Gait recognition has a wide range of application scenarios in the fields of intelligent security and *** recognition currently faces challenges:inadequate feature methods for environmental interferences and insufficie...
详细信息
Gait recognition has a wide range of application scenarios in the fields of intelligent security and *** recognition currently faces challenges:inadequate feature methods for environmental interferences and insufficient local-global information *** address these issues,we propose a gait recognition model based on feature fusion and dual *** model utilizes the ResNet architecture as the backbone network for fundamental gait features ***,the features from different network layers are passed through the feature pyramid for feature fusion,so that multi-scale local information can be fused into global information,providing a more complete feature *** dual attention module enhances the fused features in multiple dimensions,enabling the model to capture information from different semantics and scale *** model proves effective and competitive results on CASIA-B(NM:95.6%,BG:90.9%,CL:73.7%)and OU-MVLP(88.1%).The results of related ablation experiments show that the model design is effective and has strong competitiveness.
Task assignment policies play a central role in many online applications, where service requests or tasks arrive over time and are distributed across parallel servers in a data center or cloud computing platform. The ...
详细信息
Medical imaging, a cornerstone of disease diagnosis and treatment planning, faces the hurdles of subjective interpretation and reliance on specialized expertise. Deep learning algorithms show improvements in automatin...
详细信息
Suicide represents a poignant societal issue deeply entwined with mental well-being. While existing research primarily focuses on identifying suicide-related texts, there is a gap in the advanced detection of mental h...
详细信息
Medical Image Analysis (MIA) is integral to healthcare, demanding advanced computational techniques for precise diagnostics and treatment planning. The demand for accurate and interpretable models is imperative in the...
详细信息
Medical Image Analysis (MIA) is integral to healthcare, demanding advanced computational techniques for precise diagnostics and treatment planning. The demand for accurate and interpretable models is imperative in the ever-evolving healthcare landscape. This paper explores the potential of Self-Supervised Learning (SSL), transfer learning and domain adaptation methods in MIA. The study comprehensively reviews SSL-based computational techniques in the context of medical imaging, highlighting their merits and limitations. In an empirical investigation, this study examines the lack of interpretable and explainable component selection in existing SSL approaches for MIA. Unlike prior studies that randomly select SSL components based on their performance on natural images, this paper focuses on identifying components based on the quality of learned representations through various clustering evaluation metrics. Various SSL techniques and backbone combinations were rigorously assessed on diverse medical image datasets. The results of this experiment provided insights into the performance and behavior of SSL methods, paving the way for an explainable and interpretable component selection mechanism for artificial intelligence models in medical imaging. The empirical study reveals the superior performance of BYOL (Bootstrap Your Own Latent) with resnet as the backbone, as indicated by various clustering evaluation metrics such as Silhouette Coefficient (0.6), Davies-Bouldin Index (0.67), and Calinski-Harabasz Index (36.9). The study also emphasizes the benefits of transferring weights from a model trained on a similar dataset instead of a dataset from a different domain. Results indicate that the proposed mechanism expedited convergence, achieving 98.66% training accuracy and 92.48% testing accuracy in 23 epochs, requiring almost half the number of epochs for similar results with ImageNet weights. This research contributes to advancing the understanding of SSL in MIA, providin
With the continuous growth of cloud computing and virtualization technology, network function virtualization (NFV) techniques have been significantly enhanced. NFV has many advantages such as simplified services, prov...
详细信息
With the continuous growth of cloud computing and virtualization technology, network function virtualization (NFV) techniques have been significantly enhanced. NFV has many advantages such as simplified services, providing more flexible services, and reducing network capital and operational costs. However, it also poses new challenges that need to be addressed. A challenging problem with NFV is resource management, since the resources required by each virtualized network function (VNF) change with dynamic traffic variations, requiring automatic scaling of VNF resources. Due to the resource consumption importance, it is essential to propose an efficient resource auto-scaling method in the NFV networks. Inadequate or excessive utilization of VNF resources can result in diminished performance of the entire service chain, thereby affecting network performance. Therefore, predicting VNF resource requirements is crucial for meeting traffic demands. VNF behavior in networks is complex and nonlinear, making it challenging to model. By incorporating machine learning methods into resource prediction models, network service performance can be improved by addressing this complexity. As a result, this paper introduces a new auto-scaling architecture and algorithm to tackle the predictive VNF problem. Within the proposed architecture, there is a predictive VNF auto-scaling engine that comprises two modules: a predictive task scheduler and a predictive VNF auto-scaler. Furthermore, a prediction engine with a VNF resource predictor module has been designed. In addition, the proposed algorithm called GPAS is presented in three phases, VNF resource prediction using genetic programming (GP) technique, task scheduling and decision-making, and auto-scaling execution. The GPAS method is simulated in the KSN framework, a network environment based on NFV/SDN. In the evaluation results, the GPAS method shows better performance in SLA violation rate, resource usage, and response time when co
In recent years, mental health issues have profoundly impacted individuals’ well-being, necessitating prompt identification and intervention. Existing approaches grapple with the complex nature of mental health, faci...
详细信息
In recent years, mental health issues have profoundly impacted individuals’ well-being, necessitating prompt identification and intervention. Existing approaches grapple with the complex nature of mental health, facing challenges like task interference, limited adaptability, and difficulty in capturing nuanced linguistic expressions indicative of various conditions. In response to these challenges, our research presents three novel models employing multi-task learning (MTL) to understand mental health behaviors comprehensively. These models encompass soft-parameter sharing-based long short-term memory with attention mechanism (SPS-LSTM-AM), SPS-based bidirectional gated neural networks with self-head attention mechanism (SPS-BiGRU-SAM), and SPS-based bidirectional neural network with multi-head attention mechanism (SPS-BNN-MHAM). Our models address diverse tasks, including detecting disorders such as bipolar disorder, insomnia, obsessive-compulsive disorder, and panic in psychiatric texts, alongside classifying suicide or non-suicide-related texts on social media as auxiliary tasks. Emotion detection in suicide notes, covering emotions of abuse, blame, and sorrow, serves as the main task. We observe significant performance enhancement in the primary task by incorporating auxiliary tasks. Advanced encoder-building techniques, including auto-regressive-based permutation and enhanced permutation language modeling, are recommended for effectively capturing mental health contexts’ subtleties, semantic nuances, and syntactic structures. We present the shared feature extractor called shared auto-regressive for language modeling (S-ARLM) to capture high-level representations that are useful across tasks. Additionally, we recommend soft-parameter sharing (SPS) subtypes-fully sharing, partial sharing, and independent layer-to minimize tight coupling and enhance adaptability. Our models exhibit outstanding performance across various datasets, achieving accuracies of 96.9%, 97.
The cellular automaton (CA), a discrete model, is gaining popularity in simulations and scientific exploration across various domains, including cryptography, error-correcting codes, VLSI design and test pattern gener...
详细信息
Mobile crowdsensing (MCS) is a powerful technique that enables a variety of urban tasks, including temperature monitoring, location-based services, and urban path recommendations. However, these tasks often face the c...
详细信息
Mobile crowdsensing (MCS) is a powerful technique that enables a variety of urban tasks, including temperature monitoring, location-based services, and urban path recommendations. However, these tasks often face the challenge of sparse and incomplete sensing data, undermining their effectiveness and reliability. Sparse data completion (SDC) methods have been developed to infer missing or unobserved data by leveraging spatio-temporal correlations to tackle this issue. This forms the core concept of the sparse mobile crowdsensing problem (SMCS), which aims to improve the performance of downstream tasks through inferred data. Despite the potential benefits, most existing SMCS methods fail to consider the trade-off between the cost of SDC and the benefits for downstream tasks. These methods often treat SDC and downstream tasks as independent modules, resulting in suboptimal outcomes. In this paper, we investigate the impact of SDC on the SMCS paradigm, both qualitatively and quantitatively. We establish the upper bound of performance achievable when applying SDC in SMCS under different levels of sensing data sparsity. Based on these studies and findings, we propose a practical and flexible framework called SDC-EVA, Sensing Data Completion EVAluation framework. This framework allows for applying different SDC methods in SMCS, considering factors such as computing complexity, storage space, and associated costs. Our proposed framework allows researchers to assess the necessity and feasibility of integrating SDC into SMCS systems before designing and deploying them in real-world scenarios. This assessment can be tailored to specific data sparsity and contextual information. To validate the effectiveness of our proposed evaluation framework, we conduct experiments in various real-world scenarios involving different combinations of SDC and downstream tasks. The results demonstrate the superiority of our framework in improving the performance of SMCS. By presenting these find
Internet of Things (IoT) enabled Wireless Sensor Networks (WSNs) is not only constitute an encouraging research domain but also represent a promising industrial trend that permits the development of various IoT-based ...
详细信息
暂无评论