Lightweight Deep Research Articles

EpiBrCan-Lite: A Lightweight Deep Learning model for Breast Cancer Subtype Classification using Epigenomic Data

Background and objectivesEarly breast cancer subtypes classification improves the survival rate as it facilitates prognosis of the patient. In literature this problem was prominently solved by various Machine Learning and Deep Learning techniques. However, these studies have three major shortcomings: huge Trainable Weight Parameters (TWP), suffer from low performance and class imbalance problem. MethodsThis paper proposes a lightweight model named EpiBrCan-Lite for classifying breast cancer subtypes using DNA methylation data. This model encompasses three blocks namely Data Encoding, TransGRU, and Classification blocks. In Data Encoding block, the input features are encoded into equal sized chunks and then passed down to TransGRU block which is a modified version of traditional Transformer Encoder (TE). In TransGRU block, MLP module of traditional TE is replaced by GRU module, consisting of two GRU layers to reduce TWP and capture the long-range dependencies of input feature data. Furthermore, output of TransGRU block is passed to Classification block for classifying breast cancer into their subtypes. ResultsThe proposed model is validated using Accuracy, Precision, Recall, F1-score, FPR, and FNR metrics on TCGA breast cancer dataset. This dataset suffers from the class imbalance problem which is mitigated using Synthetic Minority Oversampling Technique (SMOTE). Experimentation results demonstrate that EpiBrCan-Lite model attained 95.85% accuracy, 95.96% recall, 95.85% precision, 95.90% F1-score, 1.03% FPR, and 4.12% FNR despite of utilizing only 1/1500 of TWP than other state-of-the-art models. ConclusionEpiBrCan-Lite model is efficiently classifying breast cancer subtypes, and being lightweight, it is suitable to be deployed on low computational powered devices.

Framework for Lightweight Deep Learning Model Using YOLOv5 for Arecanut Grade Assessment

Framework for Lightweight Deep Learning Model Using YOLOv5 for Arecanut Grade Assessment

Potato Leaf Disease Detection Based on a Lightweight Deep Learning Model

Traditional methods of agricultural disease detection rely primarily on manual observation, which is not only time-consuming and labor-intensive, but also prone to human error. The advent of deep learning has revolutionized plant disease detection by providing more accurate and efficient solutions. The management of potato diseases is critical to the agricultural industry, as these diseases can lead to substantial losses in crop production. The prompt identification and classification of potato leaf diseases are essential to mitigating such losses. In this paper, we present a novel approach that integrates a lightweight convolutional neural network architecture, RegNetY-400MF, with transfer learning techniques to accurately identify seven different types of potato leaf diseases. The proposed method not only enhances the precision of potato leaf disease detection but also reduces the computational and storage demands, with a mere 0.40 GFLOPs and a model size of 16.8 MB. This makes it well-suited for use on edge devices with limited resources, enabling real-time disease detection in agricultural environments. The experimental results demonstrated that the accuracy of the proposed method in identifying seven potato leaf diseases was 90.68%, providing a comprehensive solution for potato crop management.

SMOTE-Based Automated PCOS Prediction Using Lightweight Deep Learning Models.

The reproductive age of women is particularly vulnerable to the effects of polycystic ovarian syndrome (PCOS). High levels of testosterone and other male hormones are frequent contributors to PCOS. It is believed that miscarriages and ovulation problems are majorly caused by PCOS. A recent study found that 31.3% of Asian women have been afflicted with PCOS. Healing women with life-threatening disorders associated with PCOS requires more research. In prior research, methods have involved autonomously classified PCOS using a number of different machine learning techniques. ML-based approaches involve hand-crafted feature extraction and suffer from low performance issues, which cannot be ignored for the accurate prediction and identification of PCOS. Hence, predicting PCOS using cutting-edge deep learning methods for automated feature engineering with better performance is the prime focus of this study. The proposed method suggests three lightweight (LSTM-based, CNN-based, and CNN-LSTM-based) deep learning models, incorporating SMOTE for dataset balancing to obtain a valid performance. The proposed three models tend to offer an accuracy of 92.04%, 96.59%, and 94.31%, an ROC-AUC of 92.0%, 96.6%, and 94.3%, the number of parameters of 6689, 297, and 13285, and a training time of 67.27 s, 10.02 s, and 18.51 s, respectively. In addition, the DeLong test is also performed to compare AUCs to assess the statistical significance of all three models. Among all three models, the SMOTE + CNN models performs better in terms of accuracy, precision, recall, AUC, number of parameters, training time, DeLong's p-value over the other. Moreover, a performance comparison is also carried out with other state-of-the-art PCOS detection studies and methods, which validates the better performance of the proposed model. Thus, the proposed model provides the greatest performance, which can lead to a reduction in the number of failed pregnancies and help in finding PCOS in the early stages.

A Lightweight Deep Human Activity Recognition Algorithm Using Multiknowledge Distillation

A Lightweight Deep Human Activity Recognition Algorithm Using Multiknowledge Distillation

Lightweight Deep Learning Algorithm for Sorting Medical Waste Embedded System

The recent COVID-19 pandemic has led to an increased number of hospitalized patients, and in some countries, the overwhelming problem has even caused the collapse of the healthcare system. Thus, the associated waste generated and inadequate waste disposal may have deleterious impacts on public health and the surrounding environment. This paper aims to design and implement an automatic medical waste identification and sorting mechanism that can distinguish the items disposed of via a series of image processing procedures. Specifically, the system can classify, sort, and calculate the disposed items based on their visual appearance. To establish this, both software and hardware systems have been devised. Particularly, the vision system for object detection and classification is constructed based on several popular pre-trained convolutional neural networks. Upon verifying the type of waste (i.e., general infection, dangerous infection, and general garbage), an automatic sorting mechanism will be triggered to dispose of the object in the corresponding garbage bin. The experimentation has been validated on a total of self-collected 2025 images from 3 categories, and the best accuracy attained is 99.34% when adopting GoogLeNet as the backbone architecture.

YOLOv8n-WSE-Pest: A Lightweight Deep Learning Model Based on YOLOv8n for Pest Identification in Tea Gardens

YOLOv8n-WSE-Pest: A Lightweight Deep Learning Model Based on YOLOv8n for Pest Identification in Tea Gardens

Attention-Based Light Weight Deep Learning Models for Early Potato Disease Detection

Potato crop has become integral part of our diet due to its wide use in variety of dishes, making it an important food crop. Its importance also stems from the fact that it is one of the cheapest vegetables available throughout the year. This makes it crucial to keep potato prices affordable for developing countries where the majority of the population falls under the middle-income bracket. Consequently, there is a need to develop a robust, effective, and portable technique to detect diseases in potato plant leaves. In this work, an attention-based disease detection technique is proposed. This technique selectively focuses on specific parts of an image which reveal the disease. This technique leverages transfer learning combined with two attention modules: the channel attention module and spatial attention module. By focusing on specific parts of the images, the proposed technique is able to achieve almost similar accuracy with significantly fewer parameters. The proposed technique has been validated using four pre-trained models: DenseNet169, XceptionNet, MobileNet, and VGG16. All of these models are able to achieve almost the same level of training and validation accuracy, around 90–97%, even after reducing the number of parameters by 40–50%. It shows that the proposed technique effectively reduces model complexity without compromising performance.

YOLO-PBESW: A Lightweight Deep Learning Model for the Efficient Identification of Indomethacin Crystal Morphologies in Microfluidic Droplets.

Crystallization is important to the pharmaceutical, the chemical, and the materials fields, where the morphology of crystals is one of the key factors affecting the quality of crystallization. High-throughput screening based on microfluidic droplets is a potent technique to accelerate the discovery and development of new crystal morphologies with active pharmaceutical ingredients. However, massive crystal morphologies' datum needs to be identified completely and accurately, which is time-consuming and labor-intensive. Therefore, effective morphologies' detection and small-target tracking are essential for high-efficiency experiments. In this paper, a new improved algorithm YOLOv8 (YOLO-PBESW) for detecting indomethacin crystals with different morphologies is proposed. We enhanced its capability in detecting small targets through the integration of a high-resolution feature layer P2, and the adoption of a BiFPN structure. Additionally, in this paper, adding the EMA mechanism before the P2 detection head was implemented to improve network attention towards global features. Furthermore, we utilized SimSPPF to replace SPPF to mitigate computational costs and reduce inference time. Lastly, the CIoU loss function was substituted with WIoUv3 to improve detection performance. The experimental findings indicate that the enhanced YOLOv8 model attained advancements, achieving AP metrics of 93.3%, 77.6%, 80.2%, and 99.5% for crystal wire, crystal rod, crystal sheet, and jelly-like phases, respectively. The model also achieved a precision of 85.2%, a recall of 83.8%, and an F1 score of 84.5%, with a mAP of 87.6%. In terms of computational efficiency, the model's dimensions and operational efficiency are reported as 5.46 MB, and it took 12.89 ms to process each image with a speed of 77.52 FPS. Compared with state-of-the-art lightweight small object detection models such as the FFCA-YOLO series, our proposed YOLO-PBESW model achieved improvements in detecting indomethacin crystal morphologies, particularly for crystal sheets and crystal rods. The model demonstrated AP values that exceeded L-FFCA-YOLO by 7.4% for crystal sheets and 3.9% for crystal rods, while also delivering a superior F1-score. Furthermore, YOLO-PBESW maintained a lower computational complexity, with parameters of only 11.8 GFLOPs and 2.65 M, and achieved a higher FPS. These outcomes collectively demonstrate that our method achieved a balance between precision and computational speed.

Application of Lightweight Deep Learning Model-Based Shear Wave Elastic Imaging with Abdominal Probe to Diagnose Prostate Cancer: A Biomedical Approach

We aimed to investigate the diagnostic value of lightweight convolutional neural network (CNN) model abdominal probe shear wave elastic imaging (SWE) in the perineal diagnosis and guided puncture biopsy of prostate cancer (PCa), and to provide reference for the clinical diagnosis of PCa. 100 PCa patients were assigned to group I (malignant) and group II (benign), with 50 cases in each. Ultrasonic elastic imaging based on lightweight convolutional neural network denoising model was adopted for detection. In both systolic and diastolic blood pressure (SBP/DBP), there was not a significant intergroup difference (P > 0.05). The levels of prostate specific antigen (PSA) and its free variant (fPSA) in group II were markedly lower (P < 0.05). Patients in group II had obviously more cystic components and fewer solid components. Patients with hyperechogenicity was more in group II. Patients had clearly fewer irregular margins and outward margin spread in group II. Patients without focal hyperechogenicity and punctate hyperechogenicity was more in group II, and the number of calcifications in group II was less. Patients with type 0 and type I was more and patients with type IIa and type IIb was less in group II. The Emean level of patients in group II was clearly higher, and the Emax level and Esd level of patients in group II were clearly lower. The SI level of patients was clearly lower in group II TTP was higher in group II (P < 0.05). Multivariate logistic regression analysis of abdominal probe SWE for transperineal diagnosis of PCa and guided puncture biopsy showed that internal echoes had the greatest OR and were associated with the occurrence of PCa. Ultrasonic elastic imaging index based on the lightweight convolutional neural network denoising model can be used for the benign and malignant diagnosis of PCa patients.

Lightweight Deep Learning Model Optimization for Medical Image Analysis

ABSTRACTMedical image labeling requires specialized knowledge; hence, the solution to the challenge of medical image classification lies in efficiently utilizing the few labeled samples to create a high‐performance model. Building a high‐performance model requires a complicated convolutional neural network (CNN) model with numerous parameters to be trained which makes the test quite expensive. In this paper, we propose optimizing a lightweight deep learning model with only five convolutional layers using the particle swarm optimization (PSO) algorithm to find the best number of kernel filters for each convolutional layer. For colored red, green, and blue (RGB) images acquired from different data sources, we suggest using stain separation using color deconvolution and horizontal and vertical flipping to produce new versions that can concentrate the representation of the images on structures and patterns. To mitigate the effect of training with incorrectly or uncertainly labeled images, grades of disease could have small variances, we apply a second‐pass training excluding uncertain data. With a small number of parameters and higher accuracy, the proposed lightweight deep learning model optimization (LDLMO) algorithm shows strong resilience and generalization ability compared with most recent research on four MedMNIST datasets (RetinaMNIST, BreastMNIST, DermMNIST, and OCTMNIST), Medical‐MNIST, and brain tumor MRI datasets.

Achieving More with Less: A Lightweight Deep Learning Solution for Advanced Human Activity Recognition (HAR).

Human activity recognition (HAR) is a crucial task in various applications, including healthcare, fitness, and the military. Deep learning models have revolutionized HAR, however, their computational complexity, particularly those involving BiLSTMs, poses significant challenges for deployment on resource-constrained devices like smartphones. While BiLSTMs effectively capture long-term dependencies by processing inputs bidirectionally, their high parameter count and computational demands hinder practical applications in real-time HAR. This study investigates the approximation of the computationally intensive BiLSTM component in a HAR model by using a combination of alternative model components and data flipping augmentation. The proposed modifications to an existing hybrid model architecture replace the BiLSTM with standard and residual LSTM, along with convolutional networks, supplemented by data flipping augmentation to replicate the context awareness typically provided by BiLSTM networks. The results demonstrate that the residual LSTM (ResLSTM) model achieves superior performance while maintaining a lower computational complexity compared to the traditional BiLSTM model. Specifically, on the UCI-HAR dataset, the ResLSTM model attains an accuracy of 96.34% with 576,702 parameters, outperforming the BiLSTM model's accuracy of 95.22% with 849,534 parameters. On the WISDM dataset, the ResLSTM achieves an accuracy of 97.20% with 192,238 parameters, compared to the BiLSTM's 97.23% accuracy with 283,182 parameters, demonstrating a more efficient architecture with minimal performance trade-off. For the KU-HAR dataset, the ResLSTM model achieves an accuracy of 97.05% with 386,038 parameters, showing comparable performance to the BiLSTM model's 98.63% accuracy with 569,462 parameters, but with significantly fewer parameters.

Zero-Shot Proxy with Incorporated-Score for Lightweight Deep Neural Architecture Search

Zero-Shot Proxy with Incorporated-Score for Lightweight Deep Neural Architecture Search

Automatic Face Detection of Farm Images Based on an Enhanced Lightweight Deep Learning Model

In the realm of precise management, artificial intelligence has garnered significant attention and adoption, particularly within the domain of smart agriculture. In modern animal husbandry, animal face detection is conducive to individual identification, expression detection and behavior analysis of animals, and this technological advancement holds immense importance in fostering the advancement of intelligent farming practices. In order to solve the challenge of face detection caused by similar appearance features (color, texture, etc.) and no obvious feature differences between the solid-color goats and sheep in the natural environment, this research introduces a novel approach for face detection by combining the capabilities of YOLOv5 and a convolutional block attention module (CBAM). First, datasets of goats and sheep with different angles, scales and densities were constructed. Second, the basic framework of YOLOv5 was used for object detection. To address the obstacle posed by the limited presence of distinguishing features on the faces of goats and sheep, this study aims to overcome the challenge of extracting informative facial characteristics. The CBAM block was introduced to construct the YOLOv5-CBAM model to improve the feature extraction ability. Finally, 2412 images were selected and divided into training set and verification set according to 8:1. The experimental results of this dataset show that the proposed YOLOv5-CBAM model yielded remarkable results with a precision rate of 0.970, a recall rate of 0.890, a mAP@0.5 score of 0.935, an frames per second (FPS) of 140.845, and a model size of 14.680[Formula: see text]MB. In comparison to other approaches such as Faster R-CNN, SSD, YOLOv3, and YOLOv5, the proposed model demonstrated superior performance in some aspects. In addition, it excelled in both lightweight design and overall effectiveness, and it is well-suited for real-time detection of animal faces in real-world farming settings, ensuring efficient identification and monitoring of animals within practical agricultural environments.

Design and Enhancement of a Fog-Enabled Air Quality Monitoring and Prediction System: An Optimized Lightweight Deep Learning Model for a Smart Fog Environmental Gateway.

Effective air quality monitoring and forecasting are essential for safeguarding public health, protecting the environment, and promoting sustainable development in smart cities. Conventional systems are cloud-based, incur high costs, lack accurate Deep Learning (DL)models for multi-step forecasting, and fail to optimize DL models for fog nodes. To address these challenges, this paper proposes a Fog-enabled Air Quality Monitoring and Prediction (FAQMP) system by integrating the Internet of Things (IoT), Fog Computing (FC), Low-Power Wide-Area Networks (LPWANs), and Deep Learning (DL) for improved accuracy and efficiency in monitoring and forecasting air quality levels. The three-layered FAQMP system includes a low-cost Air Quality Monitoring (AQM) node transmitting data via LoRa to the Fog Computing layer and then the cloud layer for complex processing. The Smart Fog Environmental Gateway (SFEG) in the FC layer introduces efficient Fog Intelligence by employing an optimized lightweight DL-based Sequence-to-Sequence (Seq2Seq) Gated Recurrent Unit (GRU) attention model, enabling real-time processing, accurate forecasting, and timely warnings of dangerous AQI levels while optimizing fog resource usage. Initially, the Seq2Seq GRU Attention model, validated for multi-step forecasting, outperformed the state-of-the-art DL methods with an average RMSE of 5.5576, MAE of 3.4975, MAPE of 19.1991%, R2 of 0.6926, and Theil's U1 of 0.1325. This model is then made lightweight and optimized using post-training quantization (PTQ), specifically dynamic range quantization, which reduced the model size to less than a quarter of the original, improved execution time by 81.53% while maintaining forecast accuracy. This optimization enables efficient deployment on resource-constrained fog nodes like SFEG by balancing performance and computational efficiency, thereby enhancing the effectiveness of the FAQMP system through efficient Fog Intelligence. The FAQMP system, supported by the EnviroWeb application, provides real-time AQI updates, forecasts, and alerts, aiding the government in proactively addressing pollution concerns, maintaining air quality standards, and fostering a healthier and more sustainable environment.

Designing of Lightweight Deep Learning Framework for Plant Disease Detection

Designing of Lightweight Deep Learning Framework for Plant Disease Detection

Detection of QR Code-based Cyberattacks using a Lightweight Deep Learning Model

Detection of QR Code-based Cyberattacks using a Lightweight Deep Learning Model

The Impact of Web Openings on the Shear Behavior of Lightweight Deep Beams

The Impact of Web Openings on the Shear Behavior of Lightweight Deep Beams

Image Forgery Detection Based on Fusion of Light Weight Deep Learning Models

Image Forgery Detection Based on Fusion of Light Weight Deep Learning Models

Lightweight Deep Learning Based Channel Estimation for Extremely Large-Scale Massive MIMO Systems

Lightweight Deep Learning Based Channel Estimation for Extremely Large-Scale Massive MIMO Systems