细信息
In the context of increasing water scarcity and the need to enhance water distribution network efficiency, this study focuses on optimizing the design of pumping stations using data-driven evolutionary algorithms guid...
详细信息
Motivated by progress in data-driven supervised learning, semantic communication has witnessed remarkable advancements in improving the efficiency of data transmission under various channel conditions. These advanceme...
详细信息
Barchan dunes, crescent-shaped aeolian landforms shaped by unidirectional wind regimes, are integral to understanding sediment transport and landscape evolution in arid regions. This study conducts a geomorphometric a...
详细信息
ISBN:
(数字)9798331527549
ISBN:
(纸本)9798331527556
Barchan dunes, crescent-shaped aeolian landforms shaped by unidirectional wind regimes, are integral to understanding sediment transport and landscape evolution in arid regions. This study conducts a geomorphometric analysis and clustering of barchan dunes, focusing on their spatial distribution, morphological characteristics, and environmental controls. Leveraging high-resolution digital elevation models (DEMs) and advanced clustering algorithms such as K-Means, DBSCAN, and Gaussian Mixture Models, the research identifies patterns in dune morphology and examines their relationships with local topography and climatic drivers. The methodology integrates preprocessing steps, including feature extraction and scaling, with unsupervised clustering to classify dunes based on key attributes such as width, length, height, and geographic location. Morphometric analyses reveal spatial and structural variations, while clustering results highlight patterns linked to wind regimes and sediment availability. Among the clustering techniques, DBSCAN emerges as the most effective for identifying irregularly shaped clusters, achieving higher evaluation metrics such as Silhouette Scores and Davies-Bouldin Index values. This study investigates the morphology and spatial distribution of barchan dunes using advanced clustering techniques such as DBSCAN and K-Means. The primary issue addressed is the challenge of accurately classifying and analyzing irregularly shaped dune formations under varying environmental conditions. Utilizing high-resolution digital elevation models (DEMs), the research identifies distinct morphological patterns and their correlation with wind regimes and sediment availability. The study finds that DBSCAN outperforms other clustering algorithms in handling the irregular geometries of dunes, achieving superior evaluation metrics like Silhouette Scores and Davies-Bouldin Index. These findings provide valuable insights for environmental monitoring and desertification m
This paper addresses the efficient identification of candidate keyframes in long and untrimmed surveillance videos. Existing fixed- length segmentation methods for violence detection suffer from computational ineffici...
详细信息
This paper addresses the efficient identification of candidate keyframes in long and untrimmed surveillance videos. Existing fixed- length segmentation methods for violence detection suffer from computational inefficiency and fragmented short-term event repre- sentation. To overcome these limitations, we propose an Optimal Keyframe Extraction framework utilizing shot boundary detection to segment videos based on significant visual changes. Candidate Keyframe segments are extracted from the shots, focusing on potential anomalous segments. Keyframes are selected based on the highest motion changes, accurately representing short term dynamic events. This dynamic approach aims to minimize the processing time of long and untrimmed surveillance videos by reducing the number of segments required for analysis of the event. Results show that the complexity of analyzing the event ef- fectively can be done by extracting an optimal set of keyframes within 2-3% of total number frames for each video. This research improves violence detection by efficiently analyzing large video datasets and accurately identifying short-term dynamic events, thereby enhancing public safety and security applications.
With the rapid growth of cloud data centers, concerns about energy consumption and its impact on natural resources have become increasingly critical. In response, organizations and global communities are actively purs...
详细信息
暂无评论