Forest Fire Recognition Based on Lightweight Convolutional Neural Network

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.

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.

Handwritten digit recognition, a task in computer vision, is critical for applications such as postal automation, banking, and digitization of forms. Traditional approaches have leveraged statistical models, but the rise of deep learning, particularly Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM), has revolutionized the field. However, a comprehensive performance comparison of CNN and LSTM architectures in the context of handwritten digit classification remains underexplored. This study aimed to address this gap by evaluating and comparing CNN and LSTM models for the classification of handwritten digits. Two machine learning models – Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM) were trained with the preprocessed handwritten digit dataset. The CNN model was designed with multiple convolutional and pooling layers, along with dropout for regularization. The LSTM model was designed with LSTM layers to capture sequential patterns in the data, followed by a dense layer for classification. The models were implemented in python, evaluated and compared based on accuracy, precision, recall and F1-score. The evaluation and comparison results indicate that CNN achieved 99.31% accuracy, 99.0% precision, 99.0% recall, and a 99.0% F1-score, while LSTM achieved 98.90% accuracy, 99.0% precision, 99.0% recall, and a 99.0% F1-score. The results demonstrated that CNN outperformed LSTM in terms of accuracy and misclassification errors, making it the optimal choice for image-based handwritten digit recognition. This finding underscores the efficiency of CNN in addressing challenges related to digit recognition, contributing to the advancement of automated digit classification systems and improving the accuracy of image-based classification tasks.

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.

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.

Skin conditions are common and frequently need for a quick and precise diagnosis in order to be treated. In this paper, we propose a Convolutional Neural Network (CNN) based skin disease detection system. CNNs are ideally suited for the identification of skin diseases from photos because they have shown impressive effectiveness in image classification tasks. We make use of a sizable collection of skin picture annotations that span a wide variety of dermatological disorders. Multiple convolutional and pooling layers are used in our CNN architecture to automatically extract discriminative features from input photos. Using a variety of supervised learning strategies, we train the CNN model to maximize performance measures including accuracy, precision, recall, and F1-score. By means of comprehensive testing and analysis, we exhibit the efficacy of our CNN-based skin disease detector in precisely recognizing diverse skin

The maintenance of security and trustworthy access management in Internet of Things (IoT)-enabled settings in the fast-changing digital world has become one of the most pressing issues. The paper presents a face recognition model based on artificial intelligence that uses current state-of-theart deep learning and edge computing technologies to improve on the security of the IoT-based access control systems. The architecture starts with input of an IoT camera or sensor and then proceeds with preprocessing activities like face alignment, normalization and improvement of data to highlight quality output. Lightweight convolutional neural networks (CNNs) and MTCNN are used to detect faces efficiently, and TinyFace-IoTNet and EfficientNet models are used to extract features efficiently. Identity verification and classification is done based on cosine similarity and softmax functions, which guarantees recognition accuracy even in resource-limited IoT settings. The communication mechanisms and secure edge processing are combined to reduce the latency, the sensitive information, and decreased the use of centralized servers. The system then issues access control decisions which are either to grant or deny access after verifying the identity and securely logging and updating database to ensure accountability and traceability. The experimental analysis shows that the proposed model can be used as a viable solution to the next-generation IoT-based security systems because it provides real-time performance, a higher recognition accuracy, and resilience against an unauthorized access to the system.

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.

Recently, many researches have been conducted on recognition of facial emotion using convolutional neural networks (CNNs), which show excellent performance in computer vision. To obtain a high classification accuracy, a CNN architecture with many parameters and high computational complexity is required. However, this is not suitable for embedded systems where hardware resources are limited. In this paper, we present a lightweight CNN architecture optimized for embedded systems. The proposed CNN architecture has a small memory footprint and low computational complexity. Furthermore, a novel hardware-friendly quantization method that uses only integer-arithmetic is proposed. The proposed hardware-friendly quantization method maps the scale factors to power-of-two terms and replaces multiplication and division operations using scale factors with shift operations. To improve the generalization and classification performance of the CNN, we create the FERPlus-A dataset. This is a new training dataset created using a variety of image processing algorithms. After training with FERPlus-A, quantization has been performed. The size of a quantized CNN parameter is about 0.39 MB, and the number of operations is about 28 M integer operations (IOPs). By evaluating the performance of the quantized CNN that uses only integer-arithmetic on the FERPlus test dataset, the classification accuracy is approximately 86.58%. It achieved higher accuracy than other lightweight CNNs in prior studies. The proposed CNN architecture that uses only integer-arithmetic is implemented on the Xilinx ZC706 SoC platform for real-time facial emotion recognition by applying parallelism strategies and efficient data caching strategies. The FPGA-based CNN accelerator implemented for real-time facial emotion recognition achieves about 10 frame per second (FPS) at 250 MHz and consumes 2.3 W.

Abstract: Food classification using Convolutional Neural Networks (CNNs) has gained significant attention due to its potential applications in dietary analysis, food recommendation systems, and nutrition monitoring. In this study, we present a CNN-based approach for food classification, leveraging image data augmentation to enhance the model's ability to generalize to new and unseen food images. We utilize a dataset containing diverse food categories and preprocess the images by resizing and normalization. The proposed CNN architecture consists of multiple convolutional and pooling layers, along with dropout and batch normalization for regularization. To prevent overfitting, we employ early stopping as a custom callback during model training. The experimental results demonstrate promising training accuracy of 90.13% and relatively low training loss of 0.3066, indicating effective learning from the training data. the validation accuracy of 69.00% and validation loss of 1.270.

Deep convolutional neural networks (CNNs) have seen significant growth in medical image classification applications due to their ability to automate feature extraction, leverage hierarchical learning, and deliver high classification accuracy. However, Deep CNNs require substantial computational power and memory, particularly for large datasets and complex architectures. Additionally, optimising the hyperparameters of deep CNNs, although critical for enhancing model performance, is challenging due to the high computational costs involved, making it difficult without access to high-performance computing resources. To address these limitations, this study presents a fast and efficient model that aims to achieve superior classification performance compared to popular Deep CNNs by developing lightweight CNNs combined with the Nonlinear Lévy chaotic moth flame optimiser (NLCMFO) for automatic hyperparameter optimisation. NLCMFO integrates the Lévy flight, chaotic parameters, and nonlinear control mechanisms to enhance the exploration capabilities of the Moth Flame Optimiser during the search phase while also leveraging the Lévy flight theorem to improve the exploitation phase. To assess the efficiency of the proposed model, empirical analyses were performed using a dataset of 2314 brain tumour detection images (1245 images of brain tumours and 1069 normal brain images). The evaluation results indicate that the CNN_NLCMFO outperformed a non-optimised CNN by 5% (92.40% accuracy) and surpassed established models such as DarkNet19 (96.41%), EfficientNetB0 (96.32%), Xception (96.41%), ResNet101 (92.15%), and InceptionResNetV2 (95.63%) by margins ranging from 1 to 5.25%. The findings demonstrate that the lightweight CNN combined with NLCMFO provides a computationally efficient yet highly accurate solution for medical image classification, addressing the challenges associated with traditional deep CNNs.

Monitoring environmental conditions is an important application of cyber-physical systems. Typically, the monitoring is to perceive surrounding environments with battery-powered, tiny devices deployed in the field. While deep learning-based methods, especially the convolutional neural networks (CNNs), are promising approaches to enriching the functionalities offered by the tiny devices, they demand more computation and memory resources, which makes these methods difficult to be adopted on such devices. In this article, we develop a software framework, RAP , that permits the construction of the CNN designs by aggregating the existing, lightweight CNN layers, which are able to fit in the limited memory (e.g., several KBs of SRAM) on the resource-constrained devices satisfying application-specific timing constrains. RAP leverages the Python-based neural network framework Chainer to build the CNNs by mounting the C/C++ implementations of the lightweight layers, trains the built CNN models as the ordinary model-training procedure in Chainer, and generates the C version codes of the trained models. The generated programs are compiled into target machine executables for the on-device inferences. With the vigorous development of lightweight CNNs, such as binarized neural networks with binary weights and activations, RAP facilitates the model building process for the resource-constrained devices by allowing them to alter, debug, and evaluate the CNN designs over the C/C++ implementation of the lightweight CNN layers. We have prototyped the RAP framework and built two environmental monitoring applications for protecting endangered species using image- and acoustic-based monitoring methods. Our results show that the built model consumes less than 0.5 KB of SRAM for buffering the runtime data required by the model inference while achieving up to 93% of accuracy for the acoustic monitoring with less than one second of inference time on the TI 16-bit microcontroller platform.

The advent of intelligent fault diagnosis has advanced condition monitoring in industrial machinery. This study develops and evaluates two lightweight convolutional neural networks (CNNs): a 1-D CNN for time-domain vibration signals and a 2-D CNN for continuous wavelet transform (CWT)–based scalogram images in rolling-element bearing fault diagnosis. A key feature of this work is its dual-modality framework that independently examines temporal and time–frequency representations to assess diagnostic accuracy and computational efficiency. Using the Case Western Reserve University (CWRU) dataset and an in-house experimental dataset, both models demonstrate strong generalization under variable conditions. The 1-D CNN achieves 99.67% mean accuracy with significantly lower computation time and memory usage than AlexNet and GoogLeNet, while the 2-D CNN attains 98.74% accuracy with improved interpretability. Performance remains stable across 10 independent runs, with 95% confidence intervals confirming the robustness of both models for future edge-oriented fault diagnosis applications.

Self-attention based models such as vision transformers (ViTs) have emerged as a very competitive architecture alternative to convolutional neural networks (CNNs) in computer vision. Despite increasingly stronger variants with ever higher recognition accuracies, due to the quadratic complexity of self-attention, existing ViTs are typically demanding in computation and model size. Although several successful design choices (e.g., the convolutions and hierarchical multi-stage structure) of prior CNNs have been reintroduced into recent ViTs, they are still not sufficient to meet the limited resource requirements of mobile devices. This motivates a very recent attempt to develop light ViTs based on the state-of-the-art MobileNet-v2, but still leaves a performance gap behind. In this work, pushing further along this under-studied direction we introduce EdgeViTs, a new family of light-weight ViTs that, for the first time, enable attention based vision models to compete with the best light-weight CNNs in the tradeoff between accuracy and on-device efficiency. This is realized by introducing a highly cost-effective local-global-local (LGL) information exchange bottleneck based on optimal integration of self-attention and convolutions. For device-dedicated evaluation, rather than relying on inaccurate proxies like the number of FLOPs or parameters, we adopt a practical approach of focusing directly on on-device latency and, for the first time, energy efficiency. Extensive experiments on image classification, object detection and semantic segmentation validate high efficiency of our EdgeViTs when compared to the state-of-the-art efficient CNNs and ViTs in terms of accuracy-efficiency tradeoff on mobile hardware. Specifically, we show that our models are Pareto-optimal when both accuracy-latency and accuracy-energy tradeoffs are considered, achieving strict dominance over other ViTs in almost all cases and competing with the most efficient CNNs. Code is available at https://github.com/saic-fi/edgevit .