Vol.20 No.3, September 30, 2022
Abstract : The ongoing adoption of 5G will increase the data traffic, throughput, multimedia services, and power consumption for future wireless applications and services, including sensor and mobile networks. Multipath fading on wireless channels also reduces the system performance and increases energy consumption. To address these issues, device-to-device (D2D) and cooperative communications have been proposed. In this study, we propose two inter-clustering models using the relay selection method to improve system performance and increase energy efficiency in cooperative D2D networks. We develop two inter-clustering models and present their respective algorithms. Subsequently, we run a computer simulation to evaluate each model’s outage probability (OP) performance, throughput, and energy efficiency. The simulation results show that inter-clustering model II has the lowest OP, highest throughput, and highest energy efficiency compared with inter-clustering model I and the conventional inter-clustering-based multirelay method. These results demonstrate that inter-clustering model II is well-suited for use in 5G overlay D2D and cellular communications.
Abstract : Plain radiographic analysis is the initial imaging modality for suspected small bowel obstruction. Among the many features that affect the diagnosis of small bowel obstruction (SBO), the presence of gas-filled or fluid-filled small bowel loops is the most salient feature that can be automatized by computer vision algorithms. In this study, we compare three frequently applied pixel-clustering algorithms for extracting gas-filled areas without human intervention. In a comparison involving 40 suspected SBO cases, the Possibilistic C-Means and Fuzzy C-Means algorithms exhibited initialization-sensitivity problems and difficulties coping with low intensity contrast, achieving low 72.5% and 85% success rates in extraction. The Adaptive Resonance Theory 2 algorithm is the most suitable algorithm for gas-filled region detection, achieving a 100% success rate on 40 tested images, largely owing to its dynamic control of the number of clusters.
Abstract : This paper proposes an efficient method of reconstructing interconnections when the terminals of each plane change in real-time situations where randomly divided planes are interconnected. To connect all terminals when the terminals of each plane are changed, we usually reconstruct the interconnections between all terminals. This ensures a minimum connection length, but it takes considerable time to reconstruct the interconnection for the entire terminal. This paper proposes a solution to obtain an optimal tree close to the minimum spanning tree (MST) in a short time. The construction of interconnections has been used in various design-related areas, from networks to architecture. One of these areas is an ad hoc network that only consists of mobile hosts and communicates with each other without a fixed wired network. Each host of an ad hoc network may appear or disappear frequently. Therefore, the heuristic proposed in this paper may expect various cost savings through faster interconnection reconstruction using the given information in situations where the connection target is changing.
Abstract : Recently, studies have been conducted on intelligent transportation systems (ITS) that provide safety and convenience to humans. Systems that compose the ITS adopt architectures that applied the cloud computing which consists of a highperformance general-purpose processor or graphics processing unit. However, an architecture that only used the cloud computing requires a high network bandwidth and consumes much power. Therefore, applying edge computing to ITS is essential for solving these problems. In this paper, we propose an edge artificial intelligence (AI) device based ITS. Edge AI which is applicable to various systems in ITS has been applied to license plate recognition. We implemented edge AI on a field-programmable gate array (FPGA). The accuracy of the edge AI for license plate recognition was 0.94. Finally, we synthesized the edge AI logic with Magnachip/Hynix 180nm CMOS technology and the power consumption measured using the Synopsys’s design compiler tool was 482.583mW.
Abstract : Emotion recognition is an essential component of complete interaction between human and machine. The issues related to emotion recognition are a result of the different types of emotions expressed in several forms such as visual, sound, and physiological signal. Recent advancements in the field show that combined modalities, such as visual, voice and electroencephalography signals, lead to better result compared to the use of single modalities separately. Previous studies have explored the use of multiple modalities for accurate predictions of emotion; however the number of studies regarding real-time implementation is limited because of the difficulty in simultaneously implementing multiple modalities of emotion recognition. In this study, we proposed an emotion recognition system for real-time emotion recognition implementation. Our model was built with a multithreading block that enables the implementation of each modality using separate threads for continuous synchronization. First, we separately achieved emotion recognition for each modality before enabling the use of the multithreaded system. To verify the correctness of the results, we compared the performance accuracy of unimodal and multimodal emotion recognitions in real-time. The experimental results showed real-time user emotion recognition of the proposed model. In addition, the effectiveness of the multimodalities for emotion recognition was observed. Our multimodal model was able to obtain an accuracy of 80.1% as compared to the unimodality, which obtained accuracies of 70.9, 54.3, and 63.1%.
Abstract : An intelligent distributed multi-agent system (IDMS) using reinforcement learning (RL) is a challenging and intricate problem in which single or multiple agent(s) aim to achieve their specific goals (sub-goal and final goal), where they move their states in a complex and cluttered environment. The environment provided by the IDMS provides a cumulative optimal reward for each action based on the policy of the learning process. Most actions involve interacting with a given IDMS environment; therefore, it can provide the following elements: a starting agent state, multiple obstacles, agent goals, and a cluttered index. The reward in the environment is also reflected by RL-based agents, in which agents can move randomly or intelligently to reach their respective goals, to improve the agent learning performance. We extend different cases of intelligent multi-agent systems from our previous works: (a) a proposed environment-clutter-based-index for agent sub-goal selection and analysis of its effect, and (b) a newly proposed RL reward scheme based on the environmental clutter-index to identify and analyze the prerequisites and conditions for improving the overall system.
Abstract : As non-face-to-face activities have become commonplace, online video conferencing platforms have become popular collaboration tools. However, existing video conferencing platforms have a structure in which one side unilaterally exchanges information, potentially increase the fatigue of meeting participants. In this study, we designed a video conferencing platform utilizing virtual reality (VR), a metaverse technology, to enable various interactions. A virtual conferencing space and realistic VR video conferencing content authoring tool support system were designed using Meta’s Oculus Quest 2 hardware, the Unity engine, and 3D Max software. With the Photon software development kit, voice recognition was designed to perform automatic text translation with the Watson application programming interface, allowing the online video conferencing participants to communicate smoothly even if using different languages. It is expected that the proposed video conferencing platform will enable conference participants to interact and improve their work efficiency.
Abstract : Noise generated during image acquisition and transmission can negatively impact the results of image processing applications, and noise removal is typically a part of image preprocessing. Denoising techniques combined with nonlocal techniques have received significant attention in recent years, owing to the development of sophisticated hardware and image processing algorithms, much attention has been paid to; however, this approach is relatively poor for edge preservation of fine image details. To address this limitation, the current study combined a steering kernel technique with adaptive masks that can adjust the size according to the noise intensity of an image. The algorithm sets the steering weight based on a similarity comparison, allowing it to respond to edge components more effectively. The proposed algorithm was compared with existing denoising algorithms using quantitative evaluation and enlarged images. The proposed algorithm exhibited good general denoising performance and better performance in edge area processing than existing non-local techniques.
Abstract : This study evaluated the completeness of patient care report (PCR). A retrospective quality analysis was conducted using raw data of 122,140 EMS activity reports prepared by paramedics in Gyeonggi-do from April 1 to May 31, 2021. In all, 67,830 cases of normal transfers were statistically analyzed using IBM SPSS Statistics version 22, and statistical significance was set at p<0.5. The 119EMT_2 certificate was omitted in 50,037 (73.8%) cases, followed by time-related items in 1,227 (1.8%) cases. In the primary assessment of vital signs, systolic blood pressure was omitted and erroneous in 1,218 (1.9%) and 1,129 (1.8%) cases, respectively. In the secondary assessment, the completeness of all vital sign items was approximately 70%. Advanced emergency care and online medical control (OLMC) reporting showed discrepancies in all items. As the severity of the patient’s condition increased, the errors in the Patient care report (PCR) also increased, at a significant level (p= .00). Paramedics must be aware of the importance of completing the activity report.
Abstract : The performance of vision-based intelligent systems, such as self-driving cars and unmanned aerial vehicles, is subject to weather conditions, notably the frequently encountered haze or fog. As a result, studies on haze removal have garnered increasing interest from academia and industry. This paper hereby presents a 4K-capable hardware implementation of an efficient haze removal algorithm with the following two improvements. First, the depth-dependent haze distribution is predicted using a linear model of four haze-relevant features, where the model parameters are obtained through maximum likelihood estimates. Second, the approximated quad-decomposition method is adopted to estimate the atmospheric light. Extensive experimental results then follow to verify the efficacy of the proposed algorithm against well-known benchmark methods. For real-time processing, this paper also presents a pipelined architecture comprised of customized macros, such as split multipliers, parallel dividers, and serial dividers. The implementation results demonstrated that the proposed hardware design can handle DCI 4K videos at 30.8 frames per second.
Abstract : In this study, we propose training a support vector machine (SVM) model on top of deep networks for detecting Covid-19 from chest X-ray images. We started by gathering a real chest X-ray image dataset, including positive Covid-19, normal cases, and other lung diseases not caused by Covid-19. Instead of training deep networks from scratch, we fine-tuned recent pre-trained deep network models, such as DenseNet121, MobileNet v2, Inception v3, Xception, ResNet50, VGG16, and VGG19, to classify chest X-ray images into one of three classes (Covid-19, normal, and other lung). We propose training an SVM model on top of deep networks to perform a nonlinear combination of deep network outputs, improving classification over any single deep network. The empirical test results on the real chest X-ray image dataset show that deep network models, with an exception of ResNet50 with 82.44%, provide an accuracy of at least 92% on the test set. The proposed SVM on top of the deep network achieved the highest accuracy of 96.16%.
Abstract : Video surveillance is widely used in security surveillance, military navigation, intelligent transportation, etc. Its main research fields are pattern recognition, computer vision and artificial intelligence. This article uses OpenCV to detect and track vehicles, and monitors by establishing an adaptive model on a stationary background. Compared with traditional vehicle detection, it not only has the advantages of low price, convenient installation and maintenance, and wide monitoring range, but also can be used on the road. The intelligent analysis and processing of the scene image using CAMSHIFT tracking algorithm can collect all kinds of traffic flow parameters (including the number of vehicles in a period of time) and the specific position of vehicles at the same time, so as to solve the vehicle offset. It is reliable in operation and has high practical value.
Rong Ran, Member, KIICEJournal of information and communication convergence engineering 2022;20: 73-78 https://doi.org/10.6109/jicce.2022.20.2.73
Sampa ChauPattnaik, Mitrabinda Ray, Mitalimadhusmita Nayak, and Srikanta PatnaikJournal of information and communication convergence engineering 2022;20: 79-89 https://doi.org/10.6109/jicce.2022.20.2.79