This paper proposes an IGBT transient switching modeling approach based on transfer learning, designed to enhance modeling efficiency and accuracy while reducing reliance on extensive data and complex parameter extrac...
详细信息
This paper presents a Fog-enabled chest-worn device for estimating systolic blood pressure (sBP). The device integrates two sensors that simultaneously detect the phonocardiogram (PCG), ballistocardiogram (BCG), and s...
详细信息
In response to the evolving demands and challenges in recommendation systems, a comprehensive and innovative approach is proposed for delivering personalized and accurate product recommendations while mitigating exist...
详细信息
The Internet of Things (IoT) is transforming society by connecting businesses and optimizing systems across industries. Its impact has been felt in healthcare, where it has the potential to revolutionize medical treat...
详细信息
The Internet of Things (IoT) is transforming society by connecting businesses and optimizing systems across industries. Its impact has been felt in healthcare, where it has the potential to revolutionize medical treatment. Conversely, healthcare systems are targeted by attackers and security threats. Malicious activities against such systems intend to compromise privacy and acquire control over internal procedures. In this regard, advanced analytics can enhance these attacks' detection, mitigation, and prevention and improve overall IoT security. However, the process of producing realistic datasets is complex. There are critical aspects to consider when developing models that can be directly deployed in real environments (e.g., multiple devices, features, and realistic testbed). Thereupon, the main goal of thisresearch is to conduct a review of Machine learning (ML) solutions for IoT security in healthcare. Furthermore, this review is conducted from a dataset standpoint, focusing on existing datasets, resources, applications, and open challenges. Our primary objective is to highlight the current landscape of datasets for IoT security in healthcare and the immediate requirements for future datasets to support the development of novel approaches.
Localization has become an indispensable function of modern cellular communication systems [1]. In a cloud radio access network(C-RAN), the remote radio head(RRH) is the actual signal transmitter, whose location can a...
Localization has become an indispensable function of modern cellular communication systems [1]. In a cloud radio access network(C-RAN), the remote radio head(RRH) is the actual signal transmitter, whose location can assist in wireless network layout optimization and wireless resource management. The measurement of the RRH location can only be done manually on-site due to the lack of global positioning systems(GPs) at the RRH side, which is thus not a cost-effective solution for the widely used C-RAN with a large number of RRH units.
Due to the rapid evolution of Advanced Persistent Threats(APTs)attacks,the emergence of new and rare attack samples,and even those never seen before,make it challenging for traditional rule-based detection methods to ...
详细信息
Due to the rapid evolution of Advanced Persistent Threats(APTs)attacks,the emergence of new and rare attack samples,and even those never seen before,make it challenging for traditional rule-based detection methods to extract universal rules for effective *** the progress in techniquessuch as transfer learning and meta-learning,few-shot network attack detection has ***,challenges in few-shot network attack detection arise from the inability of time sequence flow features to adapt to the fixed length input requirement of deep learning,difficulties in capturing rich information from original flow in the case of insufficient samples,and the challenge of high-level abstract *** address these challenges,a few-shot network attack detection based on NFHP(Network Flow Holographic Picture)-RN(ResNet)is ***,leveraging inherent properties of imagessuch as translation invariance,rotation invariance,scale invariance,and illumination invariance,network attack traffic features and contextual relationships are intuitively represented in *** addition,an improved RN network model is employed for high-level abstract feature extraction,ensuring that the extracted high-level abstract features maintain the detailed characteristics of the original traffic behavior,regardless of changes in background ***,a meta-learning model based on the self-attention mechanism is constructed,achieving the detection of novel APT few-shot network attacks through the empirical generalization of high-level abstract feature representations of known-class network attack *** results demonstrate that the proposed method can learn high-level abstract features of network attacks across different traffic detail *** state-of-the-artmethods,it achieves favorable accuracy,precision,recall,and F1 scores for the identification of unknown-class network attacks through cross-validation onmultiple datasets.
This paper studies imitation learning in nonlinear multi-player game systems with heterogeneous control input *** propose a model-free data-driven inverse reinforcement learning(RL)algorithm for a leaner to find the c...
详细信息
This paper studies imitation learning in nonlinear multi-player game systems with heterogeneous control input *** propose a model-free data-driven inverse reinforcement learning(RL)algorithm for a leaner to find the cost functions of a N-player Nash expert system given the expert'sstates and control *** allows us to address the imitation learning problem without prior knowledge of the expert'ssystem *** achieve this,we provide a basic model-based algorithm that is built upon RL and inverse optimal *** serves as the foundation for our final model-free inverse RL algorithm which is implemented via neural network-based value function *** analysis and simulation examples verify the methods.
Information exists in various forms in the real world, and the effective interaction and fusion of multimodal information plays a key role in the research of computer vision and deep learning. Generating an image that...
详细信息
seamlesslearning refers to a learning model in which students can accomplish their learning tasks with the help of technology whenever they are curious in different real-life learning contexts. In the era of artifici...
详细信息
The evolution of edge computing has advanced the accessibility of E-health recommendation services, encompassing areassuch as medical consultations, prescription guidance, and diagnostic assessments. Traditional meth...
详细信息
The evolution of edge computing has advanced the accessibility of E-health recommendation services, encompassing areassuch as medical consultations, prescription guidance, and diagnostic assessments. Traditional methodologies predominantly utilize centralized recommendations, relying on servers to store client data and dispatch advice to ***, these conventional approaches raise significant concerns regarding data privacy and often result in computational inefficiencies. E-health recommendation services, distinct from other recommendation domains, demand not only precise and swift analyses but also a stringent adherence to privacy safeguards, given the users' reluctance to disclose their identities or health information. In response to these challenges, we explore a new paradigm called on-device recommendation tailored to E-health diagnostics, where diagnostic support(such as biomedical image diagnostics), is computed at the client *** leverage the advances of federated learning to deploy deep learning models capable of delivering expert-level diagnostic suggestions on clients. However, existing federated learning frameworks often deploy a singular model across all edge devices, overlooking their heterogeneous computational capabilities. In this work, we propose an adaptive federated learning framework utilizing BlockNets, a modular design rooted in the layers of deep neural networks, for diagnostic recommendation across heterogeneous devices. Our framework offers the flexibility for users to adjust local model configurations according to their device's computational power. To further handle the capacity skewness of edge devices, we develop a data-free knowledge distillation mechanism to ensure synchronized parameters of local models with the global model, enhancing the overall accuracy. Through comprehensive experiments across five real-world datasets, against six baseline models, within six experimental setups, and various data distribution scenario
暂无评论