Popular Convolutional Neural Networks Research Articles

Comparative study: AutoDPR-SEM for enhancing CNN reliability in SRAM-based FPGAs through autonomous reconfiguration

Convolutional neural networks (CNNs) are widely adopted in safety-critical systems, including space applications and autonomous vehicles. Field-programmable gate arrays (FPGAs) based on SRAM are preferred for accelerating CNN computations due to their unique characteristics. However, the configuration memory of FPGAs is susceptible to single event effects (SEEs), which can corrupt computations and lead to misclassification of CNN outputs. In this study, we investigated the impact of SEEs on SRAM-based FPGAs with Two-Photon Absorption (TPA) laser fault injections through a comparative analysis of two popular CNN acceleration architectures: streaming architecture (SA) and single compute engine (SCE). Experimental results show that SA-based CNNs require more hardware resources but exhibit superior resilience against single event upsets (SEUs). Without any Radiation Hardened by Design (RHBD) protection, SCE has an error rate approximately twice as high as SA. To mitigate errors, the Xilinx IP core - Soft Error Mitigation (SEM) is used for error detection and correction, leading to error rate reductions of up to 50 % in both architectures. Importantly, we propose the AutoDPR-SEM (Autonomous Dynamic Partial Reconfiguration for Soft Error Mitigation) approach, which automatically reconfigures the SEM IP core when it remains idle due to uncorrectable errors. AutoDPR-SEM significantly improves CNN error rates, reducing errors by approximately 17.8 times in SCE and 14.8 times in SA. We also applied software level simulation to validate the TPA experiment, showing similar trends of the testing results across all models. In conclusion, the study confirms the feasibility of AutoDPR-SEM in both architectures, showcasing its potential to improve CNN error rates in safety-critical systems.

Colon Cancer Detection of Colonoscopy Images Using CNN

Abstract: Colon cancer requires an early and precise diagnosis in order to be effectively treated because it is a common and potentially fatal condition. This study proposes a reliable framework for colon cancer detection through image preprocessing and transfer learning approaches. The research compares the performance of three popular convolutional neural networks (CNNs) for this task: VGG-15, ResNet-50, and AlexNet.The image preprocessing phase entails a number of critical operations, including image conversion, resizing, and contrast enhancement using histogram equalization. In order to guarantee that the neural networks receive high-quality inputs, these preprocessing techniques strive to improve the quality and consistency of the colon cancer dataset. Pre-trained models extract and classify features from big datasets using transfer learning. The preprocessed colon cancer dataset is used to fine-tune the chosen CNN architectures VGG-15, ResNet-50, and AlexNet and adapt them for this particular medical imaging purpose.The results of this study show that transfer learning has the potential for colon cancer detection and provides helpful direction for researchers and practitioners looking for the best deep-learning architectures for early cancer diagnosis. This study adds to continuing efforts to improve the precision and effectiveness of colon cancer detection techniques, ultimately leading to better patient outcomes.

Bird Species Detection Using Deep Learning

Bird species classification plays a crucial role in various ecological and conservation endeavors. Leveraging deep learning techniques has shown promise in automating this task, offering the potential for efficient and accurate species identification. This paper presents a comprehensive study on the application of the YOLOv5 architecture, a state-of-the-art object detection framework, for bird species classification from images. We explore the effectiveness of YOLOv5 in comparison to traditional convolutional neural networks (CNNs) for bird species identification. Our study involves extensive experimentation with different configurations of YOLOv5, including variations in model size, training strategies, and dataset preprocessing techniques. We evaluate the performance of the YOLOv5-based classification framework on diverse datasets, ranging from publicly available bird image datasets to custom datasets collected through field observations. Additionally, we compare the classification accuracy of YOLOv5 with other popular CNN architectures, such as ResNet and EfficientNet, to assess its efficacy in bird species recognition tasks. Furthermore, we investigate the transferability of pre-trained YOLOv5 models to different bird species datasets and examine the robustness of the models to variations in image quality, background clutter, and occlusions.Our experimental results demonstrate that YOLOv5 offers competitive performance in bird species classification tasks, achieving high accuracy and efficiency. We discuss the strengths and limitations of using YOLOv5 for this application and provide insights into potential avenues for future research.

The Classification of VOCs Based on Sensor Images Using a Lightweight Neural Network for Lung Cancer Diagnosis.

The application of artificial intelligence to point-of-care testing (POCT) disease detection has become a hot research field, in which breath detection, which detects the patient's exhaled VOCs, combined with sensor arrays of convolutional neural network (CNN) algorithms as a new lung cancer detection is attracting more researchers' attention. However, the low accuracy, high-complexity computation and large number of parameters make the CNN algorithms difficult to transplant to the embedded system of POCT devices. A lightweight neural network (LTNet) in this work is proposed to deal with this problem, and meanwhile, achieve high-precision classification of acetone and ethanol gases, which are respiratory markers for lung cancer patients. Compared to currently popular lightweight CNN models, such as EfficientNet, LTNet has fewer parameters (32 K) and its training weight size is only 0.155 MB. LTNet achieved an overall classification accuracy of 99.06% and 99.14% in the own mixed gas dataset and the University of California (UCI) dataset, which are both higher than the scores of the six existing models, and it also offers the shortest training (844.38 s and 584.67 s) and inference times (23 s and 14 s) in the same validation sets. Compared to the existing CNN models, LTNet is more suitable for resource-limited POCT devices.

Pre-rotation Only at Inference-Stage: A Way to Rotation Invariance of Convolutional Neural Networks

The popular convolutional neural networks (CNN) require data augmentation to achieve rotation invariance. We propose an alternative mechanism, Pre-Rotation Only at Inference stage (PROAI), to make CNN rotation invariant. The overall idea is to learn how the human brain observe images. At the training stage, PROAI trains a CNN with a small number using images only at one orientation. At the inference stage, PROAI introduces a pre-rotation operation to rotate each test image into its all-possible orientations and calculate classification scores using the trained CNN with a small number of parameters. The maximum of these classification scores is able to simultaneously estimate both the category and the orientation of each test image. The specific benefits of PROAI have been experimented on rotated image recognition tasks. The results shows that PROAI improves both the classification and orientation estimation performance while greatly reduced the numbers of parameters and the training time. Codes and datasets are publicly available at https://github.com/automlresearch/FRPRF.

Facial soft-biometrics obfuscation through adversarial attacks

Sharing facial pictures through online services, especially on social networks, has become a common habit for thousands of users. This practice hides a possible threat to privacy: the owners of such services, as well as malicious users, could automatically extract information from faces using modern and effective neural networks. In this paper, we propose the harmless use of adversarial attacks, i.e. variations of images that are almost imperceptible to the human eye and that are typically generated with the malicious purpose to mislead Convolutional Neural Networks (CNNs). Such attacks have been instead adopted to (i) obfuscate soft biometrics (gender, age, ethnicity) but (ii) without degrading the quality of the face images posted online. We achieve the above mentioned two conflicting goals by modifying the implementations of four of the most popular adversarial attacks, namely FGSM, PGD, DeepFool and C&W, in order to constrain the average amount of noise they generate on the image and the maximum perturbation they add on the single pixel. We demonstrate, in an experimental framework including three popular CNNs, namely VGG16, SENet and MobileNetV3, that the considered obfuscation method, which requires at most four seconds for each image, is effective not only when we have a complete knowledge of the neural network that extracts the soft biometrics (white box attacks), but also when the adversarial attacks are generated in a more realistic black box scenario. Finally, we prove that an opponent can implement defense techniques to partially reduce the effect of the obfuscation, but substantially paying in terms of accuracy over clean images; this result, confirmed by the experiments carried out with three popular defense methods, namely adversarial training, denoising autoencoder and Kullback-Leibler autoencoder, shows that it is not convenient for the opponent to defend himself and that the proposed approach is robust to defenses.

A study on fruit classification using convolutional neural network for image recognition technology

Artificial intelligence is being incorporated into more aspects of our daily lives. Agricultural production in China is at a critical juncture due to the rising fruit production and dwindling labor force, necessitating the adoption of mechanization and intelligent systems. Image processing is particularly suitable for this field. Image classification technologies in fruit categorization are examined in this research. The results of this study can help improve the development of intelligent, lightweight machinery for agricultural output. This, in turn, will enhance the efficiency of fruit cultivation, harvesting, and trading and alleviate labor constraints. Two popular convolutional neural network models, namely ResNet50 and MobileNetV2, were employed in this study. The study utilized two optimizers: SGD and Adam. The evaluation results revealed that the ResNet50 model, employing SGD optimization, achieved the highest accuracy of 95.57%. Despite its lower accuracy of 92.19%, the MobileNetV2 model demonstrates higher efficiency than ResNet50 due to its lower hardware requirements, rendering it suitable for operation on compact devices.

Leveraging Deep Learning for Fine-Grained Categorization of Parkinson's Disease Progression Levels through Analysis of Vocal Acoustic Patterns.

Speech impairments often emerge as one of the primary indicators of Parkinson's disease (PD), albeit not readily apparent in its early stages. While previous studies focused predominantly on binary PD detection, this research explored the use of deep learning models to automatically classify sustained vowel recordings into healthy controls, mild PD, or severe PD based on motor symptom severity scores. Popular convolutional neural network (CNN) architectures, VGG and ResNet, as well as vision transformers, Swin, were fine-tuned on log mel spectrogram image representations of the segmented voice data. Furthermore, the research investigated the effects of audio segment lengths and specific vowel sounds on the performance of these models. The findings indicated that implementing longer segments yielded better performance. The models showed strong capability in distinguishing PD from healthy subjects, achieving over 95% precision. However, reliably discriminating between mild and severe PD cases remained challenging. The VGG16 achieved the best overall classification performance with 91.8% accuracy and the largest area under the ROC curve. Furthermore, focusing analysis on the vowel /u/ could further improve accuracy to 96%. Applying visualization techniques like Grad-CAM also highlighted how CNN models focused on localized spectrogram regions while transformers attended to more widespread patterns. Overall, this work showed the potential of deep learning for non-invasive screening and monitoring of PD progression from voice recordings, but larger multi-class labeled datasets are needed to further improve severity classification.

FDNet: Imperceptible backdoor attacks via frequency domain steganography and negative sampling

Backdoor attacks against Deep Neural Networks (DNNs) have surfaced as a substantial and concerning security challenge. These backdoor vulnerabilities in DNNs can be introduced by third-party sources through maliciously manipulated training data. Existing backdoor attacks are primarily built on perturbation trigger patterns in the spatial domain, which makes practical deployment arduous due to the ease of detection by inspectors. Moreover, shortcut learning renders the backdoor network less robust against defense methods. This work advances an effective and adaptable approach to backdoor attacks, situated in the frequency domain. This methodology involves the incorporation of specific natural perturbations within the frequency domain of images. Remarkably, these introduced triggers yield minimal alterations in the image’s semantic content, rendering them nearly imperceptible to human observers. To evade detection by machine-based defenders, we introduce a new training paradigm that incorporates negative sampling techniques. This approach compels the neural network to learn richer differences as trigger patterns. We evaluate our attacks on popular convolutional neural networks, visual transformers, and MLP-Mixer models as well as four standard datasets including MNIST, CIFAR-10, GTSRB, and ImageNet. Experimental results demonstrate that the trained networks can be successfully injected with backdoors. Our attack methods exhibit remarkable efficacy, achieving high attack success rates in both All-to-one (near 100% on all datasets) and All-to-all (over 90% except on ImageNet) scenarios and also demonstrate robustness against contemporary state-of-the-art defense mechanisms. Furthermore, our work reveals that DNNs can capture discrepancies in the frequency components of images that are barely perceptible to humans.

Automatic stack velocity picking using a semi‐supervised ensemble learning method

AbstractPicking stack velocity from seismic velocity spectra is a fundamental method in seismic stack velocity analysis. With the increase in the scale of seismic data acquisition, manual picking cannot achieve the required efficiency. Therefore, an automatic picking algorithm is urgently needed now. Despite some supervised deep learning–based picking approaches that have been proposed, they heavily rely on sufficient training samples and lack interpretability. In contrast, utilizing physical knowledge to develop semi‐data‐driven methods has the potential to efficiently solve this problem. Thus, we propose a semi‐supervised ensemble learning method to reduce the reliance on manually labelled data and improve interpretability by incorporating the interval velocity constraint. Semi‐supervised ensemble learning fuses the information of the estimated spectrum, nearby velocity spectra and few‐shot manual picking to recognize the velocity picking. Test results of both the synthetic and field datasets indicate that semi‐supervised ensemble learning achieves more reliable and precise picking than traditional clustering‐based techniques and the currently popular convolutional neural network method.

A CNN-based model to count the leaves of rosette plants (LC-Net)

Plant image analysis is a significant tool for plant phenotyping. Image analysis has been used to assess plant trails, forecast plant growth, and offer geographical information about images. The area segmentation and counting of the leaf is a major component of plant phenotyping, which can be used to measure the growth of the plant. Therefore, this paper developed a convolutional neural network-based leaf counting model called LC-Net. The original plant image and segmented leaf parts are fed as input because the segmented leaf part provides additional information to the proposed LC-Net. The well-known SegNet model has been utilised to obtain segmented leaf parts because it outperforms four other popular Convolutional Neural Network (CNN) models, namely DeepLab V3+, Fast FCN with Pyramid Scene Parsing (PSP), U-Net, and Refine Net. The proposed LC-Net is compared to the other recent CNN-based leaf counting models over the combined Computer Vision Problems in Plant Phenotyping (CVPPP) and KOMATSUNA datasets. The subjective and numerical evaluations of the experimental results demonstrate the superiority of the LC-Net to other tested models.

Enhanced symbiotic organism search optimization algorithm for plant disease classification

Since it satisfies all prerequisites for the growth of humanity, agriculture is currently regarded as being the most significant sector for civilization. One of the main forms of human energy production is thought to be plants, which also provide nutrients, cures, etc. Any damage or disease brought on by exposure to pathogens, viruses, bacteria, etc., while cultivating plants results in a decline in productivity, making it crucial to prevent such diseases and take the required precautions to avoid them. Accurately identifying such fatal diseases is a crucial first step for both the businesses and farmers. Six different Convolutional Neural Networks (CNNs) that accept plant leaf images as input, along with the Enhanced Symbiotic Organism Search (ESOS) optimization algorithm, have been implemented in our research. We intend to extensively contrast the various models based on accuracy, precision, recall, and F1-score. In the area of image recognition and classification, convolutional neural networks (CNNs), in particular, and deep learning, in general, are developing. The literature contains a variety of CNN designs. The dataset size, the number of classes, the model’s weights, hypermeters, and optimizers are a few examples of the variables that have an impact on a CNN model’s performance. Because of its benefits, transfer learning and fine-tuning a pre-trained model are now very popular. This study examines the impact of six popular CNN models: DenseNet, MobileNet, EfficientNet, VGG19, ResNet and Inception. As a result, DenseNet demonstrates an optimal accuracy rate of 98% when compared to other models.

Accurate and robust auto-segmentation of head and neck organ-at-risks based on a novel CNN fine-tuning workflow.

Obvious inconsistencies in auto-segmentations exist among various AI software. In this study, we have developed a novel convolutional neural network (CNN) fine-tuning workflow to achieve precise and robust localized segmentation. The datasets include Hubei Cancer Hospital dataset, Cetuximab Head and Neck Public Dataset, and Québec Public Dataset. Seven organs-at-risks (OARs), including brain stem, left parotid gland, esophagus, left optic nerve, optic chiasm, mandible, and pharyngeal constrictor, were selected. The auto-segmentation results from four commercial AI software were first compared with the manual delineations. Then a new multi-scale lightweight residual CNN model with an attention module (named as HN-Net) was trained and tested on 40 samples and 10 samples from Hubei Cancer Hospital, respectively. To enhance the network's accuracy and generalization ability, the fine-tuning workflow utilized an uncertainty estimation method for automatic selection of candidate samples of worthiness from Cetuximab Head and Neck Public Dataset for further training. The segmentation performances were evaluated on the Hubei Cancer Hospital dataset and/or the entire Québec Public Dataset. A maximum difference of 0.13 and 0.7mm in average Dice value and Hausdorff distance value for the seven OARs were observed by four AI software. The proposed HN-Net achieved an average Dice value of 0.14 higher than that of the AI software, and it also outperformed other popular CNN models (HN-Net: 0.79, U-Net: 0.78, U-Net++: 0.78, U-Net-Multi-scale: 0.77, AI software: 0.65). Additionally, the HN-Net fine-tuning workflow by using the local datasets and external public datasets further improved the automatic segmentation with the average Dice value by 0.02. The delineations of commercial AI software need to be carefully reviewed, and localized further training is necessary for clinical practice. The proposed fine-tuning workflow could be feasibly adopted to implement an accurate and robust auto-segmentation model by using local datasets and external public datasets.

Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images

Early detection of prostate cancer (PCa) and benign prostatic hyperplasia (BPH) is crucial for maintaining the health and well-being of aging male populations. This study aims to evaluate the performance of transfer learning with convolutional neural networks (CNNs) for efficient classification of PCa and BPH in transrectal ultrasound (TRUS) images. A retrospective experimental design was employed in this study, with 1380 TRUS images for PCa and 1530 for BPH. Seven state-of-the-art deep learning (DL) methods were employed as classifiers with transfer learning applied to popular CNN architectures. Performance indices, including sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), Kappa value, and Hindex (Youden’s index), were used to assess the feasibility and efficacy of the CNN methods. The CNN methods with transfer learning demonstrated a high classification performance for TRUS images, with all accuracy, specificity, sensitivity, PPV, NPV, Kappa, and Hindex values surpassing 0.9400. The optimal accuracy, sensitivity, and specificity reached 0.9987, 0.9980, and 0.9980, respectively, as evaluated using twofold cross-validation. The investigated CNN methods with transfer learning showcased their efficiency and ability for the classification of PCa and BPH in TRUS images. Notably, the EfficientNetV2 with transfer learning displayed a high degree of effectiveness in distinguishing between PCa and BPH, making it a promising tool for future diagnostic applications.

Thai culture image classification with transfer learning

Classifying images of Thai culture is important for a variety of applications, such as tourism, education, and cultural preservation. However, building a Machine learning model from scratch to classify Thai cultural images can be challenging due to the limited availability of annotated data. In this study, we investigate the use of transfer learning for the task of image classification on a dataset of Thai cultural images. We utilize three popular convolutional neural network models, namely MobileNet, EfficientNet, and residual network (ResNet) as baseline pre-trained models. Their performances were evaluated when they were trained from random initialization, used as a feature extractor, and fully fine-tuned. The results showed that all three models performed better in terms of accuracy and training time when they were used as a feature extractor, with EfficientNet achieving the highest accuracy of 95.87% while maintaining the training time of 24 ms/iteration. To better understand the reasoning behind the predictions made by the models, we deployed the gradient-weighted class activation mapping (Grad-CAM) visualization technique to generate heatmaps that the models attend to when making predictions. Both our quantitative and qualitative experiments demonstrated that transfer learning is an effective approach to image classification on Thai cultural images.

Attention driven CWT-deep learning approach for discrimination of Radar PRI modulation

With the proliferation of radio frequency (RF) systems and radar applications, Electronic Warfare (EW) is receiving increasing importance. The analysis of the radar signals is a critical EW task that decides the nature of counter employments. In an Electronic Support (ES) system, the challenge is to detect hostile radiation sources efficiently and trigger a counter response. Detection of types of Pulse Repetition Interval (PRI) modulation of radar signal significantly facilitates the manifestation of RF emitters during recognition which is difficult in a dense EW environment. Recent developments in artificial intelligence (AI) methods suggest that this emerging technology can be effective for such purposes. In this direction, an automatic approach for recognizing several kinds of complex PRI modulation based on Continuous Wavelet Transform (CWT) and a combination of the vanilla Convolutional Neural Network (CNN), a multi-head self-attention (MHSA) mechanism and the popular Long Short-Term Memory (LSTM) is proposed. The CWT is used to decompose the PRI modulation sequence and obtain different time–frequency components. Further, aided by the proposed CNN-MHSA-LSTM combination, the features extracted from the CWT 2D-scalograms are used to execute PRI modulation discrimination. In this method, the vanilla CNN is employed for the extraction of deep features to figure out the class details while capturing the spatial attributes. Thereafter, to improve the discriminative power of the entire framework a MHSA mechanism is used. The temporal attributes are acquired by the LSTM which works in concert with the CNN for executing the detection of the PRI classes based on the extracted features. Also to assess the effectiveness of the proposed method, three models based on ResNet, popular CNN and SqueezeNet are implemented for benchmark comparison in terms of overall performance and complexity. The simulation results show that the proposed method enhances performance and achieves robustness in the noise-filled and imperfect channel knowledge environment. The best recognition accuracy is 98.3% with 50% spurious pulses in the environment which fluctuates with imperfect channel knowledge cases.

FPGA-Based CNN for Eye Detection in an Iris Recognition at a Distance System

Neural networks are the state-of-the-art solution to image-processing tasks. Some of these neural networks are relatively simple, but the popular convolutional neural networks (CNNs) can consist of hundreds of layers. Unfortunately, the excellent recognition accuracy of CNNs comes at the cost of very high computational complexity, and one of the current challenges is managing the power, delay and physical size limitations of hardware solutions dedicated to accelerating their inference process. In this paper, we describe the embedding of an eye detection system on a Zynq XCZU4EV UltraScale+ multiprocessor system-on-chip (MPSoC). This eye detector is used in the application framework of a remote iris recognition system, which requires high resolution images captured at high speed as input. Given the high rate of eye regions detected per second, it is also important that the detector only provides as output images eyes that are in focus, discarding all those seriously affected by defocus blur. In this proposal, the network will be trained only with correctly focused eye images to assess whether it can differentiate this pattern from that associated with the out-of-focus eye image. Exploiting the neural network’s advantage of being able to work with multi-channel input, the inputs to the CNN will be the grey level image and a high-pass filtered version, typically used to determine whether the iris is in focus or not. The complete system synthetises other cores and implements CNN using the so-called Deep Learning Processor Unit (DPU), the intellectual property (IP) block released by AMD/Xilinx. Compared to previous hardware designs for implementing FPGA-based CNNs, the DPU IP supports extensive deep learning core functions, and developers can leverage DPUs to conveniently accelerate CNN inference. Experimental validation has been successfully addressed in a real-world scenario working with walking subjects, demonstrating that it is possible to detect only eye images that are in focus. This prototype module includes a CMOS digital image sensor that provides 16 Mpixel images, and outputs a stream of detected eyes as 640 × 480 images. The module correctly discards up to 95% of the eyes present in the input images as not being correctly focused.

Reduced-complexity Convolutional Neural Network in the compressed domain

Deep neural networks have achieved outstanding performance in computer vision tasks. Convolutional Neural Networks (CNNs) typically operate in the spatial domain with raw images, but in practice, images are usually stored and transmitted in their compressed representation where JPEG is one of the most widely used encoder. Also, these networks are computationally intensive and slow. This paper proposes performing the learning and inference processes in the compressed domain in order to reduce the computational complexity and improve the speed of popular CNNs. For this purpose, a novel graph-based frequency channel selection method is proposed to identify and select the most important frequency channels. The computational complexity is reduced by retaining the important frequency components and discarding the insignificant ones as well as eliminating the unnecessary layers of the network. Experimental results show that the modified ResNet-50 operating in the compressed domain is up to 70% faster than the spatial-based traditional ResNet-50 while resulting in similar classification accuracy. Moreover, this paper proposes a preprocessing step with partial encoding to improve the resilience to distortions caused by low-quality encoded images. Finally, we show that training a network with highly compressed data can achieve a good classification accuracy with up to 93% reduction in the storage requirements of the training data.

An attentional residual feature fusion mechanism for sheep face recognition

In the era of globalization and digitization of livestock markets, sheep are considered an essential source of food production worldwide. However, sheep behavior monitoring, disease prevention, and precise management pose urgent challenges in the development of smart ranches. To address these problems, individual identification of sheep has become an increasingly viable solution. Despite the benefits of traditional sheep individual identification methods, such as accurate tracking and record-keeping, they are labor-intensive and inefficient. Popular convolutional neural networks (CNNs) are unable to extract features for specific problems, further complicating the issue. To overcome these limitations, an Attention Residual Module (ARM) is proposed to aggregate the feature mapping between different layers of the CNN. This approach enables the general model of the CNN to be more adaptable to task-specific feature extraction. Additionally, a targeted sheep face recognition dataset containing 4490 images of 38 individual sheep has been constructed. Furthermore, the experimental data was expanded using image enhancement techniques such as rotation and panning. The results of the experiments indicate that the accuracy of the VGG16, GoogLeNet, and ResNet50 networks with the ARM improved by 10.2%, 6.65%, and 4.38%, respectively, compared to these recognition networks without the ARM. Therefore, the proposed method for specific sheep face recognition tasks has been proven effective.

A Deep Learning Framework for Intelligent Fault Diagnosis Using AutoML-CNN and Image-like Data Fusion

Intelligent fault diagnosis (IFD) is essential for preventative maintenance (PM) in Industry 4.0. Data-driven approaches have been widely accepted for IFD in smart manufacturing, and various deep learning (DL) models have been developed for different datasets and scenarios. However, an automatic and unified DL framework for developing IFD applications is still required. Hence, this work proposes an efficient framework integrating popular convolutional neural networks (CNNs) for IFD based on time-series data by leveraging automated machine learning (AutoML) and image-like data fusion. After normalisation, uniaxial or triaxial signals are reconstructed into -channel pseudo-images to satisfy the input requirements for CNNs and achieve data-level fusion simultaneously. Then, the model training, hyperparameter optimisation, and evaluation can be taken automatically based on AutoML. Finally, the selected model can be deployed on a cloud server or an edge device (via tiny machine learning). The proposed framework and method were validated via two case studies, demonstrating the framework’s availability for the automatic development of IFD applications and the effectiveness of the proposed data-level fusion method.