This study introduces a data-driven approach for state and output feedback control addressing the constrained output regulation problem in unknown linear discrete-time systems. Our method ensures effective tracking pe...
详细信息
This study introduces a data-driven approach for state and output feedback control addressing the constrained output regulation problem in unknown linear discrete-time systems. Our method ensures effective tracking performance while satisfying the state and input constraints, even when system matrices are not available. We first establish a sufficient condition necessary for the existence of a solution pair to the regulator equation and propose a data-based approach to obtain the feedforward and feedback control gains for state feedback control using linear programming. Furthermore, we design a refined Luenberger observer to accurately estimate the system state, while keeping the estimation error within a predefined set. By combining output regulation theory, we develop an output feedback control strategy. The stability of the closed-loop system is rigorously proved to be asymptotically stable by further leveraging the concept of λ-contractive sets.
In recent years, mental health issues have profoundly impacted individuals’ well-being, necessitating prompt identification and intervention. Existing approaches grapple with the complex nature of mental health, faci...
详细信息
In recent years, mental health issues have profoundly impacted individuals’ well-being, necessitating prompt identification and intervention. Existing approaches grapple with the complex nature of mental health, facing challenges like task interference, limited adaptability, and difficulty in capturing nuanced linguistic expressions indicative of various conditions. In response to these challenges, our research presents three novel models employing multi-task learning (MTL) to understand mental health behaviors comprehensively. These models encompass soft-parameter sharing-based long short-term memory with attention mechanism (SPS-LSTM-AM), SPS-based bidirectional gated neural networks with self-head attention mechanism (SPS-BiGRU-SAM), and SPS-based bidirectional neural network with multi-head attention mechanism (SPS-BNN-MHAM). Our models address diverse tasks, including detecting disorders such as bipolar disorder, insomnia, obsessive-compulsive disorder, and panic in psychiatric texts, alongside classifying suicide or non-suicide-related texts on social media as auxiliary tasks. Emotion detection in suicide notes, covering emotions of abuse, blame, and sorrow, serves as the main task. We observe significant performance enhancement in the primary task by incorporating auxiliary tasks. Advanced encoder-building techniques, including auto-regressive-based permutation and enhanced permutation language modeling, are recommended for effectively capturing mental health contexts’ subtleties, semantic nuances, and syntactic structures. We present the shared feature extractor called shared auto-regressive for language modeling (S-ARLM) to capture high-level representations that are useful across tasks. Additionally, we recommend soft-parameter sharing (SPS) subtypes-fully sharing, partial sharing, and independent layer-to minimize tight coupling and enhance adaptability. Our models exhibit outstanding performance across various datasets, achieving accuracies of 96.9%, 97.
Data-driven process monitoring is an effective approach to assure safe operation of modern manufacturing and energy systems, such as thermal power plants being studied in this work. Industrial processes are inherently...
详细信息
Data-driven process monitoring is an effective approach to assure safe operation of modern manufacturing and energy systems, such as thermal power plants being studied in this work. Industrial processes are inherently dynamic and need to be monitored using dynamic algorithms. Mainstream dynamic algorithms rely on concatenating current measurement with past data. This work proposes a new, alternative dynamic process monitoring algorithm, using dot product feature analysis(DPFA).DPFA computes the dot product of consecutive samples, thus naturally capturing the process dynamics through temporal correlation. At the same time, DPFA's online computational complexity is lower than not just existing dynamic algorithms, but also classical static algorithms(e.g., principal component analysis and slow feature analysis). The detectability of the new algorithm is analyzed for three types of faults typically seen in process systems:sensor bias, process fault and gain change fault. Through experiments with a numerical example and real data from a thermal power plant, the DPFA algorithm is shown to be superior to the state-of-the-art methods, in terms of better monitoring performance(fault detection rate and false alarm rate) and lower computational complexity.
Here is a high demand for multimedia forensics analysts to locate the original camera of photographs and videos that are being taken nowadays. There has been considerable progress in the technology of identifying the ...
详细信息
Here is a high demand for multimedia forensics analysts to locate the original camera of photographs and videos that are being taken nowadays. There has been considerable progress in the technology of identifying the source of data, which has enabled conflict resolutions involving copyright infringements and identifying those responsible for serious offenses to be resolved. Video source identification is a challenging task nowadays due to easily available editing tools. This study focuses on the issue of identifying the camera model used to acquire video sequences used in this research that is, identifying the type of camera used to capture the video sequence under investigation. For this purpose, we created two distinct CNN-based camera model recognition techniques to be used in an innovative multi-modal setting. The proposed multi-modal methods combine audio and visual information in order to address the identification issue, which is superior to mono-modal methods which use only the visual or audio information from the investigated video to provide the identification information. According to legal standards of admissible evidence and criminal procedure, Forensic science involves the application of science to the legal aspects of criminal and civil law, primarily during criminal investigations, in line with the standards of admissible evidence and criminal procedure in the law. It is responsible for collecting, preserving, and analyzing scientific evidence in the course of an investigation. It has become a critical part of criminology as a result of the rapid rise in crime rates over the last few decades. Our proposed methods were tested on a well-known dataset known as the Vision dataset, which contains about 2000 video sequences gathered from various devices of varying types. It is conducted experiments on social media platforms such as YouTube and WhatsApp as well as native videos directly obtained from their acquisition devices by the means of their acquisiti
Perceptual image hashing is a significant and time-effective method for recognizing images within extensive databases, focusing on achieving two key objectives: robustness and discrimination. The right balance between...
详细信息
Total shoulder arthroplasty is a standard restorative procedure practiced by orthopedists to diagnose shoulder arthritis in which a prosthesis replaces the whole joint or a part of the *** is often challenging for doc...
详细信息
Total shoulder arthroplasty is a standard restorative procedure practiced by orthopedists to diagnose shoulder arthritis in which a prosthesis replaces the whole joint or a part of the *** is often challenging for doctors to identify the exact model and manufacturer of the prosthesis when it is *** paper proposes a transfer learning-based class imbalance-aware prosthesis detection method to detect the implant’s manufacturer automatically from shoulder X-ray *** framework of the method proposes a novel training approach and a new set of batch-normalization,dropout,and fully convolutional layers in the head *** employs cyclical learning rates and weighting-based loss calculation *** modifications aid in faster convergence,avoid local-minima stagnation,and remove the training bias caused by imbalanced *** proposed method is evaluated using seven well-known pre-trained models of VGGNet,ResNet,and DenseNet *** is performed on a shoulder implant benchmark dataset consisting of 597 shoulder X-ray *** proposed method improves the classification performance of all pre-trained models by 10–12%.The DenseNet-201-based variant has achieved the highest classification accuracy of 89.5%,which is 10%higher than existing ***,to validate and generalize the proposed method,the existing baseline dataset is supplemented to six classes,including samples of two more implant *** results have shown average accuracy of 86.7%for the extended dataset and show the preeminence of the proposed method.
Techniques that exploit spectral-spatial information have proven to be very effective in hyperspectral image classification. Joint sparse representation classification (JSRC) is one such technique which has been exten...
详细信息
Social network analysis provides quantifiable methods and topological metrics to examine the networked structure for several interdisciplinary applications. In our research, a social network of GitHub community is con...
详细信息
In vehicular ad-hoc networks (VANETs), ensuring passenger safety requires fast and reliable emergency message broadcasts. The current communication standard for messaging in VANETs is IEEE 802.11p. As IEEE 802.11p all...
详细信息
In vehicular ad-hoc networks (VANETs), ensuring passenger safety requires fast and reliable emergency message broadcasts. The current communication standard for messaging in VANETs is IEEE 802.11p. As IEEE 802.11p allows carrier-sense multiple access with collision avoidance (CSMA/CA) in the media access control (MAC) layer. A large contention window ($CW$) value will increase delay, whereas a small $CW$ value will increase the probability of collision. Therefore, adaptive regulation of the $CW$ value is needed to achieve high reliability and low delay in VANETs, in accordance with variations in the environment. However, the traditional MAC protocol cannot achieve the aforementioned requirements. Reinforcement learning (RL) emphasizes the selection of optimal action according to observations of the environment to achieve optimal system performance. In this study, a Q-learning (QL) RL algorithm based on IEEE 802.11p was used to achieve the requirements of adaptive broadcasting. Adaptive broadcasting was achieved based on a reward definition of high reliability and low delay for the QL algorithm. In this approach, the learning state is the $CW$ size, the system sets up a Q-table using RL, and the optimal action is based on the maximum Q-value. The $CW$ size can be provided with adaptive self-regulation by RL, providing high reliability and low delay for the broadcast of emergency messages. We also compared our proposed scheme to other QL-based MAC protocols in VANETs by performing simulations and demonstrated that it can achieve high reliability and low delay for the broadcast of emergency messages. IEEE
Convolutional neural networks (CNNs) have exceptionally performed across various computer vision tasks. However, their effectiveness depends heavily on the careful selection of hyperparameters. Optimizing these hyperp...
详细信息
暂无评论