Search

The traditional method for transformer moisture diagnosis is to establish empirical equations between feature parameters extracted from frequency domain spectroscopy (FDS) and the transformer’s moisture content. However, the established empirical equation may not be applicable to a novel testing environment, resulting in an unreliable evaluation result. In this regard, it is acknowledged that FDS combined with machine learning is more suitable for estimating moisture content in a variety of test environments. Nonetheless, the accuracy of the estimation results obtained using the existing method is limited by the algorithm’s inability to generalize. To address this issue, we propose an AdaBoost algorithm-enhanced back-propagation neural network (BP_AdaBoost). This study creates a database by extracting feature parameters from the FDS that characterize the insulation states of the prepared samples. Then, using the BP_AdaBoost algorithm and the newly constructed database, the moisture estimation models are trained. Finally, the results of the estimation are discussed in terms of laboratory and field transformers. By comparing the proposed BP_AdaBoost algorithm to other intelligence algorithms, it is demonstrated that it not only performs better in generalization, but also maintains a high level of accuracy. [ABSTRACT FROM AUTHOR]

Presents a study which showed how curve and surface representations of fiber network, fiber wall and fiber lumen can be computed using distance transform based algorithms. Motive for analyzing volume images of paper; Uses of the representations; Levels of detail in which the analysis of paper and paper fibers can be divided.

This paper proposes and evaluates two robust sheet tension estimation algorithms based on unwind and rewind variables, respectively. The proper sheet tension estimation is guaranteed by a continuous monitoring of the differences between the actual estimated values and the values predicted from the last calibration of the estimation parameters. The evaluation was performed with the aid of a developed winder emulator that allowed the offline testing in a real-time field environment, including the initial setting of the estimation constants, and evaluation of both four- and six-shipping-roll cycles. The sheet tension estimation results confirm the precise and stable operation of the proposed robust estimation algorithms, in tests conducted with signals from a winder model, and with tests involving actual field signals from an operational winder. [ABSTRACT FROM AUTHOR]

To satisfy the requirement of quality control in printing and packaging industry, a sheet counting apparatus is developed, which adopts a line-scan camera to image the fringes of sheet stack and is able to provide a real-time and noncontact measurement of their quantity. With a brief introduction of the system architecture, our main work focuses on the sheet counting algorithms. The basic principle is to identify each sheet profile from the 1-D image with a robust ridge strength measurement. First, a multiscale bi-Gaussian ridge likelihood measurement and a ridge-valley descriptor are utilized to improve adjacent objects detection by increasing local contrast around sheet fringes. Then, a sheet recognition scheme, which integrates a peak detection algorithm and the ridge region criteria for verification, is proposed to discriminate true sheets from the obtained ridgeness measure. According to experiments and tests in real production lines, our apparatus can reach a very high measuring accuracy for printing papers or cards with a thickness not <0.2 mm. [ABSTRACT FROM PUBLISHER]

Online sensing of sheet modulus of elasticity in the dry-end spans of printing grade paper machines (PMs) will permit the machine operators to control the mechanical properties of the produced paper. This paper develops an integrated sensorless tension control and sheet modulus of elasticity estimation algorithm, which is tested using field-recorded signals from a production PM and using a full model of the dry-end sections of this machine. Results show the ability of the proposed estimation algorithm to predict the sheet tension (tensile force) and sheet modulus of elasticity even in the presence of rapid changes in the speed and/or in other process operating conditions. The developed algorithms offer the papermaker new insights into the papermaking process. The ability to understand how modulus changes in real time provides a pathway to optimizing the operation of the PM drive system. [ABSTRACT FROM PUBLISHER]

A new dirty paper coding technique that is robust against the gain attack is presented. Such a robustness is obtained by adopting a set of (orthogonal) equienergetic codewords and a correlation-based decoder. Due to the simple structure of orthogonal codes, we developed a simple yet powerful technique to embed the hidden message within the host signal. The proposed technique is an optimal one, in that the embedding distortion is minimized for a given robustness level, where robustness is measured through the maximum pairwise error probability in the presence of an additive Gaussian attack of given strength. The performance of the dirty coding algorithm is further improved by replacing orthogonal with quasi- orthogonal codes, namely, Gold sequences, and by concatenating them with an outer turbo code. To this aim, the inner decoder is modified to produce a soft estimate of the embedded message. Performance analysis is carried out by means of extensive simulations proving the validity of the novel watermarking scheme. [ABSTRACT FROM AUTHOR]

Nonconvex constraints are valuable regularizers in many optimization problems. In particular, sparsity constraints have had a significant impact on sampling theory, where they are used in compressed sensing and allow structured signals to be sampled far below the rate traditionally prescribed. Nearly, all of the theory developed for compressed sensing signal recovery assumes that samples are taken using linear measurements. In this paper, we instead address the compressed sensing recovery problem in a setting where the observations are nonlinear. We show that, under conditions similar to those required in the linear setting, the iterative hard thresholding algorithm can be used to accurately recover sparse or structured signals from few nonlinear observations. Similar ideas can also be developed in a more general nonlinear optimization framework. In the second part of this paper, we therefore present related result that shows how this can be done under sparsity and union of subspaces constraints, whenever a generalization of the restricted isometry property traditionally imposed on the compressed sensing system holds. [ABSTRACT FROM PUBLISHER]

Visual text analytics has recently emerged as one of the most prominent topics in both academic research and the commercial world. To provide an overview of the relevant techniques and analysis tasks, as well as the relationships between them, we comprehensively analyzed 263 visualization papers and 4,346 mining papers published between 1992-2017 in two fields: visualization and text mining. From the analysis, we derived around 300 concepts (visualization techniques, mining techniques, and analysis tasks) and built a taxonomy for each type of concept. The co-occurrence relationships between the concepts were also extracted. Our research can be used as a stepping-stone for other researchers to 1) understand a common set of concepts used in this research topic; 2) facilitate the exploration of the relationships between visualization techniques, mining techniques, and analysis tasks; 3) understand the current practice in developing visual text analytics tools; 4) seek potential research opportunities by narrowing the gulf between visualization and mining techniques based on the analysis tasks; and 5) analyze other interdisciplinary research areas in a similar way. We have also contributed a web-based visualization tool for analyzing and understanding research trends and opportunities in visual text analytics. [ABSTRACT FROM AUTHOR]

A robust stability test for a class of constrained cross-directional controllers is found. Under special circumstances, the stability test is executed on a mode-by-mode basis and greatly simplified to a frequency-domain criterion. The test is also exploited to develop tuning algorithms. The control system involves a quadratic program embedded within an internal model control antiwindup structure and achieves optimal steady-state performance when the plant is known. Both the nonlinearity in the controller and the plant uncertainty satisfy certain integral quadratic inequalities. This allows us to obtain conditions for robust stability that can be expressed as linear matrix inequalities via the Kalman–Yakubovich–Popov lemma. [ABSTRACT FROM AUTHOR]

The Marching Cubes paper by Bill Lorensen and Harvey Cline, "Marching Cubes: A High Resolution 3D Surface Construction Algorithm," was published at SIGGRAPH 1987.1 According to Google Scholar, their paper has 15,667 citations (as of January 17, 2020), the most highly cited paper in computer graphics. Sadly, while writing this article Bill Lorensen passed away on December 12, 2019. Origins Department Editor Chris Johnson contributed the text in italics. EARLY [ABSTRACT FROM AUTHOR]

Since H.264/A VC achieves a high compression atio by reducing spatio-temporal redundancy in video equences, the payload of a single packet can often contain a vhole frame encoded by H.264/AVC. Therefore, the loss of a ingle packet does not only cause the loss of a whole frame, `ut also produce error propagation into succeeding frames. ~o deal with this problem, in this paper, we propose a novel ~rame error concealment method for ff264/A VC. First, the iroposed method extrapolates motion vectors from available reighboring frames onto the lost frame. Then, inter-modes of rh macroblocks in the lost frame are adaptively estimated by rsing the extrapolated motion vectors and features of 1.264/A VC. Experimental results exhibit that the proposed ~iethod outperforms the conventional methods in terms of roth objective and subjective video quality. [ABSTRACT FROM AUTHOR]

This paper focuses on minimum-time path tracking, a subproblem in motion planning of robotic systems. We generate a time-optimal velocity profile for robotic manipulators taking into account kinematic and dynamic constraints. Based on the special structure of the constraints (called peaked constraints), profile generation is formulated as a linear programming (LP) problem. The LP-based control problem is solved by a sequential optimization method. The presented algorithm has reduced computational time compared to a general LP solver. [ABSTRACT FROM AUTHOR]

This article presents a bibliography of the papers related to relay literature. The papers listed in this bibliography include references to the subjects of service restoration, testing and methods of calculation well as to the field of relaying. The references also include the title, author, publication information and a summary of the subject matter. Some of the entries in this bibliography are: "Symmetrical Components Estimation through Non-Recursive Newton-type Numerical Algorithm," "Signal Processing Module for Power System applications," "Variable-Window Algorithm for Ultra-High-Speed Distance Protection," "Wavelet-Based ANN Approach for Transmission Line Protection," and "Enhanced Transmission Line Protection Settings."

Fighting against the pandemic diseases with unique characters requires new sophisticated approaches like the artificial intelligence. This paper develops an artificial intelligence algorithm to produce multi-dimensional policies for controlling and minimizing the pandemic casualties under the limited pharmacological resources. In this respect, a comprehensive parametric model with a priority and age-specific vaccination policy and a variety of non-pharmacological policies are introduced. This parametric model is utilized for constructing an artificial intelligence algorithm by following the exact analogy of the model-based solution. Also, this parametric model is manipulated by the artificial intelligence algorithm to seek for the best multi-dimensional non-pharmacological policies that minimize the future pandemic casualties as desired. The role of the pharmacological and non-pharmacological policies on the uncertain future casualties are extensively addressed on the real data. It is shown that the developed artificial intelligence algorithm is able to produce efficient policies which satisfy the particular optimization targets such as focusing on minimization of the death casualties more than the infected casualties or considering the curfews on the people age over 65 rather than the other non-pharmacological policies. The paper finally analyses a variety of the mutant virus cases and the corresponding non-pharmacological policies aiming to reduce the morbidity and mortality rates. [ABSTRACT FROM AUTHOR]

Many datasets including social media data and bibliographic data can be modeled as graphs. Clustering such graphs is able to provide useful insights into the structure of the data. To improve the quality of clustering, node attributes can be taken into account, resulting in attributed graphs. Existing attributed graph clustering methods generally consider attribute similarity and structural similarity separately. In this paper, we represent attributed graphs as star-schema heterogeneous graphs, where attributes are modeled as different types of graph nodes. This enables the use of personalized pagerank (PPR) as a unified distance measure that captures both structural and attribute similarities. We employ DBSCAN for clustering, and we update edge weights iteratively to balance the importance of different attributes. The rapidly growing volume of data nowadays challenges traditional clustering algorithms, and thus, a distributed method is required. Hence, we adopt a popular distributed graph computing system Blogel, based on which, we develop four exact and approximate approaches that enable efficient PPR score computation when edge weights are updated. To improve the effectiveness of the clustering, we propose a simple yet effective edge weight update strategy based on entropy. In addition, we present a game theory based method that enables trading efficiency for result quality. Extensive experiments on real-life datasets offer insights into the effectiveness and efficiency of our proposals. [ABSTRACT FROM AUTHOR]

This paper is concerned with online coverage of unknown planar environments by a mobile robot of size D operating with a limited energy capacity battery. The battery capacity is represented by the path length L that the robot can travel under a full battery charge. Starting at S, the robot has to cover a planar environment containing unknown obstacles, and return to S upon task completion. During task execution, the robot may return to S at any time to recharge its battery. This paper first describes a battery powered offline coverage methodology, then introduces the battery powered coverage (BPC) algorithm that performs online battery powered coverage using position and local obstacle detection sensors. The performance of the BPC algorithm is measured by its competitiveness, determined by measuring the mobile robot’s total online path length, l, relative to the optimal offline solution lopt. This paper establishes that the BPC algorithm has a competitive performance of l \leq ( L/ D) lopt. This paper additionally establishes a universal lower bound of l \geq \log ( L/ 4 D) lopt over all online battery powered coverage algorithms. Execution example illustrates the usefulness of the BPC algorithm. [ABSTRACT FROM AUTHOR]

The latest of a series of classified lists of power system relaying references, begun in 1927, is presented. This bibliography is in continuation to the bibliographies of relay literature, which were published previously and are contained in the following volumes of the IEEE Transactions: [ABSTRACT FROM AUTHOR]

This paper presents an integrated color imaging system for taking images in extremely high dynamic range scenes. The system first fuses several differently exposed raw images to acquire more intensity information. The effective dynamic range of the image raw data can be extended to 256 times ~five differently exposed images are fused. Then it runs edge detection iterations to extract the image details in different luminance levels. The proposed tone reproduction algorithm equalizes the histogram of the extracted fine edges which tends to assign larger dynamic range for highly populated regions. Finally, the local contrast enhancement is performed to further refine the image details. The experimental results show that the proposed high dynamic range imaging system has good performance on both tone and color reproduction'. [ABSTRACT FROM AUTHOR]

Many networked embedded sensing and control systems can be modeled as hybrid systems with interacting continuous and discrete dynamics. These systems present significant challenges for monitoring and diagnosis. Many existing model-based approaches focus on diagnostic reasoning assuming appropriate fault signatures have been generated. However, an important missing piece is the integration of model-based techniques with the acquisition and processing of sensor signals and the modeling of faults to support diagnostic reasoning. This paper addresses key modeling and computational problems at the interface between model-based diagnosis techniques and signature analysis to enable the efficient detection and isolation of incipient and abrupt faults in hybrid systems. A hybrid automata model that parameterizes abrupt and incipient faults is introduced. Based on this model, an approach for diagnoser design is presented. The paper also develops a novel mode estimation algorithm that uses model-based prediction to focus distributed processing signal algorithms. Finally. the paper describes a diagnostic system architecture that integrates the modeling, prediction, and diagnosis components. The implemented architecture is applied to fault diagnosis of a complex electro-mechanical machine, the Xerox DC265 printer, and the experimental results presented validate the approach. A number of design trade-otis that were made to support implementation of the algorithms for online applications are also described. [ABSTRACT FROM AUTHOR]

In one of the several manifestations, the future cellular networks are required to accommodate a massive number of devices, several orders of magnitude compared to today’s networks. At the same time, the future cellular networks will have to fulfill stringent latency constraints. To that end, one problem that is posed as a potential showstopper is extreme congestion for requesting uplink scheduling over the physical random access channel (PRACH). Indeed, such congestion drags along scheduling delay problems. In this paper, the use of self-organized device-to-device (D2D) clustering is advocated for mitigating PRACH congestion. To this end, this paper proposes two D2D clustering schemes, namely, random-based clustering and channel-gain-based clustering. Accordingly, this paper sheds light on random access within the proposed D2D clustering schemes and presents a case study based on a stochastic geometry framework. For the sake of objective evaluation, the D2D clustering is benchmarked by the conventional scheduling request procedure. Accordingly, this paper offers insights into useful scenarios that minimize the scheduling delay for each clustering scheme. Finally, this paper discusses the implementation algorithm and some potential implementation issues and remedies. [ABSTRACT FROM AUTHOR]

The presence of condensate inside the dryer cylinders of a paper machine produces a significant increase in the power required to accelerate the section, risking a drive overload and/or section shutdown. In previous works, the authors developed a robust estimation algorithm for the condensate power and a generalized correlation for the estimation of condensate loads in industrial dryer cylinders up to 55 mm of condensate rim. This paper presents and evaluates a rule-based expert system (ES) capable of detecting the presence and amount of condensate in up to three groups of cylinders with different condensate loads. The ES can give an early warning message to the operators and determine the condensate load and number of cylinders within each group. Evaluation is done using a combined condensate load for a fictitious 1500-mm eight-cylinder dryer section. Results show the capacity of the developed ES to give an early warning as well as a correct estimation of the condensate loads and number of cylinders involved. [ABSTRACT FROM PUBLISHER]

Dirty paper coding (DPC) scheme is the capacity achieving transmission technique in multiuser MIMO downlink channels. As a suboptimal solution to DPC, successive zero-forcing DPC (SZF-DPC) has been proposed recently. The zero-interference constraint in designing the precoding matrices limits the number of supportable users. In this correspondence, we propose three low-complexity suboptimal user scheduling algorithms to exploit the multiuser diversity gain in SZF-DPC as the number of users grows. The first algorithm greedily maximizes the true sum rate. The second algorithm is based on eigenvalues. The third algorithm relies on the diagonal elements of the effective channel matrix since eigenvalues and diagonal entries of a Hermitian matrix have a strong relationship. Simulation results show that the proposed scheduling algorithms can obtain a significant fraction of sum rate of the optimal solution. Furthermore, the performance analysis is provided to prove that the proposed user selection algorithms can achieve the same asymptotic sum rate as that of DPC. [ABSTRACT FROM AUTHOR]

This article discusses how a hybrid algorithm based on a genetic algorithm (GA) and linear programming helps minimize distribution costs for the Scandinavian pulp producer Sodra Cell. The GA considers a planner's perspective by defining an individual schedule as the sequences of routes for all ships in a fixed fleet. Because the GA operates on a pool of potential solutions, constantly adjusting them to better fit the requirements, it can suggest multiple solutions. Furthermore, it can serve as a core algorithm in a support system where one can apply small changes to the set of constraints without a cold start. Applying the GA to Sodra Cell's real-world case and comparing it to mixed-integer-programming approach revealed competitive results. INSET: Related Work in Genetic Algorithms..

Recently developed monitoring-systems show the need as also the possibilities for online- and offline-onsite-diagnostics. The limit in sensitivity for electrical pd-measurements according to IEC 60270 which is reached using filters for sinusoidal disturbances and compensation for corona impulses is still not satisfactory. The acoustic partial discharge measurement (pd-measurement) is also a well known and reliable method often used by transformer manufacturers in testing. In laboratory setups a gain in sensitivity of the acoustic in comparison to the electrical pd measurements could be established. This is reached by adapting the sensors to the propagation path, a modern but moderately priced acquisition hardware and the introduction of new signal processing algorithms. The developed sophisticated measuring, systems show remarkable results in online acoustic pd-measurements onsite. [ABSTRACT FROM AUTHOR]

The presence of condensate inside the dryer cylinders produces a significant increase in the power requirements during starting, putting at risk the capacity of the drive to complete a successful start. In past papers, authors developed estimation algorithms for the detection of condensate during section starting. This paper proposes and evaluates a new strategy that will complement the previous algorithms. This strategy will detect the presence of condensate from the condensate collapsing during the section shutdown. The proposed correlations are derived through a complete experimental evaluation in two experimental cylinders covering rim thicknesses up to 55 mm. The estimation algorithms are split into a low-/moderate-condensate-load zone and a high-condensate-load zone. Results confirm the robustness and accuracy of the proposed algorithms. [ABSTRACT FROM PUBLISHER]

Seizure prediction using EEG has significant implications for the daily monitoring and treatment of epilepsy patients. However, the task is challenging due to the underlying spatiotemporal correlations and patient heterogeneity. Traditional methods often use large-scale models with independent components to capture the spatial and temporal features of EEG separately or explore shared patterns among patients with the help of pre-defined functional connectivity. In this paper, we propose a compact model, called the graph convolutional network based on adaptive functional connectivity (AFC-GCN), for seizure prediction. The model can adaptively infer evolution of functional connectivity in epilepsy patients during seizures through data-driven methods and synchronously analyze spatiotemporal response of functional connectivity in multiple topologies. On CHB-MIT datasets, the experimental results demonstrate that AFC-GCN achieves accurate and robust performance with low complexity. (AUC: 0.9820, accuracy: 0.9815, sensitivity: 0.9802, FPR: 0.0172). The proposed method has the potential to predict seizure during daily monitoring.

Early-exiting has recently provided an ideal solution for accelerating activity inference by attaching internal classifiers to deep neural networks. It allows easy activity samples to be predicted at shallower layers, without executing deeper layers, hence leading to notable adaptiveness in terms of accuracy-speed trade-off under varying resource demands. However, prior most works typically optimize all the classifiers equally on all types of activity data. As a result, deeper classifiers will only see hard samples during test phase, which renders the model suboptimal due to the training-test data distribution mismatch. Such issue has been rarely explored in the context of activity recognition. In this paper, to close the gap, we propose to organize all these classifiers as a dynamic-depth network and jointly optimize them in a similar gradient-boosting manner. Specifically, a gradient-rescaling is employed to bound the gradients of parameters at different depths, that makes such training procedure more stable. Particularly, we perform a prediction reweighting to emphasize current deep classifier while weakening the ensemble of its previous classifiers, so as to relieve the shortage of training data at deeper classifiers. Comprehensive experiments on multiple HAR benchmarks including UCI-HAR, PAMAP2, UniMiB-SHAR, and USC-HAD verify that it is state-of-the-art in accuracy and speed. A real implementation is measured on an ARM-based mobile device.

Training an accurate classifier for EEG-based brain-computer interface (BCI) requires EEG data from a large number of users, whereas protecting their data privacy is a critical consideration. Federated learning (FL) is a promising solution to this challenge. This paper proposes Federated classification with local Batch-specific batch normalization and Sharpness-aware minimization (FedBS) for privacy protection in EEG-based motor imagery (MI) classification. FedBS utilizes local batch-specific batch normalization to reduce data discrepancies among different clients, and sharpness-aware minimization optimizer in local training to improve model generalization. Experiments on three public MI datasets using three popular deep learning models demonstrated that FedBS outperformed six state-of-the-art FL approaches. Remarkably, it also outperformed centralized training, which does not consider privacy protection at all. In summary, FedBS protects user EEG data privacy, enabling multiple BCI users to participate in large-scale machine learning model training, which in turn improves the BCI decoding accuracy.

Early brain-computer interface (BCI) systems were mainly based on prior neurophysiological knowledge coupled with feedback training, while state-of-the-art interfaces rely on data-driven, machine learning (ML)-oriented methods. Despite the advances in BCI that ML can be credited with, the performance of BCI solutions is still not up to the mark, posing a major barrier to the widespread use of this technology. This paper proposes a novel, automatic feature selection method for BCI able to leverage both data-dependent and expert knowledge to suppress noisy features and highlight the most relevant ones thanks to a fuzzy logic (FL) system. Our approach exploits the capability of FL to increase the reliability of decision-making by fusing heterogeneous information channels while maintaining transparency and simplicity. We show that our method leads to significant improvement in classification accuracy, feature stability and class bias when applied to large motor imagery or attempt datasets including end-users with motor disabilities. We postulate that combining data-driven methods with knowledge derived from neuroscience literature through FL can enhance the performance, explainability, and learnability of BCIs.

Electroencephalography (EEG) artifacts are very common in clinical diagnosis and can heavily impact diagnosis. Manual screening of artifact events is labor-intensive with little benefit. Therefore, exploring algorithms for automatic detection and classification of EEG artifacts can significantly assist clinical diagnosis. In this paper, we propose a learnable and explainable wavelet neural network (WaveNet) for EEG artifact detection and classification. The model is powered by the wavelet decomposition block based on invertible neural network, which can extract signal features without information loss, and a tree generator for building wavelet tree structure automatically. They provide the model with good feature extraction capabilities and explainability. To evaluate the model's performance more fairly, we introduce the base point level matching score (BASE) and the Event-Aligned Compensation Scoring (EACS) at the event level as two metrics for model performance evaluation. On the challenging Temple University EEG Artifact (TUAR) dataset, our model outperforms other baselines in terms of F1-score for both artifact detection and classification tasks. The case study also validates the model's ability to offer explainability for predictions based on frequency band energy, suggesting potential applications in clinical diagnosis.

Recently, pressure-sensing mats have been widely used to capture static and dynamic pressure over sleep for posture recognition. Both a full-size mat with a low-density sensing array for figuring out the structure of the whole body and a miniature scale mat with a high-density sensing array for identifying the local characteristics around the chest have been investigated. However, both of the mat systems may face the challenge in the trade-off between the computational complexity (involving the size, density, etc. of the mat) and the performance of sleep posture recognition, where high performance may requires overcomplex computation and result in time latency in real-time sleep posture monitoring. In this paper, a lightweight neural network named ConcatNet, is proposed to realize sleep postures (supine, left, right, and prone) recognition in real time while maintaining a favorable performance. In ConcatNet, the inception module is proposed to extract the image features under multiple receptive fields, while the multi-layer feature fusion module is utilized to fuse deep and shallow features to enhance the model performance. To further improve the efficiency of the model, the depthwise convolution is adopoted. ConcatNet models in 3 different scales (ConcatNet-S, ConcatNet-M, and ConcatNet-L) are built to explore the impact of the sensor density on sleep posture recognition performance. Experimental results exhibit that ConcatNet-M corresponding to medium sensor density ( 16×16 ) achieved the best comprehensive performance, with short-term data cross-validation accuracy at 95.56% and overnight data testing accuracy at 94.68%. The model size is 7.91KB, FLOPs is 56.47K, and the inference time is only 0.38ms, which shows an outstanding performance of real-time sleep posture recognition with minimum consumption, indicating the potential to be deployed in mobile devices.

Advancements in machine learning offer promising avenues for the identification of ADHD symptoms in adults, an endeavour traditionally encumbered by the intricacies of human behavioural patterns. In this paper, we introduce three innovative dual-stream models. The proposed approach utilises a novel multi-modal dataset recorded for ADHD symptoms detection, leveraging RGB video alongside facial, body posture and hand landmark data. The fusion of these different sub-modalities within video enhances the discriminative capability of the ADHD symptoms detection system. A primary objective was to maintain minimal model depth while achieving competitive performance. Through randomised search cross-validation and a rigorous leave-one-out validation scheme, the proposed model achieves high generalisability and robust symptom identification, suggesting strong potential for application in clinical environments. Evaluation boasts the state-of-the-art performance of the proposed model, demonstrating an accuracy of 98.67%, a precision of 98.01%, and a recall of 98.88%. These metrics attest to the model's ability to consistently identify ADHD symptoms while maintaining a minimal parameter footprint. This delicate balance provides a significant step forward in behavioural health analytics.

Sleep staging serves as a fundamental assessment for sleep quality measurement and sleep disorder diagnosis. Although current deep learning approaches have successfully integrated multimodal sleep signals, enhancing the accuracy of automatic sleep staging, certain challenges remain, as follows: 1) optimizing the utilization of multi-modal information complementarity, 2) effectively extracting both long- and short-range temporal features of sleep information, and 3) addressing the class imbalance problem in sleep data. To address these challenges, this paper proposes a two-stream encode-decoder network, named TSEDSleepNet, which is inspired by the depth sensitive attention and automatic multi-modal fusion (DSA2F) framework. In TSEDSleepNet, a two-stream encoder is used to extract the multiscale features of electrooculogram (EOG) and electroencephalogram (EEG) signals. And a self-attention mechanism is utilized to fuse the multiscale features, generating multi-modal saliency features. Subsequently, the coarser-scale construction module (CSCM) is adopted to extract and construct multi-resolution features from the multiscale features and the salient features. Thereafter, a Transformer module is applied to capture both long- and short-range temporal features from the multi-resolution features. Finally, the long- and short-range temporal features are restored with low-layer details and mapped to the predicted classification results. Additionally, the Lovász loss function is applied to alleviate the class imbalance problem in sleep datasets. Our proposed method was tested on the Sleep-EDF-39 and Sleep-EDF-153 datasets, and it achieved classification accuracies of 88.9% and 85.2% and Macro-F1 scores of 84.8% and 79.7%, respectively, thus outperforming conventional traditional baseline models. These results highlight the efficacy of the proposed method in fusing multi-modal information. This method has potential for application as an adjunct tool for diagnosing sleep disorders.

Dopaminergic treatment has proved effective to Parkinson's disease (PD), but the conventional treatment assessment is human-administered and prone to intra- and inter-assessor variability. In this paper, we propose a knowledge-driven framework and discover that brain ACtivation-Transition-Spectrum (ACTS) features achieve effective quantified assessments of dopaminergic therapy in PD. Firstly, brain activities of fifty-one PD patients during clinical walking tests under the OFF and ON states (without and with dopaminergic medication) were measured with functional near-infrared spectroscopy (fNIRS). Then, brain ACTS features were formulated based on the medication-induced variations in temporal features of brain regional activation, transition features of brain hemodynamic states, and graph spectrum of brain functional connectivity. Afterwards, a prior selection algorithm was constructed based on recursive feature elimination and graph spectrum analysis for the selection of principal discriminative features. Further, linear discriminant analysis was conducted to predict the treatment-induced improvements. The results demonstrated that the proposed method decreased the misclassification probability from 42% to 16% in the evaluations of dopaminergic treatment and outperformed existing fNIRS-based methods. Therefore, the proposed method promises a quantified and objective approach for dopaminergic treatment assessment, and our brain ACTS features may serve as promising functional biomarkers for treatment evaluation.

Facial palsy evaluation (FPE) aims to assess facial palsy severity of patients, which plays a vital role in facial functional treatment and rehabilitation. The traditional manners of FPE are based on subjective judgment by clinicians, which may ultimately depend on individual experience. Compared with subjective and manual evaluation, objective and automated evaluation using artificial intelligence (AI) has shown great promise in improving traditional manners and recently received significant attention. The motivation of this survey paper is mainly to provide a systemic review that would guide researchers in conducting their future research work and thus make automatic FPE applicable in real-life situations. In this survey, we comprehensively review the state-of-the-art development of AI-based FPE. First, we summarize the general pipeline of FPE systems with the related background introduction. Following this pipeline, we introduce the existing public databases and give the widely used objective evaluation metrics of FPE. In addition, the preprocessing methods in FPE are described. Then, we provide an overview of selected key publications from 2008 and summarize the state-of-the-art methods of FPE that are designed based on AI techniques. Finally, we extensively discuss the current research challenges faced by FPE and provide insights about potential future directions for advancing state-of-the-art research in this field.

Decoding natural language from noninvasive brain signals has been an exciting topic with the potential to expand the applications of brain-computer interface (BCI) systems. However, current methods face limitations in decoding sentences from electroencephalography (EEG) signals. Improving decoding performance requires the development of a more effective encoder for the EEG modality. Nonetheless, learning generalizable EEG representations remains a challenge due to the relatively small scale of existing EEG datasets. In this paper, we propose enhancing the EEG encoder to improve subsequent decoding performance. Specifically, we introduce the discrete Conformer encoder (D-Conformer) to transform EEG signals into discrete representations and bootstrap the learning process by imposing EEG-language alignment from the early training stage. The D-Conformer captures both local and global patterns from EEG signals and discretizes the EEG representation, making the representation more resilient to variations, while early-stage EEG-language alignment mitigates the limitations of small EEG datasets and facilitates the learning of the semantic representations from EEG signals. These enhancements result in improved EEG representations and decoding performance. We conducted extensive experiments and ablation studies to thoroughly evaluate the proposed method. Utilizing the D-Conformer encoder and bootstrapping training strategy, our approach demonstrates superior decoding performance across various tasks, including word-level, sentence-level, and sentiment-level decoding from EEG signals. Specifically, in word-level classification, we show that our encoding method produces more distinctive representations and higher classification performance compared to the EEG encoders from existing methods. At the sentence level, our model outperformed the baseline by 5.45%, achieving a BLEU-1 score of 42.31%. Furthermore, in sentiment classification, our model exceeded the baseline by 14%, achieving a sentiment classification accuracy of 69.3%.

Deep learning methods have advanced quickly in brain imaging analysis over the past few years, but they are usually restricted by the limited labeled data. Pre-trained model on unlabeled data has presented promising improvement in feature learning in many domains, such as natural language processing. However, this technique is under-explored in brain network analysis. In this paper, we focused on pre-training methods with Transformer networks to leverage existing unlabeled data for brain functional network classification. First, we proposed a Transformer-based neural network, named as BrainNPT, for brain functional network classification. The proposed method leveraged token as a classification embedding vector for the Transformer model to effectively capture the representation of brain networks. Second, we proposed a pre-training framework for BrainNPT model to leverage unlabeled brain network data to learn the structure information of brain functional networks. The results of classification experiments demonstrated the BrainNPT model without pre-training achieved the best performance with the state-of-the-art models, and the BrainNPT model with pre-training strongly outperformed the state-of-the-art models. The pre-training BrainNPT model improved 8.75% of accuracy compared with the model without pre-training. We further compared the pre-training strategies and the data augmentation methods, analyzed the influence of the parameters of the model, and explained the trained model.

Early diagnosis and intervention of depression promote complete recovery, with its traditional clinical assessments depending on the diagnostic scales, clinical experience of doctors and patient cooperation. Recent researches indicate that functional near-infrared spectroscopy (fNIRS) based on deep learning provides a promising approach to depression diagnosis. However, collecting large fNIRS datasets within a standard experimental paradigm remains challenging, limiting the applications of deep networks that require more data. To address these challenges, in this paper, we propose an fNIRS-driven depression recognition architecture based on cross-modal data augmentation (fCMDA), which converts fNIRS data into pseudo-sequence activation images. The approach incorporates a time-domain augmentation mechanism, including time warping and time masking, to generate diverse data. Additionally, we design a stimulation task-driven data pseudo-sequence method to map fNIRS data into pseudo-sequence activation images, facilitating the extraction of spatial-temporal, contextual and dynamic characteristics. Ultimately, we construct a depression recognition model based on deep classification networks using the imbalance loss function. Extensive experiments are performed on the two-class depression diagnosis and five-class depression severity recognition, which reveal impressive results with accuracy of 0.905 and 0.889, respectively. The fCMDA architecture provides a novel solution for effective depression recognition with limited data.

In recent years, the steady-state visual evoked potentials (SSVEP) based brain control method has been employed to help people with disabilities because of its advantages of high information transmission rate and low training time. However, the existing SSVEP brain control methods cannot adapt to dynamic or unstructured environments. Moreover, the recognition accuracy from the conventional decoding algorithm still needs to improve. To address the above problems, this study proposed a steady-state hybrid visual evoked potentials (SSHVEP) paradigm using the grasping targets in their environment to improve the connection between the subjects' and their dynamic environments. Moreover, a novel EEG decoding method, using the multivariate variational mode decomposition (MVMD) algorithm for adaptive sub-band division and convolutional neural network (CNN) for target recognition, was applied to improve the decoding accuracy of the SSHVEPs. 18 subjects participated in the offline and online experiments. The offline accuracy across 18 subjects by the 9-target SSHVEP paradigm was up to 95.41 ± 2.70 %, which is a 5.80% improvement compared to the conventional algorithm. To further validate the performance of the proposed method, the brain-controlled grasping robot system using the SSHVEP paradigm was built. The average accuracy reached 93.21 ± 10.18 % for the online experiment. All the experimental results demonstrated the effectiveness of the brain-computer interaction method based on the SSHVEP paradigm and the MVMD combined CNN algorithm studied in this paper.

The existing surface electromyography-based pattern recognition system (sEMG-PRS) exhibits limited generalizability in practical applications. In this paper, we propose a stacked weighted random forest (SWRF) algorithm to enhance the long-term usability and user adaptability of sEMG-PRS. First, the weighted random forest (WRF) is proposed to address the issue of imbalanced performance in standard random forests (RF) caused by randomness in sampling and feature selection. Then, the stacking is employed to further enhance the generalizability of WRF. Specifically, RF is utilized as the base learner, while WRF serves as the meta-leaning layer algorithm. The SWRF is evaluated against classical classification algorithms in both online experiments and offline datasets. The offline experiments indicate that the SWRF achieves an average classification accuracy of 89.06%, outperforming RF, WRF, long short-term memory (LSTM), and support vector machine (SVM). The online experiments indicate that SWRF outperforms the aforementioned algorithms regarding long-term usability and user adaptability. We believe that our method has significant potential for practical application in sEMG-PRS.

Electroencephalography (EEG) signals are the brain signals acquired using the non-invasive approach. Owing to the high portability and practicality, EEG signals have found extensive application in monitoring human physiological states across various domains. In recent years, deep learning methodologies have been explored to decode the intricate information embedded in EEG signals. However, since EEG signals are acquired from humans, it has issues with acquiring enormous amounts of data for training the deep learning models. Therefore, previous research has attempted to develop pre-trained models that could show significant performance improvement through fine-tuning when data are scarce. Nonetheless, existing pre-trained models often struggle with constraints, such as the necessity to operate within datasets of identical configurations or the need to distort the original data to apply the pre-trained model. In this paper, we proposed the domain-free transformer, called DFformer, for generalizing the EEG pre-trained model. In addition, we presented the pre-trained model based on DFformer, which is capable of seamless integration across diverse datasets without necessitating architectural modification or data distortion. The proposed model achieved competitive performance across motor imagery and sleep stage classification datasets. Notably, even when fine-tuned on datasets distinct from the pre-training phase, DFformer demonstrated marked performance enhancements. Hence, we demonstrate the potential of DFformer to overcome the conventional limitations in pre-trained model development, offering robust applicability across a spectrum of domains.

Modeling the muscle response to functional electrical stimulation (FES) is an important step during model-based FES control system design. The Hammerstein structure is widely used in simulating this nonlinear biomechanical response. However, a fixed relationship cannot cope well with the time-varying property of muscles and muscle fatigue. In this paper, we proposed an adaptive Hammerstein model to predict ankle joint torque induced by electrical stimulation, which used variable forgetting factor recursive least squares (VFFRLS) method to update the model parameters. To validate the proposed model, ten healthy individuals were recruited for short-duration FES experiments, ten for long-duration FES experiments, and three stroke patients for both. The isometric ankle dorsiflexion torque induced by FES was measured, and then the test performance of the fixed-parameter Hammerstein model, the adaptive Hammerstein model based on fixed forgetting factor recursive least squares (FFFRLS) and the adaptive Hammerstein model based on VFFRLS was compared. The goodness of fit, root mean square error, peak error and success rate were applied to evaluate the accuracy and stability of the model. The results indicate a significant improvement in both the accuracy and stability of the proposed adaptive model compared to the fixed-parameter model and the adaptive model based on FFFRLS. The proposed adaptive model enhances the ability of the model to cope with muscle changes.

Robot-assisted motor training is applied for neurorehabilitation in stroke patients, using motor imagery (MI) as a representative paradigm of brain-computer interfaces to offer real-life assistance to individuals facing movement challenges. However, the effectiveness of training with MI may vary depending on the location of the stroke lesion, which should be considered. This paper introduces a multi-task electroencephalogram-based heterogeneous ensemble learning (MEEG-HEL) specifically designed for cross-subject training. In the proposed framework, common spatial patterns were used for feature extraction, and the features according to stroke lesions are shared and selected through sequential forward floating selection. The heterogeneous ensembles were used as classifiers. Nine patients with chronic ischemic stroke participated, engaging in MI and motor execution (ME) paradigms involving finger tapping. The classification criteria for the multi-task were established in two ways, taking into account the characteristics of stroke patients. In the cross-subject session, the first involved a direction recognition task for two-handed classification, achieving a performance of 0.7419 (±0.0811) in MI and 0.7061 (±0.1270) in ME. The second task focused on motor assessment for lesion location, resulting in a performance of 0.7457 (±0.1317) in MI and 0.6791 (±0.1253) in ME. Comparing the specific-subject session, except for ME on the motor assessment task, performance on both tasks was significantly higher than the cross-subject session. Furthermore, classification performance was similar to or statistically higher in cross-subject sessions compared to baseline models. The proposed MEEG-HEL holds promise in improving the practicality of neurorehabilitation in clinical settings and facilitating the detection of lesions.

Machine vision and artificial intelligence hold promise across healthcare applications. In this paper, we focus on the emerging research direction of infant action recognition, and we specifically consider the task of reaching which is an important developmental milestone. We develop E-babyNet, a lightweight yet effective neural-network-based framework for infant action recognition that leverages the spatial and temporal correlation of bounding boxes of infants' hands and objects to reach for to determine the onset and offset of the reaching action. E-babyNet consists of two main layers based on two LSTM and a Bidirectional LSTM (BiLSTM) model, respectively. The first layer provides a pre-evaluation of the reaching action for each hand by providing onset and offset keyframes. Then, the biLSTM model merges the previous outputs to deliver an outcome of the reaching actions detection for each frame including the reaching hand. We evaluated our approach against four other lightweight structures using a dataset comprising 5,865 annotated images resulting in 16,337 bounding boxes from 375 distinctive infant reaching actions performed while sitting by different subjects in unconstrained (home/clinic) environments. Results illustrate the effectiveness of our approach and ability to provide reliable reaching action detection and offer onset and offset keyframes with a precision of one frame. Moreover, the biLSTM layer can handle the transition between reaching actions and help reduce false detections.

Physical therapists play a crucial role in guiding patients through effective and safe rehabilitation processes according to medical guidelines. However, due to the therapist-patient imbalance, it is neither economical nor feasible for therapists to provide guidance to every patient during recovery sessions. Automated assessment of physical rehabilitation can help with this problem, but accurately quantifying patients' training movements and providing meaningful feedback poses a challenge. In this paper, an Expert-knowledge-based Graph Convolutional approach is proposed to automate the assessment of the quality of physical rehabilitation exercises. This approach utilizes experts' knowledge to improve the spatial feature extraction ability of the Graph Convolutional module and a Gated pooling module for feature aggregation. Additionally, a Transformer module is employed to capture long-range temporal dependencies in the movements. The attention scores and weight matrix obtained through this approach can serve as interpretability tools to help therapists understand the assessment model and assist patients in improving their exercises. The effectiveness of the proposed method is verified on the KIMORE dataset, achieving state-of-the-art performance compared to existing models. Experimental results also illustrate the interpretability of the method in both spatial and temporal dimensions.

Many challenges exist in the study of using orthotics, exoskeletons or exosuits as tools for rehabilitation and assistance of healthy people in daily activities due to the requirements of portability and safe interaction with the user and the environment. One approach to dealing with these challenges is to design a control system that can be deployed in a portable device to identify the relationships that exist between the gait variables and gait cycle for different locomotion modes. In order to estimate the knee and ankle angles in the sagittal plane for different locomotion modes, a novel multimodal feature-decoupled kinematic estimation system consisting of a multimodal locomotion classifier and an optimal joint angle estimator is proposed in this paper. The multi-source information output from different conventional primary models are fused by assigning the non-fixed weight. To improve the performance of the primary models, a data augmentation module based on the time-frequency domain analysis method is designed. The results show that the inclusion of the data augmentation module and multi-source information fusion modules has improved the classification accuracy to 98.56% and kinematic estimation performance (PCC) to 0.904 (walking), 0.956 (running), 0.899 (stair ascent), 0.851 (stair descent), respectively. The kinematic estimation quality is generally higher for faster speed (running) or proximal joint (knee) compared to other modes and ankle. The limitations and advantages of the proposed approach are discussed. Based on our findings, the multimodal kinematic estimation system has potential in facilitating the deployment for human-in-loop control of lower-limb intelligent assistive devices.

Surface electromyography (sEMG), a human-machine interface for gesture recognition, has shown promising potential for decoding motor intentions, but a variety of nonideal factors restrict its practical application in assistive robots. In this paper, we summarized the current mainstream gesture recognition strategies and proposed a gesture recognition method based on multimodal canonical correlation analysis feature fusion classification (MCAFC) for a nonideal condition that occurs in daily life, i.e., posture variations. The deep features of the sEMG and acceleration signals were first extracted via convolutional neural networks. A canonical correlation analysis was subsequently performed to associate the deep features of the two modalities. The transformed features were utilized as inputs to a linear discriminant analysis classifier to recognize the corresponding gestures. Both offline and real-time experiments were conducted on eight non-disabled subjects. The experimental results indicated that MCAFC achieved an average classification accuracy, average motion completion rate, and average motion completion time of 93.44%, 94.05%, and 1.38 s, respectively, with multiple dynamic postures, indicating significantly better performance than that of comparable methods. The results demonstrate the feasibility and superiority of the proposed multimodal signal feature fusion method for gesture recognition with posture variations, providing a new scheme for myoelectric control.

The olfactory system enables humans to smell different odors, which are closely related to emotions. The high temporal resolution and non-invasiveness of Electroencephalogram (EEG) make it suitable to objectively study human preferences for odors. Effectively learning the temporal dynamics and spatial information from EEG is crucial for detecting odor-induced emotional valence. In this paper, we propose a deep learning architecture called Temporal Attention with Spatial Autoencoder Network (TASA) for predicting odor-induced emotions using EEG. TASA consists of a filter-bank layer, a spatial encoder, a time segmentation layer, a Long Short-Term Memory (LSTM) module, a multi-head self-attention (MSA) layer, and a fully connected layer. We improve upon the previous work by utilizing a two-phase learning framework, using the autoencoder module to learn the spatial information among electrodes by reconstructing the given input with a latent representation in the spatial dimension, which aims to minimize information loss compared to spatial filtering with CNN. The second improvement is inspired by the continuous nature of the olfactory process; we propose to use LSTM-MSA in TASA to capture its temporal dynamics by learning the intercorrelation among the time segments of the EEG. TASA is evaluated on an existing olfactory EEG dataset and compared with several existing deep learning architectures to demonstrate its effectiveness in predicting olfactory-triggered emotional responses. Interpretability analyses with DeepLIFT also suggest that TASA learns spatial-spectral features that are relevant to olfactory-induced emotion recognition.