Lightweight Convolutional Neural Network Research Articles

A Lightweight Face Detector via Bi-Stream Convolutional Neural Network and Vision Transformer

Lightweight convolutional neural networks are widely used for face detection due to their ability to learn local representations through spatial induction bias and translational invariance. However, convolutional face detectors have limitations in detecting faces under challenging conditions like occlusion, blurring, or changes in facial poses, primarily attributed to fixed-size receptive fields and a lack of global modeling. Transformer-based models have advantages on learning global representations but are insensitive to capture local patterns. To address these limitations, we propose an efficient face detector that combines convolutional neural network and transformer architectures. We introduce a bi-stream structure that integrates convolutional neural network and transformer blocks within the backbone network, enabling the preservation of local pattern features and the extraction of global context. To further preserve the local details captured by convolutional neural networks, we propose a feature enhancement convolution block in a hierarchical backbone structure. Additionally, we devise a multiscale feature aggregation module to enhance obscured and blurred facial features. Experimental results demonstrate that our method has achieved improved lightweight face detection accuracy with an average precision of 95.30%, 94.20%, and 87.56% across the easy, medium, and hard subdatasets of WIDER FACE, respectively. Therefore, we believe our method will be a useful supplement to the collection of current artificial intelligence models and benefit the engineering applications of face detection.

Almond (Prunus dulcis) varieties classification with genetic designed lightweight CNN architecture

AbstractAlmond (Prunus dulcis) is a nutritious food with a rich content. In addition to consuming as food, it is also used for various purposes in sectors such as medicine, cosmetics and bioenergy. With all these usages, almond has become a globally demanded product. Accurately determining almond variety is crucial for quality assessment and market value. Convolutional Neural Network (CNN) has a great performance in image classification. In this study, a public dataset containing images of four different almond varieties was created. Five well-known and light-weight CNN models (DenseNet121, EfficientNetB0, MobileNet, MobileNet V2, NASNetMobile) were used to classify almond images. Additionally, a model called 'Genetic CNN', which has its hyperparameters determined by Genetic Algorithm, was proposed. Among the well-known and light-weight CNN models, NASNetMobile achieved the most successful result with an accuracy rate of 99.20%, precision of 99.21%, recall of 99.20% and f1-score of 99.19%. Genetic CNN outperformed well-known models with an accuracy rate of 99.55%, precision of 99.56%, recall of 99.55% and f1-score of 99.55%. Furthermore, the Genetic CNN model has a relatively small size and low test time in comparison to other models, with a parameter count of only 1.1 million. Genetic CNN is suitable for embedded and mobile systems and can be used in real-life solutions.

A Lightweight CNN with LSTM Malware Detection Architecture for 5G and IoT Networks

Fifth-generation (5G) mobile networks are being deployed all over the world and researchers are concerned about the network's security against hacking. Researchers have focused heavily on this topic in recent years as new technologies attempt to integrate into numerous sectors of corporate and social organizations. Malicious software referred to as malware, is an unwanted application that attackers frequently use to execute online attacks. Advanced packing and obfuscation methods are being used by malware variants to continue their evolution. Due to several application features in 5G networks such as APIs, calls and SMS, it is difficult to detect and classify malware attacks. In a variety of research areas, deep learning (DL) techniques are effectively utilized to address malware-related solutions. Especially, convolutional neural networks (CNN) played a crucial role in the classification of malware detection in 5G networks and the Internet of Things (IoT). In this work, a lightweight CNN architecture with a sequential Long Short-Term Memory (LSTM) layer is developed for malware detection and classification trained on the Malimg dataset. The results prove that the proposed approach achieves 99.8% accuracy with an F1-score of 0.9925 for malware detection and outperforms state-of-the-art approaches in the literature. The classification performance is improved up to 12.8% and 14% in terms of accuracy and F1-score, respectively when compared with existing malware classification models.

FER-BHARAT: a lightweight deep learning network for efficient unimodal facial emotion recognition in Indian context

Humans' ability to manage their emotions has a big impact on their ability to plan and make decisions. In order to better understand people and improve human–machine interaction, researchers in affective computing and artificial intelligence are investigating the detection and recognition of emotions. However, different cultures have distinct ways of expressing emotions, and the existing emotion recognition datasets and models may not effectively capture the nuances of the Indian population. To address this gap, this study proposes custom-built lightweight Convolutional Neural Network (CNN) models that are optimized for accuracy and computational efficiency. These models are trained and evaluated on two Indian emotion datasets: The Indian Spontaneous Expression Dataset (ISED) and the Indian Semi Acted Facial Expression Database (iSAFE). The proposed CNN model with manual feature extraction provides remarkable accuracy improvement of 11.14% for ISED and 4.72% for iSAFE datasets as compared to baseline, while reducing the training time. The proposed model also surpasses the accuracy produced by pre-trained ResNet-50 model by 0.27% ISED and by 0.24% for the iSAFE dataset with significant improvement in training time of approximately 320 s for ISED and 60 s for iSAFE dataset. The suggested lightweight CNN model with manual feature extraction offers the advantage of being computationally efficient and more accurate compared to pre-trained model making it a more practical and efficient solution for emotion recognition among Indians.

Classification of field wheat varieties based on a lightweight G-PPW-VGG11 model

IntroductionIn agriculture, especially wheat cultivation, farmers often use multi-variety planting strategies to reduce monoculture-related harvest risks. However, the subtle morphological differences among wheat varieties make accurate discrimination technically challenging. Traditional variety classification methods, reliant on expert knowledge, are inefficient for modern intelligent agricultural management. Numerous existing classification models are computationally complex, memory-intensive, and difficult to deploy on mobile devices effectively. This study introduces G-PPW-VGG11, an innovative lightweight convolutional neural network model, to address these issues.MethodsG-PPW-VGG11 ingeniously combines partial convolution (PConv) and partially mixed depthwise separable convolution (PMConv), reducing computational complexity and feature redundancy. Simultaneously, incorporating ECANet, an efficient channel attention mechanism, enables precise leaf information capture and effective background noise suppression. Additionally, G-PPW-VGG11 replaces traditional VGG11’s fully connected layers with two pointwise convolutional layers and a global average pooling layer, significantly reducing memory footprint and enhancing nonlinear expressiveness and training efficiency.ResultsRigorous testing showed G-PPW-VGG11's superior performance, with an impressive 93.52% classification accuracy and only 1.79MB memory usage. Compared to VGG11, G-PPW-VGG11 showed a 5.89% increase in accuracy, 35.44% faster inference, and a 99.64% reduction in memory usage. G-PPW-VGG11 also surpasses traditional lightweight networks in classification accuracy and inference speed. Notably, G-PPW-VGG11 was successfully deployed on Android and its performance evaluated in real-world settings. The results showed an 84.67% classification accuracy with an average time of 291.04ms per image.DiscussionThis validates the model's feasibility for practical agricultural wheat variety classification, establishing a foundation for intelligent management. For future research, the trained model and complete dataset are made publicly available.

Accurate Classification of Tunnel Lining Cracks Using Lightweight ShuffleNetV2-1.0-SE Model with DCGAN-Based Data Augmentation and Transfer Learning

Cracks in tunnel lining surfaces directly threaten structural integrity; therefore, regular inspection of cracks is essential. Lightweight convolutional neural networks (LCNNs) have recently offered a promising alternative to conventional manual inspection. However, the effectiveness of LCNNs is still adversely affected by the lack of sufficient crack images, which limits the potential detection performance. In this paper, transfer learning was used to optimize deep convolutional generative adversarial networks (DCGANs) for crack image synthesis to significantly improve the accuracy of LCNNs. In addition, an improved LCNN model named ShuffleNetV2-1.0-SE was proposed, incorporating the squeeze–excitation (SE) attention mechanism into ShuffleNetV2-1.0 and realizing highly accurate classification results while maintaining lightness. The results show that the DCGAN-based data enhancement method can significantly improve the classification accuracy of ShuffleNetV2-1.0-SE for tunnel lining cracks. ShuffleNetV2-1.0-SE achieves an accuracy of 98.14% on the enhanced dataset, which is superior to multiple advanced LCNN models.

FOOD CLASSIFICATION AND CALORIE ESTIMATION USING CNN

This research paper explores the transformative impact of deep learning methodologies in the domains of food image recognition, classification, and calorie estimation. By utilizing the convergence of machine learning with convolutional neural networks (CNNs), the study tackles the growing concerns surrounding obesity and health difficulties, highlighting the need for creative methods of nutritional monitoring. Motivated by challenges in fruit classification and the limitations of traditional methods, the research progressively shifts towards efficient and accurate image-based approaches, particularly highlighting the effectiveness of CNNs. The methodology focuses on machine learning-based approaches for food calorie estimation, with a specific emphasis on parameter-optimized lightweight CNN models utilizing TensorFlow's Object Detection API and CNN. The results showcase impressive accuracy levels, often exceeding 90%, across diverse food items, albeit with persistent challenges such as limited datasets, computational costs, and real-world application constraints. In conclusion, this comprehensive review underscores the transformative potential of deep learning in fostering healthier lifestyles, combating obesity, and providing valuable insights for dietary guidance and health management. Further research is recommended to enhance dataset representativeness and optimize model generalization for broader practical applicability Keywords: Calorie estimation, Classification, Convolutional neural network, Object detection.

SURVEY ON FOOD CLASSIFICATION AND CALORIE ESTIMATION USING CNN

This research paper explores the transformative impact of deep learning methodologies in the domains of food image recognition, classification, and calorie estimation. By utilizing the convergence of machine learning with convolutional neural networks (CNNs), the study tackles the growing concerns surrounding obesity and health difficulties, highlighting the need for creative methods of nutritional monitoring. Motivated by challenges in fruit classification and the limitations of traditional methods, the research progressively shifts towards efficient and accurate image-based approaches, particularly highlighting the effectiveness of CNNs. The methodology focuses on machine learning-based approaches for food calorie estimation, with a specific emphasis on parameter-optimized lightweight CNN models utilizing TensorFlow's Object Detection API and Mask R-CNN. The results showcase impressive accuracy levels, often exceeding 90%, across diverse food items, albeit with persistent challenges such as limited datasets, computational costs, and real-world application constraints. In conclusion, this comprehensive review underscores the transformative potential of deep learning in fostering healthier lifestyles, combating obesity, and providing valuable insights for dietary guidance and health management. Further research is recommended to enhance dataset representativeness and optimize model generalization for broader practical applicability Keywords: Calorie estimation, Classification, Convolutional neural network, Object detection.

Real-Time Intelligent Diagnosis of Co-frequency Vibration Faults in Rotating Machinery Based on Lightweight-Convolutional Neural Networks

The co-frequency vibration fault is one of the common faults in the operation of rotating equipment, and realizing the real-time diagnosis of the co-frequency vibration fault is of great significance for monitoring the health state and carrying out vibration suppression of the equipment. In engineering scenarios, co-frequency vibration faults are highlighted by rotational frequency and are difficult to identify, and existing intelligent methods require more hardware conditions and are exclusively time-consuming. Therefore, Lightweight-convolutional neural networks (LW-CNN) algorithm is proposed in this paper to achieve real-time fault diagnosis. The critical parameters are discussed and verified by simulated and experimental signals for the sliding window data augmentation method. Based on LW-CNN and data augmentation, the real-time intelligent diagnosis of co-frequency is realized. Moreover, a real-time detection method of fault diagnosis algorithm is proposed for data acquisition to fault diagnosis. It is verified by experiments that the LW-CNN and sliding window methods are used with high accuracy and real-time performance.

Lightweight Convolutional Network with Integrated Attention Mechanism for Missing Bolt Detection in Railways

Railway infrastructure safety is a paramount concern, with bolt integrity being a critical component. In the realm of railway maintenance, the detection of missing bolts is a vital task that ensures the stability and safety of tracks. Traditionally, this task has been approached through manual inspections or conventional automated methods, which are often time-consuming, costly, and prone to human error. Addressing these challenges, this paper presents a state-of-the-art solution with the development of a lightweight convolutional neural network (CNN) featuring an integrated attention mechanism. This novel model is engineered to be computationally efficient while maintaining high accuracy, making it particularly suitable for real-time analysis in resource-constrained environments commonly found in railway inspections. The proposed CNN utilises a distinctive architecture that synergises the speed of lightweight networks with the precision of attention-based mechanisms. By integrating an attention mechanism, the network selectively concentrates on regions of interest within the image, effectively enhancing the model’s capability to identify missing bolts with remarkable accuracy. Comprehensive testing showcases a remarkable 96.43% accuracy and an impressive 96 F1-score, substantially outperforming existing deep learning frameworks in the context of missing bolt detection. Key contributions of this research include the model’s innovative attention-integrated approach, which significantly reduces the model complexity without compromising detection performance. Additionally, the model offers scalability and adaptability to various railway settings, proving its efficacy not just in controlled environments but also in diverse real-world scenarios. Extensive experiments, rigorous evaluations, and real-time deployment results collectively underscore the transformative potential of the presented CNN model in advancing the domain of railway safety maintenance.

Lightweight convolutional neural network for fast visual perception of storage location status in stereo warehouse

Lightweight convolutional neural network for fast visual perception of storage location status in stereo warehouse

MCAD: Multi-classification anomaly detection with relational knowledge distillation

AbstractWith the wide application of deep learning in anomaly detection (AD), industrial vision AD has achieved remarkable success. However, current AD usually focuses on anomaly localization and rarely investigates anomaly classification. Furthermore, anomaly classification is currently requested for quality management and anomaly reason analysis. Therefore, it is essential to classify anomalies while improving the accuracy of AD. This paper designs a novel multi-classification AD (MCAD) framework to achieve high-accuracy AD with an anomaly classification function. In detail, the proposal model based on relational knowledge distillation consists of two components. The first one employs a teacher–student AD model, utilizing a relational knowledge distillation approach to transfer the interrelationships of images. The teacher–student critical layer feature activation values are used in the knowledge transfer process to achieve anomaly detection. The second component realizes anomaly multi-classification using the lightweight convolutional neural network. Our proposal has achieved 98.95, 96.04, and 92.94% AUROC AD results on MNIST, FashionMNIST, and CIFAR10 datasets. Meanwhile, we earn 97.58 and 98.10% AUROC for AD and localization in the MVTecAD dataset. The average classification accuracy of anomaly classification has reached 76.37% in fifteen categories of the MVTec-AD dataset. In particular, the classification accuracy of the leather category has gained 95.24%. The results on the MVTec-AD dataset show that MCAD achieves excellent detection, localization, and classification results.

A lightweight convolutional neural network for multipoint displacement measurements on bridge structures

A lightweight convolutional neural network for multipoint displacement measurements on bridge structures

A Lightweight Convolutional Neural Network Method for Two-Dimensional PhotoPlethysmoGraphy Signals

Data information security on wearable devices has emerged as a significant concern among users, so it becomes urgent to explore authentication methods based on wearable devices. Using PhotoPlethysmoGraphy (PPG) signals for identity authentication has been proven effective in biometric authentication. This paper proposes a convolutional neural network authentication method based on 2D PPG signals applied to wearable devices. This method uses Markov Transition Field technology to convert one-dimensional PPG signal data into two-dimensional image data, which not only retains the characteristics of the signal but also enriches the spatial information. Afterward, considering that wearable devices usually have limited resources, a lightweight convolutional neural network model is also designed in this method, which reduces resource consumption and computational complexity while ensuring high performance. It is proved experimentally that this method achieves 98.62% and 96.17% accuracy on the training set and test set, respectively, an undeniable advantage compared to the traditional one-dimensional deep learning method and the classical two-dimensional deep learning method.

Efficient image denoising with heterogeneous kernel-based CNN

Recent advancements in deep learning have notably advanced the field of image denoising. Yet, blindly increasing the depth or width of convolutional neural networks (CNNs) cannot ameliorate the network effectively, and even leads to training difficulties and sophisticated training tricks. In this paper, a lightweight CNN with heterogeneous kernels (HKCNN) is designed for efficient noise removal. HKCNN comprises four modules: a multiscale block (MB), an attention enhancement block (AEB), an elimination block (EB), and a construct block (CB). Specifically, the MB leverages heterogeneous kernels alongside re-parameterization to capture diverse complementary structure information, bolstering discriminative ability and the denoising robustness of the denoiser. The AEB incorporates an attention mechanism that prioritizes salient features, expediting the training stage and boosting denoising efficacy. The EB and CB are designed to further suppress noise and reconstruct latent clean images. Besides, the HKCNN integrates perceptual loss for both retaining semantic details and improving image perceptual quality, so as to refine the denoising output. Comprehensive qualitative and quantitative evaluations highlight the superior performance of HKCNN over state-of-the-art denoising methods, validating its efficacy in practical image denoising scenarios.

Goat-CNN: A lightweight convolutional neural network for pose-independent body condition score estimation in goats

Modern livestock farming systems face the challenge of meeting the growing demand for dairy and meat products while ensuring the well-being of animals. Body Condition Scoring serves as a vital process for assessing the body reserves in animals, impacting their health, welfare, and productivity. However, traditional body condition score (BCS) evaluation methods via observation and palpation of specific anatomical regions are labor-intensive and subjective, hindering their widespread adoption. To address this issue, Precision Livestock Farming (PLF) techniques, particularly those involving Internet of Things (IoT) devices and artificial intelligence (AI), have emerged as promising solutions. In this work, we explore the use of AI, specifically Convolutional Neural Networks (CNNs), to automate the assessment of BCS in goats utilizing imagery data. Our model was trained on 5000 images illustrating the dorsal view of the backside of goats achieving an overall accuracy of 97.94 % which was the highest compared to other popular deep learning architectures from literature (e.g. VGG16, ResNet34, ResNet50, DenseNet, GoogleNet). The proposed custom CNN model for goat-specific BCS estimation overcomes the limitations of manual sketching, providing automatic region identification for BCS assessment. Moreover, it is a lightweight model specifically designed for seamless integration with IoT devices, allowing for efficient on-board processing via cameras. The model's pose-independent nature and adaptability to environmental constraints make it a valuable tool for efficient and sustainable goat farming. This research advances the application of AI as a precision livestock farming tool, contributing to the reinforcement of the animal welfare and productivity, and supporting evidence-based decision-making processes to increase farms' resilience.

A memory-friendly class-incremental learning method for hand gesture recognition using HD-sEMG

Hand gesture recognition (HGR) plays a vital role in human-computer interaction. The integration of high-density surface electromyography (HD-sEMG) and deep neural networks (DNNs) has significantly improved the robustness and accuracy of HGR systems. These methods are typically effective for a fixed set of trained gestures. However, the need for new gesture classes over time poses a challenge. Introducing new classes to DNNs can lead to a substantial decrease in accuracy for previously learned tasks, a phenomenon known as "catastrophic forgetting," especially when the training data for earlier tasks is not retained and retrained. This issue is exacerbated in embedded devices with limited storage, which struggle to store the large-scale data of HD-sEMG. Class-incremental learning (CIL) is an effective method to reduce catastrophic forgetting. However, existing CIL methods for HGR rarely focus on reducing memory load. To address this, we propose a memory-friendly CIL method for HGR using HD-sEMG. Our approach includes a lightweight convolutional neural network, named SeparaNet, for feature representation learning, coupled with a nearest-mean-of-exemplars classifier for classification. We introduce a priority exemplar selection algorithm inspired by the herding effect to maintain a manageable set of exemplars during training. Furthermore, a task-equal-weight exemplar sampling strategy is proposed to effectively reduce memory load while preserving high recognition performance. Experimental results on two datasets demonstrate that our method significantly reduces the number of retained exemplars to only a quarter of that required by other CIL methods, accounting for less than 5% of the total samples, while still achieving comparable average accuracy.

Wide-TSNet: A Novel Hybrid Approach for Bitcoin Price Movement Classification

In this paper, we introduce Wide-TSNet, a novel hybrid approach for predicting Bitcoin prices using time-series data transformed into images. The method involves converting time-series data into Markov transition fields (MTFs), enhancing them using histogram equalization, and classifying them using Wide ResNets, a type of convolutional neural network (CNN). We propose a tripartite classification system to accurately represent Bitcoin price trends. In addition, we demonstrate the effectiveness of Wide-TSNet through various experiments, in which it achieves an Accuracy of approximately 94% and an F1 score of 90%. It is also shown that lightweight CNN models, such as SqueezeNet and EfficientNet, can be as effective as complex models under certain conditions. Furthermore, we investigate the efficacy of other image transformation methods, such as Gramian angular fields, in capturing the trends and volatility of Bitcoin prices and revealing patterns that are not visible in the raw data. Moreover, we assess the effect of image resolution on model performance, emphasizing the importance of this factor in image-based time-series classification. Our findings explore the intersection between finance, image processing, and deep learning, providing a robust methodology for financial time-series classification.

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.

LSGNet: A lightweight convolutional neural network model for tomato disease identification

Tomatoes are among the most extensively grown and consumed crops worldwide, but tomato production can be greatly reduced due to various diseases. Plant diseases show different symptoms at different stages. In addition, there are similarities in the symptoms of different types of plant diseases, which hinder the recognition of diseases by existing deep learning models. Traditional convolutional neural network (CNN) models for disease recognition have a large number of parameters that require high computational resources. To overcome these challenges, we propose a lightweight CNN model named LSGNet (lightweight sandglass network) for tomato disease identification. The LSGNet backbone consists of the sandglass with efficient channel attention (SGECA) and the position aware circular convolution sandglass (ParcSG) modules. The SGECA module reduces the interference of complex environments and thus focuses on extracting useful feature information. The ParcSG module has a global receptive field, which provides more detailed feature information on disease recognition. The results show that the recognition accuracies are 92.37%, 94.32%, 89.64%, 92.70%, 94.43%, 90.97%, 89.42%, 92.98%, 89.58%, and 95.54% for AlexNet, ResNet50, VGG16, MobileNetV3-Large, ShuffleNetV2-1 × , EfficientNetV2-Small, ViT-Base, MobileViT-Small, Swin-Tiny, and LSGNet. Therefore, LSGNet has higher accuracy in recognizing tomato diseases compared to other classical models. In addition, LSGNet uses 0.75 million parameters. Compared to the lightweight CNN model MobileNetV3-Large, it only has 18% of the parameters. As a whole, the advantages of LSGNet in efficiency and lightweight structure would make it a useful tool for tomato disease recognition on mobile or embedded devices.