Anomaly detection plays a critical role in ensuring safe, smooth, and efficient operation of machinery and equipment in industrial environments. With the wide deployment of multimodal sensors and the rapid development of Internet of Things (IoT), the data generated in modern industrial production has become increasingly diverse and complex. However, traditional methods for anomaly detection based on a single data source cannot fully utilize multimodal data to capture anomalies in industrial systems. To address this challenge, we propose a new model for anomaly detection in industrial environments using multimodal temporal data. This model integrates an attention-based autoencoder (AAE) and a generative adversarial network (GAN) to capture and fuse rich information from different data sources. Specifically, the AAE captures time-series dependencies and relevant features in each modality, and the GAN introduces adversarial regularization to enhance the model’s ability to reconstruct normal time-series data. We conduct extensive experiments on real industrial data containing both measurements from a distributed control system (DCS) and acoustic signals, and the results demonstrate the performance superiority of the proposed model over the state-of-the-art TimesNet for anomaly detection, with an improvement of 5.6% in F1 score.

The traditional 2D MUSIC algorithm fixes the azimuth or the elevation, and searches for the other without considering the directions of sources. A spectrum peak diffusion effect phenomenon is observed and may be utilized to detect the approximate directions of sources. Accordingly, a fast 2D MUSIC algorithm, which performs azimuth and elevation simultaneous searches (henceforth referred to as AESS) based on only three rounds of search is proposed. Firstly, AESS searches along a circle to detect the approximate source directions. Then, a subsequent search is launched along several straight lines based on these approximate directions. Finally, the 2D Direction of Arrival (DOA) of each source is derived by searching on several small concentric circles. Unlike the 2D MUSIC algorithm, AESS does not fix any azimuth and elevation parameters. Instead, the adjacent point of each search possesses different azimuth and elevation, i.e., azimuth and elevation are simultaneously searched to ensure that the search path is minimized, and hence the total spectral search over the angular field of view is avoided. Simulation results demonstrate the performance characters of the proposed AESS over some existing algorithms.

Fatigue detection for air traffic controllers is an important yet challenging problem in aviation safety research. Most of the existing methods for this problem are based on facial features. In this paper, we propose an ensemble learning model that combines both facial features and voice features and design a fatigue detection method through multifeature fusion, referred to as Facial and Voice Stacking (FV-Stacking). Specifically, for facial features, we first use OpenCV and Dlib libraries to extract mouth and eye areas and then employ a combination of M-Convolutional Neural Network (M-CNN) and E-Convolutional Neural Network (E-CNN) to determine the state of mouth and eye closure based on five features, i.e., blinking times, average blinking time, average blinking interval, Percentage of Eyelid Closure over the Pupil over Time (PERCLOS), and Frequency of Open Mouth (FOM). For voice features, we extract the Mel-Frequency Cepstral Coefficients (MFCC) features of speech. Such facial features and voice features are fused through a carefully designed stacking model for fatigue detection. Real-life experiments are conducted on 14 air traffic controllers in Southwest Air Traffic Management Bureau of Civil Aviation of China. The results show that the proposed FV-Stacking method achieves a detection accuracy of 97%, while the best accuracy achieved by a single model is 92% and the best accuracy achieved by the state-of-the-art detection methods is 88%.

Paper recommendation has become an increasingly important yet challenging task due to the rapidly expanding volume and scope of publications in the broad research community. Due to the lack of user profiles in public digital libraries, most existing methods for paper recommendation are through paper similarity measurements based on citations or contents, and still suffer from various performance issues. In this paper, we construct a graphical form of citation relations to identify relevant papers and design a hybrid recommendation model that combines both citation- and content-based approaches to measure paper similarities. Considering that citations at different locations in one article are likely of different significance, we define a concept of citation similarity with varying weights according to the sections of citations. We evaluate the performance of our recommendation method using Spearman correlation on real publication data from public digital libraries such as CiteSeer and Wanfang. Extensive experimental results show that the proposed hybrid method exhibits better performance than state-of-the-art techniques, and achieves 40% higher recommendation accuracy in average in comparison with citation-based approaches.

Many computing workloads in big data and machine learning applications are structured as directed acyclic graphs (DAG) and deployed on PC clusters for parallel execution using multiple physical or virtual machines. The scheduling of such workloads is critical to the application performance such as execution time and a plethora of techniques have been developed, taking into account various aspects such as data locality, network bandwidth, and server capability. We formulate DAG-structured workload scheduling as a nonlinear integer programming (NIP) problem and prove it to be NP-complete. Our empirical study reveals a positive correlation between scheduling plan distance (SPD) and finish time gap (FTG), and based on this finding, we propose a running time gap strategy (RTGS) to tackle this scheduling problem in multiprocessor environments. RTGS follows the main optimization strategy in the family of whale optimization algorithm (WOA). We derive a new function and use a greedy algorithm to generate an effective scheduling plan in RTGS. Extensive experiments with real production traces from Alibaba on simulation environments and realistic Hadoop environments show that our approach significantly improves the stability of WOA when applied to the scheduling problem of DAG-structured workloads, and also reduces the workload completion time by up to $$93\%$$ 93 % in comparison with seven state-of-the-art baseline algorithms.