CNN Classifier Research Articles

Dermatological Decision Support Systems using CNN for Binary Classification

Skin cancer diagnosis, particularly melanoma detection, is an important healthcare concern worldwide. This study uses the ISIC2017 dataset to evaluate the performance of three deep learning architectures, VGG16, ResNet50, and InceptionV3, for binary classification of skin lesions as benign or malignant. ResNet50 achieved the highest training-set accuracy of 81.1%, but InceptionV3 outperformed the other classifiers in generalization with a validation accuracy of 76.2%. The findings reveal the various strengths and trade-offs of alternative designs, providing important insights for the development of dermatological decision support systems. This study contributes to the progress of automated skin cancer diagnosis and establishes the framework for future studies aimed at improving classification accuracy.

Investigating Image Histograms using CNN and Tensor Flow-Based Gender Classification

Investigating Image Histograms using CNN and Tensor Flow-Based Gender Classification

Classifying Aerial Objects Based on Risk: A Machine Learning Approach

The spy balloon that flew across the U.S. in February 2023 posed a serious security threat. US security officials have said this balloon tried to gather intelligence by monitoring sensitive military sites, and as a result, the U.S. government began more closely scrutinizing its airspace to better categorize aerial objects and detect threats. However, the airspace is filled with a myriad of aerial objects, making the problem of classifying and risk determination very challenging. We hypothesize that if we label aerial objects based on the risks they pose, then a Machine Learning algorithm can be made to learn and predict the risks of previously unknown or unseen aerial objects. Currently, there are no known single datasets that contain both old and newer aerial objects, such as drones, planes, etc., nor do datasets have labels to identify the risks associated with the objects. The goal of this research is twofold: 1) We create a new comprehensive dataset that contains traditional and newer aerial objects. We label the objects as high, medium, low, or no risk based on the threat markers on the aerial objects. 2) We use the MobileNetV2 CNN classification algorithm to validate the dataset and provide accurate results. Advancements in this space can potentially help intelligence agencies and security analysts quickly assess developing scenarios and provide a reliable risk assessment for observed aerial objects.

Dual-stream spectral-spatial convolutional neural network for hyperspectral image classification and optimal band selection

Along with the high spectral rich information it provides, one of the difficulties in processing a hyperspectral image is the need for expert knowledge and high-spec hardware to process very high-dimensional data. 3D convolutional neural network(3D CNN), which uses spectral and spatial features together, enables a powerful solution for HSI classification. This study proposes an efficient dual-stream 3D CNN for accurate HSI classification.The proposed method offers effective classification using spectral-spatial features without relying on pre-processing or post-processing. A comparative study of how CNN classification performance is affected by hyperspectral band selection based on deep reinforcement learning (DRL) is presented. Using the most relevant bands in the hyperspectral image is decisive in deep CNN networks without losing information and accuracy. The proposed method was compared with 3D CNN, 3D + 1D CNN, Multiscale 3D deep convolutional neural network (M3D-DCNN), and InceptionV3 algorithms using Indian Pines (IP), Salinas, Pavia Center (PaviaC), Houston 2013 and QUH-Tangdaowan datasets. It achieved 92.43 % overall accuracy (OA) in IP, 95.06 % OA in Salinas dataset, 99.00 % OA in PaviaC dataset, 91.25 % OA in Houston 2013 and 94.87 % OA in QUH-Tangdaowan. Codes are released at: https://github.com/lapistlazuli/DS-3DCNN.

Research on Road Pattern Recognition of a Vision-Guided Robot Based on Improved-YOLOv8

In order to promote the accurate recognition and application of visual navigation robots to the environment, this paper carried out research on the road pattern recognition of a vision-guided robot based on improved YOLOv8 on the basis of road pattern calibration and experimental sampling. First, an experimental system for road image shooting was built independently, and 21 different kinds of road pattern image data were obtained by sampling roads with different weather conditions, road materials, and degrees of damage. Second, the road pattern recognition model based on the classical neural network Resnet 18 was constructed for model training and testing, and the initial recognition of road pattern was realized. Third, the YOLOv8 target detection model was introduced to build the road pattern recognition model based on YOLOv8n, and the model was trained and tested, improving road pattern recognition accuracy and recognition response speed by 3.1% and 200%, respectively. Finally, to further improve the accuracy of road pattern recognition, improvement research was carried out on the YOLOv8n road pattern recognition model based on the C2f-ODConv module, the AWD adaptive weight downsampling module, the EMA attention mechanism, and the collaboration of the three modules. Three network architectures, classical CNN (Resnet 18), YOLOv8n, and improved YOLOv8n, were compared. The results show that four different optimization models can further improve the accuracy of road pattern recognition, among which the accuracy of the improved YOLO v8 road pattern recognition model based on multimodule cooperation is the highest, reaching more than 93%.

Online Detection of Dry Matter in Potatoes Based on Visible Near-Infrared Transmission Spectroscopy Combined with 1D-CNN

More efficient resource utilization and increased crop utilization rate are needed to address the growing demand for food. The efficient quality testing of key agricultural products such as potatoes, especially the rapid testing of key nutritional indicators, has become an important strategy for ensuring their quality and safety. In this study, visible and near infrared (Vis/NIR) transmittance spectroscopy (600–900 nm) was used for the online analysis of multiple quality parameters in potatoes. The study concentrated on comparing three one-dimensional convolutional neural network (1D-CNN) models, specifically, the fine-tuned DeepSpectra, the fine-tuned 1D-AlexNet, and classic CNN, with UVE-PLS (uninformative variable elimination–partial least squares) models. These models utilized spectral data for the real-time detection of dry matter (DM) content in potatoes. To address the challenges posed by limited data from Vis/NIR, this study strategically implemented data augmentation techniques. This approach significantly enhanced the robustness and generalization capabilities of the models. The 1D-AlexNet and DeepSpectra models achieved 0.934 and 0.913 R2P and 0.0603 and 0.0695 g/100 g RMSEP for DM, respectively. Compared to UVE-PLS, the R2P value improved by 21.31% (0.770 to 0.934) for the 1D-AlexNet model and 18.64% (0.770 to 0.913) for the DeepSpectra model. The RMSEP value was reduced by 47.31% (0.114 to 0.0603) for 1D-AlexNet, and 39.30% (0.114 to 0.0695) for the DeepSpectra model. As a result, this study would be helpful for researching the online Vis/NIR transmission determination of potato DM using deep learning. These results highlighted the immense potential of employing specific spectral features in deep-learning models for a more precise and efficient online assessment of agricultural quality. This advancement provided some insight and reference for further contributing to the evolution of more targeted and efficient quality assessment methods in agricultural products.

Multimodal Score Fusion with Sparse Low-rank Bilinear Pooling for Egocentric Hand Action Recognition

With the advent of egocentric cameras, there are new challenges where traditional computer vision is not sufficient to handle this kind of video. Moreover, egocentric cameras often offer multiple modalities that need to be modeled jointly to exploit complimentary information. In this article, we propose a sparse low-rank bilinear score pooling approach for egocentric hand action recognition from RGB-D videos. It consists of five blocks: a baseline CNN to encode RGB and depth information for producing classification probabilities; a novel bilinear score pooling block to generate a score matrix; a sparse low-rank matrix recovery block to reduce redundant features, which is common in bilinear pooling; a one-layer CNN for frame-level classification; and an RNN for video-level classification. We proposed to fuse classification probabilities instead of traditional CNN features from RGB and depth modality, involving an effective yet simple sparse low-rank bilinear score pooling to produce a fused RGB-D score matrix. To demonstrate the efficacy of our method, we perform extensive experiments over two large-scale hand action datasets, namely, THU-READ and FPHA, and two smaller datasets, GUN-71 and HAD. We observe that the proposed method outperforms state-of-the-art methods and achieves accuracies of 78.55% and 96.87% over the THU-READ dataset in cross-subject and cross-group settings, respectively. Further, we achieved accuracies of 91.59% and 43.87% over the FPHA and Gun-71 datasets, respectively.

A novel skin cancer detection model using modified finch deep CNN classifier model

Skin cancer is one of the most life-threatening diseases caused by the abnormal growth of the skin cells, when exposed to ultraviolet radiation. Early detection seems to be more crucial for reducing aberrant cell proliferation because the mortality rate is rapidly rising. Although multiple researches are available based on the skin cancer detection, there still exists challenges in improving the accuracy, reducing the computational time and so on. In this research, a novel skin cancer detection is performed using a modified falcon finch deep Convolutional neural network classifier (Modified Falcon finch deep CNN) that efficiently detects the disease with higher efficiency. The usage of modified falcon finch deep CNN classifier effectively analyzed the information relevant to the skin cancer and the errors are also minimized. The inclusion of the falcon finch optimization in the deep CNN classifier is necessary for efficient parameter tuning. This tuning enhanced the robustness and boosted the convergence of the classifier that detects the skin cancer in less stipulated time. The modified falcon finch deep CNN classifier achieved accuracy, sensitivity, and specificity values of 93.59%, 92.14%, and 95.22% regarding k-fold and 96.52%, 96.69%, and 96.54% regarding training percentage, proving more effective than literary works.

A lightweight dynamic dual-damped wavelet-based convolutional neural network for interpretable bearing fault diagnosis

Wavelet-based convolutional neural networks (CNNS) have attracted widespread attention because they can improve the interpretability of intelligent fault diagnosis methods. However, the fault feature representation capability of typical wavelet-based convolution kernel frameworks must be strengthened to improve the diagnostic accuracy of complex faults. In the meantime, the large number of network parameters leads to high computational costs. To address these issues, a lightweight wavelet-based dynamic CNN, which comprises a dual-damping wavelet-based dynamic CNN (DWDC) block and a discrete wavelet transformation (DWT) enhancement (DWTE) block, is put forward. In the DWDC block, a wavelet convolution layer is initially designed, where a dual-damping wavelet is used as the kernel function to improve the match of the convolution kernel with fault impulses. Subsequently, a dynamic convolution layer with multiple parallel small-size convolutional kernels is designed to screen the fault features instead of a multilayer network structure, thereby greatly reducing the number of network parameters. Finally, the DWTE block is constructed by combining the DWT and residual dense block, and it can mine more fault information from the previously extracted features. The experiments on the variable speed bearing dataset, locomotive bearing dataset with constant speed and the Case Western Reserve University dataset prove that the proposed approach outperforms five classical CNN models and six advanced wavelet-based CNN models. In addition, it can effectively solve the issue of data imbalance because of its powerful feature extraction capability.

Automated medication verification system (AMVS): System based on edge detection and CNN classification drug on embedded systems

A novel automated medication verification system (AMVS) aims to address the limitation of manual medication verification among healthcare professionals with a high workload, thereby reducing medication errors in hospitals. Specifically, the manual medication verification process is time-consuming and prone to errors, especially in healthcare settings with high workloads. The proposed system strategy is to streamline and automate this process, enhancing efficiency and reducing medication errors. The system employs deep learning models to swiftly and accurately classify multiple medications within a single image without requiring manual labeling during model construction. It comprises edge detection and classification to verify medication types. Unlike previous studies conducted in open spaces, our study takes place in a closed space to minimize the impact of optical changes on image capture. During the experimental process, the system individually identifies each drug within the image by edge detection method and utilizes a classification model to determine each drug type. Our research has successfully developed a fully automated drug recognition system, achieving an accuracy of over 95 % in identifying drug types and conducting segmentation analyses. Specifically, the system demonstrates an accuracy rate of approximately 96 % for drug sets containing fewer than ten types and 93 % for those with ten types. This verification system builds an image classification model quickly. It holds promising potential in assisting nursing staff during AMVS, thereby reducing the likelihood of medication errors and alleviating the burden on nursing staff.

Refining Localized Attention Features with Multi-Scale Relationships for Enhanced Deepfake Detection in Spatial-Frequency Domain

The rapid advancement of deep learning and large-scale AI models has simplified the creation and manipulation of deepfake technologies, which generate, edit, and replace faces in images and videos. This gradual ease of use has turned the malicious application of forged faces into a significant threat, complicating the task of deepfake detection. Despite the notable success of current deepfake detection methods, which predominantly employ data-driven CNN classification models, these methods exhibit limited generalization capabilities and insufficient robustness against novel data unseen during training. To tackle these challenges, this paper introduces a novel detection framework, ReLAF-Net. This framework employs a restricted self-attention mechanism that applies self-attention to deep CNN features flexibly, facilitating the learning of local relationships and inter-regional dependencies at both fine-grained and global levels. This attention mechanism has a modular design that can be seamlessly integrated into CNN networks to improve overall detection performance. Additionally, we propose an adaptive local frequency feature extraction algorithm that decomposes RGB images into fine-grained frequency domains in a data-driven manner, effectively isolating fake indicators in the frequency space. Moreover, an attention-based channel fusion strategy is developed to amalgamate RGB and frequency information, achieving a comprehensive facial representation. Tested on the high-quality version of the FaceForensics++ dataset, our method attained a detection accuracy of 97.92%, outperforming other approaches. Cross-dataset validation on Celeb-DF, DFDC, and DFD confirms the robust generalizability, offering a new solution for detecting high-quality deepfake videos.

Emotion recognition with reduced channels using CWT based EEG feature representation and a CNN classifier

Objective. Although emotion recognition has been studied for decades, a more accurate classification method that requires less computing is still needed. At present, in many studies, EEG features are extracted from all channels to recognize emotional states, however, there is a lack of an efficient feature domain that improves classification performance and reduces the number of EEG channels. Approach. In this study, a continuous wavelet transform (CWT)-based feature representation of multi-channel EEG data is proposed for automatic emotion recognition. In the proposed feature, the time-frequency domain information is preserved by using CWT coefficients. For a particular EEG channel, each CWT coefficient is mapped into a strength-to-entropy component ratio to obtain a 2D representation. Finally, a 2D feature matrix, namely CEF2D, is created by concatenating these representations from different channels and fed into a deep convolutional neural network architecture. Based on the CWT domain energy-to-entropy ratio, effective channel and CWT scale selection schemes are also proposed to reduce computational complexity. Main results. Compared with previous studies, the results of this study show that valence and arousal classification accuracy has improved in both 3-class and 2-class cases. For the 2-class problem, the average accuracies obtained for valence and arousal dimensions are 98.83% and 98.95%, respectively, and for the 3-class, the accuracies are 98.25% and 98.68%, respectively. Significance. Our findings show that the entropy-based feature of EEG data in the CWT domain is effective for emotion recognition. Utilizing the proposed feature domain, an effective channel selection method can reduce computational complexity.

Water Pipeline Leakage Detection Based on Coherent φ-OTDR and Deep Learning Technology

Leakage in water supply pipelines remains a significant challenge. It leads to resource and economic waste. Researchers have developed several leak detection methods, including the use of embedded sensors and pressure prediction. The former approach involves pre-installing detectors inside pipelines to detect leaks. This method allows for the precise localization of leak points. The stability is compromised because of the wireless signal strength. The latter approach, which relies on pressure measurements to predict leak events, does not achieve precise leak point localization. To address these challenges, in this paper, a coherent optical time-domain reflectometry (φ-OTDR) system is employed to capture vibration signal phase information. Subsequently, two pre-trained neural network models based on CNN and Resnet18 are responsible for processing this information to accurately identify vibration events. In an experimental setup simulating water pipelines, phase information from both leaking and non-leaking pipe segments is collected. Using this dataset, classical CNN and ResNet18 models are trained, achieving accuracy rates of 99.7% and 99.5%, respectively. The multi-leakage point experiment results indicate that the Resnet18 model has better generalization compared to the CNN model. The proposed solution enables long-distance water-pipeline precise leak point localization and accurate vibration event identification.

Design and Evaluation of CPU-, GPU-, and FPGA-Based Deployment of a CNN for Motor Imagery Classification in Brain-Computer Interfaces

Brain–computer interfaces (BCIs) have gained popularity in recent years. Among noninvasive BCIs, EEG-based systems stand out as the primary approach, utilizing the motor imagery (MI) paradigm to discern movement intentions. Initially, BCIs were predominantly focused on nonembedded systems. However, there is now a growing momentum towards shifting computation to the edge, offering advantages such as enhanced privacy, reduced transmission bandwidth, and real-time responsiveness. Despite this trend, achieving the desired target remains a work in progress. To illustrate the feasibility of this shift and quantify the potential benefits, this paper presents a comparison of deploying a CNN for MI classification across different computing platforms, namely, CPU-, embedded GPU-, and FPGA-based. For our case study, we utilized data from 29 participants included in a dataset acquired using an EEG cap for training the models. The FPGA solution emerged as the most efficient in terms of the power consumption–inference time product. Specifically, it delivers an impressive reduction of up to 89% in power consumption compared to the CPU and 71% compared to the GPU and up to a 98% reduction in memory footprint for model inference, albeit at the cost of a 39% increase in inference time compared to the GPU. Both the embedded GPU and FPGA outperform the CPU in terms of inference time.

Automatic brain-tumor diagnosis using cascaded deep convolutional neural networks with symmetric U-Net and asymmetric residual-blocks

The use of various kinds of magnetic resonance imaging (MRI) techniques for examining brain tissue has increased significantly in recent years, and manual investigation of each of the resulting images can be a time-consuming task. This paper presents an automatic brain-tumor diagnosis system that uses a CNN for detection, classification, and segmentation of glioblastomas; the latter stage seeks to segment tumors inside glioma MRI images. The structure of the developed multi-unit system consists of two stages. The first stage is responsible for tumor detection and classification by categorizing brain MRI images into normal, high-grade glioma (glioblastoma), and low-grade glioma. The uniqueness of the proposed network lies in its use of different levels of features, including local and global paths. The second stage is responsible for tumor segmentation, and skip connections and residual units are used during this step. Using 1800 images extracted from the BraTS 2017 dataset, the detection and classification stage was found to achieve a maximum accuracy of 99%. The segmentation stage was then evaluated using the Dice score, specificity, and sensitivity. The results showed that the suggested deep-learning-based system ranks highest among a variety of different strategies reported in the literature.

Detection and Caption Generation of Image Using Deep Learning

In this research paper, we employ a combination of CNN and LSTM to tackle image caption generation, a task at the intersection of natural language processing and computer vision. We meticulously discuss key concepts in photograph captioning and its methodologies, leveraging resources like the Keras library, numpy, and Jupyter notebooks. Our research also delves into the flickr_dataset and CNN for photo classification, aiming to shed light on the intricate processes underlying image understanding and caption generation. Keywords- CNN ,LSTM, Image captioning, Deep Learning.

A novel SpaSA based hyper-parameter optimized FCEDN with adaptive CNN classification for skin cancer detection

Skin cancer is the most prevalent kind of cancer in people. It is estimated that more than 1 million people get skin cancer every year in the world. The effectiveness of the disease’s therapy is significantly impacted by early identification of this illness. Preprocessing is the initial detecting stage in enhancing the quality of skin images by removing undesired background noise and objects. This study aims is to compile preprocessing techniques for skin cancer imaging that are currently accessible. Researchers looking into automated skin cancer diagnosis might use this article as an excellent place to start. The fully convolutional encoder–decoder network and Sparrow search algorithm (FCEDN-SpaSA) are proposed in this study for the segmentation of dermoscopic images. The individual wolf method and the ensemble ghosting technique are integrated to generate a neighbour-based search strategy in SpaSA for stressing the correct balance between navigation and exploitation. The classification procedure is accomplished by using an adaptive CNN technique to discriminate between normal skin and malignant skin lesions suggestive of disease. Our method provides classification accuracies comparable to commonly used incremental learning techniques while using less energy, storage space, memory access, and training time (only network updates with new training samples, no network sharing). In a simulation, the segmentation performance of the proposed technique on the ISBI 2017, ISIC 2018, and PH2 datasets reached accuracies of 95.28%, 95.89%, 92.70%, and 98.78%, respectively, on the same dataset and assessed the classification performance. It is accurate 91.67% of the time. The efficiency of the suggested strategy is demonstrated through comparisons with cutting-edge methodologies.

SMoGW-based deep CNN: Plant disease detection and classification using SMoGW-deep CNN classifier

Diagnosing plant disease is a major role to reduce adequate losses in yield production, which further leads to economic losses. The various disease control measures are accessible without a proper diagnosis of the disease which results in a waste of expenses and time. The diagnosis of disease using images leads to unsatisfactory results in the prevalent methods due to the image clarity. It is mainly caused by the worst performance of the existing pre-trained image classifiers. This issue can be controlled by the SMoGW-deep convolutional neural network (deep CNN) classifier for the accurate and precise classification of plant leaf disease. The developed method transforms the poor-quality captured images into high quality by the preprocessing technique. The preprocessed input images contain pixels on their dimension and also the value of the threshold is analyzed by the Otsu method by which the particular disease-affected region is extracted based on the image pixels. The region of interest is separated from the other parts of the input leaf image using the K-means segmentation technique. The stored features in the feature vector are fed forward to the deep CNN classifier for training and are optimized by the SMoGW optimization approach. The experiments are done and achieved an accuracy of 94.5% sensitivity of 94.525%, specificity of 94.6%, precision of 95% with 90% of training data and under K-fold training with 95% of accuracy, 95% of sensitivity, 94.1% of specificity, and 92.1% of precession is achieved for the SMoGW-optimized classifier approach that is superior to the prevalent techniques for disease classification and detection. The potential, as well as the capability of the proposed method, is experimentally demonstrated for plant leaf disease classification and identification.

U-Net Segmentation for CNN Classification to Improve the Accuracy of Automatic Prediction of Brain Tumors Using MRI Images

Among various cancers, a brain tumor is a serious one that affects the patient's brain and causes sudden death. Several clinical diagnoses of brain tumors help medical experts provide the proper treatment at the right time; earlier identification and detection of brain tumors are much less. With the increase of cancer patients, managing and diagnosing efficiently with massive data collected is complex. Diagnosing patients with a brain tumor in the earlier stages is also tricky. Medical image processing methods and computer-aided diagnosis methods proposed in earlier works have not provided a high level of accuracy in classification, but the segmentation accuracy was good. Some recent research works have focused on implementing machine learning algorithms for predicting brain tumors for a massive amount of data, where the accuracy still needs to be improved. Machine learning and deep learning algorithms are used to predict brain tumors and their types earlier. With a large amount of data available, the ML and DL models are trained efficiently to make accurate prediction models. The DL models provide better accuracy in processing and predicting medical images than ML models. Some pre-trained deep learning algorithms like VGG16, VGG19, InceptionV3, and ImageNet provide improved accuracy and less computation power to achieve the required results. This paper proposes a CNN algorithm with a VGG16 pre-trained model for detecting brain tumors with MRI images. The input images are segmented using a U-Net model, improving the prediction process's accuracy, and are classified using a CNN model with VGG16, which helps in the efficient and faster prediction of brain tumors from the MRI images. The results show that the proposed model provides better accuracy than the existing ones.

EFFECTIVE CLASSIFICATION OF KNEE OSTEOARTHRITIS USING MILITARY SCRUTOLF OPTIMIZATION-TUNED DCNN CLASSIFIER

Accurately identifying the various types of knee osteoarthritis aids in an accurate diagnosis. The unique kind and severity of osteoarthritis enable medical specialists to offer the best management and treatment plans. Knee osteoarthritis greatly affects the living style of people by causing higher anxiety, mental issues, and health issues. Early treatment is possible because of early prediction, which may improve patient outcomes. Individuals may be able to prevent or postpone the development of knee osteoarthritis symptoms. An efficient categorization method for knee osteoarthritis employing the Military Scrutolf optimization-tuned deep Convolutional Neural Network (MSO-DCNN) and the advancement of study into this crippling disorder and the improvement of diagnosis, therapy, resource allocation, and disease monitoring are all made possible by the CNN classifier. The preprocessing of the data, which is carried out in three parts and involves the Circular Fourier Transform, Histogram Equalization, and Multivariate Linear Function, also contributes significantly to the success of this study. The proposed MSO technique, which improves convergence time and fine-tunes the classifier’s weight and Bias parameters, was built utilizing the features of military dogs and scrutolf to assist in getting increased seeking and hunting qualities. The MSO-tuned DCNN classifier’s adjusted weights and bias to give more effective desired classification results without using up more time or storage. By examining the performance measures and comparing the existing techniques to the MDO-based DCNN, the suggested MSO-DCNN improved based on TP accuracy by 1.33%, f1 measure by 2.9%, precision by 0.8%, and recall by 2.905%.