Search

A significant majority of the population in India makes their living through agriculture. Different illnesses that develop due to changing weather patterns and are caused by pathogenic organisms impact the yields of diverse plant species. The present article analyzed some of the existing techniques in terms of data sources, pre-processing techniques, feature extraction techniques, data augmentation techniques, models utilized for detecting and classifying diseases that affect the plant, how the quality of images was enhanced, how overfitting of the model was reduced, and accuracy. The research papers for this study were selected using various keywords from peer-reviewed publications from various databases published between 2010 and 2022. A total of 182 papers were identified and reviewed for their direct relevance to plant disease detection and classification, of which 75 papers were selected for this review after exclusion based on the title, abstract, conclusion, and full text. Researchers will find this work to be a useful resource in recognizing the potential of various existing techniques through data-driven approaches while identifying plant diseases by enhancing system performance and accuracy. [ABSTRACT FROM AUTHOR]

Automatic extraction of building contours from high-resolution images is of great significance in the fields of urban planning, demographics, and disaster assessment. Network models based on convolutional neural network (CNN) and transformer technology have been widely used for semantic segmentation of buildings from high resolution remote sensing images (HRSI). However, the fixed geometric structure and the local receptive field of the convolutional kernel are not good at global feature extraction, and the transformer technique with self-attention mechanism introduces computational redundancies and extracts local feature details poorly in the process of modeling the global contextual information. In this paper, a dual-branch fused reconstructive transformer network, DFRTNet, is proposed for efficient and accurate building extraction. In the encoder, the traditional transformer is reconfigured by designing the local and global feature extraction module (LGFE); the branch of global feature extraction (GFE) performs dynamic range attention (DRA) based on the idea of top-k attention for extracting global features; furthermore, the branch of local feature extraction (LFE) is used to obtain fine-grained features. The multilayer perceptron (MLP) is employed to efficiently fuse the local and global features. In the decoder, a simple channel attention module (CAM) is used in the up-sampling part to enhance channel dimension features. Our network achieved the best segmentation accuracy on both the WHU and Massachusetts building datasets when compared to other mainstream and state-of-the-art methods. [ABSTRACT FROM AUTHOR]

With the growing diversity of cyberattacks in recent years, anomaly-based intrusion detection systems that can detect unknown attacks have attracted significant attention. Furthermore, a wide range of studies on anomaly detection using machine learning and deep learning methods have been conducted. However, many machine learning and deep learning-based methods require significant effort to design the detection feature values, extract the feature values from network packets, and acquire the labeled data used for model training. To solve the aforementioned problems, this paper proposes a new model called DOC-IDS, which is an intrusion detection system based on Perera's deep one-class classification. The DOC-IDS, which comprises a pair of one-dimensional convolutional neural networks and an autoencoder, uses three different loss functions for training. Although, in general, only regular traffic from the computer network subject to detection is used for anomaly detection training, the DOC-IDS also uses multi-class labeled traffic from open datasets for feature extraction. Therefore, by streamlining the classification task on multi-class labeled traffic, we can obtain a feature representation with highly enhanced data discrimination abilities. Simultaneously, we perform variance minimization in the feature space, even on regular traffic, to further improve the model's ability to discriminate between normal and abnormal traffic. The DOC-IDS is a single deep learning model that can automatically perform feature extraction and anomaly detection. This paper also reports experiments for evaluating the anomaly detection performance of the DOC-IDS. The results suggest that the DOC-IDS offers higher anomaly detection performance while reducing the load resulting from the design and extraction of feature values. [ABSTRACT FROM AUTHOR]

This paper proposes a data valuation algorithm for inertial measurement unit-based human activity recognition (IMU-based HAR) data based on meta reinforcement learning. Unlike previous studies that received feature-level input, the algorithm in this study added a feature extraction structure to the data valuation algorithm, and it can receive raw-level inputs and achieve excellent performance. As IMU-based HAR data are multivariate time-series data, the proposed algorithm incorporates an architecture capable of extracting both local and global features by inserting a transformer encoder after the one-dimensional convolutional neural network (1D-CNN) backbone in the data value estimator. In addition, the 1D-CNN-based stacking ensemble structure, which exhibits excellent efficiency and performance on IMU-based HAR data, is used as a predictor to supervise model training. The Berg balance scale (BBS) IMU-based HAR dataset and the public datasets, UCI-HAR, WISDM, and PAMAP2, are used for performance evaluation in this study. The valuation performance of the proposed algorithm is observed to be excellent on IMU-based HAR data. The rate of discovering corrupted data is higher than 96% on all datasets. In addition, classification performance is confirmed to be improved by the suppression of discovery of low-value data. [ABSTRACT FROM AUTHOR]

The polysomnogram (PSG) is the gold standard for evaluating sleep quality and disorders. Attempts to automate this process have been hampered by the complexity of the PSG signals and heterogeneity among subjects and recording hardwares. Most of the existing methods for automatic sleep stage scoring rely on hand-engineered features that require prior knowledge of sleep analysis. This paper presents an end-to-end deep transfer learning framework for automatic feature extraction and sleep stage scoring based on a single-channel EEG. The proposed framework was evaluated over the three primary signals recommended by the American Academy of Sleep Medicine (C4-M1, F4-M1, O2-M1) from two data sets that have different properties and are recorded with different hardware. Different Time–Frequency (TF) imaging approaches were evaluated to generate TF representations for the 30 s EEG sleep epochs, eliminating the need for complex EEG signal pre-processing or manual feature extraction. Several training and detection scenarios were investigated using transfer learning of convolutional neural networks (CNN) and combined with recurrent neural networks. Generating TF images from continuous wavelet transform along with a deep transfer architecture composed of a pre-trained GoogLeNet CNN followed by a bidirectional long short-term memory (BiLSTM) network showed the best scoring performance among all tested scenarios. Using 20-fold cross-validation applied on the C4-M1 channel, the proposed framework achieved an average per-class accuracy of 91.2%, sensitivity of 77%, specificity of 94.1%, and precision of 75.9%. Our results demonstrate that without changing the model architecture and the training algorithm, our model could be applied to different single-channel EEGs from different data sets. Most importantly, the proposed system receives a single EEG epoch as an input at a time and produces a single corresponding output label, making it suitable for real time monitoring outside sleep labs as well as to help sleep lab specialists arrive at a more accurate diagnoses. [ABSTRACT FROM AUTHOR]

This paper is concerned with individual identification by late fusion of two-stream deep networks from Electromyogram (EMG) signals. EMG signal has more advantages on security compared to other biosignals exposed visually, such as the face, iris, and fingerprints, when used for biometrics, at least in the aspect of visual exposure, because it is measured through contact without any visual exposure. Thus, we propose an ensemble deep learning model by late information fusion of convolutional neural networks (CNN) and long short-term memory (LSTM) from EMG signals for robust and discriminative biometrics. For this purpose, in the ensemble model's first stream, one-dimensional EMG signals were converted into time–frequency representation to train a two-dimensional convolutional neural network (EmgCNN). In the second stream, statistical features were extracted from one-dimensional EMG signals to train a long short-term memory (EmgLSTM) that uses sequence input. Here, the EMG signals were divided into fixed lengths, and feature values were calculated for each interval. A late information fusion is performed by the output scores of two deep learning models to obtain a final classification result. To confirm the superiority of the proposed method, we use an EMG database constructed at Chosun University and a public EMG database. The experimental results revealed that the proposed method showed performance improvement by 10.76% on average compared to a single stream and the previous methods. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel methodology based on machine learning for identifying the most appropriate from a set of available state-of-the-art object detectors for a given application. Our particular interest is to develop a road map for identifying verifiably optimal selections, especially for challenging applications such as detecting small objects in a mixed-size object dataset. State-of-the-art object detection systems often find the localisation of small-size objects challenging since most are usually trained on large-size objects. These contain abundant information as they occupy a large number of pixels relative to the total image size. This fact is normally exploited by the model during training and inference processes. To dissect and understand this process, our approach systematically examines detectors' performances using two very distinct deep convolutional networks. The first is the single-stage YOLO V3 and the second is the double-stage Faster R-CNN. Specifically, our proposed method explores and visually illustrates the impact of feature extraction layers, number of anchor boxes, data augmentation, etc., utilising ideas from the field of explainable Artificial Intelligence (XAI). Our results, for example, show that multi-head YOLO V3 detectors trained using augmented data produce better performance even with a fewer number of anchor boxes. Moreover, robustness regarding the detector's ability to explain how a specific decision was reached is investigated using different explanation techniques. Finally, two new visualisation techniques are proposed, WS-Grad and Concat-Grad, for identifying explanation cues of different detectors. These are applied to specific object detection tasks to illustrate their reliability and transparency with respect to the decision process. It is shown that the proposed techniques can result in high resolution and comprehensive heatmaps of the image areas, significantly affecting detector decisions as compared to the state-of-the-art techniques tested. [ABSTRACT FROM AUTHOR]

To ensure the safe operation of highway traffic lines, given the imperfect feature extraction of existing road pit defect detection models and the practicability of detection equipment, this paper proposes a lightweight target detection algorithm with enhanced feature extraction based on the YOLO (You Only Look Once) algorithm. The BIFPN (Bidirectional Feature Pyramid Network) network structure is used for multi-scale feature fusion to enhance the feature extraction ability, and Varifocal Loss is used to optimize the sample imbalance problem, which improves the accuracy of road defect target detection. In the evaluation test of the model in the constructed PCD1 (Pavement Check Dataset) dataset, the mAP@.5 (mean Average Precision when IoU = 0.5) of the BV-YOLOv5S (BiFPN Varifocal Loss-YOLOv5S) model increased by 4.1%, 3%, and 0.9%, respectively, compared with the YOLOv3-tiny, YOLOv5S, and B-YOLOv5S (BiFPN-YOLOv5S; BV-YOLOv5S does not use the Improved Focal Loss function) models. Through the analysis and comparison of experimental results, it is proved that the proposed BV-YOLOv5S network model performs better and is more reliable in the detection of pavement defects and can meet the needs of road safety detection projects with high real-time and flexibility requirements. [ABSTRACT FROM AUTHOR]

In aerospace, marine, and other heavy industries, bearing fault diagnosis has been an essential part of improving machine life, reducing economic losses, and avoiding safety problems caused by machine bearing failures. Most existing bearing fault diagnosis methods face challenges in extracting the fault features from raw bearing fault data. Compared with traditional methods for bearing fault characteristics extraction, deep neural networks can automatically extract intrinsic features without expert knowledge. The convolutional neural network (CNN) was utilized most widely in extracting representative features of bearing faults. Fundamental to this, the hybrid models based on the CNN and individual classifiers were proposed to diagnose bearing faults. However, CNN may not be suitable for all bearing fault classifiers. It is crucial to identify the classifiers which can maximize the CNN feature extraction ability. In this paper, four hybrid models based on CNN were built, and their fault detection accuracy and efficiency were compared. The comparative analysis showed that the random forest (RF) and support vector machine (SVM) could make full use of the CNN feature extraction ability. [ABSTRACT FROM AUTHOR]

In this paper, we propose a symmetric series convolutional neural network (SS-CNN), which is a novel deep convolutional neural network (DCNN)-based super-resolution (SR) technique for ultrasound medical imaging. The proposed model comprises two parts: a feature extraction network (FEN) and an up-sampling layer. In the FEN, the low-resolution (LR) counterpart of the ultrasound image passes through a symmetric series of two different DCNNs. The low-level feature maps obtained from the subsequent layers of both DCNNs are concatenated in a feed forward manner, aiding in robust feature extraction to ensure high reconstruction quality. Subsequently, the final concatenated features serve as an input map to the latter 2D convolutional layers, where the textural information of the input image is connected via skip connections. The second part of the proposed model is a sub-pixel convolutional (SPC) layer, which up-samples the output of the FEN by multiplying it with a multi-dimensional kernel followed by a periodic shuffling operation to reconstruct a high-quality SR ultrasound image. We validate the performance of the SS-CNN with publicly available ultrasound image datasets. Experimental results show that the proposed model achieves a high-quality reconstruction of the ultrasound image over the conventional methods in terms of peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), while providing compelling SR reconstruction time. [ABSTRACT FROM AUTHOR]

Currently, face-swapping deepfake techniques are widely spread, generating a significant number of highly realistic fake videos that threaten the privacy of people and countries. Due to their devastating impacts on the world, distinguishing between real and deepfake videos has become a fundamental issue. This paper presents a new deepfake detection method: you only look once–convolutional neural network–extreme gradient boosting (YOLO-CNN-XGBoost). The YOLO face detector is employed to extract the face area from video frames, while the InceptionResNetV2 CNN is utilized to extract features from these faces. These features are fed into the XGBoost that works as a recognizer on the top level of the CNN network. The proposed method achieves 90.62% of an area under the receiver operating characteristic curve (AUC), 90.73% accuracy, 93.53% specificity, 85.39% sensitivity, 85.39% recall, 87.36% precision, and 86.36% F1-measure on the CelebDF-FaceForencics++ (c23) merged dataset. The experimental study confirms the superiority of the presented method as compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In the field of surface defect detection, the scale difference of product surface defects is often huge. The existing defect detection methods based on Convolutional Neural Networks (CNNs) are more inclined to express macro and abstract features, and the ability to express local and small defects is insufficient, resulting in an imbalance of feature expression capabilities. In this paper, a Multi-Scale Feature Learning Network (MSF-Net) based on Dual Module Feature (DMF) extractor is proposed. DMF extractor is mainly composed of optimized Concatenated Rectified Linear Units (CReLUs) and optimized Inception feature extraction modules, which increases the diversity of feature receptive fields while reducing the amount of calculation; the feature maps of the middle layer with different sizes of receptive fields are merged to increase the richness of the receptive fields of the last layer of feature maps; the residual shortcut connections, batch normalization layer and average pooling layer are used to replace the fully connected layer to improve training efficiency, and make the multi-scale feature learning ability more balanced at the same time. Two representative multi-scale defect data sets are used for experiments, and the experimental results verify the advancement and effectiveness of the proposed MSF-Net in the detection of surface defects with multi-scale features. [ABSTRACT FROM AUTHOR]

Traditional pattern recognition approaches have gained a lot of popularity. However, these are largely dependent upon manual feature extraction, which makes the generalized model obscure. The sequences of accelerometer data recorded can be classified by specialized smartphones into well known movements that can be done with human activity recognition. With the high success and wide adaptation of deep learning approaches for the recognition of human activities, these techniques are widely used in wearable devices and smartphones to recognize the human activities. In this paper, convolutional layers are combined with long short-term memory (LSTM), along with the deep learning neural network for human activities recognition (HAR). The proposed model extracts the features in an automated way and categorizes them with some model attributes. In general, LSTM is alternative form of recurrent neural network (RNN) which is famous for temporal sequences' processing. In the proposed architecture, a dataset of UCI-HAR for Samsung Galaxy S2 is used for various human activities. The CNN classifier, which should be taken single, and LSTM models should be taken in series and take the feed data. For each input, the CNN model is applied, and each input image's output is transferred to the LSTM classifier as a time step. The number of filter maps for mapping of the various portions of image is the most important hyperparameter used. Transformation on the basis of observations takes place by using Gaussian standardization. CNN-LSTM, a proposed model, is an efficient and lightweight model that has shown high robustness and better activity detection capability than traditional algorithms by providing the accuracy of 97.89%. [ABSTRACT FROM AUTHOR]

Recognizing the sport of cricket on the basis of different batting shots can be a significant part of context-based advertisement to users watching cricket, generating sensor-based commentary systems and coaching assistants. Due to the similarity between different batting shots, manual feature extraction from video frames is tedious. This paper proposes a hybrid deep-neural-network architecture for classifying 10 different cricket batting shots from offline videos. We composed a novel dataset, CricShot10, comprising uneven lengths of batting shots and unpredictable illumination conditions. Impelled by the enormous success of deep-learning models, we utilized a convolutional neural network (CNN) for automatic feature extraction, and a gated recurrent unit (GRU) to deal with long temporal dependency. Initially, conventional CNN and dilated CNN-based architectures were developed. Following that, different transfer-learning models were investigated—namely, VGG16, InceptionV3, Xception, and DenseNet169—which freeze all the layers. Experiment results demonstrated that the VGG16–GRU model outperformed the other models by attaining 86% accuracy. We further explored VGG16 and two models were developed, one by freezing all but the final 4 VGG16 layers, and another by freezing all but the final 8 VGG16 layers. On our CricShot10 dataset, these two models were 93% accurate. These results verify the effectiveness of our proposed architecture compared with other methods in terms of accuracy. [ABSTRACT FROM AUTHOR]

As a critical part of a hydraulic transmission system, a hydraulic axial piston pump plays an indispensable role in many significant industrial fields. Owing to the practical undesirable working environment and hidden faults, it is challenging to precisely and effectively detect and diagnose the varying fault in the engineering. Deep learning-based technology presents special strengths in processing mechanical big data. It can simultaneously complete the feature extraction and classification, and achieve the automatic information learning. The popular convolutional neural network (CNN) is exploited for its potent ability of image processing. In this paper, a novel combined intelligent method is developed for fault diagnosis towards a hydraulic axial piston pump. First, the conversion of signals to images is conducted via continuous wavelet transform; the effective feature is preliminarily extracted from the transformed time-frequency images. Second, a novel deep CNN model is constructed to achieve the fault classification. To disclose the potential learning in the disparate layers of the CNN model, the visualization of reduced features is performed by employing t-distributed stochastic neighbor embedding. The effectiveness and stability of the proposed model are validated through the experiments. With the proposed method, different fault types can be precisely identified and high classification accuracy is achieved in a hydraulic axial piston pump. [ABSTRACT FROM AUTHOR]

Person re-identification (ReID) is gaining more attention due to its important applications in pedestrian tracking and security prevention. Recently developed part-based methods have proven beneficial for stronger and explicit feature descriptions, but how to find real significant parts and reduce miscorrelation between images to improve accuracy of ReID still leaves much room to improve. In this paper, we propose a dynamic part-attention (DPA) method based on masks, which aims to improve the use of variable attention parts. Particularly, a two-branch network with a dynamic loss function is designed to extract features of the global image and the parts of the body separately. With the comprehensive but targeting learning strategy, the proposed method can capture discriminative features based, but not depending on, masks, which guides the whole network to focus on body features more consciously and achieves more robust performance. Our method achieves rank-1 accuracy of 91.68% on public dataset Market1501, and experimental results on three public datasets indicate that the proposed method is effective and achieves favorable accuracy when compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep learning approaches have been recently applied to traffic prediction because of their ability to extract features of traffic data. While convolutional neural networks may improve the predictive accuracy by transiting traffic data to images and extracting features in the images, the convolutional results can be improved by using the global-level representation that is a direct way to extract features. The time intervals are not considered as aspects of convolutional neural networks for traffic prediction. The attention mechanism may adaptively select a sequence of regions and only process the selected regions to better extract features when aspects are considered. In this paper, we propose the attention mechanism over the convolutional result for traffic prediction. The proposed method is based on multiple links. The time interval is considered as the aspect of attention mechanism. Based on the dataset provided by Highways England, the experimental results show that the proposed method can achieve better accuracy than the baseline methods. [ABSTRACT FROM AUTHOR]

With the popularity of using deep learning-based models in various categorization problems and their proven robustness compared to conventional methods, a growing number of researchers have exploited such methods in environment sound classification tasks in recent years. However, the performances of existing models use auditory features like log-mel spectrogram (LM) and mel frequency cepstral coefficient (MFCC), or raw waveform to train deep neural networks for environment sound classification (ESC) are unsatisfactory. In this paper, we first propose two combined features to give a more comprehensive representation of environment sounds Then, a fourfour-layer convolutional neural network (CNN) is presented to improve the performance of ESC with the proposed aggregated features. Finally, the CNN trained with different features are fused using the Dempster–Shafer evidence theory to compose TSCNN-DS model. The experiment results indicate that our combined features with the four-layer CNN are appropriate for environment sound taxonomic problems and dramatically outperform other conventional methods. The proposed TSCNN-DS model achieves a classification accuracy of 97.2%, which is the highest taxonomic accuracy on UrbanSound8K datasets compared to existing models. [ABSTRACT FROM AUTHOR]