Search

Deep convolutional neural networks (CNNs) have shown strong abilities in the application of artificial intelligence. However, due to their extensive amount of computation, traditional processors have low energy efficiency when executing CNN algorithms, which is unacceptable for portable devices with limited hardware cost and battery capacity, so designing a CNN-specific processor is necessary. In this paper, we propose an energy-efficient CNN processor architecture for lightweight devices with a processing elements (PEs) array consisting of 384 PEs. Using the systolic array-based PE array, it realizes parallel operations between filter rows and between channels of output feature maps, supporting the acceleration of 3D convolution and fully connected computation with various parameters by configuring internal instruction registers. The computing strategy based on the proposed systolic dataflow achieves less hardware overhead compared with other strategies, and the reuse of image values and weight values, which effectively reduce the power of memory access. A memory system with a multi-level storage structure combined with register file (RF) and SRAM is used in the proposed CNN processor, which further reduces the energy overhead of computing. The proposed CNN processor architecture has been verified on a ZC706 FPGA platform using VGG-16 based on the proposed image segmentation method, the evaluation results indicate that the peak throughput achieves 115.2 GOP/s consuming 3.801 W at 150 MHz, energy efficiency and DSP efficiency reaches 30.32 GOP/s/W and 0.26 GOP/s/DSP, respectively.

Breast cancer is one of the most common types of cancer among women. Accurate diagnosis at an early stage can reduce the mortality associated with this disease. Governments and health organizations stress the importance of early detection of breast cancer as it is related to an increase in the number of available treatment options and increased survival. Early detection gives patients the best chance of receiving effective treatment. Different types of images and imaging modalities are used in the detection and diagnosis of breast cancer. One of the imaging types is “infrared thermal” breast imaging, where a screening instrument is used to measure the temperature distribution of breast tissue. Although it has not been used often, compared to mammograms, it showed promising results when used for early detection. It also has many advantages as it is non-invasive, safe, painless, and inexpensive. The literature has indicated that the use of thermal images with deep neural networks improves the accuracy of early diagnosis of breast malformation. Therefore, in this paper, we aim to investigate to what extent convolutional neural networks (CNNs) with attention mechanisms (AMs) can provide satisfactory detection results in thermal breast cancer images. We present a model for breast cancer detection based on deep neural networks with AMs using thermal images from the Database for Research Mastology with Infrared Image (DMR-IR). The model will be evaluated in terms of accuracy, sensitivity and specificity, and will be compared against state-of-the-art breast cancer detection methods. The AMs with the CNN model achieved encouraging test accuracy rates of 99.46%, 99.37%, and 99.30% on the breast thermal dataset. The test accuracy of CNNs without AMs was 92.32%, whereas CNNs with AMs achieved an improvement in accuracy of 7%. Moreover, the proposed models outperformed previous models that were reviewed in the literature.

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 34 inch pipes. The technique can be readily generalized for pipes of different diameters and materials.

Shadows are widely used in the tracking of moving targets by video synthetic aperture radar (video SAR). However, they always appear in groups in video SAR images. In such cases, track effects produced by existing single-target tracking methods are no longer satisfactory. To this end, an effective way to obtain the capability of multiple target tracking (MTT) is in urgent demand. Note that tracking by detection (TBD) for MTT in optical images has achieved great success. However, TBD cannot be utilized in video SAR MTT directly. The reasons for this is that shadows of moving target are quite different from in video SAR image than optical images as they are time-varying and their pixel sizes are small. The aforementioned characteristics make shadows in video SAR images hard to detect in the process of TBD and lead to numerous matching errors in the data association process, which greatly affects the final tracking performance. Aiming at the above two problems, in this paper, we propose a multiple target tracking method based on TBD and the Siamese network. Specifically, to improve the detection accuracy, the multi-scale Faster-RCNN is first proposed to detect the shadows of moving targets. Meanwhile, dimension clusters are used to accelerate the convergence speed of the model in the training process as well as to obtain better network weights. Then, SiamNet is proposed for data association to reduce matching errors. Finally, we apply a Kalman filter to update the tracking results. The experimental results on two real video SAR datasets demonstrate that the proposed method outperforms other state-of-art methods, and the ablation experiment verifies the effectiveness of multi-scale Faster-RCNN and SimaNet.

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%.

Transient stability (TS) and short-term voltage stability (STVS) assessment are of fundamental importance for the operation security of power systems. Both phenomena can be mutually influenced in weak power systems due to the proliferation of power electronic interface devices and the phase-out of conventional heavy machines (e.g., thermal power plants). There is little research on the assessment of both types of stability together, despite the fact that they develop over the same short-term period, and that they can have a major influence on the overall transient performance driven by large electrical disturbances (e.g., short circuits). This work addresses this open research challenge by proposing a methodology for the joint assessment of TS and STVS. The methodology aims at estimating the resulting short-term stability state (STSS) in stable, or unstable conditions, following critical events, such as the synchronism loss of synchronous generators (SG) or the stalling of induction motors (IM). The estimations capture the mechanisms responsible for the degradations of TS and STVS, respectively. The paper overviews the off-line design of the data-driven STSS classification methodology, which supports the design and training of a hybrid deep neural network RCNN (recurrent convolutional neural network). The RCNN can automatically capture spatial and temporal features from the power system through a time series of selected physical variables, which results in a high estimation degree for STSS in real-time applications. The methodology is tested on the New England 39-bus system, where the results demonstrate the superiority of the proposed methodology over other traditional and deep learning-based methodologies. For reference purposes, the numerical tests also illustrate the classification performance in special situations, when the training is performed by exclusively using measurements from generation and motor load buses, which constitute locations where the investigated stability can be observed.

Dense breast tissue is a significant factor that increases the risk of breast cancer. Current mammographic density classification approaches are unable to provide enough classification accuracy. However, it remains a difficult problem to classify breast density. This paper proposes TwoViewDensityNet, an end-to-end deep learning-based method for mammographic breast density classification. The craniocaudal (CC) and mediolateral oblique (MLO) views of screening mammography provide two different views of each breast. As the two views are complementary, and dual-view-based methods have proven efficient, we use two views for breast classification. The loss function plays a key role in training a deep model; we employ the focal loss function because it focuses on learning hard cases. The method was thoroughly evaluated on two public datasets using 5-fold cross-validation, and it achieved an overall performance (F-score of 98.63%, AUC of 99.51%, accuracy of 95.83%) on DDSM and (F-score of 97.14%, AUC of 97.44%, accuracy of 96%) on the INbreast. The comparison shows that the TwoViewDensityNet outperforms the state-of-the-art methods for classifying breast density into BI-RADS class. It aids healthcare providers in providing patients with more accurate information and will help improve the diagnostic accuracy and reliability of mammographic breast density evaluation in clinical care.

A battery’s charging data include the timing information with respect to the charge. However, the existing State of Health (SOH) prediction methods rarely consider this information. This paper proposes a dilated convolution-based SOH prediction model to verify the influence of charging timing information on SOH prediction results. The model uses holes to fill in the standard convolutional kernel in order to expand the receptive field without adding parameters, thereby obtaining a wider range of charging timing information. Experimental data from six batteries of the same battery type were used to verify the model’s effectiveness under different experimental conditions. The proposed method is able to accurately predict the battery SOH value in any range of voltage input through cross-validation, and the SDE (standard deviation of the error) is at least 0.28% lower than other methods. In addition, the influence of the position and length of the range of input voltage on the model’s prediction ability is studied as well. The results of our analysis show that the proposed method is robust to different sampling positions and different sampling lengths of input data, which solves the problem of the original data being difficult to obtain due to the uncertainty of charging–discharging behaviour in actual operation.

Radar data mining is the key module for signal analysis, where patterns hidden inside of signals are gradually available in the learning process and its superiority is significant for enhancing the security of the radar emitter classification (REC) system. Owing to the disadvantage that radio frequency fingerprinting (RFF) caused by the imperfection of emitter’s hardware is difficult to forge, current deep-learning REC methods based on deep-learning techniques, e.g., convolutional neural network (CNN) and long short term memory (LSTM) are difficult to capture the stable RFF features. In this paper, an online and non-cooperative multi-modal generic representation auxiliary learning REC model, namely muti-modal generic representation auxiliary learning networks (MGRALN), is put forward. Multi-modal means that multi-domain transformations are unified to a generic representation. After this, the representation is employed to facilitate mining the implicit information inside of the signals and to perform the better model robustness, which is achieved by using the available generic genenation to guide the network training and learning. Online means the learning process of REC is only once and the REC is end-to-end. Non-cooperative denotes no demodulation techniques are used before the REC task. Experimental results on the measured civil aviation radar data demonstrate that the proposed method enables one to achieve superior performance.

Simultaneous localization and mapping (SLAM) systems play an important role in the field of automated robotics and artificial intelligence. Feature detection and matching are crucial aspects affecting the overall accuracy of the SLAM system. However, the accuracy of the position and matching cannot be guaranteed when confronted with a cross-view angle, illumination, texture, etc. Moreover, deep learning methods are very sensitive to perspective change and do not have the invariance of geometric transformation. Therefore, a novel pseudo-Siamese convolutional network of a transformation invariance feature detection and a description for the SLAM system is proposed in this paper. The proposed method, by learning transformation invariance features and descriptors, simultaneously improves the front-end landmark detection and tracking module of the SLAM system. We converted the input image to the transform field; the backbone network was designed to extract feature maps. Then, the feature detection subnetwork and feature description subnetwork were decomposed and designed; finally, we constructed a convolutional network of transformation invariance feature detections and a description for the visual SLAM system. We implemented many experiments in datasets, and the results of the experiments demonstrated that our method has a state-of-the-art performance in global tracking when compared to that of the traditional visual SLAM systems.

The condition of a bee colony can be predicted by monitoring bees upon hive entrance. The presence of pollen grains gives beekeepers significant information about the well-being of the bee colony in a non-invasive way. This paper presents a field-programmable-gate-array (FPGA)-based pollen detector from images obtained at the hive entrance. The image dataset was acquired at native entrance ramps from six different hives. To evaluate and demonstrate the performance of the system, various densities of convolutional neural networks (CNNs) were trained and tested to find those suitable for pollen grain detection at the chosen image resolution. We propose a new CNN accelerator architecture that places a pre-trained CNN on an SoC FPGA. The CNN accelerator was implemented on a cost-optimized Z-7020 FPGA with 16-bit fixed-point operations. The kernel binarization and merging with the batch normalization layer were applied to reduce the number of DSPs in the multi-channel convolutional core. The estimated average performance was 32 GOPS for a single convolutional core. We found that the CNN with four convolutional and two dense layers gave a 92% classification accuracy, and it matched those declared for state-of-the-art methods. It took 8.8 ms to classify a 512 × 128 px frame and 2.4 ms for a 256 × 64 px frame. The frame rate of the proposed method outperformed the speed of known pollen detectors. The developed pollen detector is cost effective and can be used as a real-time image classification module for hive status monitoring.

Diabetic retinopathy (DR) is an increasingly common eye disorder that gradually damages the retina. Identification at the early stage can significantly reduce the severity of vision loss. Deep learning techniques provide detection for retinal images based on data size and quality, as the error rate increases with low-quality images and unbalanced data classes. This paper proposes a hybrid intelligent framework of a conventional neural network and a fuzzy inference system to measure the stages of DR automatically, Diabetic Retinopathy Stage Measurement using Conventional Neural Network and Fuzzy Inference System (DRSM-CNNFIS). The fuzzy inference used human experts’ rules to overcome data dependency problems. At first, the Conventional Neural Network (CNN) model was used for feature extraction, and then fuzzy rules were used to measure diabetic retinopathy stage percentage. The framework is trained using images from Kaggle datasets (Diabetic Retinopathy Detection, 2022). The efficacy of this framework outperformed the other models with regard to accuracy, macro average precision, macro average recall, and macro average F1 score: 0.9281, 0.7142, 0.7753, and 0.7301, respectively. The evaluation results indicate that the proposed framework, without any segmentation process, has a similar performance for all the classes, while the other classification models (Dense-Net-201, Inception-ResNet ResNet-50, Xception, and Ensemble methods) have different levels of performance for each class classification.

The spatial distribution of remote-sensing scene images is highly complex in character, so how to extract local key semantic information and discriminative features is the key to making it possible to classify accurately. However, most of the existing convolutional neural network (CNN) models tend to have global feature representations and lose the shallow features. In addition, when the network is too deep, gradient disappearance and overfitting tend to occur. To solve these problems, a lightweight, multi-instance CNN model for remote sensing scene classification is proposed in this paper: MILRDA. In the instance extraction and classifier part, more discriminative features are extracted by the constructed residual dense attention block (RDAB) while retaining shallow features. Then, the extracted features are transformed into instance-level vectors and the local information associated with bag-level labels is highlighted by the proposed channel-attention-based multi-instance pooling, while suppressing the weights of useless objects or backgrounds. Finally, the network is constrained by the cross-entropy loss function to output the final prediction results. The experimental results on four public datasets show that our proposed method can achieve comparable results to other state-of-the-art methods. Moreover, the visualization of feature maps shows that MILRDA can find more effective features.

FY4A/GIIRS (Geostationary Interferometric Infrared Sounder) is the first infrared hyperspectral atmospheric vertical sounder onboard a geostationary satellite. It can achieve observations of atmospheric temperature and humidity profiles with high vertical and temporal resolutions. Presently, convolutional neural network algorithms are relatively less used in the field of atmospheric profile retrieval, and different convolutional neural network approaches have different characteristics. The one-dimensional convolutional neural network scheme 1D-Net and two three-dimensional retrieval schemes U-Net 1 and U-Net 2 are used to achieve atmospheric temperature and humidity profiles under all skies based on GIIRS-observed brightness temperatures in this paper. After validation with test training data, the retrievals of different schemes derived from actual GIIRS observations and level 2 operational products were verified with ERA5 reanalysis data and radiosonde measurements in summer and winter respectively. The retrieved three-dimensional temperature and humidity fields from U-Net 1 and U-Net 2 are closer to the ERA5 reanalysis field in both distribution and value than the retrievals from the 1D-Net scheme and level 2 operational products. In particular, the inversion field of the U-Net 2 scheme is more continuous in space. Compared with radiosonde observations, the accuracy of the level 2 temperature product is the highest when the field of view is completely clear both in winter and summer month. The root mean square error (RMSE) of temperature retrieval of the two U-Net schemes is the second highest, and the RMSE and bias of the 1D-Net scheme are both large. Two U-Net schemes overestimate the temperature and humidity slightly in winter and underestimate it in summer in both clear and all sky cases. Under all sky conditions, the temperature retrieval RMSE and bias of the two U-Net schemes above 800 hPa are lower than those of the level 2 products, especially the U-Net 2 scheme with an RMSE of approximately 2.5 K. The U-Net 2 scheme bias is the smallest, with a value of approximately 0.5 K in winter. Since the level 2 product only provides the atmospheric temperature above the cloud top, it indicates that its temperature product accuracy is very low when the field of view is influenced by clouds. The humidity retrieval RMSEs of the two U-Net schemes is within 2 g/kg, better than that of the 1D-Net scheme. The retrieval accuracy of the U-Net 2 scheme is approximately 0.3 g/kg better than that of the U-Net 1 scheme below 600 hPa in winter. Level 2 does not provide humidity products. The summer humidity retrieval is worse than in winter. In general, among the three deep machine learning algorithms, 1D-Net has a large retrieval error, and the temperature and humidity from U-Net 2 have the highest accuracy. The retrieval speeds of the two U-Net schemes are nearly the same, and both are faster than that of scheme 1D-Net.

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.

According to the World Health Organization (WHO), the COVID-19 coronavirus pandemic has resulted in a worldwide public health crisis. One effective method of protection is to use a mask in public places. Recent advances in object detection, which are based on deep learning models, have yielded promising results in terms of finding objects in images. Annotating and finding medical face mask objects in real-life images is the aim of this paper. While in public places, people can be protected from the transmission of COVID-19 between themselves by wearing medical masks made of medical materials. Our works employ Yolo V4 CSP SPP to identify the medical mask. Our experiment combined the Face Mask Dataset (FMD) and Medical Mask Dataset (MMD) into one dataset to investigate through this study. The proposed model improves the detection performance of the previous research study with FMD and MMD datasets from 81% to 99.26%. We have shown that our proposed Yolo V4 CSP SPP model scheme is an accurate mechanism for identifying medically masked faces. Each algorithm conducts a comprehensive analysis of, and provides a detailed description of, the benefits that come with using Cross Stage Partial (CSP) and Spatial Pyramid Pooling (SPP). Furthermore, after the study, a comparison between the findings and those of similar works has been provided. In terms of accuracy and precision, the suggested detector surpassed earlier works.

Researchers have made great progress in developing cutting-edge solar energy forecasting methods. However, these methods are far from optimal in terms of their accuracy, generalizability, benchmarking, and other requirements. Particularly, no single method performs well across all climates and weather due to the large variations in meteorological data. This paper proposes SENERGY (an acronym for sustainable energy), a novel deep learning-based auto-selective approach and tool that, instead of generalizing a specific model for all climates, predicts the best performing deep learning model for global horizontal irradiance (GHI) forecasting in terms of forecasting error. The approach is based on carefully devised deep learning methods and feature sets created through an extensive analysis of deep learning forecasting and classification methods using ten meteorological datasets from three continents. We analyze the tool in great detail through a variety of metrics and means for performance analysis, visualization, and comparison of solar forecasting methods. SENERGY outperforms existing methods in all performance metrics including mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), the normalized versions of these three metrics (nMAE, nRMSE, nMAPE), forecast skill (FS), and relative forecasting error. The long short-term memory-autoencoder model (LSTM-AE) outperformed the other four forecasting models and achieved the best results (nMAE = nRMSE = nMAPE = 0.02). The LSTM-AE model is the most accurate in all weather conditions. Predictions for sunny days are more accurate than for cloudy days as well as for summer compared to winter. SENERGY can predict the best forecasting model with 81% accuracy. The proposed auto-selective approach can be extended to other research problems, such as wind energy forecasting, and to predict forecasting models based on different criteria such as the energy required or speed of model execution, different input features, different optimizations of the same models, or other user preferences.

In the highway intelligent monitoring system, it is difficult to find the target vehicle through millions of pictures because of the presence of fake-licensed vehicles. In order to solve this problem, a vehicle comparison and re-identification (Re-ID) system is built in this paper. By introducing Circle loss and Generalized-Mean(GeM) pooling, vehicle feature extraction and storage, vehicle comparison and vehicle search can be realized. Experimental results show that the proposed algorithm reaches 95.79% of the mean Average Precision (mAP) on the vehicle search task, which meets the requirements of practical applications.

The problem of simultaneous localization and mapping (SLAM) in mobile robotics currently remains a crucial issue to ensure the safety of autonomous vehicles’ navigation. One approach addressing the SLAM problem and odometry estimation has been through perception sensors, leading to V-SLAM and visual odometry solutions. Furthermore, for these purposes, computer vision approaches are quite widespread, but LiDAR is a more reliable technology for obstacles detection and its application could be broadened. However, in most cases, definitive results are not achieved, or they suffer from a high computational load that limits their operation in real time. Deep Learning techniques have proven their validity in many different fields, one of them being the perception of the environment of autonomous vehicles. This paper proposes an approach to address the estimation of the ego-vehicle positioning from 3D LiDAR data, taking advantage of the capabilities of a system based on Machine Learning models, analyzing possible limitations. Models have been used with two real datasets. Results provide the conclusion that CNN-based odometry could guarantee local consistency, whereas it loses accuracy due to cumulative errors in the evaluation of the global trajectory, so global consistency is not guaranteed.

Change detection (CD) in hyperspectral images has become a research hotspot in the field of remote sensing due to the extremely wide spectral range of hyperspectral images compared to traditional remote sensing images. It is challenging to effectively extract features from redundant high-dimensional data for hyperspectral change detection tasks due to the fact that hyperspectral data contain abundant spectral information. In this paper, a novel feature extraction network is proposed, which uses a Recurrent Neural Network (RNN) to mine the spectral information of the input image and combines this with a Convolutional Neural Network (CNN) to fuse the spatial information of hyperspectral data. Finally, the feature extraction structure of hybrid RNN and CNN is used as a building block to complete the change detection task. In addition, we use an unsupervised sample generation strategy to produce high-quality samples for network training. The experimental results demonstrate that the proposed method yields reliable detection results. Moreover, the proposed method has fewer noise regions than the pixel-based method.

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.

Human pose estimation has long been a fundamental problem in computer vision and artificial intelligence. Prominent among the 2D human pose estimation (HPE) methods are the regression-based approaches, which have been proven to achieve excellent results. However, the ground-truth labels are usually inherently ambiguous in challenging cases such as motion blur, occlusions, and truncation, leading to poor performance measurement and lower levels of accuracy. In this paper, we propose Cofopose, which is a two-stage approach consisting of a person and keypoint detection transformers for 2D human pose estimation. Cofopose is composed of conditional cross-attention, a conditional DEtection TRansformer (conditional DETR), and an encoder-decoder in the transformer framework; this allows it to achieve person and keypoint detection. In a significant departure from other approaches, we use conditional cross-attention and fine-tune conditional DETR for our person detection, and encoder-decoders in the transformers for our keypoint detection. Cofopose was extensively evaluated using two benchmark datasets, MS COCO and MPII, achieving an improved performance with significant margins over the existing state-of-the-art frameworks.

It is known that synthetic aperture radar (SAR) images obtained by typical matched filtering (MF)-based algorithms always suffer from serious noise, sidelobes and clutter. However, the improvement in image quality means that the complexity of SAR systems will increase, which affects the applications of SAR images. The introduction of sparse signal processing technologies into SAR imaging proposes a new way to solve this problem. Sparse SAR images obtained by sparse recovery algorithms show better image performance than typical complex SAR images with lower sidelobes and higher signal-to-noise ratios (SNR). As the most widely applied fields of SAR images, target detection and target classification rely on SAR images with high quality. Therefore, in this paper, a target detection framework based on sparse images recovered by complex approximate message passing (CAMP) algorithm and a novel classification network via sparse images reconstructed by the new iterative soft thresholding (BiIST) algorithm are proposed. Experimental results show that sparse SAR images have better performance whether for target classification or for target detection than the images recovered by MF-based algorithms, which validates the huge application potentials of sparse images.

The connectivity of devices through the internet plays a remarkable role in our daily lives. Many network-based applications are utilized in different domains, e.g., health care, smart environments, and businesses. These applications offer a wide range of services and provide services to large groups. Therefore, the safety of network-based applications has always been an area of research interest for academia and industry alike. The evolution of deep learning has enabled us to explore new areas of research. Hackers make use of the vulnerabilities in networks and attempt to gain access to confidential systems and information. This information and access to systems can be very harmful and portray losses beyond comprehension. Therefore, detection of these network intrusions is of the utmost importance. Deep learning based techniques require minimal inputs while exploring every possible feature set in the network. Thus, in this paper, we present a one-dimensional convolutional neural network-based deep learning architecture for the detection of network intrusions. In this research, we detect four different types of network intrusions, i.e., DoS Hulk, DDoS, and DoS Goldeneye which belong to the active attack category, and PortScan, which falls in the passive attack category. For this purpose, we used the benchmark CICIDS2017 dataset for conducting the experiments and achieved an accuracy of 98.96% as demonstrated in the experimental results.

In this paper, the time series classification frontier method MiniRocket was used to classify earthquakes, blasts, and background noise. From supervised to unsupervised classification, a comprehensive analysis was carried out, and finally, the supervised method achieved excellent results. The relatively simple model, MiniRocket, is only a one-dimensional convolutional neural network structure which has achieved the best comprehensive results, and its computational efficiency is far stronger than other supervised classification methods. Through our experimental results, we found that the MiniRocket model could well-extract the decisive features of the seismic sensing signal. In order to try to eliminate the tedious work of making data labels, we proposed a novel lightweight collaborative learning for seismic sensing signals (LCL-SSS) based on the method of feature extraction in MiniRocket combined with unsupervised classification. The new method gives new vitality to the unsupervised classification method that could not be used originally and opens up a new path for the unsupervised classification of seismic sensing signals.

Supervised learning for Unmanned Aerial Vehicle (UAVs) visual-based navigation raises the need for reliable datasets with multi-task labels (e.g., classification and regression labels). However, current public datasets have limitations: (a) Outdoor datasets have limited generalization capability when being used to train indoor navigation models; (b) The range of multi-task labels, especially for regression tasks, are in different units which require additional transformation. In this paper, we present a Hull Drone Indoor Navigation (HDIN) dataset to improve the generalization capability for indoor visual-based navigation. Data were collected from the onboard sensors of a UAV. The scaling factor labeling method with three label types has been proposed to overcome the data jitters during collection and unidentical units of regression labels simultaneously. An open-source Convolutional Neural Network (i.e., DroNet) was employed as a baseline algorithm to retrain the proposed HDIN dataset, and compared with DroNet’s pretrained results on its original dataset since we have a similar data format and structure to the DroNet dataset. The results show that the labels in our dataset are reliable and consistent with the image samples.

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.

To address the problem of low prediction accuracy of precipitation time series data, an improved overall mean empirical modal decomposition–prediction–reconstruction model (MDPRM) is constructed in this paper. First, the non-stationary precipitation time series are decomposed into multiple decomposition terms by the improved overall mean empirical modal decomposition (MEEMD). Then, a particle swarm optimization support vector machine (PSO-SVM) and convolutional neural network (CNN) and recurrent neural network (RNN) models are used to make predictions according to the characteristics of different decomposition terms. Finally, the prediction results of each decomposition term are superimposed and reconstructed to form the final prediction results. In addition, the application is carried out with the summer precipitation in the Wujiang River basin of Guizhou Province from 1961 to 2018, using the first 38 years of data to train MDPRM and the last 20 years of data to test MDPRM, and comparing with a feedback neural network (BP), a support vector machine (SVM), a particle swarm optimization support vector machine (PSO-SVM), a convolutional neural network (CNN), and a recurrent neural network (RNN), etc. The results show that the mean relative error (MAPE) of the proposed MDPRM is reduced from 0.31 to 0.09, the root mean square error (RMSE) is reduced from 0.56 to 0.30, and the consistency index (α) is significantly improved from 0.33 to 0.86, which has a higher prediction accuracy. Finally, the trained MDPRM predicts the average summer precipitation in the Wujiang River basin from 2019 to 2028 to be 466.42 mm, the minimum precipitation in 2020 to be 440.94 mm, and the maximum precipitation in 2024 to be 497.94 mm. Based on the prediction results, the agricultural drought level is evaluated using the Z index, which indicates that the summer is normal in the 10-year period. The study provides technical support for the effective guidance of regional water resources’ allocation and scheduling and drought mitigation.

Machine-learning models have great potential to accelerate the design and performance assessment of photocatalysts, leveraging their unique advantages in detecting patterns and making predictions based on data. However, most machine-learning models are “black-box” models due to lack of interpretability. This paper describes the development of an interpretable neural-network model on the performance of photocatalytic degradation of organic contaminants by TiO2. The molecular structures of the organic contaminants are represented by molecular images, which are subsequently encoded by feeding into a special convolutional neural network (CNN), EfficientNet, to extract the critical structural features. The extracted features in addition to five other experimental variables were input to a neural network that was subsequently trained to predict the photodegradation reaction rates of the organic contaminants by TiO2. The results show that this machine-learning (ML) model attains a higher accuracy to predict the photocatalytic degradation rate of organic contaminants than a previously developed machine-learning model that used molecular fingerprint encoding. In addition, the most relevant regions in the molecular image affecting the photocatalytic rates can be extracted with gradient-weighted class activation mapping (Grad-CAM). This interpretable machine-learning model, leveraging the graphic interpretability of CNN model, allows us to highlight regions of the molecular structure serving as the active sites of water contaminants during the photocatalytic degradation process. This provides an important piece of information to understand the influence of molecular structures on the photocatalytic degradation process.

Recently, deep learning has greatly promoted the development of detection methods for ship targets in synthetic aperture radar (SAR) images. However, existing detection networks are mostly based on large-scale models and high-cost computations, which require high-performance computing equipment to realize real-time processing and limit their hardware transplantation to onboard platforms. To address this problem, a lightweight ship detection network via YOLOX-s is proposed in this paper. Firstly, we remove the computationally heavy pyramidal structure and build a streamlined network based on a one-level feature for higher detection efficiency. Secondly, to expand the limited receptive field and enhance the semantic information of a single-feature map, a residual asymmetric dilated convolution (RADC) block is proposed. Through four branches with different dilation rates, the RADC block can help the detector to capture various ships in complex backgrounds. Finally, to tackle the imbalance problem between ships of different scales in the training stage, we put forward a balanced label assignment strategy called center-based uniform matching. To verify the effectiveness of the proposed method, we conduct extensive experiments on the SAR Ship Detection Dataset (SSDD) and High-Resolution SAR Images Dataset (HRSID). The results show that our method can achieve comparable performance to general detection networks with much less computational cost.

Hyperspectral images (HSIs) are frequently contaminated by different noises (Gaussian noise, stripe noise, deadline noise, impulse noise) in the acquisition process as a result of the observation environment and imaging system limitations, which makes image information lost and difficult to recover. In this paper, we adopt a 3D-based SSCA block neural network of U-Net architecture for remote sensing HSI denoising, named SSCANet (Spatial and Spectral-Channel Attention Network), which is mainly constructed by a so-called SSCA block. By fully considering the characteristics of spatial-domain and spectral-domain of remote sensing HSIs, the SSCA block consists of a spatial attention (SA) block and a spectral-channel attention (SCA) block, in which the SA block is to extract spatial information and enhance spatial representation ability, as well as the SCA block to explore the band-wise relationship within HSIs for preserving spectral information. Compared to earlier 2D convolution, 3D convolution has a powerful spectrum preservation ability, allowing for improved extraction of HSIs characteristics. Experimental results demonstrate that our method holds better-restored results than other compared approaches, both visually and quantitatively.

Convolutional neural networks (CNNs) play an important role in hyperspectral image (HSI) classification due to their powerful feature extraction ability. Multiscale information is an important means of enhancing the feature representation ability. However, current HSI classification models based on deep learning only use fixed patches as the network input, which may not well reflect the complexity and richness of HSIs. While the existing methods achieve good classification performance for large-scale scenes, the classification of boundary locations and small-scale scenes is still challenging. In addition, dimensional dislocation often exists in the feature fusion process, and the up/downsampling operation for feature alignment may introduce extra noise or result in feature loss. Aiming at the above issues, this paper deeply explores multiscale features, proposes an adaptive attention constraint fusion module for different scale features, and designs a semantic feature enhancement module for high-dimensional features. First, HSI data of two different spatial scales are fed into the model. For the two inputs, we upsample them using bilinear interpolation to obtain their subpixel data. The proposed multiscale feature extraction module is intended to extract the features of the above four parts of the data. For the extracted features, the multiscale attention fusion module is used for feature fusion, and then, the fused features are fed into the high-level feature semantic enhancement module. Finally, based on the fully connected layer and softmax layer, the prediction results of the proposed model are obtained. Experimental results on four public HSI databases verify that the proposed method outperforms several state-of-the-art methods.

COVID-19 which was announced as a pandemic on 11 March 2020, is still infecting millions to date as the vaccines that have been developed do not prevent the disease but rather reduce the severity of the symptoms. Until a vaccine is developed that can prevent COVID-19 infection, the testing of individuals will be a continuous process. Medical personnel monitor and treat all health conditions; hence, the time-consuming process to monitor and test all individuals for COVID-19 becomes an impossible task, especially as COVID-19 shares similar symptoms with the common cold and pneumonia. Some off-the-counter tests have been developed and sold, but they are unreliable and add an additional burden because false-positive cases have to visit hospitals and perform specialized diagnostic tests to confirm the diagnosis. Therefore, the need for systems that can automatically detect and diagnose COVID-19 automatically without human intervention is still an urgent priority and will remain so because the same technology can be used for future pandemics and other health conditions. In this paper, we propose a modified machine learning (ML) process that integrates deep learning (DL) algorithms for feature extraction and well-known classifiers that can accurately detect and diagnose COVID-19 from chest CT scans. Publicly available datasets were made available by the China Consortium for Chest CT Image Investigation (CC-CCII). The highest average accuracy obtained was 99.9% using the modified ML process when 2000 features were extracted using GoogleNet and ResNet18 and using the support vector machine (SVM) classifier. The results obtained using the modified ML process were higher when compared to similar methods reported in the extant literature using the same datasets or different datasets of similar size; thus, this study is considered of added value to the current body of knowledge. Further research in this field is required to develop methods that can be applied in hospitals and can better equip mankind to be prepared for any future pandemics.

In the current Industry 4.0 revolution, prognostics and health management (PHM) is an emerging field of research. The difficulty of obtaining data from electromechanical systems in an industrial setting increases proportionally with the scale and accessibility of the automated industry, resulting in a less interpolated PHM system. To put it another way, the development of an accurate PHM system for each industrial system necessitates a unique dataset acquired under specified conditions. In most circumstances, obtaining this one-of-a-kind dataset is difficult, and the resulting dataset has a significant imbalance, a lack of certain useful information, and contains multi-domain knowledge. To address those issues, this paper provides a fault detection and diagnosis system that evaluates and preprocesses imbalanced, scarce, multi-domain (ISMD) data acquired from an industrial robot, utilizing signal processing (SP) techniques and deep learning-based (DL) domain knowledge transfer. The domain knowledge transfer is used to produce a synthetic dataset with a high interpolation rate that contains all the useful information about each domain. For domain knowledge transfer and data generation, continuous wavelet transform (CWT) with a generative adversarial network (GAN) was used, as well as a convolutional neural network (CNN), to test the suggested methodology using transfer learning and categorize several faults. The proposed methodology was tested on a real experimental bench that included an industrial robot created by Hyundai Robotics. This test had a satisfactory outcome with a 99.7% (highest) classification accuracy achieved by transfer learning on several CNN benchmark models.

Lung cancer is a deadly disease with a high mortality rate. Endobronchial ultrasonography (EBUS) is one of the methods for detecting pulmonary lesions. Computer-aided diagnosis of pulmonary lesions from images can help radiologists to classify lesions; however, most of the existing methods need a large volume of data to give good results. Thus, this paper proposes a novel pulmonary lesion classification framework for EBUS images that works well with small datasets. The proposed framework integrates the statistical results from three classification models using the weighted ensemble classification. The three classification models include the radiomics feature and patient data-based model, the single-image-based model, and the multi-patch-based model. The radiomics features are combined with the patient data to be used as input data for the random forest, whereas the EBUS images are used as input data to the other two CNN models. The performance of the proposed framework was evaluated on a set of 200 EBUS images consisting of 124 malignant lesions and 76 benign lesions. The experimental results show that the accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the curve are 95.00%, 100%, 86.67%, 92.59%, 100%, and 93.33%, respectively. This framework can significantly improve the pulmonary lesion classification.

During the use and management of lead–acid batteries, it is very important to carry out prediction and study of the state of the health (SOH) of the battery. To this end, this paper proposes a SOH prediction method for lead–acid batteries based on the CNN-BiLSTM-Attention model. The model utilizes the convolutional neural network (CNN) to carry out feature extraction and data dimension reduction in the input factors of model, and then these factors are used as the input of the bidirectional long short-term memory network (BiLSTM). The BiLSTM is used to learn the temporal correlation information in the local features of input time series bidirectionally. The attention mechanism is introduced to assign more attention to key features in the input sequence with more significant influence on the output result by assigning weights to important features, and finally, multi-step prediction of the battery SOH is realized. Compared with the prediction results of battery SOH using other neural network methods, the method proposed in this study can provide higher prediction accuracy and achieve accurate multi-step prediction of battery SOH. Measured results show that most of the multi-step prediction errors of the proposed method are controlled within 3%.

Recently, ship detection in synthetic aperture radar (SAR) images has received extensive attention. Most of the current ship detectors preset dense anchor boxes to achieve spatial alignment with ground-truth (GT) objects. Then, the detector defines the positive and negative samples based on the intersection-over-unit (IoU) between the anchors and GT objects. However, this label assignment strategy confuses the learning process of the model to a certain extent and results in suboptimal classification and regression results. In this paper, an adaptive sample assignment (ASA) strategy is proposed to select high-quality positive samples according to the spatial alignment and the knowledge learned from the regression and classification branches. Using our model, the selection of positive and negative samples is more explicit, which achieves better detection performance. A regression guided loss is proposed to further lead the detector to select well-classified and well-regressed anchors as high-quality positive samples by introducing the regression performance as a soft label in the calculation of the classification loss. In order to alleviate false alarms, a feature aggregation enhancement pyramid network (FAEPN) is proposed to enhance multi-scale feature representations and suppress the interference of background noise. Extensive experiments using the SAR ship detection dataset (SSDD) and high-resolution SAR images dataset (HRSID) demonstrate the superiority of our proposed approach.

The purpose of this paper is to study the recognition of ships and their structures to improve the safety of drone operations engaged in shore-to-ship drone delivery service. This study has developed a system that can distinguish between ships and their structures by using a convolutional neural network (CNN). First, the dataset of the Marine Traffic Management Net is described and CNN’s object sensing based on the Detectron2 platform is discussed. There will also be a description of the experiment and performance. In addition, this study has been conducted based on actual drone delivery operations—the first air delivery service by drones in Korea.

Sign language recognition is one of the most challenging applications in machine learning and human-computer interaction. Many researchers have developed classification models for different sign languages such as English, Arabic, Japanese, and Bengali; however, no significant research has been done on the general-shape performance for different datasets. Most research work has achieved satisfactory performance with a small dataset. These models may fail to replicate the same performance for evaluating different and larger datasets. In this context, this paper proposes a novel method for recognizing Bengali sign language (BSL) alphabets to overcome the issue of generalization. The proposed method has been evaluated with three benchmark datasets such as ‘38 BdSL’, ‘KU-BdSL’, and ‘Ishara-Lipi’. Here, three steps are followed to achieve the goal: segmentation, augmentation, and Convolutional neural network (CNN) based classification. Firstly, a concatenated segmentation approach with YCbCr, HSV and watershed algorithm was designed to accurately identify gesture signs. Secondly, seven image augmentation techniques are selected to increase the training data size without changing the semantic meaning. Finally, the CNN-based model called BenSignNet was applied to extract the features and classify purposes. The performance accuracy of the model achieved 94.00%, 99.60%, and 99.60% for the BdSL Alphabet, KU-BdSL, and Ishara-Lipi datasets, respectively. Experimental findings confirmed that our proposed method achieved a higher recognition rate than the conventional ones and accomplished a generalization property in all datasets for the BSL domain.

Vehicle detection on aerial remote sensing images under the complex background of urban areas has always received great attention in the field of remote sensing; however, the view of remote sensing images usually covers a large area, and the size of the vehicle is small and the background is complex. Therefore, compared with object detection in the ground view images, vehicle detection in aerial images remains a challenging problem. In this paper, we propose a single-scale rapid convolutional neural network (SSRD-Net). In the proposed framework, we design a global relational (GR) block to enhance the fusion of local and global features; moreover, we adjust the image segmentation method to unify the vehicle size in the input image, thus simplifying the model structure and improving the detection speed. We further introduce an aerial remote sensing image dataset with rotating bounding boxes (RO-ARS), which has complex backgrounds such as snow, clouds, and fog scenes. We also design a data augmentation method to get more images with clouds and fog. Finally, we evaluate the performance of the proposed model on several datasets, and the experimental results show that the recall and precision are improved compared with existing methods.

Offshore oil platforms are difficult to detect due to the complex sea state, the sparseness of target distribution, and the similarity of targets with ships. In this paper, we propose an oil platform detection method in polarimetric synthetic aperture radar (PolSAR) images using level set segmentation of a limited initial region and a convolutional neural network (CNN). Firstly, to reduce the interference of sea clutter, the offshore strong scattering targets were initially detected by the generalized optimization of polarimetric contrast enhancement (GOPCE) detector. Secondly, to accurately locate the contour of targets and eliminate false alarms, the coarse results were refined using an improved level set segmentation method. An algorithm for splitting and merging the smallest enclosing circle (SMSEC) was proposed to cover the coarse results and obtain the initial level set function. Finally, the LeNet-5 CNN model was used to classify the oil platforms and ships. Experimental results using multiple sets of polarimetric SAR data acquired by RADARSAT-2 show that the performance of the proposed method, including the detection rate, the false alarm rate, and the Intersection over Union (IOU) index between the extracted ROI and the ground truth, is better than the performance of a method that combines a GOPCE detector and a support vector machine classifier.

This paper describes the construction a short-text aspect-based sentiment analysis method based on Convolutional Neural Network (CNN) and Bidirectional Gating Recurrent Unit (BiGRU). The hybrid model can fully extract text features, solve the problem of long-distance dependence on the sequence, and improve the reliability of training. This article reports empirical research conducted on the basis of literature research. The first step was to obtain the dataset and perform preprocessing, after which scikit-learn was used to perform TF-IDF calculations to obtain the feature word vector weight, obtain the aspect-level feature ontology words of the evaluated text, and manually mark the ontology of the reviewed text and the corresponding sentiment analysis polarity. In the sentiment analysis section, a hybrid model based on CNN and BiGRU (CNN + BiGRU) was constructed, which uses corpus sentences and feature words as the vector input and predicts the emotional polarity. The experimental results prove that the classification accuracy of the improved CNN + BiGRU model was improved by 12.12%, 8.37%, and 4.46% compared with the Convolutional Neural Network model (CNN), Long-Short Term Memory model (LSTM), and Convolutional Neural Network (C-LSTM) model.

A brain tumor occurs in humans when a normal cell turns into an aberrant cell inside the brain. Primarily, there are two types of brain tumors in Homo sapiens: benign tumors and malignant tumors. In brain tumor diagnosis, magnetic resonance imaging (MRI) plays a vital role that requires high precision and accuracy for diagnosis, otherwise, a minor error can result in severe consequences. In this study, we implemented various configured convolutional neural network (CNN) paradigms on brain tumor MRI scans that depict whether a person is a brain tumor patient or not. This paper emphasizes objective function values (OFV) achieved by various CNN paradigms with the least validation cross-entropy loss (LVCEL), maximum validation accuracy (MVA), and training time (TT) in seconds, which can be used as a feasible tool for clinicians and the medical community to recognize tumor patients precisely. Experimentation and evaluation were based on a total of 2189 brain MRI scans, and the best architecture shows the highest accuracy of 0.8275, maximum objective function value of 1.84, and an area under the ROC (AUC-ROC) curve of 0.737 to accurately recognize and classify whether or not a person has a brain tumor.

With the development of technology and the rise of the meta-universe concept, the brain-computer interface (BCI) has become a hotspot in the research field, and the BCI based on motor imagery (MI) EEG has been widely concerned. However, in the process of MI-EEG decoding, the performance of the decoding model needs to be improved. At present, most MI-EEG decoding methods based on deep learning cannot make full use of the temporal and frequency features of EEG data, which leads to a low accuracy of MI-EEG decoding. To address this issue, this paper proposes a two-branch convolutional neural network (TBTF-CNN) that can simultaneously learn the temporal and frequency features of EEG data. The structure of EEG data is reconstructed to simplify the spatio-temporal convolution process of CNN, and continuous wavelet transform is used to express the time-frequency features of EEG data. TBTF-CNN fuses the features learned from the two branches and then inputs them into the classifier to decode the MI-EEG. The experimental results on the BCI competition IV 2b dataset show that the proposed model achieves an average classification accuracy of 81.3% and a kappa value of 0.63. Compared with other methods, TBTF-CNN achieves a better performance in MI-EEG decoding. The proposed method can make full use of the temporal and frequency features of EEG data and can improve the decoding accuracy of MI-EEG.

This paper presents an automatic ECG signal classification system that applied the Deep Learning (DL) model to classify four types of ECG signals. In the first part of our work, we present the model development. Four different classes of ECG signals from the PhysioNet open-source database were selected and used. This preliminary study used a Deep Learning (DL) technique namely Convolutional Neural Network (CNN) to classify and predict the ECG signals from four different classes: normal, sudden death, arrhythmia, and supraventricular arrhythmia. The classification and prediction process includes pulse extraction, image reshaping, training dataset, and testing process. In general, the training accuracy achieved up to 95% after 100 epochs. However, the prediction of each ECG single type shows a differentiation. Among the four classes, the results show that the predictions for sudden death ECG waveforms are the highest, i.e., 80 out of 80 samples are correct (100% accuracy). In contrast, the lowest is the prediction for normal sinus ECG waveforms, i.e., 74 out of 80 samples are correct (92.5% accuracy). This is due to the image features of normal sinus ECG waveforms being almost similar to the image features of supraventricular arrhythmia ECG waveforms. However, the model has been tuned to achieve an optimal prediction. In the second part, we presented the hardware implementation with the predictive model embedded in an NVIDIA Jetson Nanoprocessor for the online and real-time classification of ECG waveforms.

Sea level rise is an important and topical issue in the South Pacific region and needs an urgent assessment of trends for informed decision making. This paper presents mean sea level trend assessment using harmonic analysis and a hybrid deep learning (DL) model based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) technique, Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU) and Neighbourhood Component Analysis (NCA) to build a highly accurate sea level forecasting model for three small islands (Fiji, Marshall Island and Papua New Guinea (PNG)) in the South Pacific. For a 20-year period, the estimated mean sea level rise per year from the harmonic computation is obtained: 112 mm for PNG, 98 mm for Marshall Island and 52 mm for Fiji. The DL procedure uses climate and environment-based remote sensing satellite (MODIS, GLDAS-2.0, MODIS TERRA, MERRA-2) predictor variables with tide gauge base mean sea level (MSL) data for model training and development for forecasting. The developed CEEMDAN-CNN-GRU as the objective model is benchmarked by comparison to the hybrid model without data decomposition, CNN-GRU and standalone models, Decision Trees (DT) and Support Vector Regression (SVR). All model performances are evaluated using reliable statistical metrics. The CEEMDAN-CNN-GRU shows superior accuracy when compared with other standalone and hybrid models. It shows an accuracy of >96% for correlation coefficient and an error of

The Cobb angle measurement of the scoliotic spine is prone to inter- and intra-observer variations in the clinical setting. This paper proposes a deep learning architecture for detecting spine vertebrae from X-ray images to evaluate the Cobb angle automatically. The public AASCE MICCAI 2019 anterior-posterior X-ray image dataset and local images were used to train and test the proposed convolutional neural network architecture. Sixty-eight landmark features of the spine were detected from the input image to obtain seventeen vertebrae on the spine. The vertebrae locations obtained were processed to automatically measure the Cobb angle. The proposed method can measure the Cobb angle with accuracies up to 93.6% and has excellent reliability compared to clinicians’ measurement (intraclass correlation coefficient > 0.95). The proposed deep learning architecture may be used as a tool to augment Cobb angle measurement in X-ray images of patients with adolescent idiopathic scoliosis in a real-world clinical setting.