Narrow Results

The characteristics of hyperspectral remote sensing images such as inconspicuous feature representativeness, single feature level, and complex information content, can lead to unstable classification results. We propose a lightweight dense network model that injects channel attention in the form of dense connections between network layers (DSE-DN) for the classification of hyperspectral images. In the DSE-DN network, principal component analysis (PCA) is applied to reduce redundancy in the hyperspectral images. Subsequently, a densely connected network is constructed, incorporating channel attention mechanisms through dense connections to enhance the analysis of spectral image features. Finally, the processed hyperspectral images are classified using a fully interconnected layer. We assess two classical hyperspectral datasets and construct 2DCNN, 3DCNN, ResNet, and the network that injects channel attention layer by layer to compare with DSE-DN. The experimental results indicate the utility of the DSE-DN network in hyperspectral image classification and its superiority over other networks.

Due to the harsh working environments of certain bridges, the bridge structural health monitoring systems (SHMs) are prone to error warning because of anomaly data. Therefore, it is of great significance to accurately classify and locate the anomaly data for effectively addressing these issues. This paper proposes a method for classifying and locating anomaly data utilizing one-dimensional monitoring data based on convolutional neural networks. Compared to previous research reliant on visual features, the proposed method has lower computational costs. By incorporating the anomaly data localization network, manual localization operations for data restoration are replaced. The analysis in this paper is based on monitoring data from a large-span cable-stayed bridge, along with artificially generated anomaly data. The two neural network frameworks proposed in this paper are trained and validated, showcasing precise classification and localization of anomaly data. Furthermore, the paper discusses the impact of common errors in labeling data categories and locating training samples in practical operations. The results demonstrate that even in the presence of noticeable yet non-extreme labeling errors in the training set, the proposed method still achieves accurate classification and localization, highlighting its robustness.

The conventional approaches for detecting structural degradation are time-consuming, labor-intensive, and costly. The physical monitoring of the structure also poses risks to the health and safety of supervisors. Therefore, damage estimation of any structure using artificial intelligence (AI), more specifically deep learning (DL), is becoming more significant in civil infrastructure. In the presented research article, an efficient two-stage damage detection method is proposed for structural damage detection (SDD) from time domain vibration signals. The proposed method utilizes two-dimensional convolutional neural network (2D-CNN) architecture as a DL algorithm for damage detection. Here, a computer-aided damage detection method for steel beam and frame-type structures is developed using 2D-CNN algorithm in the Google Colab platform. The effectiveness of the proposed method is first verified, and it provides more than 90% accuracy for identifying the damage location and severity of a cantilever beam for single- and multi-damage scenarios from numerically simulated noisy displacement data. The algorithm is also experimentally validated through the raw acceleration data of damaged steel frame joints collected from the Qatar University Grandstand simulator (QUGS). The proposed 2D-CNN algorithm performs better than other DL algorithms by achieving 100% accuracy within 10 epochs for damage detection of steel frames using QUGS data. It demonstrates significant potential for detecting damage location and quantifying damages for single- and multi-damage scenarios using noise-free and noisy datasets. The primary contribution of this study resides in the implementation of two-stage damage detection algorithm utilizing 2D-CNN with time domain vibration response for multiclass damage identification and quantification.

Aiming at rapid and economical damage detection of a large number of simple supported bridges, a new structural damage identification method under moving load based on variational mode decomposition (VMD) and deep learning is proposed. Firstly, a moving vehicle is used as an exciting load to invoke structural damage feature and enhance the signal-to-noise ratio, and the structural vertical acceleration response is extracted by a finite element simulating analysis under various damage cases. In order to simulate the influence of noise and expand the samples, Gaussian white noise is added to the extracted data, and then the response signal is decomposed into a series of intrinsic mode functions (IMFs) using VMD, and the optimal IMF component is selected as the damage sample of the structure. Then, a one-dimensional convolutional neural network (CNN) model is built and trained by the various samples of damage. The vibration response of the practical bridge is processed and inputted by the trained CNN model to identify the location of the damage and degree of the structure. Finally, the effectiveness and anti-noise performance of the proposed method are verified through numerical analysis and a simply supported beam bridge model experiment. The results show that the average identification accuracy of the numerical simulations and experimental is 93.4% and 86.8% with 20% Gaussian white noise, respectively. Sensors at different locations have almost the same identification effect for various cases of damage, so it is possible to identify structural damage only using a small amount of accelerometer.

In the field of structural health monitoring, vibration-based damage identification remains a formidable challenge. Key to this challenge is the establishment of a reliable association between observed vibration characteristics and the actual state of structural damage (e.g. stiffness reduction). This association not only accurately indicates the presence of damage, but also the location and severity of the damage. To solve this complex pattern identification problem, a large number of approaches, including deep learning, have emerged in recent years. In this paper, we propose a new structural damage identification method that utilizes the vibration information of the structure and a convolutional neural network based on Alex NET improvement. The method consists of calculating the acceleration response power spectral density of damaged and undamaged structures under impact loading separately, and then making a difference between the two power spectral data, and subsequently introducing these power spectral difference data into the convolutional neural network for training. The use of power spectral density analysis as a preprocessing step converts the time-domain signals into frequency-domain signals, and this conversion allows the convolutional neural network to capture and learn from the specific frequency characteristics of the data, thus facilitating the learning process of the neural network model. In this paper, the effectiveness of the method is critically evaluated through numerical simulation and experimental validation, and 3% and 5% noise are added to the numerical study to test the robustness of the method. During the convolution neural network training process, the optimal training mean squared error (MSE) is $5\times 10^{-6}$ in the case of no noise addition; the optimal training MSE is $1.3\times 10^{-5}$ in the case of noise addition. Both the results of simulations and experiments confirm the high accuracy and good robustness of the method in localizing structural damage.

The leaves of plants often display signs of nutritional shortages. Therefore, to identify the nutrient shortages in plants, the color as well as the shape of the leaves can be wielded. Image classification is a quick and efficient methodology for this diagnosis task. In image classification, even though Deep Convolutional Neural Networks (DCNNs) are successful, little emphasis has been paid to their use in detecting plant nutrient deficits. Thus, to classify rice plant nutrient deficits, a DenseNet121 model is proposed in this paper. This proposed technique includes inserting additional new layers, early stopping criteria, model checkpoints, and five-fold cross-validation to enhance the model’s accuracy. After that, the model’s efficacy has been assessed utilizing specific performance metrics like accuracy, $F$1 score, precision, and recall. The performance of the suggested model is also analogized with the newer deep learning algorithms. From experimental results, the modified DenseNet121 attained 99.98% of accuracy, 99.99% of Precision, 99.98% of Recall, and 99.97% of $F$1-score. Lastly, to classify nutrient deficiencies in rice plants automatically on the web and mobile devices, an application was created for the farmers.

Aiming at the new coronavirus that appeared in 2019, which has caused a large number of infected patients worldwide due to its high contagiousness, in order to detect the source of infection in time and cut off the chain of transmission, we developed a new Chest X-ray (CXR) image classification algorithm with high accuracy, simple operation and fast processing for COVID-19. The algorithm is based on ConvNeXt pure convolutional neural network, we adjusted the network structure and loss function, added some new Data Augmentation methods and introduced attention mechanism. Compared with other classical convolutional neural network classification algorithms such as AlexNet, ResNet-34, ResNet-50, ResNet-101, ConvNeXt-tiny, ConvNeXt-small and ConvNeXt-base, the improved algorithm has better performance on COVID dataset.

Lung cancer is the leading cause of cancer-related death worldwide. Therefore, early diagnosis remains essential to allow access to appropriate curative treatment strategies. This paper presents a novel approach to assess the ability of Positron Emission Tomography/Computed Tomography (PET/CT) images for the classification of lung cancer in association with artificial intelligence techniques. We have built, in this work, a multi output Convolutional Neural Network (CNN) as a tool to assist the staging of patients with lung cancer. The TNM staging system as well as histologic subtypes classification were adopted as a reference. The VGG 16 network is applied to the PET/CT images to extract the most relevant features from images. The obtained features are then transmitted to a three-branch classifier to specify Nodal (N), Tumor (T) and histologic subtypes classification. Experimental results demonstrated that our CNN model achieves good results in TN staging and histology classification. The proposed architecture classified the tumor size with a high accuracy of 0.94 and the area under the curve (AUC) of 0.97 when tested on the Lung-PET-CT-Dx dataset. It also has yielded high performance for N staging with an accuracy of 0.98. Besides, our approach has achieved better accuracy than state-of-the-art methods in histologic classification.

As an important form of expression in modern civilization art, printmaking has a rich variety of types and a prominent sense of artistic hierarchy. Therefore, printmaking is highly favored around the world due to its unique artistic characteristics. Classifying print types through image feature elements will improve people’s understanding of print creation. Convolutional neural networks (CNNs) have good application effects in the field of image classification, so CNN is used for printmaking analysis. Considering that the classification effect of the traditional convolutional neural image classification model is easily affected by the activation function, the T-ReLU activation function is introduced. By utilizing adjustable parameters to enhance the soft saturation characteristics of the model and avoid gradient vanishing, a T-ReLU convolutional model is constructed. A better convolutional image classification model is proposed based on the T-ReLU convolutional model, taking into account the issue of subpar multi-level feature fusion in deep convolutional image classification models. Utilize normalization to analyze visual input, an eleven-layer convolutional network with residual units in the convolutional layer, and cascading thinking to fuse convolutional network defects. The performance test results showed that in the data test of different styles of artificial prints, the GT-ReLU model can obtain the best image classification accuracy, and the image classification accuracy rate is 0.978. The GT-ReLU model maintains a classification accuracy above 94.4% in the multi-dataset test classification performance test, which is higher than that of other image classification models. For the use of visual processing technology in the field of classifying prints, the research content provides good reference value.

Insect and rodents constantly cause trouble to the farmers leading to different kinds of diseases in the crop. Controlling as well as crop maintenance becomes a highly essential task for the farmers to ensure the health of the crop. However, they cause various social as well as environmental issues. Excessive pesticide usage may affect the contamination of soil and water, and also, it becomes highly toxic to plants. Hence, bugs and insects become more cautious against plants along with constant exposure, which pushes the farmer to utilize heavy pesticides. However, genetic seed manipulation is mainly used to provide high robustness against pest attacks, and they are highly expensive for practical execution. Implementation of the Internet-of-Things (IoT) in the agricultural domain has brought an enhanced improvement in on-field pest management. Several pest detections, as well as classification models, have been implemented in prior works, and they are based on effective techniques. The main purpose of this survey paper is to provide a literature review of IoT-aided pest detection and classification using different images. The datasets used in different pest detection and classification, the simulated platforms, and performance measures are analyzed. Further, the recent trends of machine learning and deep learning methods in this field are reviewed and categorized. Thus, the given survey impacts the economy for analyzing pest detection in the early stage, which provides better crop production, and also maximizes the protection of crops. Moreover, it helps to minimize human errors, and also it provides the best efforts to increase the automated monitoring system for large fields.

Due to its significant applications in security, the iris recognition process has been considered as the most active research area over the last few decades. In general, the iris recognition framework has been crucially utilized for various security applications because it includes a set of features as well as does not alter its character according to the time. In recent times, emerging deep learning techniques have attained huge success, particularly in the field of the iris recognition framework model. Moreover, in considering the field of iris recognition, there is no possibility for the remarkable capability of the deep learning model as well as to attain superior performance. To handle the issues in the conventional model of iris recognition, a novel heuristic-aided deep learning framework has been implemented for recognizing the iris system. Initially, the required source iris images are gathered from the data sources. It is then followed by the pre-processing stage, where the pre-processed image is obtained. Consequently, the image segmentation process is carried out by Adaptive Deeplabv3+layers, in which the parameters are optimized using the Modified Weighted Flow Direction Algorithm (MWFDA). Finally, the iris recognition is accomplished by hybrid Hybridization of Multiscale Dilated-Assisted Learning (MDAL) that will be composed of both a Convolutional Neural Network (CNN) and a Residual Network (ResNet). To achieve optimal recognition results, the parameters in CNN and ResNet are tuned optimally by using MWFDA. The experimental results are estimated with the help of distinct measures. Contrary to conventional methods, the empirical results prove that the recommended model achieves the desired value to enhance the recognition performance.

Stroke is a disease that is caused due to the blockage and burst in the blood vessels of the brain, thus resulting in abrupt brain dysfunction, like sensory or motor disorders, unconsciousness, limb paralysis, and pronunciation disorders. The existing stroke prediction algorithms have some limitations because of the lengthy testing procedures and hefty testing expenses. The main goal of this study is to develop and implement the proposed fusion-based, optimized deep learning model for stroke disease prediction using multimodalities. For that, this research considers the Computed Tomography (CT) and electroencephalogram (EEG) signals as input, and all of these inputs are processed separately to predict the stroke disease. While predicting the stroke disease with a CT image, the bilateral filter performs the pre-processing and the disease prediction is done with the DenseNet model, which is tuned by the proposed Jaya Fractional Reptile Search Algorithm (Jaya FRSA). Similar to how the proposed FRSA does CNN-LSTM training, the Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) predicts the stroke disease using the EEG data as an input after the Gaussian filter removes signal noise. Additionally, the CT image and the EEG signal are processed independently from the image and signal properties. Additionally, the CNN-LSTM model and DenseNet model results are combined using the overlap coefficient to get the final disease prediction. According to the experimental study, the suggested method achieved the maximum image accuracy, sensitivity, and specificity of 0.924, 0.930, and 0.935.

The pandemic disease Coronavirus 2019 (COVID-19) caused thousands of infections and deaths globally. It is important to introduce new medicines to address the critical situation in the medical system. The determination of approximate pIC value is necessary for designing medicines based on molecular compounds. Generally, the approximation of pIC value is a lengthy process, so it is difficult and time-consuming. Hence it is essential to introduce a new technique for automatic approximation. In this research, a Convolutional Neural Network-based transfer learning (CNN-TL) is designed for approximating the pIC value. Initially, Simplified Molecular Input Line Entry System (SMILES) notation is extracted from SMILES string symbols using an entropy-based one-hot encoding matrix and the molecular formula-based encoding. The molecular features are then extracted from the input data using Lorentzian similarity and Deep Residual Network (DRN). The pIC value approximation is performed using the CNN-TL model, where the Visual Geometry Group Network-16 (VGGNet-16) is used to fetch hyperparameters used to initialize the CNN. The experimental results proved that the designed CNN-TL technique achieved minimum error rates with normalized values of 0.406 for R², 0.516 for Root Mean Square Error (RMSE), 0.267 for Mean Square Error (MSE), and for 0.277 Mean Absolute Percentage Error (MAPE).

Public health initiatives must be made using evidence-based decision-making to have the greatest impact. Machine learning algorithms are created to gather, store, process, and analyze data to provide knowledge and guide decisions. A crucial part of any surveillance system is image analysis. The communities of computer vision and machine learning have become curious about it as of late. This study uses a variety of machine learning, and image processing approaches to detect and forecast malarial illness. In our research, we discovered the potential of deep learning techniques as innovative tools with a broader applicability for malaria detection, which benefits physicians by assisting in the diagnosis of the condition. We investigate the common confinements of deep learning for computer frameworks and organizing, including the requirement for data preparation, preparation overhead, real-time execution, and explaining ability, and uncover future inquiries about bearings focusing on these constraints.

In the new era of digital communications, cyberbullying is a significant concern for society. Cyberbullying can negatively impact stakeholders and can vary from psychological to pathological, such as self-isolation, depression and anxiety potentially leading to suicide. Hence, detecting any act of cyberbullying in an automated manner will be helpful for stakeholders to prevent any unfortunate results from the victim’s perspective. Data-driven approaches, such as machine learning (ML), particularly deep learning (DL), have shown promising results. However, the meta-analysis shows that ML approaches, particularly DL, have not been extensively studied for the Arabic text classification of cyberbullying. Therefore, in this study, we conduct a performance evaluation and comparison for various DL algorithms (LSTM, GRU, LSTM-ATT, CNN-BLSTM, CNN-LSTM and LSTM-TCN) on different datasets of Arabic cyberbullying to obtain more precise and dependable findings. As a result of the models’ evaluation, a hybrid DL model is proposed that combines the best characteristics of the baseline models CNN, BLSTM and GRU for identifying cyberbullying. The proposed hybrid model improves the accuracy of all the studied datasets and can be integrated into different social media sites to automatically detect cyberbullying from Arabic social datasets. It has the potential to significantly reduce cyberbullying. The application of DL to cyberbullying detection problems within Arabic text classification can be considered a novel approach due to the complexity of the problem and the tedious process involved, besides the scarcity of relevant research studies.

Diabetic retinopathy is a leading cause of blindness among diabetic patients, and early detection is crucial. This research proposes DiabNet, a novel convolutional neural network (CNN) architecture designed to enhance the accuracy, efficiency, and robustness of diabetic retinopathy detection from retinal images. DiabNet incorporates unique features like skip connections, attention mechanisms, and batch normalisation to improve feature extraction. The paper details DiabNet’s architecture, feature extraction, and training process. Evaluation on a standard dataset shows that DiabNet surpasses existing methods in accuracy, efficiency, and robustness. The research also explores the interpretability of DiabNet and suggests future research directions. The potential impact of DiabNet includes improved early detection and management of diabetic retinopathy. In addition, DiabNet’s deployment as a mobile app enables convenient and accessible diabetic retinopathy screening. Finally, it is noted that DiabNet, as a mobile app, has the potential to significantly impact the field of diabetic retinopathy detection, leading to improved early detection of diabetic retinopathy. The experimental validation proves that the proposed DiabNet architecture is feasible for real-time deployment yielding an accuracy of 98.72%.

With the rapid development of the railway industry, railway safety has received increasing attention. However, traditional methods for signal detection are limited by high cost and energy requirements. Data-driven methods are becoming increasingly popular for railway signal detection. In this paper, we propose a wavelet-based network model for railway track stiffness signal detection by combining deep neural networks and wavelet transform. In the training phase, we propose a wavelet-based convolutional neural network. We use wavelet coefficients to enhance the input features to improve the convolutional neural network. In the detection phase, we combine the sliding window algorithm and the voting algorithm to detect anomalous signals. Extensive experiments on general metrics demonstrate the effectiveness of our proposed model. The classification performance still outperforms the general network by 30–50% in terms of accuracy, precision and F1 score, which is a huge improvement. In addition, we test the model classification performance under different wavelet functions to validate the superiority of neural networks using wavelets.

Classroom teaching evaluation is one of the important contents of the new round of basic education curriculum reform in China. The new curriculum reform puts forward new requirements for the construction of the teaching evaluation system: promoting the all-round development of students, promoting the continuous improvement of teachers’ level, and promoting the curriculum of continuous development. However, from the current situation of the implementation of the new curriculum, the original teaching evaluation system is far from the requirements of the new curriculum reform, and does not have much practical value, and cannot provide strong support for the new curriculum reform. If it is not reformed, it will inevitably have a negative impact on the overall promotion of curriculum reform. How to improve classroom teaching evaluation under the background of the new curriculum reform, and how to establish a teaching evaluation scale and system suitable for the new curriculum reform, so as to play the role of evaluation in guiding, motivating and promoting, is an urgent problem to be solved at present. By referring to the relevant literature, the concepts of evaluation, teaching evaluation and classroom teaching evaluation are defined and discussed, and the object of classroom teaching evaluation is clarified.

The popularity of Unmanned Aerial Vehicles (UAVs), aka drones, has increased rapidly in recent years. UAVs are becoming easily accessible to more users. Malicious intentions can erode public safety when least expected. Current methods used for UAV detection systems include computer vision, radar, radio frequency and audio approaches. We choose the audio method for its high accuracy, low computational requirement and low cost. However, the lack of publicly available datasets is one of the main bottlenecks for developing an audio-based UAV detection and classification system. To fill this gap, we select 15 different UAVs, ranging from toy hand drones to Class I drones and record a total of 8120 s length of audio data generated from the flying UAVs. To the best of our knowledge, the proposed dataset is the largest audio dataset for UAVs so far. We further implement a Convolutional Neural Network (CNN) model for 15-class UAV classification and trained the model with the collected data. The average test accuracy of the trained model is 98.7% and the test loss is 0.076.

Cancer of the breast is a deadly disease that can take a person’s life in many different ways. Predicting breast cancer at an early stage is crucial in the fight to end the disease. The usage of deep learning and blockchain technology has been implemented with the intention of integrating optimal prediction with clinical diagnostics and protecting private health information. Patients’ medical records are encrypted and stored in the blockchain for maximum safety. As a result, a large portion of time and energy is spent on feature engineering, a tedious process that requires prior expert domain knowledge of the data to develop effective features, and is crucial to the success of most conventional classification systems. Deep learning, on the other hand, can arrange the discriminative information in the data without the need for a domain expert to develop feature extractors. The research community and industry have paid attention to deep, feedforward networks like convolutional neural networks (CNNs) because of their empirical results in areas including speech recognition, signal processing, object recognition, natural language processing, and transfer learning. For the best breast cancer prediction, a new method called a “Hybrid CNN” combining the Sine Cosine Algorithm (SCA) with a transfer learning algorithm has been presented. Mini-batch size and drop-out rate are just two of the factors that the SCA algorithm may fine-tune. To stop the model from overfitting, we employ a transfer learning strategy. The hyperparameters found using sine cosine algorithm is used in Visual geometry Group (VGG 16) architecture. ImageNet is used to pretrain the network and last three convolutional layers are trained using transfer learning. The integration of sine cosine algorithm and transfer learning together increases the accuracy thereby preventing the model from overfitting. The experimentation is performed in Google Colab and the proposed Hybrid CNN is compared with existing methodologies such as K-NN, SVM. Also, the proposed Hybrid CNN is compared with CNN without transfer learning and CNN without SCA. The metrics taken into account for comparison are accuracy, sensitivity, specificity, F-score. The proposed Hybrid CNN achieves 96.9% accuracy that shows the effectiveness of the integration of SCA and transfer learning.