Search

In recent years, deep learning methods have achieved remarkable success in hyperspectral image classification (HSIC), and the utilization of convolutional neural networks (CNNs) has proven to be highly effective. However, there are still several critical issues that need to be addressed in the HSIC task, such as the lack of labeled training samples, which constrains the classification accuracy and generalization ability of CNNs. To address this problem, a deep multi-scale attention fusion network (DMAF-NET) is proposed in this paper. This network is based on multi-scale features and fully exploits the deep features of samples from multiple levels and different perspectives with an aim to enhance HSIC results using limited samples. The innovation of this article is mainly reflected in three aspects: Firstly, a novel baseline network for multi-scale feature extraction is designed with a pyramid structure and densely connected 3D octave convolutional network enabling the extraction of deep-level information from features at different granularities. Secondly, a multi-scale spatial–spectral attention module and a pyramidal multi-scale channel attention module are designed, respectively. This allows modeling of the comprehensive dependencies of coordinates and directions, local and global, in four dimensions. Finally, a multi-attention fusion module is designed to effectively combine feature mappings extracted from multiple branches. Extensive experiments on four popular datasets demonstrate that the proposed method can achieve high classification accuracy even with fewer labeled samples. [ABSTRACT FROM AUTHOR]

The monitoring of the lifetime of cutting tools often faces problems such as life data loss, drift, and distortion. The prediction of the lifetime in this situation is greatly compromised with respect to the accuracy. The recent rise of deep learning, such as Gated Recurrent Unit Units (GRUs), Hidden Markov Models (HMMs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Attention networks, and Transformers, has dramatically improved the data problems in tool lifetime prediction, substantially enhancing the accuracy of tool wear prediction. In this paper, we introduce a novel approach known as PCHIP-Enhanced ConvGRU (PECG), which leverages multiple—feature fusion for tool wear prediction. When compared to traditional models such as CNNs, the CNN Block, and GRUs, our method consistently outperformed them across all key performance metrics, with a primary focus on the accuracy. PECG addresses the challenge of missing tool wear measurement data in relation to sensor data. By employing PCHIP interpolation to fill in the gaps in the wear values, we have developed a model that combines the strengths of both CNNs and GRUs with data augmentation. The experimental results demonstrate that our proposed method achieved an exceptional relative accuracy of 0.8522, while also exhibiting a Pearson's Correlation Coefficient (PCC) exceeding 0.95. This innovative approach not only predicts tool wear with remarkable precision, but also offers enhanced stability. [ABSTRACT FROM AUTHOR]

In recent years, radar emitter signal recognition has enjoyed a wide range of applications in electronic support measure systems and communication security. More and more deep learning algorithms have been used to improve the recognition accuracy of radar emitter signals. However, complex deep learning algorithms and data preprocessing operations have a huge demand for computing power, which cannot meet the requirements of low power consumption and high real-time processing scenarios. Therefore, many research works have remained in the experimental stage and cannot be actually implemented. To tackle this problem, this paper proposes a resource reuse computing acceleration platform based on field programmable gate arrays (FPGA), and implements a one-dimensional (1D) convolutional neural network (CNN) and long short-term memory (LSTM) neural network (NN) model for radar emitter signal recognition, directly targeting the intermediate frequency (IF) data of radar emitter signal for classification and recognition. The implementation of the 1D-CNN-LSTM neural network on FPGA is realized by multiplexing the same systolic array to accomplish the parallel acceleration of 1D convolution and matrix vector multiplication operations. We implemented our network on Xilinx XCKU040 to evaluate the effectiveness of our proposed solution. Our experiments show that the system can achieve 7.34 giga operations per second (GOPS) data throughput with only 5.022 W power consumption when the radar emitter signal recognition rate is 96.53%, which greatly improves the energy efficiency ratio and real-time performance of the radar emitter recognition system. [ABSTRACT FROM AUTHOR]

In order to more effectively monitor and interfere with enemy signals, it is particularly important to accurately and efficiently identify the intercepted signals and estimate their parameters in the increasingly complex electromagnetic environment. Therefore, in non-cooperative situations, it is of great practical significance to study how to accurately detect direct sequence spread spectrum (DSSS) signals in real time and estimate their parameters. The traditional time-delay correlation algorithm encounters the challenges such as peak energy leakage and false peak interference. As an alternative, this paper introduces a Pseudo-Noise (PN) code period estimation method utilizing a one-dimensional (1D) convolutional neural network based on the residual network (CNN-ResNet). This method transforms the problem of spread spectrum code period estimation into a multi-classification problem of spread spectrum code length estimation. Firstly, the In-phase/Quadrature(I/Q) two-way of the received DSSS signals is directly input into the CNN-ResNet model, which will automatically learn the characteristics of the DSSS signal with different PN code lengths and then estimate the PN code length. Simulation experiments are conducted using a data set with DSSS signals ranging from −20 to 10 dB in terms of signal-to-noise ratios (SNRs). Upon training and verifying the model using BPSK modulation, it is then put to the test with QPSK-modulated signals, and the estimation performance was analyzed through metrics such as loss function, accuracy rate, recall rate, and confusion matrix. The results demonstrate that the 1D CNN-ResNet proposed in this paper is capable of effectively estimating the PN code period of the non-cooperative DSSS signal, exhibiting robust generalization abilities. [ABSTRACT FROM AUTHOR]

With the wide application of direct sequence spread spectrum (DSSS) signals, the comprehensive performance of DSSS communication systems has been continuously improved, making the electronic reconnaissance link in communication countermeasures more difficult. Electronic reconnaissance technology, as the fundamental means of modern electronic warfare, mainly includes signal detection, recognition, and parameter estimation. At present, research on DSSS detection algorithms is mostly based on the correlation characteristics of DSSS signals, and autocorrelation algorithm is the most mature and widely used method in practical engineering. With the continuous development of deep learning, deep-learning-based methods have gradually been introduced to replace traditional algorithms in the field of signal processing. This paper proposes a spread spectrum signal detection method based on convolutional neural network (CNN). Through experimental analysis, the detection performance of the CNN model proposed in this paper on DSSS signals in various situations has been compared and analyzed with traditional autocorrelation detection methods for different signal-to-noise ratios. The experiments verified the estimation performance of the model in this paper under different signal-to-noise ratios, different spreading code lengths, different spreading code types, and different modulation methods and compared it with the autocorrelation detection algorithm. It was found that the detection performance of the model in this paper was higher than that of the autocorrelation detection method, and the overall performance was improved by 4 dB. [ABSTRACT FROM AUTHOR]

This paper proposed a real-time fault diagnostic method for hydraulic systems using data collected from multiple sensors. The method is based on a proposed multi-sensor convolutional neural network (MS-CNN) that incorporates feature extraction, sensor selection, and fault diagnosis into an end-to-end model. Both the sensor selection process and fault diagnosis process are based on abstract fault-related features learned by a CNN deep learning model. Therefore, compared with the traditional sensor-and-feature selection method, the proposed MS-CNN can find the sensor channels containing higher-level fault-related features, which provides two advantages for diagnosis. First, the sensor selection can reduce the redundant information and improve the diagnostic performance of the model. Secondly, the reduced number of sensors simplifies the model, reducing communication burden and computational complexity. These two advantages make the MS-CNN suitable for real-time hydraulic system fault diagnosis, in which the multi-sensor feature extraction and the computation speed are both significant. The proposed MS-CNN approach is evaluated experimentally on an electric-hydraulic subsea control system test rig and an open-source dataset. The proposed method shows obvious superiority in terms of both diagnosis accuracy and computational speed when compared with traditional CNN models and other state-of-the-art multi-sensor diagnostic methods. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) sensor often produces a shadow in pairs with the target due to its slant-viewing imaging. As a result, shadows in SAR images can provide critical discriminative features for classifiers, such as target contours and relative positions. However, shadows possess unique properties that differ from targets, such as low intensity and sensitivity to depression angles, making it challenging to extract depth features from shadows directly using convolutional neural networks (CNN). In this paper, we propose a new SAR image-classification framework to utilize target and shadow information comprehensively. First, we design a SAR image segmentation method to extract target regions and shadow masks. Second, based on SAR projection geometry, we propose a data-augmentation method to compensate for the geometric distortion of shadows due to differences in depression angles. Finally, we introduce a feature-enhancement module (FEM) based on depthwise separable convolution (DSC) and convolutional block attention module (CBAM), enabling deep networks to fuse target and shadow features adaptively. The experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset show that when only using target and shadow information, the published deep-learning models can still achieve state-of-the-art performance after embedding the FEM. [ABSTRACT FROM AUTHOR]

A brain–computer interface (BCI) is a computer-based system that allows for communication between the brain and the outer world, enabling users to interact with computers using neural activity. This brain signal is obtained from electroencephalogram (EEG) signals. A significant obstacle to the development of BCIs based on EEG is the classification of subject-independent motor imagery data since EEG data are very individualized. Deep learning techniques such as the convolutional neural network (CNN) have illustrated their influence on feature extraction to increase classification accuracy. In this paper, we present a multi-branch (five branches) 2D convolutional neural network that employs several hyperparameters for every branch. The proposed model achieved promising results for cross-subject classification and outperformed EEGNet, ShallowConvNet, DeepConvNet, MMCNN, and EEGNet_Fusion on three public datasets. Our proposed model, EEGNet Fusion V2, achieves 89.6% and 87.8% accuracy for the actual and imagined motor activity of the eegmmidb dataset and scores of 74.3% and 84.1% for the BCI IV-2a and IV-2b datasets, respectively. However, the proposed model has a bit higher computational cost, i.e., it takes around 3.5 times more computational time per sample than EEGNet_Fusion. [ABSTRACT FROM AUTHOR]

Video anomaly event detection (VAED) is one of the key technologies in computer vision for smart surveillance systems. With the advent of deep learning, contemporary advances in VAED have achieved substantial success. Recently, weakly supervised VAED (WVAED) has become a popular VAED technical route of research. WVAED methods do not depend on a supplementary self-supervised substitute task, yet they can assess anomaly scores straightway. However, the performance of WVAED methods depends on pretrained feature extractors. In this paper, we first address taking advantage of two pretrained feature extractors for CNN (e.g., C3D and I3D) and ViT (e.g., CLIP), for effectively extracting discerning representations. We then consider long-range and short-range temporal dependencies and put forward video snippets of interest by leveraging our proposed temporal self-attention network (TSAN). We design a multiple instance learning (MIL)-based generalized architecture named CNN-ViT-TSAN, by using CNN- and/or ViT-extracted features and TSAN to specify a series of models for the WVAED problem. Experimental results on publicly available popular crowd datasets demonstrated the effectiveness of our CNN-ViT-TSAN. [ABSTRACT FROM AUTHOR]

Although measuring worker productivity is crucial, the measurement of the productivity of each worker is challenging due to their dispersion across various construction jobsites. This paper presents a framework for measuring productivity based on an inertial measurement unit (IMU) and activity classification. Two deep learning algorithms and three sensor combinations were utilized to identify and analyze the feasibility of the framework in masonry work. Using the proposed method, worker activity classification could be performed with a maximum accuracy of 96.70% using the convolutional neural network model with multiple sensors, and a minimum accuracy of 72.11% using the long short-term memory (LSTM) model with a single sensor. Productivity could be measured with an accuracy of up to 96.47%. The main contributions of this study are the proposal of a method for classifying detailed activities and an exploration of the effect of the number of IMU sensors used in measuring worker productivity. [ABSTRACT FROM AUTHOR]

Recently, attention has been paid to the convolutional neural network (CNN) based synthetic aperture radar (SAR) target recognition method. Because of its advantages of automatic feature extraction and the preservation of translation invariance, the recognition accuracies are stronger than traditional methods. However, similar to other deep learning models, CNN is a "black-box" model, whose working process is vague. It is difficult to locate the decision reasons. Because of this, we focus on the process analysis of a pre-trained CNN model. The role of the processing to feature extraction and final recognition decision is discussed. The discussed components of CNN models are convolution, activation function, and full connection. Here, the convolution processing can be deemed as image filtering. The activation function provides a nonlinear element of processing. Moreover, the fully connected layers can also further extract features. In the experiment, four classical CNN models, i.e., AlexNet, VGG16, GoogLeNet, and ResNet-50, are trained by public MSTAR data, which can realize ten-category SAR target recognition. These pre-trained CNN models are processing objects of the proposed process analysis method. After the analysis, the content of the SAR image target features concerned by these pre-trained CNN models is further clarified. In summary, we provide a paradigm to process the analysis of pre-trained CNN models used for SAR target recognition in this paper. To some degree, the adaptability of these models to SAR images is verified. [ABSTRACT FROM AUTHOR]

Object detection is a fundamental task in computer vision. Over the past several years, convolutional neural network (CNN)-based object detection models have significantly improved detection accuracyin terms of average precision (AP). Furthermore, feature pyramid networks (FPNs) are essential modules for object detection models to consider various object scales. However, the AP for small objects is lower than the AP for medium and large objects. It is difficult to recognize small objects because they do not have sufficient information, and information is lost in deeper CNN layers. This paper proposes a new FPN model named ssFPN (scale sequence (S 2 ) feature-based feature pyramid network) to detect multi-scale objects, especially small objects. We propose a new scale sequence (S 2 ) feature that is extracted by 3D convolution on the level of the FPN. It is defined and extracted from the FPN to strengthen the information on small objects based on scale-space theory. Motivated by this theory, the FPN is regarded as a scale space and extracts a scale sequence (S 2 ) feature by three-dimensional convolution on the level axis of the FPN. The defined feature is basically scale-invariant and is built on a high-resolution pyramid feature map for small objects. Additionally, the deigned S 2 feature can be extended to most object detection models based on FPNs. We also designed a feature-level super-resolution approach to show the efficiency of the scale sequence (S 2 ) feature. We verified that the scale sequence (S 2 ) feature could improve the classification accuracy for low-resolution images by training a feature-level super-resolution model. To demonstrate the effect of the scale sequence (S 2 ) feature, experiments on the scale sequence (S 2 ) feature built-in object detection approach including both one-stage and two-stage models were conducted on the MS COCO dataset. For the two-stage object detection models Faster R-CNN and Mask R-CNN with the S 2 feature, AP improvements of up to 1.6% and 1.4%, respectively, were achieved. Additionally, the AP S of each model was improved by 1.2% and 1.1%, respectively. Furthermore, the one-stage object detection models in the YOLO series were improved. For YOLOv4-P5, YOLOv4-P6, YOLOR-P6, YOLOR-W6, and YOLOR-D6 with the S 2 feature, 0.9%, 0.5%, 0.5%, 0.1%, and 0.1% AP improvements were observed. For small object detection, the AP S increased by 1.1%, 1.1%, 0.9%, 0.4%, and 0.1%, respectively. Experiments using the feature-level super-resolution approach with the proposed scale sequence (S 2 ) feature were conducted on the CIFAR-100 dataset. By training the feature-level super-resolution model, we verified that ResNet-101 with the S 2 feature trained on LR images achieved a 55.2% classification accuracy, which was 1.6% higher than for ResNet-101 trained on HR images. [ABSTRACT FROM AUTHOR]

In this paper, a structural health monitoring (SHM) system is proposed to provide automatic early warning for detecting damage and its location in composite pipelines at an early stage. The study considers a basalt fiber reinforced polymer (BFRP) pipeline with an embedded Fiber Bragg grating (FBG) sensory system and first discusses the shortcomings and challenges with incorporating FBG sensors for accurate detection of damage information in pipelines. The novelty and the main focus of this study is, however, a proposed approach that relies on designing an integrated sensing-diagnostic SHM system that has the capability to detect damage in composite pipelines at an early stage via implementation of an artificial intelligence (AI)-based algorithm combining deep learning and other efficient machine learning methods using an Enhanced Convolutional Neural Network (ECNN) without retraining the model. The proposed architecture replaces the softmax layer by a k-Nearest Neighbor (k-NN) algorithm for inference. Finite element models are developed and calibrated by the results of pipe measurements under damage tests. The models are then used to assess the patterns of the strain distributions of the pipeline under internal pressure loading and under pressure changes due to bursts, and to find the relationship of strains at different locations axially and circumferentially. A prediction algorithm for pipe damage mechanisms using distributed strain patterns is also developed. The ECNN is designed and trained to identify the condition of pipe deterioration so the initiation of damage can be detected. The strain results from the current method and the available experimental results in the literature show excellent agreement. The average error between the ECNN data and FBG sensor data is 0.093%, thus confirming the reliability and accuracy of the proposed method. The proposed ECNN achieves high performance with 93.33 % accuracy (P%), 91.18 % regression rate (R%) and a 90.54 % F1-score (F%). [ABSTRACT FROM AUTHOR]

It is considered that 1 in 10 adults worldwide have diabetes. Diabetic foot ulcers are some of the most common complications of diabetes, and they are associated with a high risk of lower-limb amputation and, as a result, reduced life expectancy. Timely detection and periodic ulcer monitoring can considerably decrease amputation rates. Recent research has demonstrated that computer vision can be used to identify foot ulcers and perform non-contact telemetry by using ulcer and tissue area segmentation. However, the applications are limited to controlled lighting conditions, and expert knowledge is required for dataset annotation. This paper reviews the latest publications on the use of artificial intelligence for ulcer area detection and segmentation. The PRISMA methodology was used to search for and select articles, and the selected articles were reviewed to collect quantitative and qualitative data. Qualitative data were used to describe the methodologies used in individual studies, while quantitative data were used for generalization in terms of dataset preparation and feature extraction. Publicly available datasets were accounted for, and methods for preprocessing, augmentation, and feature extraction were evaluated. It was concluded that public datasets can be used to form a bigger, more diverse datasets, and the prospects of wider image preprocessing and the adoption of augmentation require further research. [ABSTRACT FROM AUTHOR]

In brain–computer interface (BCI) systems, motor imagery electroencephalography (MI-EEG) signals are commonly used to detect participant intent. Many factors, including low signal-to-noise ratios and few high-quality samples, make MI classification difficult. In order for BCI systems to function, MI-EEG signals must be studied. In pattern recognition and other fields, deep learning approaches have recently been successfully applied. In contrast, few effective deep learning algorithms have been applied to BCI systems, especially MI-based systems. In this paper, we address these problems from two aspects based on the characteristics of EEG signals: first, we proposed a combined time–frequency domain data enhancement method. This method guarantees that the size of the training data is effectively increased while maintaining the intrinsic composition of the data. Second, our design consists of a parallel CNN that takes both raw EEG images and images transformed through continuous wavelet transform (CWT) as inputs. We conducted classification experiments on a public data set to verify the effectiveness of the algorithm. According to experimental results based on the BCI Competition IV Dataset2a, the average classification accuracy is 97.61%. A comparison of the proposed algorithm with other algorithms shows that it performs better in classification. The algorithm can be used to improve the classification performance of MI-based BCIs and BCI systems created for people with disabilities. [ABSTRACT FROM AUTHOR]

Some recent studies use a convolutional neural network (CNN) or long short-term memory (LSTM) to extract gait features, but the methods based on the CNN and LSTM have a high loss rate of time-series and spatial information, respectively. Since gait has obvious time-series characteristics, while CNN only collects waveform characteristics, and only uses CNN for gait recognition, this leads to a certain lack of time-series characteristics. LSTM can collect time-series characteristics, but LSTM results in performance degradation when processing long sequences. However, using CNN can compress the length of feature vectors. In this paper, a sequential convolution LSTM network for gait recognition using multimodal wearable inertial sensors is proposed, which is called SConvLSTM. Based on 1D-CNN and a bidirectional LSTM network, the method can automatically extract features from the raw acceleration and gyroscope signals without a manual feature design. 1D-CNN is first used to extract the high-dimensional features of the inertial sensor signals. While retaining the time-series features of the data, the dimension of the features is expanded, and the length of the feature vectors is compressed. Then, the bidirectional LSTM network is used to extract the time-series features of the data. The proposed method uses fixed-length data frames as the input and does not require gait cycle detection, which avoids the impact of cycle detection errors on the recognition accuracy. We performed experiments on three public benchmark datasets: UCI-HAR, HuGaDB, and WISDM. The results show that SConvLSTM performs better than most of those reporting the best performance methods, at present, on the three datasets. [ABSTRACT FROM AUTHOR]

Telecommunication networks are growing exponentially due to their significant role in civilization and industry. As a result of this very significant role, diverse applications have been appeared, which require secured links for data transmission. However, Internet-of-Things (IoT) devices are a substantial field that utilizes the wireless communication infrastructure. However, the IoT, besides the diversity of communications, are more vulnerable to attacks due to the physical distribution in real world. Attackers may prevent the services from running or even forward all of the critical data across the network. That is, an Intrusion Detection System (IDS) has to be integrated into the communication networks. In the literature, there are numerous methodologies to implement the IDSs. In this paper, two distinct models are proposed. In the first model, a custom Convolutional Neural Network (CNN) was constructed and combined with Long Short Term Memory (LSTM) deep network layers. The second model was built about the all fully connected layers (dense layers) to construct an Artificial Neural Network (ANN). Thus, the second model, which is a custom of an ANN layers with various dimensions, is proposed. Results were outstanding a compared to the Logistic Regression algorithm (LR), where an accuracy of 97.01% was obtained in the second model and 96.08% in the first model, compared to the LR algorithm, which showed an accuracy of 92.8%. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel technique for the inspection of high-density polyethylene (HDPE) pipes using ultrasonic sensors, signal processing, and deep neural networks (DNNs). Specifically, we propose a technique that detects whether there is a diversion on a pipe or not. The proposed model transmits ultrasound signals through a pipe using a custom-designed array of piezoelectric transmitters and receivers. We propose to use the Zadoff–Chu sequence to modulate the input signals, then utilize its correlation properties to estimate the pipe channel response. The processed signal is then fed to a DNN that extracts the features and decides whether there is a diversion or not. The proposed technique demonstrates an average classification accuracy of 90.3 % (when one sensor is used) and 99.6 % (when two sensors are used) on 3 4 inch pipes. The technique can be readily generalized for pipes of different diameters and materials. [ABSTRACT FROM AUTHOR]

The development of the smartphone and computer vision technique provides customers with a convenient approach to identify tea species, as well as qualities. However, the prediction model may not behave robustly due to changes in illumination conditions. Fluorescence imaging can induce the fluorescence signal from typical components, and thus may improve the prediction accuracy. In this paper, a tea classification method based on fluorescence imaging and convolutional neural networks (CNN) is proposed. Ultra-violet (UV) LEDs with a central wavelength of 370 nm were utilized to induce the fluorescence of tea samples so that the fluorescence images could be captured. Five kinds of tea were included and pre-processed. Two CNN-based classification models, e.g., the VGG16 and ResNet-34, were utilized for model training. Images captured under the conventional fluorescent lamp were also tested for comparison. The results show that the accuracy of the classification model based on fluorescence images is better than those based on the white-light illumination images, and the performance of the VGG16 model is better than the ResNet-34 model in our case. The classification accuracy of fluorescence images reached 97.5%, which proves that the LED-induced fluorescence imaging technique is promising to use in our daily life. [ABSTRACT FROM AUTHOR]

Vehicle fault detection and diagnosis (VFDD) along with predictive maintenance (PdM) are indispensable for early diagnosis in order to prevent severe accidents due to mechanical malfunction in urban environments. This paper proposes an early voiceprint driving fault identification system using machine learning algorithms for classification. Previous studies have examined driving fault identification, but less attention has focused on using voiceprint features to locate corresponding faults. This research uses 43 different common vehicle mechanical malfunction condition voiceprint signals to construct the dataset. These datasets were filtered by linear predictive coefficient (LPC) and wavelet transform(WT). After the original voiceprint fault sounds were filtered and obtained the main fault characteristics, the deep neural network (DNN), convolutional neural network (CNN), and long short-term memory (LSTM) architectures are used for identification. The experimental results show that the accuracy of the CNN algorithm is the best for the LPC dataset. In addition, for the wavelet dataset, DNN has the best performance in terms of identification performance and training time. After cross-comparison of experimental results, the wavelet algorithm combined with DNN can improve the identification accuracy by up to 16.57% compared with other deep learning algorithms and reduce the model training time by up to 21.5% compared with other algorithms. Realizing the cross-comparison of recognition results through various machine learning methods, it is possible for the vehicle to proactively remind the driver of the real-time potential hazard of vehicle machinery failure. [ABSTRACT FROM AUTHOR]

This paper presents an automatic recognition system for classifying stones belonging to different Calabrian quarries (Southern Italy). The tool for stone recognition has been developed in the SILPI project (acronym of "Sistema per l'Identificazione di Lapidei Per Immagini"), financed by POR Calabria FESR-FSE 2014-2020. Our study is based on the Convolutional Neural Network (CNNs) that is used in literature for many different tasks such as speech recognition, neural language processing, bioinformatics, image classification and much more. In particular, we propose a two-stage hybrid approach based on the use of a model of Deep Learning (DL), in our case the CNN, in the first stage and a model of Machine Learning (ML) in the second one. In this work, we discuss a possible solution to stones classification which uses a CNN for the feature extraction phase and the Softmax or Multinomial Logistic Regression (MLR), Support Vector Machine (SVM), k-Nearest Neighbors (kNN), Random Forest (RF) and Gaussian Naive Bayes (GNB) ML techniques in order to perform the classification phase basing our study on the approach called Transfer Learning (TL). We show the image acquisition process in order to collect adequate information for creating an opportune database of the stone typologies present in the Calabrian quarries, also performing the identification of quarries in the considered region. Finally, we show a comparison of different DL and ML combinations in our Two-Stage Hybrid Model solution. [ABSTRACT FROM AUTHOR]

Based on experimental observations, there is a correlation between time and consecutive gaze positions in visual behaviors. Previous studies on gaze point estimation usually use images as the input for model trainings without taking into account the sequence relationship between image data. In addition to the spatial features, the temporal features are considered to improve the accuracy in this paper by using videos instead of images as the input data. To be able to capture spatial and temporal features at the same time, the convolutional neural network (CNN) and long short-term memory (LSTM) network are introduced to build a training model. In this way, CNN is used to extract the spatial features, and LSTM correlates temporal features. This paper presents a CNN Concatenating LSTM network (CCLN) that concatenates spatial and temporal features to improve the performance of gaze estimation in the case of time-series videos as the input training data. In addition, the proposed model can be optimized by exploring the numbers of LSTM layers, the influence of batch normalization (BN) and global average pooling layer (GAP) on CCLN. It is generally believed that larger amounts of training data will lead to better models. To provide data for training and prediction, we propose a method for constructing datasets of video for gaze point estimation. The issues are studied, including the effectiveness of different commonly used general models and the impact of transfer learning. Through exhaustive evaluation, it has been proved that the proposed method achieves a better prediction accuracy than the existing CNN-based methods. Finally, 93.1% of the best model and 92.6% of the general model MobileNet are obtained. [ABSTRACT FROM AUTHOR]

Usage of effective classification techniques on Magnetic Resonance Imaging (MRI) helps in the proper diagnosis of brain tumors. Previous studies have focused on the classification of normal (nontumorous) or abnormal (tumorous) brain MRIs using methods such as Support Vector Machine (SVM) and AlexNet. In this paper, deep learning architectures are used to classify brain MRI images into normal or abnormal. Gender and age are added as higher attributes for more accurate and meaningful classification. A deep learning Convolutional Neural Network (CNN)-based technique and a Deep Neural Network (DNN) are also proposed for effective classification. Other deep learning architectures such as LeNet, AlexNet, ResNet, and traditional approaches such as SVM are also implemented to analyze and compare the results. Age and gender biases are found to be more useful and play a key role in classification, and they can be considered essential factors in brain tumor analysis. It is also worth noting that, in most circumstances, the proposed technique outperforms both existing SVM and AlexNet. The overall accuracy obtained is 88% (LeNet Inspired Model) and 80% (CNN-DNN) compared to SVM (82%) and AlexNet (64%), with best accuracy of 100%, 92%, 92%, and 81%, respectively. [ABSTRACT FROM AUTHOR]

Since Synthetic Aperture Radar (SAR) targets are full of coherent speckle noise, the traditional deep learning models are difficult to effectively extract key features of the targets and share high computational complexity. To solve the problem, an effective lightweight Convolutional Neural Network (CNN) model incorporating transfer learning is proposed for better handling SAR targets recognition tasks. In this work, firstly we propose the Atrous-Inception module, which combines both atrous convolution and inception module to obtain rich global receptive fields, while strictly controlling the parameter amount and realizing lightweight network architecture. Secondly, the transfer learning strategy is used to effectively transfer the prior knowledge of the optical, non-optical, hybrid optical and non-optical domains to the SAR target recognition tasks, thereby improving the model's recognition performance on small sample SAR target datasets. Finally, the model constructed in this paper is verified to be 97.97% on ten types of MSTAR datasets under standard operating conditions, reaching a mainstream target recognition rate. Meanwhile, the method presented in this paper shows strong robustness and generalization performance on a small number of randomly sampled SAR target datasets. [ABSTRACT FROM AUTHOR]

This paper presents a wearable device, fitted on the waist of a participant that recognizes six activities of daily living (walking, walking upstairs, walking downstairs, sitting, standing, and laying) through a deep-learning algorithm, human activity recognition (HAR). The wearable device comprises a single-board computer (SBC) and six-axis sensors. The deep-learning algorithm employs three parallel convolutional neural networks for local feature extraction and for subsequent concatenation to establish feature fusion models of varying kernel size. By using kernels of different sizes, relevant local features of varying lengths were identified, thereby increasing the accuracy of human activity recognition. Regarding experimental data, the database of University of California, Irvine (UCI) and self-recorded data were used separately. The self-recorded data were obtained by having 21 participants wear the device on their waist and perform six common activities in the laboratory. These data were used to verify the proposed deep-learning algorithm on the performance of the wearable device. The accuracy of these six activities in the UCI dataset and in the self-recorded data were 97.49% and 96.27%, respectively. The accuracies in tenfold cross-validation were 99.56% and 97.46%, respectively. The experimental results have successfully verified the proposed convolutional neural network (CNN) architecture, which can be used in rehabilitation assessment for people unable to exercise vigorously. [ABSTRACT FROM AUTHOR]

In recent years, more and more frameworks have been applied to brain-computer interface technology, and electroencephalogram-based motor imagery (MI-EEG) is developing rapidly. However, it is still a challenge to improve the accuracy of MI-EEG classification. A deep learning framework termed IS-CBAM-convolutional neural network (CNN) is proposed to address the non-stationary nature, the temporal localization of excitation occurrence, and the frequency band distribution characteristics of the MI-EEG signal in this paper. First, according to the logically symmetrical relationship between the C3 and C4 channels, the result of the time-frequency image subtraction (IS) for the MI-EEG signal is used as the input of the classifier. It both reduces the redundancy and increases the feature differences of the input data. Second, the attention module is added to the classifier. A convolutional neural network is built as the base classifier, and information on the temporal location and frequency distribution of MI-EEG signal occurrences are adaptively extracted by introducing the Convolutional Block Attention Module (CBAM). This approach reduces irrelevant noise interference while increasing the robustness of the pattern. The performance of the framework was evaluated on BCI competition IV dataset 2b, where the mean accuracy reached 79.6%, and the average kappa value reached 0.592. The experimental results validate the feasibility of the framework and show the performance improvement of MI-EEG signal classification. [ABSTRACT FROM AUTHOR]

The emergence of an aging society is inevitable due to the continued increases in life expectancy and decreases in birth rate. These social changes require new smart healthcare services for use in daily life, and COVID-19 has also led to a contactless trend necessitating more non-face-to-face health services. Due to the improvements that have been achieved in healthcare technologies, an increasing number of studies have attempted to predict and analyze certain diseases in advance. Research on stroke diseases is actively underway, particularly with the aging population. Stroke, which is fatal to the elderly, is a disease that requires continuous medical observation and monitoring, as its recurrence rate and mortality rate are very high. Most studies examining stroke disease to date have used MRI or CT images for simple classification. This clinical approach (imaging) is expensive and time-consuming while requiring bulky equipment. Recently, there has been increasing interest in using non-invasive measurable EEGs to compensate for these shortcomings. However, the prediction algorithms and processing procedures are both time-consuming because the raw data needs to be separated before the specific attributes can be obtained. Therefore, in this paper, we propose a new methodology that allows for the immediate application of deep learning models on raw EEG data without using the frequency properties of EEG. This proposed deep learning-based stroke disease prediction model was developed and trained with data collected from real-time EEG sensors. We implemented and compared different deep-learning models (LSTM, Bidirectional LSTM, CNN-LSTM, and CNN-Bidirectional LSTM) that are specialized in time series data classification and prediction. The experimental results confirmed that the raw EEG data, when wielded by the CNN-bidirectional LSTM model, can predict stroke with 94.0% accuracy with low FPR (6.0%) and FNR (5.7%), thus showing high confidence in our system. These experimental results demonstrate the feasibility of non-invasive methods that can easily measure brain waves alone to predict and monitor stroke diseases in real time during daily life. These findings are expected to lead to significant improvements for early stroke detection with reduced cost and discomfort compared to other measuring techniques. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles (UAVs) have been widely used in search and rescue (SAR) missions due to their high flexibility. A key problem in SAR missions is to search and track moving targets in an area of interest. In this paper, we focus on the problem of Cooperative Multi-UAV Observation of Multiple Moving Targets (CMUOMMT). In contrast to the existing literature, we not only optimize the average observation rate of the discovered targets, but we also emphasize the fairness of the observation of the discovered targets and the continuous exploration of the undiscovered targets, under the assumption that the total number of targets is unknown. To achieve this objective, a deep reinforcement learning (DRL)-based method is proposed under the Partially Observable Markov Decision Process (POMDP) framework, where each UAV maintains four observation history maps, and maps from different UAVs within a communication range can be merged to enhance UAVs' awareness of the environment. A deep convolutional neural network (CNN) is used to process the merged maps and generate the control commands to UAVs. The simulation results show that our policy can enable UAVs to balance between giving the discovered targets a fair observation and exploring the search region compared with other methods. [ABSTRACT FROM AUTHOR]

Deep learning models are widely employed in hyperspectral image processing to integrate both spatial features and spectral features, but the correlations between them are rarely taken into consideration. However, in hyperspectral mineral identification, not only the spectral and spatial features of minerals need to be considered, but also the correlations between them are crucial to further promote identification accuracy. In this paper, we propose hierarchical spatial-spectral feature extraction with long short term memory (HSS-LSTM) to explore correlations between spatial features and spectral features and obtain hierarchical intrinsic features for mineral identification. In the proposed model, the fusion spatial-spectral feature is primarily extracted by stacking local spatial features obtained by a convolution neural network (CNN)-based model and spectral information together. To better exploit spatial features and spectral features, an LSTM-based model is proposed to capture correlations and obtain hierarchical features for accurate mineral identification. Specifically, the proposed model shares a uniform objective function, so that all the parameters in the network can be optimized in the meantime. Experimental results on the hyperspectral data collected by the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) in the Nevada mining area show that HSS-LSTM achieves an overall accuracy of 94.70% and outperforms other commonly used identification methods. [ABSTRACT FROM AUTHOR]

Multiplexed deep neural networks (DNN) have engendered high-performance predictive models gaining popularity for decoding brain waves, extensively collected in the form of electroencephalogram (EEG) signals. In this paper, to the best of our knowledge, we introduce a first-ever DNN-based generalized approach to estimate reaction time (RT) using the periodogram representation of single-trial EEG in a visual stimulus-response experiment with 48 participants. We have designed a Fully Connected Neural Network (FCNN) and a Convolutional Neural Network (CNN) to predict and classify RTs for each trial. Though deep neural networks are widely known for classification applications, cascading FCNN/CNN with the Random Forest model, we designed a robust regression-based estimator to predict RT. With the FCNN model, the accuracies obtained for binary and 3-class classification were 93% and 76%, respectively, which further improved with the use of CNN (94% and 78%, respectively). The regression-based approach predicted RTs with correlation coefficients (CC) of 0.78 and 0.80 for FCNN and CNN, respectively. Investigating further, we found that the left central as well as parietal and occipital lobes were crucial for predicting RT, with significant activities in the theta and alpha frequency bands. [ABSTRACT FROM AUTHOR]

The mobile terminals used in the logistics industry can be exposed to wildly varying environments, which may hinder effective operation. In particular, those used in cold storages can be subject to frosting in the scanner window when they are carried out of the warehouses to a room-temperature space outside. To prevent this, they usually employ a film heater on the scanner window. However, the temperature and humidity conditions of the surrounding environment and the temperature of the terminal itself that cause frosting vary widely. Due to the complicated frost-forming conditions, existing industrial mobile terminals choose to implement rather simple rules that operate the film heater well above the freezing point, which inevitably leads to inefficient energy use. This paper demonstrates that to avoid such waste, on-device artificial intelligence (AI) a.k.a. edge AI can be readily employed to industrial mobile terminals and can improve their energy efficiency. We propose an artificial-intelligence-based approach that utilizes deep learning technology to avoid the energy-wasting defrosting operations. By combining the traditional temperature-sensing logic with a convolutional neural network (CNN) classifier that visually checks for frost, we can more precisely control the defrosting operation. We embed the CNN classifier in the device and demonstrate that the approach significantly reduces the energy consumption. On our test terminal, the net ratio of the energy consumption by the existing system to that of the edge AI for the heating film is almost 14:1. Even with the common current-dissipation accounted for, our edge AI system would increase the operating hours by 86%, or by more than 6 h compared with the system without the edge AI. [ABSTRACT FROM AUTHOR]

The automatic detection of atrial fibrillation (AF) is crucial for its association with the risk of embolic stroke. Most of the existing AF detection methods usually convert 1D time-series electrocardiogram (ECG) signal into 2D spectrogram to train a complex AF detection system, which results in heavy training computation and high implementation cost. This paper proposes an AF detection method based on an end-to-end 1D convolutional neural network (CNN) architecture to raise the detection accuracy and reduce network complexity. By investigating the impact of major components of a convolutional block on detection accuracy and using grid search to obtain optimal hyperparameters of the CNN, we develop a simple, yet effective 1D CNN. Since the dataset provided by PhysioNet Challenge 2017 contains ECG recordings with different lengths, we also propose a length normalization algorithm to generate equal-length records to meet the requirement of CNN. Experimental results and analysis indicate that our method of 1D CNN achieves an average F1 score of 78.2%, which has better detection accuracy with lower network complexity, as compared with the existing deep learning-based methods. [ABSTRACT FROM AUTHOR]

High-density surface electromyography (HD-sEMG) and deep learning technology are becoming increasingly used in gesture recognition. Based on electrode grid data, information can be extracted in the form of images that are generated with instant values of multi-channel sEMG signals. In previous studies, image-based, two-dimensional convolutional neural networks (2D CNNs) have been applied in order to recognize patterns in the electrical activity of muscles from an instantaneous image. However, 2D CNNs with 2D kernels are unable to handle a sequence of images that carry information concerning how the instantaneous image evolves with time. This paper presents a 3D CNN with 3D kernels to capture both spatial and temporal structures from sequential sEMG images and investigates its performance on HD-sEMG-based gesture recognition in comparison to the 2D CNN. Extensive experiments were carried out on two benchmark datasets (i.e., CapgMyo DB-a and CSL-HDEMG). The results show that, where the same network architecture is used, 3D CNN can achieve a better performance than 2D CNN, especially for CSL-HDEMG, which contains the dynamic part of finger movement. For CapgMyo DB-a, the accuracy of 3D CNN was 1% higher than 2D CNN when the recognition window length was equal to 40 ms, and was 1.5% higher when equal to 150 ms. For CSL-HDEMG, the accuracies of 3D CNN were 15.3% and 18.6% higher than 2D CNN when the window length was equal to 40 ms and 150 ms, respectively. Furthermore, 3D CNN achieves a competitive performance in comparison to the baseline methods. [ABSTRACT FROM AUTHOR]

Cylindrical panorama stitching is able to generate high resolution images of a scene with a wide field-of-view (FOV), making it a useful scene representation for applications like environmental sensing and robot localization. Traditional image stitching methods based on hand-crafted features are effective for constructing a cylindrical panorama from a sequence of images in the case when there are sufficient reliable features in the scene. However, these methods are unable to handle low-texture environments where no reliable feature correspondence can be established. This paper proposes a novel two-step image alignment method based on deep learning and iterative optimization to address the above issue. In particular, a light-weight end-to-end trainable convolutional neural network (CNN) architecture called ShiftNet is proposed to estimate the initial shifts between images, which is further optimized in a sub-pixel refinement procedure based on a specified camera motion model. Extensive experiments on a synthetic dataset, rendered photo-realistic images, and real images were carried out to evaluate the performance of our proposed method. Both qualitative and quantitative experimental results demonstrate that cylindrical panorama stitching based on our proposed image alignment method leads to significant improvements over traditional feature based methods and recent deep learning based methods for challenging low-texture environments. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar (SAR) scene classification is challenging but widely applied, in which deep learning can play a pivotal role because of its hierarchical feature learning ability. In the paper, we propose a new scene classification framework, named Feature Recalibration Network with Multi-scale Spatial Features (FRN-MSF), to achieve high accuracy in SAR-based scene classification. First, a Multi-Scale Omnidirectional Gaussian Derivative Filter (MSOGDF) is constructed. Then, Multi-scale Spatial Features (MSF) of SAR scenes are generated by weighting MSOGDF, a Gray Level Gradient Co-occurrence Matrix (GLGCM) and Gabor transformation. These features were processed by the Feature Recalibration Network (FRN) to learn high-level features. In the network, the Depthwise Separable Convolution (DSC), Squeeze-and-Excitation (SE) Block and Convolution Neural Network (CNN) are integrated. Finally, these learned features will be classified by the Softmax function. Eleven types of SAR scenes obtained from four systems combining different bands and resolutions were trained and tested, and a mean accuracy of 98.18% was obtained. To validate the generality of FRN-MSF, five types of SAR scenes sampled from two additional large-scale Gaofen-3 and TerraSAR-X images were evaluated for classification. The mean accuracy of the five types reached 94.56%; while the mean accuracy for the same five types of the former tested 11 types of scene was 96%. The high accuracy indicates that the FRN-MSF is promising for SAR scene classification without losing generality. [ABSTRACT FROM AUTHOR]

Recently, research on data-driven bearing fault diagnosis methods has attracted increasing attention due to the availability of massive condition monitoring data. However, most existing methods still have difficulties in learning representative features from the raw data. In addition, they assume that the feature distribution of training data in source domain is the same as that of testing data in target domain, which is invalid in many real-world bearing fault diagnosis problems. Since deep learning has the automatic feature extraction ability and ensemble learning can improve the accuracy and generalization performance of classifiers, this paper proposes a novel bearing fault diagnosis method based on deep convolutional neural network (CNN) and random forest (RF) ensemble learning. Firstly, time domain vibration signals are converted into two dimensional (2D) gray-scale images containing abundant fault information by continuous wavelet transform (CWT). Secondly, a CNN model based on LeNet-5 is built to automatically extract multi-level features that are sensitive to the detection of faults from the images. Finally, the multi-level features containing both local and global information are utilized to diagnose bearing faults by the ensemble of multiple RF classifiers. In particular, low-level features containing local characteristics and accurate details in the hidden layers are combined to improve the diagnostic performance. The effectiveness of the proposed method is validated by two sets of bearing data collected from reliance electric motor and rolling mill, respectively. The experimental results indicate that the proposed method achieves high accuracy in bearing fault diagnosis under complex operational conditions and is superior to traditional methods and standard deep learning methods. [ABSTRACT FROM AUTHOR]