Automatic recognition system of pointer meters based on lightweight CNN and WSNs with on-sensor image processing

Even though smart instruments are popular in modern industrial processes, pointer meters without computer interfaces are still widely employed in many application areas. Automatic reading recognition of pointer meters based on computer vision provides a promising solution to input the meter readings to the existing monitoring system or IoT. However, most of the current reading recognition approaches for pointer meters are based on inconvenient wired systems or expensive inspection robots. Compared with a wired system, wireless sensor networks (WSNs) are low-cost, easy to install and relocate. To leverage these advantages of WSNs and address the limitation of its radio bandwidth, this paper proposes a novel automated meter reading system for pointer meter using WSNs with on-sensor image processing, in which meter image capturing, image preprocessing, and reading recognition are completed on WSNs end node, and then only the recognition result is transmitted through WSNs. The feasibility of the proposed method is evaluated by a set of experiments on the prototype. Experimental results indicate that the presented approach can recognize the meter reading with an error of 0.3% and significantly reduce the payload transmission data in the WSNs.

In order to combine the indicated value of pointer meters into the existing monitoring system or IoT directly, this paper proposed a wireless sensor network (WSN) for pointer meter recognition using image processing technology. The feasibility and effectiveness of the proposed WSN have been verified by a set of experiments on a pressure meter. Experimental results show that the presented WSN can recognize the meter indicated value with a fiducial error of around 0.5%. Compared with raw image data transmission, the proposed approach only needs to transmit the final recognition result, which can significantly reduce the payload transmission data in the WSN.

The key to preventing the COVID-19 is to diagnose patients quickly and accurately. Studies have shown that using Convolutional Neural Networks (CNN) to analyze chest Computed Tomography (CT) images is helpful for timely COVID-19 diagnosis. However, personal privacy issues, public chest CT data sets are relatively few, which has limited CNN's application to COVID-19 diagnosis. Also, many CNNs have complex structures and massive parameters. Even if equipped with the dedicated Graphics Processing Unit (GPU) for acceleration, it still takes a long time, which is not conductive to widespread application. To solve above problems, this paper proposes a lightweight CNN classification model based on transfer learning. Use the lightweight CNN MobileNetV2 as the backbone of the model to solve the shortage of hardware resources and computing power. In order to alleviate the problem of model overfitting caused by insufficient data set, transfer learning is used to train the model. The study first exploits the weight parameters trained on the ImageNet database to initialize the MobileNetV2 network, and then retrain the model based on the CT image data set provided by Kaggle. Experimental results on a computer equipped only with the Central Processing Unit (CPU) show that it consumes only 1.06 s on average to diagnose a chest CT image. Compared to other lightweight models, the proposed model has a higher classification accuracy and reliability while having a lightweight architecture and few parameters, which can be easily applied to computers without GPU acceleration. Code:github.com/ZhouJie-520/paper-codes.

Unmanned aerial vehicles (UAVs) are invaluable technologies concerning their remote control and monitoring capabilities. Convolutional neural networks (CNNs), known for their high pattern recognition capabilities, are appropriate for forest fire detection with UAVs. Deep convolutional neural networks show substantial performance on hardware with high processing capabilities. While these networks can be operated in unmanned aerial vehicles controlled from ground control stations equipped with GPU-supported hardware, the execution on a typical UAV’s limited computational resources necessitates the use of lightweight, small-sized networks. To overcome these impediments, this article presents a lightweight and attention-based approach for performing forest fire detection tasks using UAV vision data (images acquired by cameras mounted on UAVs). In this paper, we also present comprehensive research for different approaches such as transfer learning, deep CNNs, and lightweight CNNs. Among the experimented models, the attention-based EfficientNetB0 backboned model emerged as the most successful architecture for forest fire detection. With the test accuracy of , the F1-score of , the recall of , and the precision of have strongly reinforced the efficiency of the EfficientNetB0-based model in wildfire recognition. Moreover, the network has a less parameter size than the experimented networks. It proves the model’s suitability for wildfire detection with UAVs having limited hardware resources.

Identification of crops is an important topic in the agricultural domain. Hyperspectral remote sensing data are very useful for crop feature extraction and classification. Remote sensing data is an unstructured data and Convolutional Neural Network (CNN) can work on unstructured data efficiently. This paper presents an evaluation of CNN for crop classification using the Indian Pines standard dataset obtained from the AVIRIS sensor and the study area dataset obtained from the EO-1hyperion sensor. Optimized CNN has been tuned by training the model on different parameters. It has been compared with two classification algorithms: Deep Neural Network (DNN) and Convolutional Autoencoder. According to the test results, the proposed optimized CNN model provided better results as compared to the other two methods. CNN has given 97 ± 0.58% overall accuracy for the Indian Pines standard dataset and 78 ± 2.43% for our study area dataset.

The recognition of analog pointer meters under nature environment is commonly a challenge task due to many influences like types of meters, shooting angle, lighting condition, etc. Most existing recognition algorithms consist of multiple steps including the detection and extraction of dial, scale marks and pointers followed by reading calculation, which is complex and sensitive to image quality. To address this issue, a one-stage, end-to-end recognition method for pointer meter based on deep regression is proposed in this paper. The proposed method simultaneously locates the position of the end point of a pointer, obtains a meter reading and determines whether the pointer exceeds the normal range through a fully convolutional neural network. Without complicated image pre-processing and post-processing, the algorithm can read multiple meters in one image just through a simple one-round forward inference. Experimental results show that the recognition accuracy achieves 92.59% under ±5% reading error, and the processing speed reaches approximately 25 FPS on a NVIDIA GTX 1080 GPU.

The report presents an algorithm for constructing a convolutional hierarchical neural network classifier, which is a modification of the algorithm for constructing hierarchical neural network classifiers suggested before. The original algorithm was designed to exploit intrinsic class hierarchy to build a class tree with a neural network in each node classifying groups of initial classes (in a non-terminal node) or a subset of original classes (in a terminal node). The convolutional modification utilizes convolutional neural networks instead of regular fully connected networks in order to apply the model to image classification tasks. Use of class hierarchy for image classification should reduce the number of adjusted neural network parameters compared to deep convolutional neural networks, and therefore it should reduce training and inference time. In this context the algorithm may be compared with some pruning techniques. The convolutional hierarchical neural network classifier inherits some hyperparameters of a conventional hierarchical neural network classifier, like the activation threshold and the threshold by the share of voting patterns. The goal of this study was to explore different strategies of choosing these hyperparameters. To test these strategies, we used the CIFAR-10 dataset. Also, for demonstration purposes we apply the convolutional hierarchical neural network classifier to the CIFAR-100 dataset.

White blood cells (WBCs) are the most diverse types of cells observed in the healing process of injured skeletal muscles. In the recovery process, WBCs exhibit a dynamic cellular response and undergo multiple changes of the protein expression. The progress of healing can be analyzed by the number of WBCs or by the number of specific proteins observed in light microscopy images obtained at different time points after injury. We propose a deep learning quantification and analysis system called DeepQuantify to analyze WBCs in light microscopy images of uninjured and injured muscles of female mice. The DeepQuantify system features in segmentation using the localized iterative Otsu's thresholding method, masking postprocessing, and classification of WBCs with a convolutional neural network (CNN) classifier to achieve a high accuracy and a low manpower cost. The proposed two-layer CNN classifier designed based on the optimization hypothesis is evaluated and compared with other CNN classifiers. The DeepQuantify system adopting these CNN classifiers is evaluated for quantifying CD68-positive macrophages and 7/4-positive neutrophils and compared with the state-of-the-art deep learning segmentation architectures. DeepQuantify achieves an accuracy of 90.64% and 89.31% for CD68-positive macrophages and 7/4-positive neutrophils, respectively. The DeepQuantify system employing the proposed two-layer CNN architecture achieves better performance than those deep segmentation architectures. The quantitative analysis of two protein dynamics during muscle recovery is also presented.

We present a multigrid-in-channels (MGIC) approach that tackles the quadratic growth of the number of parameters with respect to the number of channels in standard convolutional neural networks (CNNs). Thereby our approach addresses the redundancy in CNNs that is also exposed by the recent success of lightweight CNNs. Lightweight CNNs can achieve comparable accuracy to standard CNNs with fewer parameters; however, the number of weights still scales quadratically with the CNN’s width. Our MGIC architectures replace each CNN block with an MGIC counterpart that utilizes a hierarchy of nested grouped convolutions of small group size to address this. Hence, our proposed architectures scale linearly with respect to the network’s width while retaining full coupling of the channels as in standard CNNs. Our extensive experiments on image classification, segmentation, and point cloud classification show that applying this strategy to different architectures like ResNet and MobileNetV3 reduces the number of parameters while obtaining similar or better accuracy.

As urbanization accelerates, the prevalence of fire incidents leads to significant hazards. Enhancing the accuracy of remote fire detection systems while reducing computation complexity and power consumption in edge hardware are crucial. Therefore, this paper investigates an innovative lightweight Convolutional Spiking Neural Network (CSNN) method for fire detection based on acoustics. In this model, Poisson encoder and convolution encoder strategies are considered and compared. Additionally, the study investigates the impact of observation time steps, surrogate gradient functions, and the threshold and decay rate of membrane potential on network performance. A comparison is made between the classification metrics of the traditional Convolutional Neural Network (CNN) approaches and the proposed lightweight CSNN method. To assess the generalization performance of the proposed lightweight method, publicly available datasets are merged with our experimental data for training, which results in a high accuracy of 99.02%, a precision of 99.37%, a recall of 98.75%, and an F1 score of 99.06% on the test datasets.

Instead of using current deep-learning segmentation models (like the UNet and variants), we approach the segmentation problem using trained Convolutional Neural Network (CNN) classifiers, which automatically extract important features from images for classification. Those extracted features can be visualized and formed into heatmaps using Gradient-weighted Class Activation Mapping (Grad-CAM). This study tested whether the heatmaps could be used to segment the classified targets. We also proposed an evaluation method for the heatmaps; that is, to re-train the CNN classifier using images filtered by heatmaps and examine its performance. We used the mean-Dice coefficient to evaluate segmentation results. Results from our experiments show that heatmaps can locate and segment partial tumor areas. But use of only the heatmaps from CNN classifiers may not be an optimal approach for segmentation. We have verified that the predictions of CNN classifiers mainly depend on tumor areas, and dark regions in Grad-CAM's heatmaps also contribute to classification.

IntroductionColon cancer (CC) image classification plays a key role in the diagnostic process in clinical contexts, especially as computational medical solutions become the trend for future radiology and pathology practices. This study presents a novel lightweight Convolutional Neural Network (CNN) model designed with effective data cleaning strategy for the classification and visualization of histopathology images of various colon cancer tissues.MethodsAddressing the critical need for efficient diagnostic tools in colon cancer detection, the proposed model leverages a non-pretrained architecture optimized for performance in resource-constrained environments. Utilizing the NCT-CRC-HE-100K and CRC-VAL-HE-7K datasets, this model employs a parametric Gaussian distribution-based data cleaning approach to enhance data quality by removing outliers.ResultsWith a total of 4,414,217 parameters and a total size of 16.9 megabytes, the model achieves a test accuracy of 0.990 ± 0.003 with 95% level of confidence, which demonstrates high precision, recall, specificity, and F1 scores across various tissue classes.DiscussionComparative analysis with benchmark studies underscores the model’s effectiveness, while discussions on underfitting and overfitting provide insights into potential fine-tuning strategies. This research presents a robust, lightweight solution for colon cancer histopathology image classification, offering a foundation for future advancements in colon cancer diagnostics with result visualization.

Convolutional neural networks (CNNs) have achieved significant accuracy improvement in many intelligent applications at the cost of intensive convolution operations and massive data movements. To efficiently deploy CNNs on low power embedded platforms in real time, the depthwise separable convolution has been proposed to replace the standard convolution, especially in lightweight CNNs, which remarkably reduces the computation complexity and model size. However, it is difficult for a general convolution engine to obtain the theoretical performance improvement as the decreased data dependency of depthwise convolution significantly reduces the data reuse opportunity. To address this issue, a flexible and highperformance accelerator based on FPGA is proposed to efficiently process the inference of both large-scale and lightweight CNNs. Firstly, by sharing the activation dataflow between the depthwise convolution and pooling layers, the control logic and data bus of the two layers are reused to maximize the data utilization and minimize the logic overhead. Furthermore, these two layers can be processed either directly after standard convolutions to eliminate the external memory accesses or independently to gain better flexibility. Thirdly, a performance model is proposed to automatically explore the optimal design options of the accelerator. The proposed hardware accelerator is evaluated on Intel Arria 10 SoC FPGA and demonstrates state-of-the-art performance on both large-scale CNNs, e.g., VGG, and lightweight ones, e.g., MobileNet.

In this study, a lightweight convolutional neural network (CNN) is employed to identify Lamb modes. The proposed approach consists of five convolutional and pooling layers, then a fully-connected layer and a sigmoid layer. In which, the first convolutional layer is a wide-scale kernel. Lamb wave responses based on froward modelling are obtained for different plate materials (aluminium, steel and titanium), different excitation frequencies (250 kHz, 500 kHz), and different excitation cycles (4-cycle, 5-cycle). 16800 Lamb wave samples labelled by ‘A0 mode’ and ‘S0 mode’ are beforehand and hosted in a database, then trained via the lightweight CNN. In validation process, the lightweight CNN reaches 100% accuracy. The performance of light-weight CNN is also compared with some popular networks. Now, the well-trained network can be used to identify Lamb mode. Some responses are stimulated by ABAQUS under different excitation signal, different propagating distance, different plate material, and the predicted results via the lightweight CNN are all right. In addition, the extensibility of the network is validated by identifying new-converted Lamb mode correctly.

A biosensing method for the direct serological detection of liver diseases by integrating a SERS-based sensor and a CNN classifier