Abstracts:Healthcare systems have significantly benefited from Artificial Intelligence (AI) and the Internet of Things (IoT). The vital signs of patients can be continuously monitored using the technologies mentioned above, and timely treatment can be provided. To this end, this paper proposes a scalable, responsive, and reliable AI-enabled IoT and edge computing-based healthcare solution with low latency when serving patients. The system comprises the collection of health-related data, data processing and analysis at edge nodes, and permanent storage and sharing at edge data centers. The edge nodes and edge controller schedule patients and provide resources in real time. Simulations were conducted to test system performance. The results for end-to-end time, computing, optimization, and transmission latency prove to be very promising. To determine system performance in a real-world scenario, a neural network was used to model transmission latency. The system is extremely useful for those who are disabled or elderly, as well as in pandemic situations.

Abstracts:Vehicle ad-hoc networks use message authentication to ensure message integrity and sender authenticity. However, this increases computational overhead. Collaborative message authentication uses message aggregation or batch verification to reduce the overall computational overhead, but this increases the authentication delay, resulting in a high message drop rate. In this paper, a single-message cooperative authentication scheme based on certificateless signatures is proposed, where a small number of vehicles verify the signature of a new message and construct the evidence, which can be used for rapid message verification and is difficult to forge. Security analysis shows that the message evidence has high security and can resist a variety of malicious attacks. The scheme implementation is simple, thus balancing the trade-off between authentication delay and total computational cost.

Abstracts:Cardiovascular disease has become a significant cause of modern people's health problems. The mobile electrocardiogram can be a non-intrusive and convenient tool to provide an auxiliary diagnosis of cardiovascular diseases for the virtual heath community. In this paper, a new diagnostic framework for mobile electrocardiogram signal is proposed with two improved methods. They are (1) the sliding segmentation method, which enhances the model's generalization ability and (2) the large-scale convolution kernel of a one-dimensional neural network, that is designed for mobile electrocardiogram signal with more resistant to sparseness and noise issues. According our experiments, the results show that the proposed sliding large kernel algorithm has a better accuracy than previous algorithms.

Abstracts:As an efficacy classification technique, linear regression based classification (LRC) has been popularly used for image recognition. However, since LRC neglects the local structure as well as dissimilarities between different classes, its performance may degrade in many real-world applications. To alleviate this problem, a robust classification method, namely local median based linear regression classification (LMLRC) is put forward in this paper. In the proposed model, based on a concept that the samples of one class having more similar features should be nearer and to handle errors brought by noise and variations between images, the test sample is linearly coded by its local median vectors of all classes; then the test sample is classified to the class which owns the biggest element in the coefficient vector. Extensive experiments on AR, CMU PIE, FRGC and PolyU Palmprint datasets show that the presented approach has superior performance to some other state-of-the-art classification algorithms.

Abstracts:Significant progress has been made in recent years in image quality assessment (IQA). In particular, the development of deep learning has provided no-reference (NR)-IQA with more impressive solutions. However, improving the generalization of NR-IQA models is still an urgent necessity. In this study, we propose a new framework that uses the range mapping method to map an existing full-reference (FR)-IQA dataset to an NR-IQA dataset, thereby further enhancing the accuracy and generalization of the NR-IQA model. First, an NR-IQA model is employed to score an FR-IQA dataset to obtain the corresponding mean opinion score (MOS) values. Then, the correlation coefficients between these MOS values and the original differential mean opinion score (DMOS) values marked by the FR-IQA dataset itself is calculated. Subsequently, the matching sequence pair is obtained according to these correlation coefficients. Then, a range mapping function is selected based on this sequence pair, and this function is used to map the entire FR-IQA dataset to the existing NR-IQA dataset, and a new NR-IQA dataset is generated. Finally, the new and the existing NR-IQA datasets are merged into a new dataset, which can train an end-to-end multi-task network to obtain the final model RM-IQA. This model exhibits better performance as it exploits more prior information. Based on the largest available NR-IQA dataset KonIQ-10k and FR-IQA dataset KADID-10K, the experimental results proved the effectiveness of the proposed framework.

Abstracts:Virtual view synthesis from monocular video is challenging, as it aims to infer photorealistic views from single reference view. Previous work have achieved acceptable visual quality, however, are heavily relied on supervision information, such as depth or pristine virtual view, which are inadequate in practical application. In this paper, an unsupervised virtual view synthesis method is proposed to get rid of the supervision information. Firstly, it embed a spatiotemporal generative adversarial network into traditional depth-image-based rendering framework with no explicit depth information provided. Secondly, it utilized novel perceptual constraints without relying on pristine images, including the blind synthesized image quality metric and no-reference structure similarity. The entire framework is fully convolutional, producing hallucinated results in an end-to-end way. Particularly, the whole framework is independent of supervision information. Experimental results demonstrate that the proposed method produces pleasant virtual views in comparison with supervised methods, thereby can be beneficial to practical applications.

Abstracts:In the complex underwater environment, it is difficult to complete teleoperation tasks due to dynamic environments. Through cooperation among manipulators, a multilateral teleoperation system has the potential to achieve better performance than conventional bilateral teleoperation systems. In this paper, we propose a multilateral teleoperation control method that can be easily applied for underwater grasping tasks. Specifically, a new structure involving two (or multiple) masters and a single slave is investigated, which is treated as a linear combination of multiple subsystems under time delays. A control method based on linear matrix inequality exponential convergence and nonlinear disturbance is presented to estimate the model uncertainties of the system and unknown external disturbances during grasping process. The asymptotic stability is analyzed using the established Lyapunov–Krasovskii functional. Numerical simulations and real experiments performed for the task of grasping a plastic foam block are reported to verify the proposed control method in real applications.

Abstracts:This paper presents an autonomous humanoid robot, namely, LABOR, for apple harvesting. Comprised of a binocular camera, a humanoid dual-arm operating system, and a mobile vehicle platform, the devised robot is capable of identifying, positioning, grasping, and picking up apples via its vision identification and dual-arm harvesting systems. Both the robot structure design and the functional systems, as well as their implementations are described in detail and were verified via experiments in a simulated orchard environment. Results show success rates of 82.5% and 72% for the apple recognition and harvesting functions respectively, and the average apple harvesting time was approximately 14.6 s. The wide flexibility and high scalability in the robotic structure, dual-arm coordinate control, and independent harvest planning may facilitate its application in agriculture for the harvesting of other fruits, such as tomatoes, pomegranates, and pears.

Abstracts:The reachability query is a fundamental problem in graph analysis. Most existing studies assume there is no or only one type of relation on the edges. To fill the gap, we propose two new reachability problems in multi-relation graphs. Specifically, given a multi-relation graph G, two vertices u,v, and a query relation set C, it aims to check whether u can reach v under the necessity/existence relation constraint. A baseline online reachability query framework firstly is proposed by extending the BFS method. To accelerate the processing, index-based methods are developed based on 2-hop cover framework. Moreover, several optimized strategies are developed to improve the efficiency of index construction. Extensive experiments are conducted to demonstrate the advantages of developed techniques. As shown, the optimized method can achieve up to 3X acceleration for index construction and the index-based strategy can achieve up to 36X speedup compared with the baseline for query processing.

Abstracts:One processing task in Ethernet nodes is to manage Media Access Control (MAC) addresses: search, insert new, and delete old ones. For this purpose, Content-Addressable Memorys (CAMs) offer low latency and no collisions; however, they consume too many electronic resources, and working frequency is constrained. On the other hand, hash tables demand few circuits allowing fast operations; unfortunately, collisions often occur, causing delays in the process. Finally, binary trees arise as one efficient technique to search addresses by hardware, although updating them is complex. The design presented in this paper, based on an Adelson-Velsky and Landis (AVL) binary tree, takes advantage of the mixed hardware/software capabilities of Multiprocessor Programmable System-on-a-Chip (MPSoC) devices. It forwards frames on the fly: a hardware core, searches addresses in an AVL tree, and a program inserts and deletes them. This solution requires few resources and, to the best of our knowledge, is the first to manage MAC addresses in an AVL tree and to exploit a hardware/software System-on-a-Chip (SoC) for this purpose.