Article
Computer Science, Interdisciplinary Applications
Ildar Lomov, Mark Lyubimov, Ilya Makarov, Leonid E. Zhukov
Summary: This paper investigates advanced approaches using deep learning methods in the field of fault detection in chemical processes, showing that with the recent advent of deep learning neural network methods and abundance of available sensor data, it became possible to develop advanced approaches to early fault detection and prediction that do not require feature engineering and provide more accurate and timely results. The proposed temporal CNN1D2D architecture achieved overall better performance on the dataset than any referenced method, and the use of Generative Adversarial Network GAN was suggested to extend and enrich data used in training.
JOURNAL OF INDUSTRIAL INFORMATION INTEGRATION
(2021)
Article
Computer Science, Interdisciplinary Applications
Davide Cacciarelli, Murat Kulahci
Summary: In recent years, studies have focused on the use of various types of autoencoders for monitoring complex nonlinear data in industrial and chemical processes. However, these studies have primarily focused on detection, resulting in difficulties for practitioners in interpreting complex models and obtaining candidate variables for root cause analysis. This paper proposes a novel statistical process control framework based on orthogonal autoencoders, which regularize the loss function to eliminate correlation among the features of latent variables. This significantly improves detection and diagnosis performance, particularly when the process variables are highly correlated.
COMPUTERS & CHEMICAL ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Zhen Cheng, Siwei Wang, Pei Zhang, Siqi Wang, Xinwang Liu, En Zhu
Summary: Deep autoencoder-based methods are the majority of deep anomaly detection, but they may have poor performance when distinguishing anomalies from normal data. To address this issue, an Improved AutoEncoder for unsupervised Anomaly Detection (IAEAD) is proposed, which optimizes for anomaly detection tasks and learns representations that preserve the local data structure.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2021)
Article
Energy & Fuels
Mingfei Hu, Xinyi Hu, Zhenzhou Deng, Bing Tu
Summary: In this paper, a kernel extreme learning machine (KELM) based on an adaptive variation sparrow search algorithm (AVSSA) is proposed for fault detection and diagnosis in large industrial systems. The performance of the fault classifier is improved by optimizing the dataset and the network hyperparameters, and the effectiveness of the proposed method is verified using multidimensional diagnostic metrics in a chemical process.
Article
Engineering, Chemical
Yu Bao, Bo Wang, Pandeng Guo, Jingtao Wang
Summary: The study proposes a fault diagnosis method combining deep convolutional neural networks with recurrent neural networks, which can adaptively learn the dynamic information of raw data in both spatial and temporal domains, and has unique advantages in multivariate chemical processes. The application of this method in the Tennessee Eastman process demonstrates high accuracy in identifying abnormal conditions compared to traditional fault identification algorithms of deep learning.
CANADIAN JOURNAL OF CHEMICAL ENGINEERING
(2022)
Article
Engineering, Chemical
Piyush Agarwal, Jorge Ivan Mireles Gonzalez, Ali Elkamel, Hector Budman
Summary: This paper presents a hierarchical structure based on a Deep LSTM Supervised Autoencoder Neural Network for the detection and classification of faults in industrial plants. The proposed methodology can classify incipient faults that are difficult to detect and diagnose with traditional and recent methods, and groups faults into subsets based on the difficulty of accurate classification.
Article
Computer Science, Information Systems
Wenhao Yu, Mengqiu Huang, Shangyou Wu, Yifan Zhang
Summary: Road anomaly detection aims to find exceptional roads in a transportation network that are different from others, which poses challenges for spatial data mining and urban infrastructure management. Existing methods mostly rely on the topology of road networks and have difficulty capturing spatial and temporal characteristics. To overcome this, we propose an ensembled autoencoder framework that combines spatiotemporal graph learning and graph masking methods to effectively detect topological and attribute anomalies based on traffic flow data.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Lei Zhang, Zhihuan Song, Qinghua Zhang, Zhiping Peng
Summary: Fault diagnosis is an important and challenging task, with intelligent fault diagnosis using deep learning becoming a research hotspot. The proposed generalized transformer method utilizes attention mechanism and ideas from graph attention network to achieve high performance in handling structured data.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Plant Sciences
Miro Miranda, Laura Zabawa, Anna Kicherer, Laurenz Strothmann, Uwe Rascher, Ribana Roscher
Summary: In this study, an automatic image-based machine learning approach is proposed for monitoring the damage of grape berries. A fully convolutional variational autoencoder is trained to detect damaged berries, and heatmaps are used to visualize the results and assist decision making. The proposed method outperforms a conventional convolutional autoencoder.
FRONTIERS IN PLANT SCIENCE
(2022)
Article
Engineering, Chemical
Shuyuan Zhang, Tong Qiu
Summary: Deep learning has gained significant attention in the field of chemical process fault diagnosis. However, most existing deep learning methods rely heavily on labeled data, while the mass of unlabeled data remains underutilized. In this study, a novel approach called LSTM-LAE is proposed to effectively utilize unlabeled data and improve fault diagnosis performance. LSTM is used to extract temporal features, while LAE is adopted for semi-supervised learning. The proposed method achieves interpretability and correctly localizes faults to relevant variables.
CHEMICAL ENGINEERING SCIENCE
(2022)
Article
Engineering, Chemical
Jian Wang, Yakun Li, Zhiyan Han
Summary: In this study, a novel unsupervised fault detection method named one-dimension convolutional adversarial autoencoder (1DAAE) is proposed, which utilizes one-dimensional convolution layers for feature extraction and imposes a prior distribution on the latent variables. Experimental results show that the proposed method outperforms other algorithms on the Tennessee Eastman process.
Article
Computer Science, Artificial Intelligence
Markus Thill, Wolfgang Konen, Hao Wang, Thomas Back
Summary: Learning temporal patterns in time series, especially for anomaly detection, remains challenging. The TCN-AE, an unsupervised temporal convolutional network autoencoder based on dilated convolutions, significantly outperforms other state-of-the-art anomaly detection algorithms on a real-world benchmark. Each new enhancement contributes to improving the overall performance of the algorithm.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Marta Catillo, Antonio Pecchia, Umberto Villano
Summary: The use of system logs to detect and troubleshoot anomalies in production systems has been known since the early days of computers. This paper presents the AutoLog approach, which focuses on anomaly detection by sampling logs and computing numeric scores at regular intervals. The results show high performance in detecting anomalies in industrial systems and public datasets, with a recall range between 0.96 and 0.99, and precision between 0.93 and 0.98. A comparative study with other methods further validates the effectiveness of AutoLog.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Interdisciplinary Applications
Piyush Agarwal, Melih Tamer, Hector Budman
Summary: This study focuses on the Statistical Process Control (SPC) of a manufacturing process using deep learning for fault detection and diagnosis (FDD). The application of explainable artificial intelligence (XAI) enhances model accuracy by quantifying explainability through a novel relevance measure of input variables, iteratively discards redundant input feature vectors/variables.
COMPUTERS & CHEMICAL ENGINEERING
(2021)
Article
Environmental Sciences
Nan Wang, Yuetian Shi, Haiwei Li, Geng Zhang, Siyuan Li, Xuebin Liu
Summary: Hyperspectral anomaly detection (HAD) is an important technique for object-based image analysis. This study proposes a Multi-Prior Graph Autoencoder (MPGAE) for HAD, which utilizes band selection, adaptive salient weight, and graph autoencoder. Experimental results demonstrate that the proposed MPGAE outperforms other state-of-the-art HAD detectors.
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.