In today's era of rapidly advancing technologies, such as sensors and the Internet of Things (IoT), and the increasing focus on promoting healthy lifestyles, smart wearable devices play a crucial role in real-time detection and diagnosis of physical health conditions. Through analyzing the multi-featured time series data captured by these devices with multiple sensors, we can uncover hidden diseases and provide timely treatment. Therefore, it is imperative to study an anomaly detection model with robust feature learning and anomaly diagnosis capabilities. To address this need, this paper proposes an enhanced autoencoder-based anomaly detection model for time series data obtained from wearable medical devices. Initially, the model utilizes a convolutional neural network to learn the correlations between multiple features. Subsequently, a long and short-term memory network is employed to capture the sequence correlations, and an multi-head attention mechanism is used to mitigate the performance degradation caused by increasing the sequence length. The residual loss is also used to effectively mitigate the vanishing gradient problem. Finally, the model is evaluated using two widely recognized public datasets: the Heart Disease dataset, which contains information on patients with heart conditions, and the MIMIC dataset, a comprehensive database of de-identified health data related to critical care. The experimental results demonstrate that our model can achieve an accuracy of 95.37% and 95.56% on the two datasets, respectively. Compared to the best performing baseline methods, our model improves 8.6% and 12.3% on the two datasets, respectively. Overall, our model enables efficient analysis of sequential data, effectively captures long-term dependencies, and significantly improves the success rate of early health diagnosis for individuals.

As a new networking paradigm, Software-Defined Networking (SDN) separates data and control planes to facilitate programmable functions and improve the efficiency of packet delivery. Recent studies have shown that there exist various security threats in SDN. For example, a saturation attack may disturb the normal delivery of packets and even make the SDN system out of service by flooding the data plane, the control plane, or both. The existing research has focused on saturation attacks caused by SYN flooding. This paper presents an anomaly detection method, called SA-Detector, for dealing with a family of saturation attacks through IP spoofing, ICMP flooding, UDP flooding, and other types of TCP flooding, in addition to SYN flooding. SA-Detector builds upon the study of self-similarity characteristics of OpenFlow traffic between the control and data planes. Our work has shown that the normal and abnormal traffic flows through the OpenFlow communication channel have different statistical properties. Specifically, normal OpenFlow traffic has a low self-similarity degree whereas the occurrences of saturation attacks typically imply a higher degree of self-similarity. Therefore, SA-Detector exploits statistical results and self-similarity degrees of OpenFlow traffic, measured by Hurst exponents, for anomaly detection. We have evaluated our approach in both physical and simulation SDN environments with various time intervals, network topologies and applications, Internet protocols, and traffic generation tools. For the physical SDN environment, the average accuracy of detection is 97.68% and the average precision is 94.67%. For the simulation environment, the average accuracy is 96.54% and the average precision is 92.06%. In addition, we have compared SA-Detector with the existing saturation attack detection methods in terms of the aforementioned performance metrics and controller's CPU utilization. The experiment results indicate that SA-Detector is effective for the detection of saturation attacks in SDN.

Recently, content dissemination has become more and more important for opportunistic social networks. The challenges of opportunistic content dissemination result from random movement of nodes and uncertain positions of a destination, which seriously affect the efficiency of content dissemination. In this paper, we firstly construct time-varying interest communities based on the temporal and spatial regularities of users. Next, we design a content dissemination algorithm on the basis of time-varying interest communities. Our proposed content dissemination algorithm can run in O(nlog⁡n) time. Finally, the comparisons between the proposed content dissemination algorithm and state-of-the-art content dissemination algorithms show that our proposed content dissemination algorithm can (a) keep high query success rate, (b) reduce the average query latency, (c) reduce the hop count of a query, and (d) maintain low system overhead.

Software-Defined Networking (SDN) is a new net-working paradigm that has revolutionized network architectures. The separation of data and control planes improves the efficiency of packet delivery. However, there exist various security attacks against SDN systems. For example, a saturation attack may disturb the normal delivery of packets and even make the SDN system out of service by flooding the data plane, the control plane, or both. This paper presents an anomaly detection method, called SA-Detector, for dealing with a family of saturation attacks. SA-Detector builds upon the study of self-similarity of OpenFlow traffic, which has shown that the normal and abnormal traffic patterns between the controller and the OpenFlow switches have different characteristics. We have evaluated the performance of SA-Detector with different time scales, network scales, Internet applications, and attack implementations. The experimental results show that the average accuracy is 96.54% and the average precision is 92.06%. This indicates that SA-Detector is effective for detecting saturation attacks.

Recently, the service discovery has become more and more important for intermittently-connected mobile social networking (MSN). The previous researchers focus on querying the desirable service using the label with the description of keywords. However, it is impossible for millions of services to be tagged with the accurate keywords in MSN. In this paper, we propose a non- keyword service discovery scheme for the intermittently-connected MSN. In this scheme, the temporal and spatial regularities of users are fully exploited to construct the initial community. Next, the temporal-spatial correlation community transition model is proposed to implement the time-varying community. And the service discovery is given on the basis of the temporal and spatial correlated community. Finally, we verify the relationship between the temporal and spatial factors on two well-known MSN datasets. Additionally, the performance comparisons of the proposed scheme with classical schemes show that the proposed scheme can: (a) improve the success rate of service discovery, (b) reduce the required time for service query, and (c) maintain the lower communication overhead.

Given the wide range deployment of disconnected delay-tolerant social Internet of Things (SIoT), efficient resource discovery remains a fundamental challenge for large-scale SIoT. The existing search mechanisms over the SIoT do not consider preference similarity and are designed in Cartesian coordinates without sufficient consideration of real-world network deployment environments. In this paper, we propose a novel resource discovery mechanism in a 3-D Cartesian coordinate system with the aim of enhancing the search efficiency over the SIoT. Our scheme is based on both of preference and movement pattern similarity to achieve higher search efficiency and to reduce the system overheads of SIoT. Simulation experiments have been conducted to evaluate this new scheme in a large-scale SIoT environment. The simulation results show that our proposed scheme outperforms the state-of-the-art resource discovery schemes in terms of search efficiency and average delay.

To protect user privacy in mobile peer to peer (MP2P) networks, a network coding-based mutual anonymity communication protocol (NMA) is proposed. Our contributions are described as below. We first design a network coding scheme which can defend against various omniscient adversary attacks. Then a novel anonymous communication protocol is presented to meet the anonymity requirement for MP2P applications. The novel anonymous communication protocol is comprised of three steps: query issuance, reply-confirm and file delivery. They all employ the network coding scheme to split and encrypt the signaling and data information. The splitted fragments are flooded at a certain number of hops until some intermediate peers called agents, can collect enough fragments to recover the original information. Next, the agents forward the messages to their neighboring peers. For the query issuance, the neighboring peers forward the query message to the responders by random walk mechanism. For the rest steps, the data information is delivered along the reversed paths discovered by the way of onion routing plus buffer information in routing table. In the entire process, the identities and sensitive information about the initiator and responder are completely hidden. The advantages of the scheme lie in the fact that the network coding and mutli-agent can improve the load balance, the successful rate of information transmission and anonymity degree. The experimental results demonstrate that when the percentage of malicious peers is lower than 50%, the various performances of the NMA, including the response time and the success rate, outperform other mutual anonymity schemes.