CNN For Extraction Research Articles

Enhancing Low-Light Medical Imaging through Deep Learning-Based Noise Reduction Techniques

Background/ Objectives: Low-light medical imaging is highly challenging in clinical diagnostics due to increased noise levels that mask or obscure important anatomical details. In this respect, conventional noise reduction methods such as Gaussian filtering and median filtering usually lead to a trade-off between noise suppression and the preservation of important features in an image, thus resulting in poor-quality images. More advanced wavelet-based denoising and Non-Local Means methods exhibit superior noise reduction but remain computationally intensive and introduce artifacts. These challenges come with a need to develop more effective and efficient noise-reduction techniques. Methods: This study proposes an end-to-end deep learning framework for low-light medical image enhancement. We present a comprehensive deep-learning framework to enhance low-light medical images by integrating Convolutional Neural Networks with denoising autoencoders to build a robust noise reduction model. The CNN extracts the feature from the noisy input images, while the autoencoder does so for the reconstruction of clean images through the encoding of a noisy input in a lower-dimensional representation for the reduction of noise while retaining critical information. Findings: This study validates the proposed model through rigorous quantitative metrics such as peak signal-to-noise ratio and structural similarity index. These metrics are designed to provide a full assessment of image quality concerning noise reduction capability and preservation of details related to structure. Our model improves traditional methods in PSNR by about 5 dB on average and SSIM by 0.15, which means better noise reduction and preservation of image details. A comparative analysis of traditional techniques for noise reduction has been included, pointing out the advantages of deep learning approaches. Experimental results depict significant improvements over previous approaches. For instance, the proposed model reduces the noise level by up to 40% and facilitates clear and sharp images by up to 30%. In terms of quantification, these improvements manifest in a PSNR value of 35 dB and an SSIM score of 0.85 compared to 30 dB and 0.70 using traditional techniques. Furthermore, the study illustrates the training dynamics, feature maps, and evolution of images to present the model's incremental learning process. Novelty: This study's findings validate the proposed model's efficacy in enhancing diagnosis accuracy and improving patient outcomes in medical imaging. Keywords: Low-light medical imaging, Noise reduction, Convolutional Neural Networks, Denoising autoencoders, Medical diagnostics

A position-enhanced sequential feature encoding model for lung infections and lymphoma classification on CT images.

Differentiating pulmonary lymphoma from lung infections using CT images is challenging. Existing deep neural network-based lung CT classification models rely on 2D slices, lacking comprehensive information and requiring manual selection. 3D models that involve chunking compromise image information and struggle with parameter reduction, limiting performance. These limitations must be addressed to improve accuracy and practicality. We propose a transformer sequential feature encoding structure to integrate multi-level information from complete CT images, inspired by the clinical practice of using a sequence of cross-sectional slices for diagnosis. We incorporate position encoding and cross-level long-range information fusion modules into the feature extraction CNN network for cross-sectional slices, ensuring high-precision feature extraction. We conducted comprehensive experiments on a dataset of 124 patients, with respective sizes of 64, 20 and 40 for training, validation and testing. The results of ablation experiments and comparative experiments demonstrated the effectiveness of our approach. Our method outperforms existing state-of-the-art methods in the 3D CT image classification problem of distinguishing between lung infections and pulmonary lymphoma, achieving an accuracy of 0.875, AUC of 0.953 and F1 score of 0.889. The experiments verified that our proposed position-enhanced transformer-based sequential feature encoding model is capable of effectively performing high-precision feature extraction and contextual feature fusion in the lungs. It enhances the ability of a standalone CNN network or transformer to extract features, thereby improving the classification performance. The source code is accessible at https://github.com/imchuyu/PTSFE .

Python Based Stress Detection System Using Machine Learning & Algorithm’s

In today's high-pressure world, the need for innovative, non-intrusive stress monitoring solutions is more critical than ever. This paper introduces a sophisticated stress detection system that combines facial expression analysis with machine learning to deliver real-time, continuous stress assessment. Our system employs Haar Cascade classifiers for precise face detection, CNN for feature extraction and utilizes the K-Nearest Neighbors (KNN) algorithm to classify stress-related facial expressions. A significant advantage of our system is its non-intrusive nature, relying solely on visual data, thus eliminating the need for cumbersome wearable sensors. This enhances user comfort and convenience. This paper outlines the design, implementation, and evaluation of our stress detection system, emphasizing its potential applications in workplace wellness, mental health monitoring, and human-computer interaction Key Words: - KNN, Facial Expressions, Machine Learning, Stress Detection, Image Processing, CNN

Alzheimer’s Disease Detection via Multiscale Feature Modelling Using Improved Spatial Attention Guided Depth Separable CNN

Early detection of Alzheimer's disease (AD) is critical due to its rising prevalence. AI-aided AD diagnosis has grown for decades. Most of these systems use deep learning using CNN. However, a few concerns must be addressed to identify AD: a. there is a lack of attention paid to spatial features; b. there is a lack of scale-invariant feature modelling; and c. the convolutional spatial attention block (C-SAB) mechanism is available in the literature, but it exploits limited feature sets from its input features to obtain a spatial attention map, which needs to be enhanced. The suggested model addresses these issues in two ways: through a backbone of multilayers of depth-separable CNN. Firstly, we propose an improved spatial convolution attention block (I-SAB) to generate an enhanced spatial attention map for the multilayer features of the backbone. The I-SAB, a modified version of the C-SAB, generates a spatial attention map by combining multiple cues from input feature maps. Such a map is forwarded to a multilayer of depth-separable CNN for further feature extraction and employs a skip connection to produce an enhanced spatial attention map. Second, we combine multilayer spatial attention features to make scale-invariant spatial attention features that can fix scale issues in MRI images. We demonstrate extensive experimentation and ablation studies using two open-source datasets, OASIS and AD-Dataset. The recommended model outperforms existing best practices with 99.75% and 96.20% accuracy on OASIS and AD-Dataset. This paper also performed a domain adaptation test on the OASIS dataset, which obtained 83.25% accuracy.

Debris Flow Susceptibility Evaluation Based on Multi-level Feature Extraction CNN Model: A Case Study of Nujiang Prefecture, China

Debris Flow Susceptibility Evaluation Based on Multi-level Feature Extraction CNN Model: A Case Study of Nujiang Prefecture, China

An Improved Index Price/Movement Prediction by using Ensemble CNN and DNN Deep Learning Technique

As it knows prediction is always a challenging task in all terms. The goal of any stock prediction method is to develop a robust method for predicting trading price that can be used to improve investment decisions and accurate models. The paper proposes a hybrid model that combines the strengths of deep learning models CNN and DNN, and to develop a comprehensive methodology for the prediction of stock/index prices on Banknifty (NSE Bank), a highly volatile Indian sectorial Index that represents 12 major banks of the country. The hybrid model consists of two main components a CNN for feature extraction and a DNN for regression or classification tasks. In the context of stock price prediction, CNN layers can be used to extract features from input data (such as stock prices and indicators) related to an estimated future value. DNN layer can be used to combine features learned from the CNN layers. Model performance will be evaluated using various metrics including Accuracy, Precision, Recall, Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and R-squared. The method also analyses the impact of various factors on stock prices, including market volatility, economic indicators, and geopolitical events. The achieved accuracy of 97.48% indicates that the model was successful in accurately predicting the stock prices of Bank Nifty. The proposed method is expected to provide investors and financial analysts with a valuable tool for making informed investment decisions.

Fault diagnosis with high accuracy and timeliness for semi‐batch crystallization process based on deep learning with multiple pattern representation

AbstractThe research on chemical process fault diagnosis has made significant progress, but there is still a big gap in its application to complex practical industrial processes. As for the fault diagnosis of batch crystallization processes, the recently‐proposed dynamic time warping–convolutional neural network (DTW‐CNN) model has achieved a great improvement in the fault diagnosis. However, its fault diagnosis rate (FDR) and timeliness of fault diagnosis are still low, and thus, it needs to improve further before being applied to the practical application. In this paper, a multiple pattern representation–convolutional neural network (MPR‐CNN) model is proposed and applied for the fault diagnosis of a semi‐batch crystallization process. The MPR‐CNN model enables the manual extraction of features with four pattern representation algorithms in the data pre‐processing stage, and generates a three‐dimensional matrix which is used as the training sample and input to the CNN for the formal feature extraction and weight learning. An excellent classification performance, with an average FDR of 97.5%, is achieved. This model is also applied for the fault diagnosis of process data within a shorter period of time after the occurrence of faults. The results indicate that the model could make timely fault diagnosis with a highly stable and accurate performance after the occurrence of a fault.

Author identification of literary works based on text analysis and deep learning

With the development of science, speech, picture, and other analysis, problems have been gradually better solved, but the study of Chinese text has been a complex problem to overcome. Chinese text analysis requires not only statistics but also semantic comprehension analysis. Different text types need other language style feature modeling to obtain good recognition results. In this study, we use the deep learning method to construct an automatic text feature extraction model and classify it with the author as a classification label. This study presents a literature author recognition model based on deep learning, which is mainly divided into three phases: text preprocessing, feature extraction, and classification. Each part consists of several small modules or steps. First, we input the corpus to Word2Vec to generate the new word vector. Then, the improved text feature extractor based on CNN and Attention extracts the text features and uses them as the input of the CNN convolution layer. After convolution, the text is combined with bits to get Window Feature Sequence. It is the text feature vector. Next, based on LSTM and Softmax classification output, Window Feature Sequence is used as the input of LSTM to obtain two one-dimensional vectors spliced by concatenate layer. Finally, the result is classified through the fully connected layer, Batch Normalization layer, and Softmax. The performance of the proposed model in recognizing authors of Chinese literature was evaluated using two datasets. In the research process, the data we collected included works of different forms, such as prose and fiction. The research results show that the proposed model can effectively identify author identity. The classification accuracy of our proposed algorithm is significantly better than that of the benchmark model.

QUIZ: An arbitrary volumetric point matching method for medical image registration

Rigid pre-registration involving local–global matching or other large deformation scenarios is crucial. Current popular methods rely on unsupervised learning based on grayscale similarity, but under circumstances where different poses lead to varying tissue structures, or where image quality is poor, these methods tend to exhibit instability and inaccuracies. In this study, we propose a novel method for medical image registration based on arbitrary voxel point of interest matching, called query point quizzer (QUIZ). QUIZ focuses on the correspondence between local–global matching points, specifically employing CNN for feature extraction and utilizing the Transformer architecture for global point matching queries, followed by applying average displacement for local image rigid transformation.We have validated this approach on a large deformation dataset of cervical cancer patients, with results indicating substantially smaller deviations compared to state-of-the-art methods. Remarkably, even for cross-modality subjects, it achieves results surpassing the current state-of-the-art.

OPTIMIZING CROP MANAGEMENT AND PRODUCTION WITH ARTIFICIAL INTELLIGENCE DATA MINING USING 3D CONVOLUTIONAL NEURAL NETWORK FOR PRECISION AGRICULTURE

In precision agriculture, optimizing crop management is essential for sustainable and efficient food production. This research leverages artificial intelligence (AI) data mining techniques, specifically employing a 3D CNN, to enhance precision in wheat crop production. The background underscores the need for advanced technologies in agriculture to address the challenges of increasing global demand and environmental sustainability. The method involves the utilization of 3D CNN for simultaneous feature extraction and prediction, providing a holistic approach to crop monitoring. The contribution of this research lies in the integration of AI-driven data mining to streamline crop management processes, resulting in improved resource utilization and increased yield. The application of 3D CNN demonstrated superior performance in accurately predicting wheat crop production. The model effectively extracted intricate spatial and temporal features, contributing to enhanced decision-making capabilities for farmers. The findings highlight the potential of AI-driven precision agriculture in revolutionizing crop management, offering a scalable solution for sustainable food production.

Speaker recognition system based on MFCC feature extraction CNN architecture

Speaker recognition system based on MFCC feature extraction CNN architecture

A surface electromyography based hand gesture recognition framework leveraging variational mode decomposition technique and deep learning classifier

Deciphering and classifying surface electromyography (sEMG) signals is highly essential in rehabilitation robotics, myoelectric prosthetic control, sign languages and human–computer-interface. Researchers have generally focused on utilizing multi-channel sEMG signals for gesture classification. However, in case of amputees, the residual muscles are limited and the gesture classification needs to be reframed with minimum sEMG channels. Moreover, another key problem in the gesture classification system is the nonlinear and non-stationary nature of sEMG signals, leading to poor generalization ability. Hence, to address the aforementioned problems, this study puts forward a novel deep learning classifier framework which leverages the potentials of variational mode decomposition (VMD) technique and a hybrid convolutional neural network–long short term memory (CNN–LSTM) classifier model to recognize the hand gestures from single channel sEMG signals. Collecting the sEMG signals from forearm muscles of 25 intact subjects for ten functional and grasping actions, this work implements a VMD technique to identify the prominent frequency modes in the sEMG signals. From the decomposed modes of sEMG signals, the prominent intrinsic mode functions (IMFs) are extracted through spectral analysis to minimize the computation burden on the hybrid classifier model. Furthermore, as the muscle contractions result in substantial temporal dependencies, this work exploits the potentials of CNN and LSTM networks and extracts the spatiotemporal features of the sEMG signals for various hand gestures. The experimental results corroborate that the proposed classifier framework can achieve an average classification accuracy of 98.04% and provide 3% improvement in the classification accuracy compared to conventional CNN classifier.

Gesture Recognition of sEMG Signals Based on CNN-GRU Network

To improve the accuracy of surface electromyogram signal (sEMG) gesture recognition algorithm and solve the problem of manually extracting many features, this paper proposes a deep neural network-based gesture recognition method. A neural network integrating CNN and GRU was designed. The 8-channel sEMG data collected by the MYO armband is input to the CNN for feature extraction, and then the obtained feature sequence is input to the GRU network for gesture classification, and finally the recognition result of the gesture category is output. The experimental findings that the proposed technology reaches 76.41% recognition accuracy on the MyoUP dataset. This demonstrates the practicality of the suggested plan.

DPENet: Dual-path extraction network based on CNN and transformer for accurate building and road extraction

DPENet: Dual-path extraction network based on CNN and transformer for accurate building and road extraction

Multi-Method Analysis of Histopathological Image for Early Diagnosis of Oral Squamous Cell Carcinoma Using Deep Learning and Hybrid Techniques.

Oral cancer is a fatal disease and ranks seventh among the most common cancers throughout the whole globe. Oral cancer is a type of cancer that usually affects the head and neck. The current gold standard for diagnosis is histopathological investigation, however, the conventional approach is time-consuming and requires professional interpretation. Therefore, early diagnosis of Oral Squamous Cell Carcinoma (OSCC) is crucial for successful therapy, reducing the risk of mortality and morbidity, while improving the patient's chances of survival. Thus, we employed several artificial intelligence techniques to aid clinicians or physicians, thereby significantly reducing the workload of pathologists. This study aimed to develop hybrid methodologies based on fused features to generate better results for early diagnosis of OSCC. This study employed three different strategies, each using five distinct models. The first strategy is transfer learning using the Xception, Inceptionv3, InceptionResNetV2, NASNetLarge, and DenseNet201 models. The second strategy involves using a pre-trained art of CNN for feature extraction coupled with a Support Vector Machine (SVM) for classification. In particular, features were extracted using various pre-trained models, namely Xception, Inceptionv3, InceptionResNetV2, NASNetLarge, and DenseNet201, and were subsequently applied to the SVM algorithm to evaluate the classification accuracy. The final strategy employs a cutting-edge hybrid feature fusion technique, utilizing an art-of-CNN model to extract the deep features of the aforementioned models. These deep features underwent dimensionality reduction through principal component analysis (PCA). Subsequently, low-dimensionality features are combined with shape, color, and texture features extracted using a gray-level co-occurrence matrix (GLCM), Histogram of Oriented Gradient (HOG), and Local Binary Pattern (LBP) methods. Hybrid feature fusion was incorporated into the SVM to enhance the classification performance. The proposed system achieved promising results for rapid diagnosis of OSCC using histological images. The accuracy, precision, sensitivity, specificity, F-1 score, and area under the curve (AUC) of the support vector machine (SVM) algorithm based on the hybrid feature fusion of DenseNet201 with GLCM, HOG, and LBP features were 97.00%, 96.77%, 90.90%, 98.92%, 93.74%, and 96.80%, respectively.

Transformer-based hierarchical dynamic decoders for salient object detection

Global context and global contrast are crucial clues for Salient Object Detection (SOD) in images. Most advanced SOD methods exploit CNN-based architectures, achieving impressive results. However, these methods have intrinsic limitations in capturing long-range global information since a CNN extracts feature in local sliding windows. In contrast, transformers exploit a self-attention mechanism to extract features, gaining a powerful capability of learning global cues. Nonetheless, a pure transformer-based network consumes a large computational overhead and easily suffers from attention collapse, as it goes deeper. To address this issue, in this paper, we propose a Transformer-based Hierarchical Dynamic Decoder (T-HDDNet) for image salient object detection. Specifically, our T-HDDNet employs the transformer to encode each image patch into multi-level and multi-resolution features based on the long-range dependencies among pixels. To obtain an accurate saliency map of high resolution, we develop a dynamic dual upsampling mechanism to enlarge feature spatial size in a data-driven manner, together with a dynamic feature fusion unit. Ultimately, the hierarchical dynamic decoders built on the basis of these two units are used to attain the final saliency progressively. Extensive experimental results show that the proposed method achieves the best performance on all benchmarks, in comparison with state-of-the-art technologies.

Conv-eRVFL: Convolutional Neural Network Based Ensemble RVFL Classifier for Alzheimer's Disease Diagnosis.

As per the latest statistics, Alzheimer's disease (AD) has become a global burden over the following decades. Identifying AD at the intermediate stage became challenging, with mild cognitive impairment (MCI) utilizing credible biomarkers and robust learning approaches. Neuroimaging techniques like magnetic resonance imaging (MRI) and positron emission tomography (PET) are practical research approaches that provide structural atrophies and metabolic variations. With the help of MRI and PET scans, metabolic and structural changes in AD patients can be visible even ten years before the disease's onset. This paper proposes a novel wavelet packet transform-based structural and metabolic image fusion approach using MRI and PET scans. An eight-layer trained CNN extracts features from multiple layers and these features are fed to an ensemble of non-iterative random vector functional link (RVFL) models. The RVFL network incorporates the s-membership fuzzy function as an activation function that helps overcome outliers. Lastly, outputs of all the customized RVFL classifiers are averaged and fed to the RVFL classifier to make the final decision. Experiments are performed over Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and classification is made over CN vs. AD vs. MCI. The model performance obtained is decent enough to prove the effectiveness of the fusion-based ensemble approach.

Two-Stage Focus Measurement Network with Joint Boundary Refinement for Multifocus Image Fusion

Focus measurement, one of the key tasks in multifocus image fusion (MFIF) frameworks, identifies the clearer parts of multifocus images pairs. Most of the existing methods aim to achieve disposable pixel-level focus measurement. However, the lack of sufficient accuracy often gives rise to misjudgments in the results. To this end, a novel two-stage focus measurement with joint boundary refinement network is proposed for MFIF. In this work, we adopt a coarse-to-fine strategy to gradually achieve block-level and pixel-level focus measurement for producing more fine-grained focus probability maps, instead of directly predicting at the pixel level. In addition, the joint boundary refinement optimizes the performance on the focused/defocused boundary component (FDB) during the focus measurement. To improve feature extraction capability, both CNN and transformer are employed to, respectively, encode local patterns and capture long-range dependencies. Then, the features from two input branches are legitimately aggregated by modeling the spatial complementary relationship in each pair of multifocus images. Extensive experiments demonstrate that the proposed model achieves state-of-the-art performance in both subjective perception and objective assessment.

Enhanced transformer model for video caption generation

AbstractAutomatic Video captioning system is a method of describing the content in a video by analysing its visual aspects with regard to space and time and producing a meaningful caption that explains the video. A decade of research in this area has resulted in a steep growth in the quality and appropriateness of the generated caption compared with the expected result. The research has been driven from the very basic method to most advanced transformer method. Machine generated caption of a video must be adhering to many expected standards. For humans, this task may be a trivial one, however its not the same for a machine to analyse the content and generate a semantically coherent description for it. The caption which is generated in a natural language must also adhere to its lexical and syntactical structure. The video captioning process is a culmination of computer vision and natural language processing tasks. Commencing with template based conventional approach, it has surpassed statistical method, traditional deep learning approaches and is now in the trend of using transformers. This work made an extensive study of the literature and has proposed an improved transformer‐based architecture for video captioning process. The transformer architecture made use of an encoder and decoder model that has two and three sublayers respectively. Multi‐head self attention and cross attention are part of the model which bring about very beneficial results. The decoder is auto‐regressive and uses a masked layer to prevent the model from foreseeing future words in the caption. An enhanced encoder‐decoder Transformer model with CNN for feature extraction has been used in our work. This model captures the long‐range dependencies and temporal relationships more effectively. The model has been evaluated with benchmark datasets and compared with state‐of‐the‐art methods and found to be slightly better in the performance. The performance scores are slightly varying for BLEU, METEOR, ROUGE and CIDEr. Furthermore, we propose the idea of curriculum learning if incorporated can improve the results again.

Aspect Based Sentiment Analysis Marketplace Product Reviews Using BERT, LSTM, and CNN

Bukalapak is one of the largest marketplaces in Indonesia. Reviews on Bukalapak are only in the form of text, images, videos, and stars without any special filters. Reading and analyzing manually makes it difficult for potential buyers. To help with this, we can extract this review by using aspect-based sentiment analysis because an entity cannot be represented by just one sentiment. Several previous research stated that using LSTM-CNN got better results than using LSTM or CNN. In addition, using BERT as word embedding gets better results than using word2vec or glove. For this reason, this study aims to classify aspect-based sentiment analysis from the Bukalapak marketplace with BERT as word embedding and using the LSTM-CNN method, where LSTM is for aspect extraction and CNN for sentiment extraction. Based on testing the LSTM-CNN method, it gets better results than LSTM or CNN. The LSTM-CNN model gets an accuracy of 93.91%. Unbalanced dataset distribution can affect model performance. With the increasing number of datasets used, the accuracy of a model will increase. Classification without using stemming on datasets can increase accuracy by 2.04%.