Search

Objective: Motivated by Health Care 4.0, this study aims to reducing the dimensionality of traditional EEG features based on manual extracted features, including statistical features in the time and frequency domains. Methods: A total of 22 multi-scale features were extracted from the UNM and Iowa datasets using a 4th order Butterworth filter and wavelet packet transform. Based on single-channel validation, 29 channels with the highest R2 scores were selected from a pool of 59 common channels. The proposed channel selection scheme was validated on the UNM dataset and tested on the Iowa dataset to compare its generalizability against models trained without channel selection. Results: The experimental results demonstrate that the proposed model achieves an optimal classification accuracy of 100%. Additionally, the generalization capability of the channel selection method is validated through out-of-sample testing based on the Iowa dataset Conclusions: Using single-channel validation, we proposed a channel selection scheme based on traditional statistical features, resulting in a selection of 29 channels. This scheme significantly reduced the dimensionality of EEG feature vectors related to Parkinson's disease by 50%. Remarkably, this approach demonstrated considerable classification performance on both the UNM and Iowa datasets. For the closed-eye state, the highest classification accuracy achieved was 100%, while for the open-eye state, the highest accuracy reached 93.75%. [ABSTRACT FROM AUTHOR]

Correctly identifying sleep stages is essential for assessing sleep quality and treating sleep disorders. However, the current sleep staging methods have the following problems: (1) Manual or semi-automatic extraction of features requires professional knowledge, which is time-consuming and laborious. (2) Due to the similarity of stage features, it is necessary to strengthen the learning of features. (3) Acquisition of a variety of data has high requirements on equipment. Therefore, this paper proposes a novel feature relearning method for automatic sleep staging based on single-channel electroencephalography (EEG) to solve these three problems. Specifically, we design a bottom–up and top–down network and use the attention mechanism to learn EEG information fully. The cascading step with an imbalanced strategy is used to further improve the overall classification performance and realize automatic sleep classification. The experimental results on the public dataset Sleep-EDF show that the proposed method is advanced. The results show that the proposed method outperforms the state-of-the-art methods. The code and supplementary materials are available at GitHub: https://github.com/raintyj/A-novel-feature-relearning-method. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) using smartphone sensors have been recently studied in various applications including healthcare, fitness, and smart home. Their recognition accuracy often depends on high-quality feature design and effectiveness of classification algorithms, where existing work mostly replies on laborious hand-crafted design and shallow feature learning architecture. Recent deep learning techniques demonstrate outstanding effectiveness in performing automatic feature learning and outperform traditional models in terms of accuracy. But their performance is limited by the quality and volumes of available labelled data. It is challenging to achieve accurate multisubject HAR with only smartphone sensing data. This article proposes a novel optimal activity graph generation model incorporating a deep learning framework for automatic and accurate HAR with multiple subjects using only acceleration and gyroscope data. The activity graph generation model presents a multisensory integration mechanism with three-steps sorting algorithms for producing optimal activity graphs containing alignments of neighbored signals in their width and height. Then, we propose a deep convolutional neural network to automatically learn distinguishable features from the graphs for HAR. By leveraging superior presentation of correlations between human activities and neighbored signals alignments via optimal activity graphs, the learned features are endowed with more discriminative power. The experimental evaluation was carried out on several benchmark datasets (i.e., UCI, USCHAD, and UTD-MHAD). The results showed that our approach improved the average recognition accuracy by about 5% when compared with other state-of-the-art HAR methods. Particularly towards multisubject HAR cases (UTD-MHAD dataset with 21 subjects), it achieved up to 10% accuracy gain over other methods. These improvements show the advantage and potential of our method dealing with complex HAR problems with multiple subjects using limited sensing data. [ABSTRACT FROM AUTHOR]

Objective: The m6A modification is the most common ribonucleic acid (RNA) modification, playing a role in prompting the virus's gene mutation and protein structure changes in the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). Nanopore single-molecule direct RNA sequencing (DRS) provides data support for RNA modification detection, which can preserve the potential $m^6A$ signature compared to second-generation sequencing. However, due to insufficient DRS data, there is a lack of methods to find m6A RNA modifications in DRS. Our purpose is to identify $m^6A$ modifications in DRS precisely. Methods: We present a methodology for identifying $m^6A$ modifications that incorporated mapping and extracted features from DRS data. To detect $m^6A$ modifications, we introduce an ensemble method called mixed-weight neural bagging (MWNB), trained with 5-base RNA synthetic DRS containing modified and unmodified $m^6A$. Results: Our MWNB model achieved the highest classification accuracy of 97.85% and AUC of 0.9968. Additionally, we applied the MWNB model to the COVID-19 dataset; the experiment results reveal a strong association with biomedical experiments. Conclusion: Our strategy enables the prediction of $m^6A$ modifications using DRS data and completes the identification of $m^6A$ modifications on the SARS-CoV-2. Significance: The Corona Virus Disease 2019 (COVID-19) outbreak has significantly influence, caused by the SARS-CoV-2. An RNA modification called $m^6A$ is connected with viral infections. The appearance of $m^6A$ modifications related to several essential proteins affects proteins’ structure and function. Therefore, finding the location and number of $m^6A$ RNA modifications is crucial for subsequent analysis of the protein expression profile. [ABSTRACT FROM AUTHOR]

Specialized control of pests and diseases have been a high-priority issue for the agriculture industry in many countries. On account of automation and cost effectiveness, image analytic pest recognition systems are widely utilized in practical crops prevention applications. But due to powerless hand-crafted features, current image analytic approaches achieve low accuracy and poor robustness in practical large-scale multiclass pest detection and recognition. To tackle this problem, this article proposes a novel deep learning based automatic approach using hybrid and local activated features for pest monitoring. In the presented method, we exploit the global information from feature maps to build our global activated feature pyramid network to extract pests’ highly discriminative features across various scales over both depth and position levels. It makes changes of depth or spatial sensitive features in pest images more visible during downsampling. Next, an improved pest localization module named local activated region proposal network is proposed to find the precise pest objects positions by augmenting contextualized and attentional information for feature completion and enhancement in local level. The approach is evaluated on our seven-year large-scale pest data-set containing 88.6 K images (16 types of pests) with 582.1 K manually labeled pest objects. The experimental results show that our solution performs over 75.03% mean average precision (mAP) in industrial circumstances, which outweighs two other state-of-the-art methods: Faster R-CNN with mAP up to 70% and feature pyramid network mAP up to 72%. [ABSTRACT FROM AUTHOR]

Detection of lung cancer at early stages is critical, in most of the cases radiologists read computed tomography (CT) images to prescribe follow-up treatment. The conventional method for detecting nodule presence in CT images is tedious. In this article, we propose an enhanced multidimensional region-based fully convolutional network (mRFCN) based automated decision support system for lung nodule detection and classification. The mRFCN is used as an image classifier backbone for feature extraction along with the novel multilayer fusion region proposal network (mLRPN) with position-sensitive score maps being explored. We applied a median intensity projection to leverage three-dimensional information from CT scans and introduced deconvolutional layer to adopt proposed mLRPN in our architecture to automatically select the potential region of interest. Our system has been trained and evaluated using LIDC dataset, and the experimental results showed promising detection performance in comparison to the state-of-the-art nodule detection/classification methods, achieving a sensitivity of 98.1% and classification accuracy of 97.91%. [ABSTRACT FROM AUTHOR]

Intracranial blood vessels segmentation from computed tomography angiography (CTA) volumes is a promising biomarker for diagnosis and therapeutic treatment in cerebrovascular diseases. These segmentation outputs are a fundamental requirement in the development of automated decision support systems for preoperative assessment or intraoperative guidance in neuropathology. The state-of-the-art in medical image segmentation methods are reliant on deep learning architectures based on convolutional neural networks. However, despite their popularity, there is a research gap in the current deep learning architectures optimized to address the technical challenges in blood vessel segmentation. These challenges include: (i) the extraction of concrete brain vessels close to the skull; and (ii) the precise marking of the vessel locations. We propose an Optimally Fused Fully end-to-end Network (OFF-eNET) for automatic segmentation of the volumetric 3D intracranial vascular structures. OFF-eNET comprises of three modules. In the first module, we exploit the up-skip connections to enhance information flow, and dilated convolution for detailed preservation of spatial feature map that are designed for thin blood vessels. In the second module, we employ residual mapping along with inception module for speedy network convergence and richer visual representation. For the third module, we make use of the transferred knowledge in the form of cascaded training strategy to gradually optimize the three segmentation stages (basic, complete, and enhanced) to segment thin vessels located close to the skull. All these modules are designed to be computationally efficient. Our OFF-eNET, evaluated using 70 CTA image volumes, resulted in 90.75% performance in the segmentation of intracranial blood vessels and outperformed the state-of-the-art counterparts. [ABSTRACT FROM AUTHOR]

Epilepsy seizure prediction paves the way of timely warning for patients to take more active and effective intervention measures. Compared to seizure detection that only identifies the inter-ictal state and the ictal state, far fewer researches have been conducted on seizure prediction because the high similarity makes it challenging to distinguish between the pre-ictal state and the inter-ictal state. In this paper, a novel solution on seizure prediction is proposed using common spatial pattern (CSP) and convolutional neural network (CNN). Firstly, artificial pre-ictal EEG signals based on the original ones are generated by combining the segmented pre-ictal signals to solve the trial imbalance problem between the two states. Secondly, a feature extractor employing wavelet packet decomposition and CSP is designed to extract the distinguishing features in both the time domain and the frequency domain. It can improve overall accuracy while reducing the training time. Finally, a shallow CNN is applied to discriminate between the pre-ictal state and the inter-ictal state. Our proposed solution is evaluated on 23 patients’ data from Boston Children's Hospital-MIT scalp EEG dataset by employing a leave-one-out cross-validation, and it achieves a sensitivity of 92.2% and false prediction rate of 0.12/h. Experimental result demonstrates that the proposed approach outperforms most state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, we present a method (Action-Fusion) for human action recognition from depth maps and posture data using convolutional neural networks (CNNs). Two input descriptors are used for action representation. The first input is a depth motion image that accumulates consecutive depth maps of a human action, whilst the second input is a proposed moving joints descriptor which represents the motion of body joints over time. In order to maximize feature extraction for accurate action classification, three CNN channels are trained with different inputs. The first channel is trained with depth motion images (DMIs), the second channel is trained with both DMIs and moving joint descriptors together, and the third channel is trained with moving joint descriptors only. The action predictions generated from the three CNN channels are fused together for the final action classification. We propose several fusion score operations to maximize the score of the right action. The experiments show that the results of fusing the output of three channels are better than using one channel or fusing two channels only. Our proposed method was evaluated on three public datasets: 1) Microsoft action 3-D dataset (MSRAction3D); 2) University of Texas at Dallas-multimodal human action dataset; and 3) multimodal action dataset (MAD) dataset. The testing results indicate that the proposed approach outperforms most of existing state-of-the-art methods, such as histogram of oriented 4-D normals and Actionlet on MSRAction3D. Although MAD dataset contains a high number of actions (35 actions) compared to existing action RGB-D datasets, this paper surpasses a state-of-the-art method on the dataset by 6.84%. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have yielded state-of-the-art performance in image classification and other computer vision tasks. Their application in fire detection systems will substantially improve detection accuracy, which will eventually minimize fire disasters and reduce the ecological and social ramifications. However, the major concern with CNN-based fire detection systems is their implementation in real-world surveillance networks, due to their high memory and computational requirements for inference. In this paper, we propose an original, energy-friendly, and computationally efficient CNN architecture, inspired by the SqueezeNet architecture for fire detection, localization, and semantic understanding of the scene of the fire. It uses smaller convolutional kernels and contains no dense, fully connected layers, which helps keep the computational requirements to a minimum. Despite its low computational needs, the experimental results demonstrate that our proposed solution achieves accuracies that are comparable to other, more complex models, mainly due to its increased depth. Moreover, this paper shows how a tradeoff can be reached between fire detection accuracy and efficiency, by considering the specific characteristics of the problem of interest and the variety of fire data. [ABSTRACT FROM AUTHOR]

The expansion of automation techniques and increased risk of identity theft have led emphasis on the tremendous need of automated identification system. Due to the high recognition accuracy and robustness to changes in human physiology, retinal biometric identification system has drawn much attention in this research field. In this paper, we aim to propose an automatic fast and accurate retinal identification system for the multisample dataset. The proposed approach uses a hybrid segmentation technique to segment out both thick/thin vessels for effectively balancing the difference of wavelet response between thick/thin blood vessels. As a result, recognition accuracy is improved. A Principle Component Analysis-based feature processing approach is proposed for efficiently reducing the dimensionality of a large number of vessels features. It significantly reduces computation time and accelerates the matching process in the retinal identification system. The proposed technique is validated on DRIVE, STARE, VARIA, RIDB, HRF, Messidor, DIARETDB0, and a large multisample per subject database created by authors using the images provided by Dr. Chen (Shanghai Jiao Tong University Affiliated Sixth People Hospital). Experimental results demonstrated that the proposed approach outperforms other existing techniques. Segmentation achieves an overall accuracy of 99.65% with the recognition rate of 99.40% on all these databases. [ABSTRACT FROM AUTHOR]

Due to the complexity of process operation, industrial process data are often nonlinear and nonstationary, high dimensional, and multivariate with complex interactions between multiple outputs. To address all these issues, this paper proposes a novel industrial predictive model that integrates deep feature extraction and fast online adaptation, and can effectively deal with multiple process outputs. Specifically, a multi-output gradient radial basis function network (MGRBF) with excellent predictive capacity of nonstationary data is first used to provide preliminary prediction of target outputs. This prior quality information is combined with the original process input for deep feature learning and dimensional reduction. Through layer-wise feature extraction by the stacked autoencoder (SAE), deep quality-enhanced features can be obtained, which is further fed into a MGRBF tracker for online prediction. In order to timely capture the fast-changing process characteristics, the first two modules, namely, preliminary MGRBF predictor and SAE feature extractor are frozen after training, while the structure and parameters of the MGRBF tracker are updated online in an efficient manner. Two industrial case studies demonstrate that the proposed adaptive deep MGRBF network outperforms existing state-of-the-art online modeling approaches as well as deep learning models, in terms of both multi-output modeling accuracy and online computational complexity. • A quality-relevant feature extraction strategy integrating MGRBF predictor and SAE feature extractor. • An efficient online adaptation strategy is designed to tune the adaptive part of the deep model. • Evaluation with two industrial case studies. • Outperforming SOTA approaches with better prediction accuracy and computational complexity. [ABSTRACT FROM AUTHOR]

The means of distributing dense passive radio-frequency identification (RFID) tags has been widely utilized for accurate indoor localization. However, they suffer a disadvantage on low localization precision due to the increasing interference of RFID tag collisions and the variation of behavior of tags. Current localization algorithms used in passive RFID location systems are mostly deterministic and have a limited capability on improving localization precision in a dynamic environment with uncertain sensor measurement. This paper investigates the feasibility of using particle filter technique as an efficient localization approach to deliver both relatively good accuracy and precision in dense passive RFID tag distribution applications. A position feature-based system model is first built to apply the typical particle filter technique in passive RFID location applications. Then, a new particle filter algorithm by using a moving direction estimation-based feature improvement scheme is proposed to enhance localization precision in a dense passive RFID tag environment. Experimental results show that the proposed method can provide relatively good accuracy and precision for passive RFID location applications, with an improved performance over the typical particle filter algorithm and a state-of-the-art deterministic method. [ABSTRACT FROM PUBLISHER]

To achieve high localisation accuracy and precision is a fundamental requirement of passive radio‐frequency identification (RFID) location systems. Current passive RFID location systems mostly deploy a dense RFID tag distribution to give initial localisation accuracy and use advanced localisation algorithms to extract the reliable features for enhancing localisation precision. High quality features are capable of significantly improving precision of passive RFID localisation systems, but it is hardly achieved in practice because of the environmental noise interference and the variety of tag behaviours. A localisation approach by using moving direction estimation to improve the quality of extracted features is proposed for enhancing localisation precision of passive RFID location systems. This approach relies on a general distribution of false‐reading occurring probability function derived from experimental measurements. A feature adjustment scheme is introduced to correct these features regarding the estimation of moving direction of object. The experimental results demonstrate that the proposed localisation approach with feature improvement achieves higher precision for the state‐of‐the art deterministic localisation algorithm (Han et al. 2007) in passive RFID location systems. [ABSTRACT FROM AUTHOR]

Deep learning has become a popular approach for fault diagnosis due to its powerful feature extraction and adaptability. However, its reliance on extensive annotations poses challenges in real-world applications. To confront this issue, this article proposes the CLTrans, a contrastive learning-based knowledge transfer method for semi-supervised fault diagnosis. CLTrans utilizes large-scale unlabeled data to benefit downstream tasks by simply performing unsupervised similarity matching. A feature encoder pre-trained by CLTrans can extract discriminative representations of vibration signals and can efficiently adapt to various tasks, even with data under different distributions. Experimental results of inner-dataset and inter-dataset knowledge transfer demonstrate that CLTrans outperforms conventional deep learning and state-of-the-art semi-supervised fault diagnosis approaches in terms of accuracy and domain adaptability, especially under limited labels. The capability of unsupervised knowledge mining and transfer allows for reducing the burden of data collection and annotation. • Contrastive learning is used for vibration signal representation embedding. • A stop-gradient strategy is used to simplify the proposed contrastive framework. • Well-generalized representations can be embedded in an unsupervised manner. • Massive unlabeled data are effectively used for fault diagnosis under limited labels. • Knowledge transfer across complicated different working conditions is realized. [ABSTRACT FROM AUTHOR]