Search

Coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), emerged as a global outbreak in 2019, profoundly affecting both human health and the global economy. Various vaccine modalities were developed and commercialized to overcome this challenge, including inactivated vaccines, mRNA vaccines, adenovirus vector-based vaccines, and subunit vaccines. While intramuscular vaccines induce high IgG levels, they often fail to stimulate significant mucosal immunity in the respiratory system. We employed the Newcastle disease virus (NDV) vector expressing the spike protein of the SARS-CoV-2 Beta variant (rK148/beta-S), and evaluated the efficacy of intranasal vaccination with rK148/beta-S in K18-hACE2 transgenic mice. Intranasal vaccination with a low dose (106.0 EID50) resulted in an 86% survival rate after challenge with the SARS-CoV-2 Beta variant. Administration at a high dose (107.0 EID50) led to a reduction in lung viral load and 100% survival against the SARS-CoV-2 Beta and Delta variants. A high level of the SARS-CoV-2 spike-specific IgA was also induced in vaccinated mice lungs following the SARS-CoV-2 challenge. Our findings suggest that rK148/beta-S holds promise as an intranasal vaccine candidate that effectively induces mucosal immunity against SARS-CoV-2. [ABSTRACT FROM AUTHOR]

Due to the immutability of blockchain, the integration with big-data systems creates limitations on redundancy, scalability, cost, and latency. Additionally, large amounts of invaluable data result in the waste of energy and storage resources. As a result, the demand for data deletion possibilities in blockchain has risen over the last decade. Although several prior studies have introduced methods to address data modification features in blockchain, most of the proposed systems need shorter deletion delays and security requirements. This study proposes a novel blockchain architecture called Unlichain that provides data-modification features within public blockchain architecture. To achieve this goal, Unlichain employed a new indexing technique that defines the deletion time for predefined lifetime data. The indexing technique also enables the deletion possibility for unknown lifetime data. Unlichain employs a new metadata verification consensus among full and meta nodes to avoid delays and extra storage usage. Moreover, Unlichain motivates network nodes to include more transactions in a new block, which motivates nodes to scan for expired data during block mining. The evaluations proved that Unlichain architecture successfully enables instant data deletion while the existing solutions suffer from block dependency issues. Additionally, storage usage is reduced by up to 10%. [ABSTRACT FROM AUTHOR]

Radiator reliability is crucial in environments characterized by high temperatures and friction, where prompt interventions are often required to prevent system failures. This study introduces a proactive approach to radiator fault diagnosis, leveraging the integration of the Gaussian Mixture Model and Long-Short Term Memory autoencoders. Vibration signals from radiators were systematically collected through randomized durability vibration bench tests, resulting in four operating states—two normal, one unknown, and one faulty. Time-domain statistical features of these signals were extracted and subjected to Principal Component Analysis to facilitate efficient data interpretation. Subsequently, this study discusses the comparative effectiveness of the Gaussian Mixture Model and Long Short-Term Memory in fault detection. Gaussian Mixture Models are deployed for initial fault classification, leveraging their clustering capabilities, while Long-Short Term Memory autoencoders excel in capturing time-dependent sequences, facilitating advanced anomaly detection for previously unencountered faults. This alignment offers a potent and adaptable solution for radiator fault diagnosis, particularly in challenging high-temperature or high-friction environments. Consequently, the proposed methodology not only provides a robust framework for early-stage fault diagnosis but also effectively balances diagnostic capabilities during operation. Additionally, this study presents the foundation for advancing reliability life assessment in accelerated life testing, achieved through dynamic threshold adjustments using both the absolute log-likelihood distribution of the Gaussian Mixture Model and the reconstruction error distribution of the Long-Short Term Memory autoencoder model. [ABSTRACT FROM AUTHOR]

As the utilization of complex and heavy applications increases in autonomous driving, research on using mobile edge computing and task offloading for autonomous driving is being actively conducted. Recently, researchers have been studying task offloading algorithms using artificial intelligence, such as reinforcement learning or partial offloading. However, these methods require a lot of training data and critical deadlines and are weakly adaptive to complex and dynamically changing environments. To overcome this weakness, in this paper, we propose a novel task offloading algorithm based on Lyapunov optimization to maintain the system stability and minimize task processing delay. First, a real-time monitoring system is built to utilize distributed computing resources in an autonomous driving environment efficiently. Second, the computational complexity and memory access rate are analyzed to reflect the characteristics of the deep learning applications to the task offloading algorithm. Third, Lyapunov and Lagrange optimization solves the trade-off issues between system stability and user requirements. The experimental results show that the system queue backlog remains stable, and the tasks are completed within an average of 0.4231 s, 0.7095 s, and 0.9017 s for object detection, driver profiling, and image recognition, respectively. Therefore, we ensure that the proposed task offloading algorithm enables the deep learning application to be processed within the deadline and keeps the system stable. [ABSTRACT FROM AUTHOR]

IOTA Tangle offers a promising approach for distributed ledger technology with the capability to compete with the traditional blockchain. To enable microtransactions the Internet of things (IoT) environment, IOTA employs a direct acrylic graph that ensures the integrity and immutability of the transactions. However, IoT data exhibit time sensitivity, wherein the value is lost after a period. Storing these temporary data for immutable storage would not be affordable in the distributed ledger. This study proposes a novel approach—referred to as D-Tangle—that enables data deletions in the Tangle architecture. To achieve this goal, D-Tangle divides transactions into three categories based on their expiration features and employs the climb-up writing technique. Extensive evaluations prove that D-Tangle enables instant deletions in finite lifetime data. Moreover, immutability and deletion upon request are guaranteed for unknown lifetime data. [ABSTRACT FROM AUTHOR]

Edge computing represents the future of computing paradigms that perform tasks near the user plane. The integration of blockchain with edge computing provides the added advantage of secured and trusted communication. In this paper, we propose a blockchain-based service migration by developing edge clusters using NVIDIA Jetson boards in an embedded edge environment, using containers and Kubernetes as a container orchestration capable of handling real-time computation-intensive deep learning tasks. Resource constraints in the edge and client movement are the proposed scenarios for service migration. Container migration due to mobile clients is integrated with blockchain to find a suitable destination, meta-based node evaluation, and secured data transfer in the connected car environment. Each service request migration takes, on average, 361 ms. The employed container migration method takes 75.11 s and 70.46 s to migrate application containers that use NVIDIA CUDA Toolkit. Finally, we evaluate the efficiency of blockchain to find the destination node through performance parameters such as latency, throughput, storage, and bandwidth. [ABSTRACT FROM AUTHOR]

Currently, the existing vehicle-centric semi-autonomous driving modules do not consider the driver's situation and emotions. In an autonomous driving environment, when changing to manual driving, human–machine interface and advanced driver assistance systems (ADAS) are essential to assist vehicle driving. This study proposes a human–machine interface that considers the driver's situation and emotions to enhance the ADAS. A 1D convolutional neural network model based on multimodal bio-signals is used and applied to control semi-autonomous vehicles. The possibility of semi-autonomous driving is confirmed by classifying four driving scenarios and controlling the speed of the vehicle. In the experiment, by using a driving simulator and hardware-in-the-loop simulation equipment, we confirm that the response speed of the driving assistance system is 351.75 ms and the system recognizes four scenarios and eight emotions through bio-signal data. [ABSTRACT FROM AUTHOR]

We evaluated the benefits of the MotionFree algorithm through phantom and patient studies. The various sizes of phantom and vacuum vials were linked to RPM moving with or without MotionFree application. A total of 600 patients were divided into six groups by breathing protocols and CT scanning time. Breathing protocols were applied as follows: (a) patients who underwent scanning without any breathing instructions; (b) patients who were instructed to hold their breath after expiration during CT scan; and (c) patients who were instructed to breathe naturally. The length of PET/CT misregistration was measured and we defined the misregistration when it exceeded 10 mm. In the phantom tests, the images produced by the MotionFree algorithm were observed to have excellent agreement with static images. There were significant differences in PET/CT misregistration according to CT scanning time and each breathing protocol. When applying the type (c) protocol, decreasing the CT scanning time significantly reduced the frequency and length of misregistrations (p < 0.05). The MotionFree application is able to correct respiratory motion artifacts and to accurately quantify lesions. The shorter time of CT scan can reduce the frequency, and the natural breathing protocol also decreases the lengths of misregistrations. [ABSTRACT FROM AUTHOR]

The gradual increase in latency-sensitive, real-time applications for embedded systems encourages users to share sensor data simultaneously. Streamed sensor data have deficient performance. In this paper, we propose a new edge-based scheduling method with high-bandwidth for decreasing driver-profiling latency. The proposed multi-level memory scheduling method places data in a key-value storage, flushes sensor data when the edge memory is full, and reduces the number of I/O operations, network latency, and the number of REST API calls in the edge cloud. As a result, the proposed method provides significant read/write performance enhancement for real-time embedded systems. In fact, the proposed application improves the number of requests per second by 3.5, 5, and 4 times, respectively, compared with existing light-weight FCN-LSTM, FCN-LSTM, and DeepConvRNN Attention solutions. The proposed application also improves the bandwidth by 5.89, 5.58, and 4.16 times respectively, compared with existing light-weight FCN-LSTM, FCN-LSTM, and DeepConvRNN Attention solutions. [ABSTRACT FROM AUTHOR]

Nonlinear model predictive control (NMPC) is based on a numerical optimization method considering the target system dynamics as constraints. This optimization process requires large amount of computation power and the computation time is often unpredictable which may cause the control update rate to overrun. Therefore, the performance must be carefully balanced against the computational time. To solve the computation problem, we propose a data-based control technique based on a deep neural network (DNN). The DNN is trained with closed-loop driving data of an NMPC. The proposed "DNN control technique based on NMPC driving data" achieves control characteristics comparable to those of a well-tuned NMPC within a reasonable computation period, which is verified with an experimental scaled-car platform and realistic numerical simulations. [ABSTRACT FROM AUTHOR]

Emotional awareness is vital for advanced interactions between humans and computer systems. This paper introduces a new multimodal dataset called MERTI-Apps based on Asian physiological signals and proposes a genetic algorithm (GA)—long short-term memory (LSTM) deep learning model to derive the active feature groups for emotion recognition. This study developed an annotation labeling program for observers to tag the emotions of subjects by their arousal and valence during dataset creation. In the learning phase, a GA was used to select effective LSTM model parameters and determine the active feature group from 37 features and 25 brain lateralization features extracted from the electroencephalogram (EEG) time, frequency, and time–frequency domains. The proposed model achieved a root-mean-square error (RMSE) of 0.0156 in terms of the valence regression performance in the MAHNOB-HCI dataset, and RMSE performances of 0.0579 and 0.0287 in terms of valence and arousal regression performance, and 65.7% and 88.3% in terms of valence and arousal accuracy in the in-house MERTI-Apps dataset, which uses Asian-population-specific 12-channel EEG data and adds an additional brain lateralization (BL) feature. The results revealed 91.3% and 94.8% accuracy in the valence and arousal domain in the DEAP dataset owing to the effective model selection of a GA. [ABSTRACT FROM AUTHOR]

This study focuses on driver-behavior identification and its application to finding embedded solutions in a connected car environment. We present a lightweight, end-to-end deep-learning framework for performing driver-behavior identification using in-vehicle controller area network (CAN-BUS) sensor data. The proposed method outperforms the state-of-the-art driver-behavior profiling models. Particularly, it exhibits significantly reduced computations (i.e., reduced numbers both of floating-point operations and parameters), more efficient memory usage (compact model size), and less inference time. The proposed architecture features depth-wise convolution, along with augmented recurrent neural networks (long short-term memory or gated recurrent unit), for time-series classification. The minimum time-step length (window size) required in the proposed method is significantly lower than that required by recent algorithms. We compared our results with compressed versions of existing models by applying efficient channel pruning on several layers of current models. Furthermore, our network can adapt to new classes using sparse-learning techniques, that is, by freezing relatively strong nodes at the fully connected layer for the existing classes and improving the weaker nodes by retraining them using data regarding the new classes. We successfully deploy the proposed method in a container environment using NVIDIA Docker in an embedded system (Xavier, TX2, and Nano) and comprehensively evaluate it with regard to numerous performance metrics. [ABSTRACT FROM AUTHOR]