Search

To explore whether the brain contains pattern differences in the rock–paper–scissors (RPS) imagery task, this paper attempts to classify this task using fNIRS and deep learning. In this study, we designed an RPS task with a total duration of 25 min and 40 s, and recruited 22 volunteers for the experiment. We used the fNIRS acquisition device (FOIRE-3000) to record the cerebral neural activities of these participants in the RPS task. The time series classification (TSC) algorithm was introduced into the time-domain fNIRS signal classification. Experiments show that CNN-based TSC methods can achieve 97% accuracy in RPS classification. CNN-based TSC method is suitable for the classification of fNIRS signals in RPS motor imagery tasks, and may find new application directions for the development of brain–computer interfaces (BCI).

The rapid advancement of autonomous vehicle technology has brought into focus the critical need for enhanced road safety systems, particularly in the areas of road damage detection and surface classification. This paper explores these two essential components, highlighting their importance in autonomous driving. In the domain of road damage detection, this study explores a range of deep learning methods, particularly focusing on one-stage and two-stage detectors. These methodologies, including notable ones like YOLO and SSD for one-stage detection and Faster R-CNN for two-stage detection, are critically analyzed for their efficacy in identifying various road damages under diverse conditions. The review provides insights into their comparative advantages, balancing between real-time processing and accuracy in damage localization. For road surface classification, the paper investigates the classification techniques based on both environmental conditions and material road composition. It highlights the role of different convolutional neural network architectures and innovations at the neural level in enhancing classification accuracy under varying road and weather conditions. The main finding of this work is that it offers a comprehensive overview of the current state of the art, showcasing significant strides in utilizing deep learning for road analysis in autonomous vehicle systems. The study concludes by underscoring the importance of continued research in these areas to further refine and improve the safety and efficiency of autonomous driving.

This paper addresses the persistent threat of botnet attacks on IoT devices, emphasizing their continued existence despite various conventional and deep learning methodologies developed for intrusion detection. Utilizing the Bot-IoT dataset, we propose a hierarchical CNN (HCNN) approach featuring three levels of classification. The HCNN approach, presented in this paper, consists of two networks: the non-hierarchical and the hierarchical network. The hierarchical network works by combining features obtained at a higher level with those of its descender. This combined information is subsequently fed into the following level to extract features for the descendant nodes. The overall network consists of 1790 parameters, with the hierarchical network introducing an additional 942 parameters to the existing backbone. The classification levels comprise a binary classification of normal vs attack in the first level, followed by 5 classes in the second level, and 11 classes in the third level. To assess the effectiveness of our proposed approach, we evaluate performance metrics such as Precision (P), Recall (R), F1 Score (F1), and Accuracy (Acc). Rigorous experiments are conducted to compare the performance of both the hierarchical and non-hierarchical models and existing state-of-the-art approaches, providing valuable insights into the efficiency of our proposed hierarchical CNN approach for addressing botnet attacks on IoT devices.

Power load forecasting plays an important role in power systems, and the accuracy of load forecasting is of vital importance to power system planning as well as economic efficiency. Power load data are nonsmooth, nonlinear time-series and “noisy” data. Traditional load forecasting has low accuracy and curves not fitting the load variation. It is not well predicted by a single forecasting model. In this paper, we propose a novel model based on the combination of data mining and deep learning to improve the prediction accuracy. First, data preprocessing is performed. Second, identification and correction of anomalous data, normalization of continuous sequences, and one-hot encoding of discrete sequences are performed. The load data are decomposed and denoised using the double decomposition modal (LVMD) strategy, the load curves are clustered using the double weighted fuzzy C-means (DBFCM) algorithm, and the typical curves obtained are used as load patterns. In addition, data feature analysis is performed. A convolutional neural network (CNN) is used to extract data features. A bidirectional long short-term memory (BLSTM) network is used for prediction, in which the number of hidden layer neurons, the number of training epochs, the learning rate, the regularization coefficient, and other relevant parameters in the BLSTM network are optimized using the influenza virus immunity optimization algorithm (IVIA). Finally, the historical data of City H from 1 January 2016 to 31 December 2018, are used for load forecasting. The experimental results show that the novel model based on LVMD-DBFCM load c1urve clustering combined with CNN-IVIA-BLSTM proposed in this paper has an error of only 2% for electric load forecasting.

With the increasing popularity of deep learning, enterprises are replacing traditional inefficient and non-robust defect detection methods with intelligent recognition technology. This paper utilizes TL (transfer learning) to enhance the model’s recognition performance by integrating the Adam optimizer and a learning rate decay strategy. By comparing the TL-ResNet50 model with other classic CNN models (ResNet50, VGG19, and AlexNet), the superiority of the model used in this paper was fully demonstrated. To address the current lack of understanding regarding the internal mechanisms of CNN models, we employed an interpretable algorithm to analyze pre-trained models and visualize the learned semantic features of defects across various models. This further confirms the efficacy and reliability of CNN models in accurately recognizing different types of defects. Results showed that the TL-ResNet50 model achieved an overall accuracy of 99.4% on the testing set and demonstrated good identification ability for defect features.

In this paper, anomaly detection of wheel flats based on signal processing and deep learning techniques is analyzed. Wheel flats mostly affect running stability and ride comfort. Currently, domestic railway companies visually inspect wheel flats one by one with their eyes after railway vehicles enter the railway depots for maintenance. Therefore, CBM (Condition-Based Maintenance) is required for wheel flats resolution. Anomaly detection for wheel flat signals of railway vehicles using Order analysis and STFT (Short Time Fourier Transform) is studied in this paper. In the case of railway vehicles, it is not easy to obtain actual failure data through running vehicles in a university laboratory due to safety and cost issues. Therefore, vibration-induced acceleration was obtained using a multibody dynamics simulation software, SIMPACK. This method is also proved in the other paper by rig tests. In addition, since the noise signal was not included in the simulated vibration, the noise signal obtained from the Seoul Metro Subway Line 7 vehicle was overlapped with the simulated one. Finally, to improve the performance of both detection rate and real-time of characteristics based on existing LeNet-5 architectures, spectrogram images transformed from time domain data were proceeded with the LeNet deep learning model modified with the pooling method and activation function. As a result, it is validated that the method using the spectrogram with a deep learning approach yields higher accuracy than the time domain data.

Air collection around the lung regions can cause lungs to collapse. Conditions like emphysema can cause chronic obstructive pulmonary disease (COPD), wherein lungs get progressively damaged, and the damage cannot be reversed by treatment. It is recommended that these conditions be detected early via highly complex image processing models applied to chest X-rays so that the patient’s life may be extended. Due to COPD, the bronchioles are narrowed and blocked with mucous, and causes destruction of alveolar geometry. These changes can be visually monitored via feature analysis using effective image classification models such as convolutional neural networks (CNN). CNNs have proven to possess more than 95% accuracy for detection of COPD conditions for static datasets. For consistent performance of CNNs, this paper presents an incremental learning mechanism that uses deep transfer learning for incrementally updating classification weights in the system. The proposed model is tested on 3 different lung X-ray datasets, and an accuracy of 99.95% is achieved for detection of COPD. In this paper, a model for temporal analysis of COPD detected imagery is proposed. This model uses Gated Recurrent Units (GRUs) for evaluating lifespan of patients with COPD. Analysis of lifespan can assist doctors and other medical practitioners to take recommended steps for aggressive treatment. A smaller dataset was available to perform temporal analysis of COPD values because patients are not advised continuous chest X-rays due to their long-term side effects, which resulted in an accuracy of 97% for lifespan analysis.

In the last 10 years, the demand for robot-based depalletization systems has constantly increased due to the growth of sectors such as logistics, storage, and supply chains. Since the scenarios are becoming more and more unstructured, characterized by unknown pallet layouts and stock-keeping unit shapes, the classical depalletization systems based on the knowledge of predefined positions within the pallet frame are going to be substituted by innovative and robust solutions based on 2D/3D vision and Deep Learning (DL) methods. In particular, the Convolutional Neural Networks (CNNs) are deep networks that have proven to be effective in processing 2D/3D images, for example in the automatic object detection task, and robust to the possible variability among the data. However, deep neural networks need a big amount of data to be trained. In this context, whenever deep networks are involved in object detection for supporting depalletization systems, the dataset collection represents one of the main bottlenecks during the commissioning phase. The present work aims at comparing different training strategies to customize an object detection model aiming at minimizing the number of images required for model fitting, while ensuring reliable and robust performances. Different approaches based on a CNN for object detection are proposed, evaluated, and compared in terms of the F1-score. The study was conducted considering different starting conditions in terms of the neural network’s weights, the datasets, and the training set sizes. The proposed approaches were evaluated on the detection of different kinds of paper boxes placed on an industrial pallet. The outcome of the work validates that the best strategy is based on fine-tuning of a CNN-based model already trained on the detection of paper boxes, with a median F1-score greater than 85.0%.

In recent years, the continuous development of artificial intelligence has largely been driven by algorithms and computing power. This paper mainly discusses the training and inference methods of artificial intelligence from the perspective of computing power. To address the issue of computing power, it is necessary to consider performance, cost, power consumption, flexibility, and robustness comprehensively. At present, the training of artificial intelligence models mostly are based on GPU platforms. Although GPUs offer high computing performance, their power consumption and cost are relatively high. It is not suitable to use GPUs as the implementation platform in certain application scenarios with demanding power consumption and cost. The emergence of high-performance heterogeneous architecture devices provides a new path for the integration of artificial intelligence training and inference. Typically, in Xilinx and Intel’s multi-core heterogeneous architecture, multiple high-performance processors and FPGAs are integrated into a single chip. When compared with the current separate training and inference method, heterogeneous architectures leverage a single chip to realize the integration of AI training and inference, providing a good balance of training and inference of different targets, further reducing the cost of training and implementation of AI inference and power consumption, so as to achieve the lightweight goals of computation, and to improve the flexibility and robustness of the system. In this paper, based on the LeNet-5 network structure, we first introduced the process of network training using a multi-core CPU in Xilinx’s latest multi-core heterogeneous architecture device, MPSoC. Then, the method of converting the network model into hardware logic implementation was studied, and the model parameters were transferred from the processing system of the device to the hardware accelerator structure, composed of programmable logic through the bus interface AXI provided on the chip. Finally, the integrated implementation method was tested and verified in Xilinx MPSoC. According to the test results, the recognition accuracy of this lightweight deployment scheme on MNIST dataset and CIFAR-10 dataset reached 99.5 and 75.4% respectively, while the average processing time of the single frame was only 2.2 ms. In addition, the power consumption of the network within the SoC hardware accelerator is only 1.363 W at 100 MHz.

The convolutional neural network (CNN) has been widely used in the field of self-driving cars. To satisfy the increasing demand, the deeper and wider neural network has become a general trend. However, this leads to the main problem that the deep neural network is computationally expensive and consumes a considerable amount of memory. To compress and accelerate the deep neural network, this paper proposes a filter pruning method based on feature maps clustering. The basic idea is that by clustering, one can know how many features the input images have and how many filters are enough to extract all features. This paper chooses Retinanet and WIDER FACE datasets to experiment with the proposed method. Experiments demonstrate that the hierarchical clustering algorithm is an effective method for filtering pruning, and the silhouette coefficient method can be used to determine the number of pruned filters. This work evaluates the performance change by increasing the pruning ratio. The main results are as follows: Firstly, it is effective to select pruned filters based on feature maps clustering, and its precision is higher than that of a random selection of pruned filters. Secondly, the silhouette coefficient method is a feasible method for finding the best clustering number. Thirdly, the detection speed of the pruned model improves greatly. Lastly, the method we propose can be used not only for Retinanet, but also for other CNN models. Its effect will be verified in future work.

Image denoising and super-resolution play vital roles in imaging systems, greatly reducing the preprocessing cost of many AI techniques for object detection, segmentation, and tracking. Various advancements have been accomplished in this field, but progress is still needed. In this paper, we have proposed a novel technique named the Enhanced Learning Enriched Features (ELEF) mechanism using a deep convolutional neural network, which makes significant improvements to existing techniques. ELEF consists of two major processes: (1) Denoising, which removes the noise from images; and (2) Super-resolution, which improves the clarity and details of images. Features are learned through deep CNN and not through traditional algorithms so that we can better refine and enhance images. To effectively capture features, the network architecture adopted Dual Attention Units (DUs), which align with the Multi-Scale Residual Block (MSRB) for robust feature extraction, working sidewise with the feature-matching Selective Kernel Extraction (SKF). In addition, resolution mismatching cases are processed in detail to produce high-quality images. The effectiveness of the ELEF model is highlighted by the performance metrics, achieving a Peak Signal-to-Noise Ratio (PSNR) of 42.99 and a Structural Similarity Index (SSIM) of 0.9889, which indicates the ability to carry out the desired high-quality image restoration and enhancement.

Simulating animal movement has long been a central focus of study in the area of wildlife behaviour studies. Conventional modelling methods have difficulties in accurately representing changes over time and space in the data, and they generally do not effectively use telemetry data. Thus, this paper introduces a new and innovative deep reinforcement learning technique known as AnimalEnvNet. This approach combines historical trajectory data and remote sensing images to create an animal agent using deep reinforcement learning techniques. It overcomes the constraints of conventional modelling approaches. We selected pandas as the subject of our research and carried out research using GPS trajectory data, Google Earth images, and Sentinel-2A remote sensing images. The experimental findings indicate that AnimalEnvNet reaches convergence during supervised learning training, attaining a minimal mean absolute error (MAE) of 28.4 m in single-step prediction when compared to actual trajectories. During reinforcement learning training, the agent has the capability to replicate animal locomotion for a maximum of 12 iterations, while maintaining an error margin of 1000 m. This offers a novel approach and viewpoint for mimicking animal behaviour.

Effective air quality prediction models are crucial for the timely prevention and control of air pollution. However, previous models often fail to fully consider air quality’s temporal and spatial distribution characteristics. In this study, Xi’an City is used as the study area. Data from 1 January 2019 to 31 October 2020 are used as the training set, while data from 1 November 2020 to 31 December 2020 are used as the test set. This paper proposes a multi-time and multi-site air quality prediction model for Xi’an, leveraging a deep learning network model based on APSO-CNN-Bi-LSTM. The CNN model extracts the spatial features of the input data, the Bi-LSTM model extracts the time series features, and the PSO algorithm with adaptive inertia weight (APSO) optimizes the model’s hyperparameters. The results show that the model achieves the best results in terms of MAE and RMSE. Compared to the PSO-SVR, BPTT, CNN-LSTM, and GA-ACO-BP models, the MAE improved by 9.375%, 6.667%, 2.276%, and 4.975%, while the RMSE improved by 8.371%, 8.217%, 6.327%, and 5.293%. These significant improvements highlight the model’s accuracy and its promising application prospects.

Emotion detection holds significant importance in facilitating human–computer interaction, enhancing the depth of engagement. By integrating this capability, we pave the way for forthcoming AI technologies to possess a blend of cognitive and emotional understanding, bridging the divide between machine functionality and human emotional complexity. This progress has the potential to reshape how machines perceive and respond to human emotions, ushering in an era of empathetic and intuitive artificial systems. The primary research challenge involves developing models that can accurately interpret and analyze emotions from both auditory and textual data, whereby auditory data require optimizing CNNs to detect subtle and intense emotional fluctuations in speech, and textual data necessitate access to large, diverse datasets to effectively capture nuanced emotional cues in written language. This paper introduces a novel approach to multimodal emotion recognition, seamlessly integrating speech and text modalities to accurately infer emotional states. Employing CNNs, we meticulously analyze speech using Mel spectrograms, while a BERT-based model processes the textual component, leveraging its bidirectional layers to enable profound semantic comprehension. The outputs from both modalities are combined using an attention-based fusion mechanism that optimally weighs their contributions. The proposed method here undergoes meticulous testing on two distinct datasets: Carnegie Mellon University’s Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) dataset and the Multimodal Emotion Lines Dataset (MELD). The results demonstrate superior efficacy compared to existing frameworks, achieving an accuracy of 88.4% and an F1-score of 87.9% on the CMU-MOSEI dataset, and a notable weighted accuracy (WA) of 67.81% and a weighted F1 (WF1) score of 66.32% on the MELD dataset. This comprehensive system offers precise emotion detection and introduces several significant advancements in the field.

Affective computing is a multidisciplinary field encompassing artificial intelligence, natural language processing, linguistics, computer science, and social sciences. This field aims to deepen our comprehension and capabilities by deploying inventive algorithms. This article presents a groundbreaking approach, the Cumulative Attribute-Weighted Graph Neural Network, which is innovatively designed to integrate trimodal textual, audio, and visual data from the two multimodal datasets. This method exemplifies its effectiveness in performing comprehensive multimodal sentiment analysis. Our methodology employs vocal inputs to generate speaker embeddings trimodal analysis. Using a weighted graph structure, our model facilitates the efficient integration of these diverse modalities. This approach underscores the interrelated aspects of various emotional indicators. The paper’s significant contribution is underscored by its experimental results. Our novel algorithm achieved impressive performance metrics on the CMU-MOSI dataset, with an accuracy of 94% and precision, recall, and F1-scores above 92% for Negative, Neutral, and Positive emotion categories. Similarly, on the IEMOCAP dataset, the algorithm demonstrated its robustness with an overall accuracy of 93%, where exceptionally high precision and recall were noted in the Neutral and Positive categories. These results mark a notable advancement over existing state-of-the-art models, illustrating the potential of our approach in enhancing Sentiment Recognition through the synergistic use of trimodal data. This study’s comprehensive analysis and significant results demonstrate the proposed algorithm’s effectiveness in nuanced emotional state recognition and pave the way for future advancements in affective computing, emphasizing the value of integrating multimodal data for improved accuracy and robustness.

As there is a lack of public mark samples of Tibetan historical document image characters at present, this paper proposes an unsupervised Tibetan historical document character recognition method based on deep learning (UD-CNN). Firstly, using the Tibetan historical document character component, the Tibetan historical document character sample data set is constructed for model-aided training. Then, the character baseline information is introduced, and a fine-grained feature learning strategy is proposed. For the samples above and below the baseline, the Up-CNN recognition model and Down-CNN recognition model are established. The convolution neural network model is trained and optimized for the samples above and below the baseline, respectively, to improve the recognition accuracy. The experimental results show that the proposed method obviously affects the unmarked character classification and recognition of real Tibetan historical document images. The recognition rate of Top5 can reach 92.94%, and the recognition rate of Top1 can be increased from 82.25% to 87.27% using the CNN model only.

Brain tumors (BT) represent a severe and potentially life-threatening cancer. Failing to promptly diagnose these tumors can significantly shorten a person’s life. Therefore, early and accurate detection of brain tumors is essential, allowing for appropriate treatment and improving the chances of a patient’s survival. Due to the different characteristics and data limitations of brain tumors is challenging problems to classify the three different types of brain tumors. A convolutional neural networks (CNNs) learning algorithm integrated with data augmentation techniques was used to improve the model performance. CNNs have been extensively utilized in identifying brain tumors through the analysis of Magnetic Resonance Imaging (MRI) images The primary aim of this research is to propose a novel method that achieves exceptionally high accuracy in classifying the three distinct types of brain tumors. This paper proposed a novel Stack Ensemble Transfer Learning model called “SETL_BMRI”, which can recognize brain tumors in MRI images with elevated accuracy. The SETL_BMRI model incorporates two pre-trained models, AlexNet and VGG19, to improve its ability to generalize. Stacking combined outputs from these models significantly improved the accuracy of brain tumor detection as compared to individual models. The model’s effectiveness is evaluated using a public brain MRI dataset available on Kaggle, containing images of three types of brain tumors (meningioma, glioma, and pituitary). The experimental findings showcase the robustness of the SETL_BMRI model, achieving an overall classification accuracy of 98.70%. Additionally, it delivers an average precision, recall, and F1-score of 98.75%, 98.6%, and 98.75%, respectively. The evaluation metric values of the proposed solution indicate that it effectively contributed to previous research in terms of achieving high detection accuracy.

Advances in information and signal processing, driven by artificial intelligence techniques and recent breakthroughs in deep learning, have significantly impacted autonomous driving by enhancing safety and reducing the dependence on human intervention. Generally, prevailing ADASs (advanced driver assistance systems) incorporate costly components, making them financially unattainable for a substantial portion of the population. This paper proposes a solution: an embedded system designed for real-time pedestrian and priority sign detection, offering affordability and universal applicability across various vehicles. The suggested system, which comprises two cameras, an NVIDIA Jetson Nano B01 low-power edge device and an LCD (liquid crystal system) display, ensures seamless integration into a vehicle without occupying substantial space and provides a cost-effective alternative. The primary focus of this research is addressing accidents caused by the failure to yield priority to other drivers or pedestrians. Our study stands out from existing research by concurrently addressing traffic sign recognition and pedestrian detection, concentrating on identifying five crucial objects: pedestrians, pedestrian crossings (signs and road paintings separately), stop signs, and give way signs. Object detection was executed using a lightweight, custom-trained CNN (convolutional neural network) known as SSD (Single Shot Detector)-MobileNet, implemented on the Jetson Nano. To tailor the model for this specific application, the pre-trained neural network underwent training on our custom dataset consisting of images captured on the road under diverse lighting and traffic conditions. The outcomes of the proposed system offer promising results, positioning it as a viable candidate for real-time implementation; its contributions are noteworthy in advancing the safety and accessibility of autonomous driving technologies.

The term “Liver disease” refers to a broad category of disorders affecting the liver. There are a variety of common liver ailments, such as hepatitis, cirrhosis, and liver cancer. Accurate and early diagnosis is an emergent demand for the prediction and diagnosis of liver disease. Conventional diagnostic techniques, such as radiological, CT scan, and liver function tests, are often time-consuming and prone to inaccuracies in several cases. An application of machine learning (ML) and deep learning (DL) techniques is an efficient approach to diagnosing diseases in a wide range of medical fields. This type of machine-related learning can handle various tasks, such as image recognition, analysis, and classification, because it helps train large datasets and learns to identify patterns that might not be perceived by humans. This paper is presented here with an evaluation of the performance of various DL models on the estimation and subtyping of liver ailment and prognosis. In this manuscript, we propose a novel approach, termed CNN+LSTM, which is an integration of convolutional neural network (CNN) and long short-term memory (LSTM) networks. The results of the study prove that ML and DL can be used to improve the diagnosis and prognosis of liver disease. The CNN+LSTM model achieves a better accuracy of 98.73% compared to other models such as CNN, Recurrent Neural Network (RNN), and LSTM. The incorporation of the proposed CNN+LSTM model has better results in terms of accuracy (98.73%), precision (99%), recall (98%), F1 score (98%), and AUC (Area Under the Curve)-ROC (Receiver Operating Characteristic) (99%), respectively. The use of the CNN+LSTM model shows robustness in predicting the liver ailment with an accurate diagnosis and prognosis.

In order to achieve the goal of detecting the fertility of hatching eggs which are divided into fertile eggs and dead eggs more accurately and effectively, a novel method combining a convolution neural network (CNN) and a heartbeat signal of the hatching eggs is proposed in this paper. Firstly, we collected heartbeat signals of 9-day-later hatching eggs by the method of PhotoPlethysmoGraphy (PPG), which is a non-invasive method to detect the change of blood volume in living tissues by photoelectric means. Secondly, a sequential convolutional neural network E-CNN, which was used to analyze heartbeat sequence of hatching eggs, was designed. Thirdly, an end-to-end trainable convolutional neural network SR-CNN, which was used to process heartbeat waveform images of hatching eggs, was designed to improve the classification performance in this paper. Key to improving the classification performance of SR-CNN is the SE-Res module, which combines the channel weighting unit “Squeeze-and-Excitation„ (SE) block and the residual structure. The experimental results show that two models trained on our dataset, with E-CNN and SR-CNN, are able to achieve the fertility detection of the hatching eggs with superior identification accuarcy, up to 99.50% and 99.62% respectively, on our test set. It is demonstrated that the proposed method is feasible for identifying and classifying the survival of hatching eggs accurately and effectively.

Recently, deep learning techniques have been used for low-dose CT (LDCT) reconstruction to reduce the radiation risk for patients. Despite the improvement in performance, the network models used for LDCT reconstruction are becoming increasingly complex and computationally expensive under the mantra of “deeper is better”. However, in clinical settings, lightweight models with a low computational cost and short reconstruction times are more popular. For this reason, this paper proposes a computationally efficient CNN model with a simple structure for sparse-view LDCT reconstruction. Inspired by super-resolution networks for natural images, the proposed model interpolates projection data directly in the sinogram domain with a fully convolutional neural network that consists of only four convolution layers. The proposed model can be used directly for sparse-view CT reconstruction by concatenating the classic filtered back-projection (FBP) module, or it can be incorporated into existing dual-domain reconstruction frameworks as a generic sinogram domain module. The proposed model is validated on both the 2016 NIH-AAPM-Mayo Clinic LDCT Grand Challenge dataset and The Lung Image Database Consortium dataset. It is shown that despite the computational simplicity of the proposed model, its reconstruction performance at lower sparsity levels (1/2 and 1/4 radiation dose) is comparable to that of the sophisticated baseline models and shows some advantages at higher sparsity levels (1/8 and 1/15 radiation dose). Compared to existing sinogram domain baseline models, the proposed model is computationally efficient and easy to train on small training datasets, and is thus well suited for clinical real-time reconstruction tasks.

Among the many problems in machine learning, the most critical ones involve improving the categorical response prediction rate based on extracted features. In spite of this, it is noted that most of the time from the entire cycle of multi-class machine modeling for sign language recognition tasks is spent on data preparation, including collection, filtering, analysis, and visualization of data. To find the optimal solution for the above-mentioned problem, this paper proposes a methodology for automatically collecting the spatiotemporal features of gestures by calculating the coordinates of the found area of the pose and hand, normalizing them, and constructing an optimal multilayer perceptron for multiclass classification. By extracting and analyzing spatiotemporal data, the proposed method makes it possible to identify not only static features, but also the spatial (for gestures that touch the face and head) and dynamic features of gestures, which leads to an increase in the accuracy of gesture recognition. This classification was also carried out according to the form of the gesture demonstration to optimally extract the characteristics of gestures (display ability of all connection points), which also led to an increase in the accuracy of gesture recognition for certain classes to the value of 0.96. This method was tested using the well-known Ankara University Turkish Sign Language Dataset and the Dataset for Argentinian Sign Language to validate the experiment, which proved effective with a recognition accuracy of 0.98.

High-efficiency video coding (HEVC) outperforms H.264 in coding efficiency. However, the rate–distortion optimization (RDO) process in coding tree unit (CTU) partitioning requires an exhaustive exploration of all possible quad-tree partitions, resulting in high encoding complexity. To simplify this process, this paper proposed a convolution neural network (CNN) based optimization algorithm combined with a hybrid attention mechanism module. Firstly, we designed a CNN compatible with the current coding unit (CU) size to accurately predict the CU partitions. In addition, we also designed a convolution block to enhance the information interaction between CU blocks. Then, we introduced the convolution block attention module (CBAM) into CNN, called CNN-CBAM. This module concentrates on important regions in the image and attends to the target object correctly. Finally, we integrated the CNN-CBAM into the HEVC coding framework for CU partition prediction in advance. The proposed network was trained, validated, and tested using a large scale dataset covering various scenes and objects, which provides extensive samples for intra-frame CU partition prediction in HEVC. The experimental findings demonstrate that our scheme can reduce the coding time by up to 64.05% on average compared to a traditional HM16.5 encoder, with only 0.09 dB degradation in BD-PSNR and a 1.94% increase in BD-BR.

Intracerebral hemorrhage is a severe problem where more than one-third of patients die within a month. In diagnosing intracranial hemorrhage, neuroimaging examinations are essential. As a result, the interpretation of neuroimaging becomes a crucial process in medical procedures. However, human-based image interpretation has inherent limitations, as it can only handle a restricted range of tasks. To address this, a study on medical image captioning has been conducted, but it primarily focused on single medical images. However, actual medical images often consist of continuous sequences, such as CT scans, making it challenging to directly apply existing studies. Therefore, this paper proposes a CT image captioning model that utilizes a 3D-CNN model and distilGPT-2. In this study, four combinations of 3D-CNN models and language models were compared and analyzed for their performance. Additionally, the impact of applying penalties to the loss function and adjusting penalty values during the training process was examined. The proposed CT image captioning model demonstrated a maximum BLEU score of 0.35 on the in-house dataset, and it was observed that the text generated by the model became more similar to human interpretations in medical image reports with the application of loss function penalties.

As one of the most common forms of corrosion in the marine environment, pitting corrosion can have a detrimental impact on the ultimate strength of steel columns. Pitting pits are usually covered by corrosion products, and the detection of pitting is very difficult, so how to effectively identify random pitting corrosion on steel columns has become a very vital issue. In this paper, a deep-learning-based pitting damage determination method for steel columns is investigated by combining numerical simulation and theoretical analysis, which was validated by experimental results. First, a multi-parameter localized pitting corrosion model was proposed that considered the pitting corrosion randomness in time and space distribution. Second, the relationship between the ultimate strength and corrosion rate of steel columns was analyzed. Finally, a steel column damage determination framework was constructed based on the convolutional neural network. Results showed that the ultimate strength and corrosion rate developed different trends in various corrosion regions, and a damage determination accuracy of 90.2% could be achieved by the neural network after training, which satisfied the practical engineering requirements. This study lays the groundwork for further application of deep learning to the research on the pitting damage to steel structures.

Thermal imaging is a cutting-edge technology which has the capability to detect objects in any environmental conditions, such as smoke, fog, smog, etc. This technology finds its importance mainly during nighttime since it does not require light to detect the objects. Applications of this technology span into various sectors, most importantly in border security to detect any incoming hazards. Object detection and classification are generally difficult with thermal imaging. In this paper, a one-stage deep convolution network-based object detection and classification called retina net is introduced. Existing surveys are based on object detection using infrared information obtained from the objects. This research is focused on detecting and identifying objects from thermal images and surveillance data.

The primary objective of this study is to provide an extensive review of deep learning techniques for medical image recognition, highlighting their potential for improving diagnostic accuracy and efficiency. We systematically organize the paper by first discussing the characteristics and challenges of medical imaging techniques, with a particular focus on magnetic resonance imaging (MRI) and computed tomography (CT). Subsequently, we delve into direct image processing methods, such as image enhancement and multimodal medical image fusion, followed by an examination of intelligent image recognition approaches tailored to specific anatomical structures. These approaches employ various deep learning models and techniques, including convolutional neural networks (CNNs), transfer learning, attention mechanisms, and cascading strategies, to overcome challenges related to unclear edges, overlapping regions, and structural distortions. Furthermore, we emphasize the significance of neural network design in medical imaging, concentrating on the extraction of multilevel features using U-shaped structures, dense connections, 3D convolution, and multimodal feature fusion. Finally, we identify and address the key challenges in medical image recognition, such as data quality, model interpretability, generalizability, and computational resource requirements. By proposing future directions in data accessibility, active learning, explainable AI, model robustness, and computational efficiency, this study paves the way for the successful integration of AI in clinical practice and enhanced patient care.

One of the main concerns in precision agriculture (PA) is the growth of weeds within a crop field. Currently, to prevent the spread of weeds, automatic techniques and computational tools are used to help to identify, classify, and detect the different types of weeds found in agricultural fields. One of the technologies that can help us to process digital information gathered from the agricultural fields is high-performance computing (HPC); this technology has been adopted to carry out projects requiring extra processing and storage in order to execute tasks with a large computational cost. This paper shows the implementation of an HPC cluster (HPCC), in which image processing (IP) and analysis are executed using deep learning (DL) techniques, specifically, convolutional neural networks (CNNs) with the VGG16 and InceptionV3 models, to classify different weed species. The results show the great benefits of using high-performance computing clusters in PA, specifically for classifying images. To apply distributed computing within the HPCC, the Keras and Horovod frameworks were used to train the CNN models, obtaining the best time with the InceptionV3 model with a value of 37 min 55.193 s using six HPCC cores, obtaining an accuracy of 0.65 as a result.

HAR technology uses computer and machine vision to analyze human activity and gestures by processing sensor data. The 3-axis acceleration and gyro sensor data are particularly effective in measuring human activity as they can calculate movement speed, direction, and angle. Our paper emphasizes the importance of developing a method to expand the recognition range of human activity due to the many types of activities and similar movements that can result in misrecognition. The proposed method uses 3-axis acceleration and gyro sensor data to visually define human activity patterns and improve recognition accuracy, particularly for similar activities. The method involves converting the sensor data into an image format, removing noise using time series features, generating visual patterns of waveforms, and standardizing geometric patterns. The resulting data (1D, 2D, and 3D) can simultaneously process each type by extracting pattern features using parallel convolution layers and performing classification by applying two fully connected layers in parallel to the merged data from the output data of three convolution layers. The proposed neural network model achieved 98.1% accuracy and recognized 18 types of activities, three times more than previous studies, with a shallower layer structure due to the enhanced input data features.

Medication should be consumed as prescribed with little to zero margins for errors, otherwise consequences could be fatal. Due to the pervasiveness of camera-equipped mobile devices, patients and practitioners can easily take photos of unidentified pills to avert erroneous prescriptions or consumption. This area of research goes under the umbrella of information retrieval and, more specifically, image retrieval or recognition. Several studies have been conducted in the area of image retrieval in order to propose accurate models, i.e., accurately matching an input image with stored ones. Recently, neural networks have been shown to be effective in identifying digital images. This study aims to provide an enhancement to image retrieval in terms of accuracy and efficiency through image segmentation and classification. This paper suggests three neural network (CNN) architectures: two models that are hybrid networks paired with a classification method (CNN+SVM and CNN+kNN) and one ResNet-50 network. We perform various preprocessing steps by using several detection techniques on the selected dataset. We conduct extensive experiments using a real-life dataset obtained from the National Library of Medicine database. The results demonstrate that our proposed model is capable of deriving an accuracy of 90.8%. We also provide a comparison of the above-mentioned three models with some existing methods, and we notice that our proposed CNN+kNN architecture improved the pill image retrieval accuracy by 10% compared to existing models.

Most of the world’s crops can be attacked by various diseases or pests, affecting their quality and productivity. In recent years, transfer learning with deep learning (DL) models has been used to detect diseases in maize, tomato, rice, and other crops. In the specific case of coffee, some recent works have used fixed hyperparameters to fine-tune the pre-trained models with the new dataset and/or applied data augmentation, such as image patching, to improve classifier performance. However, a detailed evaluation of the impact of architecture (e.g., backbone) and training (e.g., optimizer and learning rate) hyperparameters on the performance of coffee rust classification models has not been performed. Therefore, this paper presents a comprehensive study of the impact of five types of hyperparameters on the performance of coffee rust classification models. Specifically, eight pre-trained models are compared, each with four different amounts of transferred layers and three different numbers of neurons in the fully-connected (FC) layer, and the models are fine-tuned with three types of optimizers, each with three learning rate values. Comparing more than 800 models in terms of F1-score and accuracy, it is identified that the type of backbone is the hyperparameter with the greatest impact (with differences between models of up to 70%), followed by the optimizer (with differences of up to 20%). At the end of the study, specific recommendations are made on the values of the most suitable hyperparameters for the identification of this type of disease in coffee crops.

Examining and predicting skin cancer from skin lesion images is challenging due to the complexity of the images. Early detection and treatment of skin lesion disease can prevent mortality as it can be curable. Computer-aided diagnosis (CAD) provides a second opinion for dermatologists as they can classify the type of skin lesion with high accuracy due to their ability to show various clinical identification features locally and globally. Convolutional neural networks (CNNs) have significantly improved the performance of CAD systems for medical image segmentation and classifications. However, tuning CNNs are challenging since the search space of all possible hyperparameter configurations is substantially vast. In this paper, we adopt a genetic algorithm to automatically configure a CNN model for an accurate, reliable, and robust automated skin lesion classification for early skin lesion diagnosis. The optimized CNN model uses four public datasets to train and be able to detect abnormalities based on skin lesion features in different orientations. The model achieves the best scores for each of the DICE coefficients, precision measure, and F-score. These scores compare better than other existing methods. Considering the success of this optimized model, it could be a valuable method to implement in clinical settings.

Industrial defect detection methods based on deep learning can reduce the cost of traditional manual quality inspection, improve the accuracy and efficiency of detection, and are widely used in industrial fields. Traditional computer defect detection methods focus on manual features and require a large amount of defect data, which has some limitations. This paper proposes a texture surface defect detection method based on convolutional neural network and wavelet analysis: TSDNet. The approach combines wavelet analysis with patch extraction, which can detect and locate many defects in a complex texture background; a patch extraction method based on random windows is proposed, which can quickly and effectively extract defective patches; and a judgment strategy based on a sliding window is proposed to improve the robustness of CNN. Our method can achieve excellent detection accuracy on DAGM 2007, a micro-surface defect database and KolektorSDD dataset, and can find the defect location accurately. The results show that in the complex texture background, the method can obtain high defect detection accuracy with only a small amount of training data and can accurately locate the defect position.

The accurate detection of pineapples of different maturity levels in a complex field environment is the key step to achieving the early yield estimation and mechanized picking of pineapple. This study proposes a target detection model based on the improved YOLOv7 to achieve the accurate detection and maturity classification of pineapples in the field. First, the attention mechanism SimAM is inserted into the structure of the original YOLOv7 network to improve the feature extraction ability of the model. Then, the max-pooling convolution (MPConv) structure is improved to reduce the feature loss in the downsampling process. Finally, the non-maximum suppression (NMS) algorithm is replaced by the soft-NMS algorithm, with a better effect at improving the detection effect when pineapple is in occlusion or overlaps. According to the test, the mean average precision (mAP) and recall of the model proposed in this paper are 95.82% and 89.83%, which are 2.71% and 3.41% higher than those of the original YOLOv7, respectively. The maturity classification accuracy of the model and the detection performance under six different field scenarios were analyzed quantitatively. This method provides an effective scheme for the vision system of the field pineapple picking robot.

In the recent past, the COVID-19 epidemic has impeded global economic progress and, by extension, all of society. This type of pandemic has spread rapidly, posing a threat to human lives and the economy. Because of the growing scale of COVID-19 cases, employing artificial intelligence for future prediction purposes during this pandemic is crucial. Consequently, the major objective of this research paper is to compare various deep learning forecasting algorithms, including auto-regressive integrated moving average, long short-term memory, and conventional neural network techniques to forecast how COVID-19 would spread in Saudi Arabia in terms of the number of people infected, the number of deaths, and the number of recovered cases. Three different time horizons were used for COVID-19 predictions: short-term forecasting, medium-term forecasting, and long-term forecasting. Data pre-processing and feature extraction steps were performed as an integral part of the analysis work. Six performance measures were applied for comparing the efficacy of the developed models. LSTM and CNN algorithms have shown superior predictive precision with errors of less than 5% measured on available real data sets. The best model to predict the confirmed death cases is LSTM, which has better RMSE and R2 values. Still, CNN has a similar comparative performance to LSTM. LSTM unexpectedly performed badly when predicting the recovered cases, with RMSE and R2 values of 641.3 and 0.313, respectively. This work helps decisionmakers and health authorities reasonably evaluate the status of the pandemic in the country and act accordingly.

This paper provides novel insights into the robustness of machine learning and signal-processing-based acoustic material classification for material transport in modern iron- and steelmaking. The proposed method is designed to deal with the specific harsh and challenging environmental conditions encountered in steel plants. Robust classification depends on the dataset and its contamination with noise. The present work investigates the application of noise detection together with classification algorithms and shows the impact on classification performance. Four contributions are addressed: (i) an evaluation of an outlier detection method for time series, which is based on the short-term enhanced root mean square value RMS (RMSe), (ii) a comparison of different artificial neural network (ANN) structures applied for acoustic classification of material classes, (iii) results on the test dataset splits and (iv) evaluation of the robustness of proposed convolutional neural network (CNN) architecture against environmental disturbances such as the adversarial dropping sound of contaminants. With the combination of preprocessing and CNN on a material transport process dataset, we show an improvement of the overall classification accuracy. It proves the significance of preprocessing a contaminated dataset and the applicability of CNN for real-world acoustic sensoring systems.

Sentiment analysis (SA), and emotion detection and recognition from text (EDRT) are recent areas of study that are closely related to each other. Sentiment analysis strives to identify and detect neutral, positive, or negative feelings from text. On the other hand, emotion analysis seeks to identify and distinguish types of feelings such as happiness, surprise, grief, disgust, fear, and anger through the expression of texts. We suggest a four-level strategy in this paper for recommending the best book to users. The levels include semantic network grouping of comparable sentences, sentiment analysis, reviewer clustering, and recommendation system. The semantic network groups comparable sentences at the first level utilizing pre-processed data from reviewer and book datasets using the parts of speech (POS) tagger. In order to extract keywords from the pre-processed data, feature extraction uses the bag of words (BOW) and term frequency-inverse document frequency (TF-IDF) approaches. SA is performed at the second level in two phases: training and testing, employing deep learning methodologies such as convolutional neural networks (CNN)-long short-term memory (LSTM). The results of this level are sent into the third level (clustering), which uses the clustering method to group the reviewers by age, location, and gender. In the last level, the model assessment is carried out with accuracy, precision, recall, sensitivity, specificity, G-mean, and F1-measure. The book suggestion system is designed to provide the highest level of accuracy within a minimum number of epochs when compared to the state-of-the methods, SVM, CNN, ANN, LSTM, and Bi-directional (BI)-LSTM.

In this research paper, the acoustic emission technique and a deep learning framework based on two types of pre-trained CNN models (alexNet and squeezeNet) and a new model are proposed to characterize and classify the mechanical behavior of AlSi10Mg components. Specimens are built in a Selective Laser Melting machine with different bed orientations along X, Y, Z, and 45 degrees. Tensile tests are performed, and AE signals are recorded from these tests. To characterize the elastic and plastic deformation stages, a time-frequency domain analysis was performed using CWT-based spectrograms. Three different categories of damage classification strategies were implemented, and CNN models were trained for each strategy. CNN models including AlexNet, SqueezeNet, and the new model were used. Several training modes were performed to determine the CNN model that can accurately classify AE data. Understanding the minimum set of AE signals needed to train the CNN while having 100% accuracy and understanding the parameters affecting the accuracy of a CNN and the training time for the efficient classification of AE signals are the main objectives of this work. The results obtained demonstrated that the new simplified CNN model proposed can accurately classify the AE signals in a short time compared to AlexNet and SqueezeNet.

Forecasting algorithms have been used to support decision making in companies, and it is necessary to apply approaches that facilitate a good forecasting result. The present paper describes assessments based on a combination of different neural network models, tested to forecast steel production in the world. The main goal is to find the best machine learning model that fits the steel production data in the world to make a forecast for a nine-year period. The study is important for understanding the behavior of the models and sensitivity to hyperparameters of convolutional LSTM and GRU recurrent neural networks. The results show that for long-term prediction, the GRU model is easier to train and provides better results. The article contributes to the validation of the use of other variables that are correlated with the steel production variable, thus increasing forecast accuracy.

The high-speed train (HST) is one of the most important transport tools in China, and the sound quality of its interior noise affects passengers’ comfort. This paper proposes a HST sound quality model. The model combines Mel-scale frequency cepstral coefficients (MFCCs), the most popular spectral-based input parameter in deep learning models, with convolutional neural networks (CNNs) to evaluate the sound quality of HSTs. Meanwhile, two input channels are applied to simulate binaural hearing so that the different sound signals can be processed separately. The binaural MFCC-CNN model achieves an accuracy of 96.2% and outperforms the traditional shallow neural network model because it considers the time-varying characteristics of noise. The MFCC features are capable of capturing the characteristics of noise and improving the accuracy of sound quality evaluations. Besides, the results suggest that the time and level differences in sound signals are important factors affecting sound quality at low annoyance levels. The proposed model is expected to optimize the comfort of the interior acoustic environment of HSTs.

More than four million people worldwide suffer from hearing loss. Recently, new CNNs and deep ensemble-learning technologies have brought promising opportunities to the image-recognition field, so many studies aiming to recognize American Sign Language (ASL) have been conducted to help these people express their thoughts. This paper proposes an ASL Recognition System using Multiple deep CNNs and accuracy-based weighted voting (ARS-MA) composed of three parts: data preprocessing, feature extraction, and classification. Ensemble learning using multiple deep CNNs based on LeNet, AlexNet, VGGNet, GoogleNet, and ResNet were set up for the feature extraction and their results were used to create three new datasets for classification. The proposed accuracy-based weighted voting (AWV) algorithm and four existing machine algorithms were compared for the classification. Two parameters, α and λ, are introduced to increase the accuracy and reduce the testing time in AWV. The experimental results show that the proposed ARS-MA achieved 98.83% and 98.79% accuracy on the ASL Alphabet and ASLA datasets, respectively.

In recent years, deep learning has been widely used in emotion recognition, but the models and algorithms in practical applications still have much room for improvement. With the development of graph convolutional neural networks, new ideas for emotional recognition based on EEG have arisen. In this paper, we propose a novel deep learning model-based emotion recognition method. First, the EEG signal is spatially filtered by using the common spatial pattern (CSP), and the filtered signal is converted into a time–frequency map by continuous wavelet transform (CWT). This is used as the input data of the network; then the feature extraction and classification are performed by the deep learning model. We called this model CNN-BiLSTM-MHSA, which consists of a convolutional neural network (CNN), bi-directional long and short-term memory network (BiLSTM), and multi-head self-attention (MHSA). This network is capable of learning the time series and spatial information of EEG emotion signals in depth, smoothing EEG signals and extracting deep features with CNN, learning emotion information of future and past time series with BiLSTM, and improving recognition accuracy with MHSA by reassigning weights to emotion features. Finally, we conducted experiments on the DEAP dataset for sentiment classification, and the experimental results showed that the method has better results than the existing classification. The accuracy of high and low valence, arousal, dominance, and liking state recognition is 98.10%, and the accuracy of four classifications of high and low valence-arousal recognition is 89.33%.

Fault early warning is a challenge in the field of operation and maintenance. Considering the improvement of accuracy and real-time standards, as well as the explosive growth of operation and maintenance data, traditional manual experience and static threshold can no longer meet the production requirements. This research fully digs into the difficulties in fault early warning and provides targeted solutions in several aspects, such as difficulty in feature extraction, insufficient prediction accuracy, and difficulty in determining alarm threshold. The TCAG model proposed in this paper creatively combines the spatiotemporal characteristics and topological characteristics of specific time series data to apply to time series prediction and gives the recommended dynamic threshold interval for fault early warning according to the prediction value. A data comparison experiment of a core router of Ningxia Electric Power Co., Ltd. shows that the combination of topological data analysis (TDA) and convolutional neural network (CNN) enables the TCAG model to obtain superior feature extraction capability, and the support of the attention mechanism improves the prediction accuracy of the TCAG model compared to the benchmark models.

In modern medicine, medical imaging technologies such as computed tomography (CT), X-ray, ultrasound, magnetic resonance imaging (MRI), nuclear medicine, etc., have been proven to provide useful diagnostic information by displaying areas of a lesion or tumor not visible to the human eye, and may also help provide additional recessive information by using modern data analysis methods. These methods, including Artificial Intelligence (AI) technologies, are based on deep learning architectures, and have shown remarkable results in recent studies. However, the lack of explanatory ability of connection-based, instead of algorithm-based, deep learning technologies is one of the main reasons for the delay in the acceptance of these technologies in the mainstream medical field. One of the recent methods that may offer the explanatory ability for the CNN classes of deep learning neural networks is the gradient-weighted class activation mapping (Grad-CAM) method, which produces heat-maps that may offer explanations of the classification results. There are already many studies in the literature that compare the objective metrics of Grad-CAM-generated heat-maps against other methods. However, the subjective evaluation of AI-based classification/prediction results using medical images by qualified personnel could potentially contribute more to the acceptance of AI than objective metrics. The purpose of this paper is to investigate whether and how the Grad-CAM heat-maps can help physicians and radiologists in making diagnoses by presenting the results from AI-based classifications as well as their associated Grad-CAM-generated heat-maps to a qualified radiologist. The results of this study show that the radiologist considers Grad-CAM-generated heat-maps to be generally helpful toward diagnosis.

In the wake of the restrictions imposed on social interactions due to the COVID-19 pandemic, traditional classroom education was replaced by distance education in many universities. Under the changed circumstances, students are required to learn more independently. The challenge for teachers has been to duly ascertain students’ learning efficiency and engagement during online lectures. This paper proposes an optimized lightweight convolutional neural network (CNN) model for engagement recognition within a distance-learning setup through facial expressions. The ShuffleNet v2 architecture was selected, as this model can easily adapt to mobile platforms and deliver outstanding performance compared to other lightweight models. The proposed model was trained, tested, evaluated and compared with other CNN models. The results of our experiment showed that an optimized model based on the ShuffleNet v2 architecture with a change of activation function and the introduction of an attention mechanism provides the best performance concerning engagement recognition. Further, our proposed model outperforms many existing works in engagement recognition on the same database. Finally, this model is suitable for student engagement recognition for distance learning on mobile platforms.

Over the past few years, Internet applications have become more advanced and widely used. This has increased the need for Internet networks to be secured. Intrusion detection systems (IDSs), which employ artificial intelligence (AI) methods, are vital to ensuring network security. As a branch of AI, deep learning (DL) algorithms are now effectively applied in IDSs. Among deep learning neural networks, the convolutional neural network (CNN) is a well-known structure designed to process complex data. The CNN overcomes the typical limitations of conventional machine learning approaches and is mainly used in IDSs. Several CNN-based approaches are employed in IDSs to handle privacy issues and security threats. However, there are no comprehensive surveys of IDS schemes that have utilized CNN to the best of our knowledge. Hence, in this study, our primary focus is on CNN-based IDSs so as to increase our understanding of various uses of the CNN in detecting network intrusions, anomalies, and other types of attacks. This paper innovatively organizes the studied CNN-IDS approaches into multiple categories and describes their primary capabilities and contributions. The main features of these approaches, such as the dataset, architecture, input shape, evaluated metrics, performance, feature extraction, and classifier method, are compared. Because different datasets are used in CNN-IDS research, their experimental results are not comparable. Hence, this study also conducted an empirical experiment to compare different approaches based on standard datasets, and the comparative results are presented in detail.

In this paper, we proposed a hybrid deep learning approach for detecting and classifying tomato plant leaf diseases early. This hybrid system is a combination of a convolutional neural network (CNN), convolutional attention module (CBAM), and support vector machines (SVM). Initially, the proposed model can detect nine different tomato diseases but is not limited to this. The proposed system is tested using a database containing images of tomato leaves. The obtained results were very encouraging, giving us accuracy up to 97.2%, which can be improved with the improvement of learning processes. The proposed system is very efficient and lightweight, so the farmer can install it on any smart device having a digital camera and processing capabilities. With a bit of training, a farmer can detect any disease immediately, which will help him take timely pre-emptive action.

With the spread of the modern media industry, harmful genre contents are indiscriminately disseminated to teenagers. The password identification method used to block sensational and violent genre content has become a problem that teenagers can easily steal. Therefore, a user identification method with less risk of theft and hacking is required. The surface EMG (sEMG) signal, which is an electrical signal generated inside the body and has individual features, is being studied as a next-generation user identification method. sEMG involves measuring an individual’s unique muscular strength activated over time as digital signals, thus giving it the advantage of generating different signal patterns. However, it is difficult to constantly and repeatedly acquire each motion signal and the number of repetitions for each motion is insufficient, thus there is a limit to improving user identification accuracy. In this paper, we propose a user identification system that solves the problem of insufficient data by applying the matching pursuit that enables signal generation to the sEMG signal from which the resting signal has been removed and improves classification accuracy by extracting STFT-based time–frequency features. As a result of the experiment, the user identification accuracy of the sEMG spectrogram with the resting state signal removed was 85.4%. In addition, when the training data were increased through data generation, the accuracy was improved, showing a user identification accuracy of 96.1%. Improved user recognition accuracy was confirmed when the training data of the sEMG signal from which the resting signal was removed were increased and multidimensional features including time–frequency were used.

Nowadays, large-scale human mobility has led to increasingly severe traffic congestion in cities, how to accurately identify people’s travel mode has become particularly important for urban traffic planning and management. However, traditional methods are based on telephone interviews or questionnaires, which makes it difficult to obtain accurate and effective data. Nowadays, numbers of smartphones are equipped with various sensors, including accelerometers, gyroscopes, and GPS, providing a novel social sensing data source to detect people’s travel modes. The fusion of multiple sensor data is a promising way for travel mode detection. However, how to use these sensor data to accurately detect travel mode is still a challenging task. In this paper, we presented a light-weight method for travel mode detection based on four types of smartphone sensor data collected from an accelerometer, gyroscope, magnetometer, and barometer, and a prototype application was developed. Then, a novel convolutional neural network (CNN) was designed to identify five representative travel modes (walk, bicycle, bus, car, and metro). We compared the overall performance of the proposed method via different hyperparameters, and the experimental results show that the F value of the proposed method reaches 97%, which verified the effectiveness of the proposed method for travel mode classification.