Convolutional Neural Network Technique Research Articles

Wide-band spectrum sensing with convolution neural network using spectral correlation function

Recognition of signals is a spectrum sensing challenge requiring simultaneous detection, temporal and spectral localization, and classification. In this approach, we present the convolution neural network (CNN) architecture, a powerful portrayal of the cyclo-stationarity trademark, for remote range detection and sign acknowledgment. Spectral correlation function is used along with CNN. In two scenarios, method-1 and method-2, the suggested approach is used to categorize wireless signals without any previous knowledge. Signals are detected and classified simultaneously in method-1. In method-2, the sensing and classification procedures take place sequentially. In contrast to conventional spectrum sensing techniques, the proposed CNN technique need not bother with a factual judgment process or past information on the signs’ separating qualities. The method beats both conventional sensing methods and signal-classifying deep learning networks when used to analyze real-world, over-the-air data in cellular bands. Despite the implementation’s emphasis on cellular signals, any signal having cyclo-stationary properties may be detected and classified using the provided approach. The proposed model has achieved more than 90% of testing accuracy at 15 dB.

Diagnosis of skull-base invasion by nasopharyngeal tumors on CT with a deep-learning approach

PurposeTo develop a convolutional neural network (CNN) model to diagnose skull-base invasion by nasopharyngeal malignancies in CT images and evaluate the model’s diagnostic performance.Materials and methodsWe divided 100 malignant nasopharyngeal tumor lesions into a training (n = 70) and a test (n = 30) dataset. Two head/neck radiologists reviewed CT and MRI images and determined the positive/negative skull-base invasion status of each case (training dataset: 29 invasion-positive and 41 invasion-negative; test dataset: 13 invasion-positive and 17 invasion-negative). Preprocessing involved extracting continuous slices of the nasopharynx and clivus. The preprocessed training dataset was used for transfer learning with Residual Neural Networks 50 to create a diagnostic CNN model, which was then tested on the preprocessed test dataset to determine the invasion status and model performance. Original CT images from the test dataset were reviewed by a radiologist with extensive head/neck imaging experience (senior reader: SR) and another less-experienced radiologist (junior reader: JR). Gradient-weighted class activation maps (Grad-CAMs) were created to visualize the explainability of the invasion status classification.ResultsThe CNN model’s diagnostic accuracy was 0.973, significantly higher than those of the two radiologists (SR: 0.838; JR: 0.595). Receiver operating characteristic curve analysis gave an area under the curve of 0.953 for the CNN model (versus 0.832 and 0.617 for SR and JR; both p < 0.05). The Grad-CAMs suggested that the invasion-negative cases were present predominantly in bone marrow, while the invasion-positive cases exhibited osteosclerosis and nasopharyngeal masses.ConclusionsThis CNN technique would be useful for CT-based diagnosis of skull-base invasion by nasopharyngeal malignancies.

Numerical approximation based on deep convolutional neural network for high‐dimensional fully nonlinear merged PDEs and 2BSDEs

This paper proposes two efficient approximation methods to solve high‐dimensional fully nonlinear partial differential equations (NPDEs) and second‐order backward stochastic differential equations (2BSDEs), where such high‐dimensional fully NPDEs are extremely difficult to solve because the computational cost of standard approximation methods grows exponentially with the number of dimensions. Therefore, we consider the following methods to overcome this difficulty. For the merged fully NPDEs and 2BSDEs system, combined with the time forward discretization and ReLU function, we use multiscale deep learning fusion and convolutional neural network (CNN) techniques to obtain two numerical approximation schemes, respectively. Finally, three practical high‐dimensional test problems involving Allen–Cahn, Black–Scholes–Barenblatt, and Hamilton–Jacobi–Bellman equations are given so that the first proposed method exhibits higher efficiency and accuracy than the existing method, while the second proposed method can extend the dimensionality of the completely NPDEs–2BSDEs system over 400 dimensions, from which the numerical results highlight the effectiveness of proposed methods.

Predicting Cyclone Michaung's Wrath: Leveraging Deep Learning Technique for Intensity and Track Forecasting

Tropical cyclones pose significant threats to coastal regions, necessitating accurate and timely monitoring systems for effective disaster management. In this study, Convolutional Neural Networks (CNN) is used to identify and track the tropical cyclone Michaung using a comprehensive dataset comprising INSAT3D captured INFRARED and RAW Cyclone Imagery over the Indian Ocean from 2012 to 2021. The raw data, sourced from the MOSDAC server, has been meticulously labeled by timestamp and corresponding coordinates on the intensity-time graph of each cyclone directory. Our methodology involves training the CNN model on this extensive dataset and subsequently validating its efficacy by predicting satellite images of cyclone Michaung obtained from the MODIS satellite. The integration of both INSAT3D and MODIS imagery enhances the robustness of our model, providing a more comprehensive understanding of cyclone dynamics. Results indicate a high level of accuracy in cyclone identification, showcasing the potential of CNN techniques in satellite image analysis for cyclone monitoring. The approach not only contributes to the field of meteorology but also establishes a framework for the utilization of diverse satellite datasets in training neural networks for real-time cyclone detection and tracking. This research represents a significant step toward leveraging advanced machine learning techniques to enhance the efficiency and accuracy of tropical cyclone monitoring systems, ultimately aiding in early warning and disaster preparedness efforts.

Deep convolutional neural networks with Bee Collecting Pollen Algorithm (BCPA)-based landslide data balancing and spatial prediction

Predicting the landslide-prone area is critical for various applications, including emergency response, land planning, and disaster mitigation. There needs to be a thorough landslide inventory in current studies and appropriate sampling uncertainty issues. Landslide risk mapping has expanded significantly as machine learning techniques have developed. However, one of the primary issues in Landslide Prediction is data imbalance (DI). This is problematic since it is challenging or expensive to generate an accurate inventory map of landslides based on previous data. This study proposes a novel landslide prediction method using Generative Adversarial Networks (GAN) for generating the synthetic data, Synthetic Minority Oversampling Technique (SMOTE) for overcoming the data imbalance problem, and Bee Collecting Pollen Algorithm (BCPA) for feature extraction. Combining 184 landslides and ten criteria, including topographic wetness index (TWI), aspect, distance from the road, total curvature, sediment transport index (STI), height, slope, stream, lithology, and slope length, a geographical database was produced. The data was generated using GAN, a Deep Convolutional Neural Network (DCNN) technique to populate the dataset. The proposed DCNN-BCPA approach findings were merged with current machine learning methods such as Random Forests (RF), Artificial Neural Networks (ANN), k-Nearest Neighbours (k-NN), Decision Trees (DT), Support Vector Machine (SVM), logistic regression (LR). The model’s accuracy, precision, recall, f-score, and RMSE were measured using the following metrics: 92.675%, 96.298%, 90.536%, 96.637%, and 45.623%. This study suggests that harmonizing landslide data may have a substantial impact on the predictive capabilities of machine learning models.

SSC-SFN: spectral-spatial non-local segment federated network for hyperspectral image classification with limited labeled samples

ABSTRACT Hyperspectral image (HSI) classification methods based on deep learning (DL) have performed well in numerous investigations. Although many modified superpixel-wise neural networks are utilized to enhance spatial information, their ability to mine spectral information in graph structures is insufficient. Moreover, single classifier approaches are unable to extract adequate spatial and spectral information simultaneously. For the classification of large-scale research areas, many works have relied on the use of a large number of labeled samples, leading to low efficiency and weak generalization. To address these issues, an effective spectral-spatial HSI classification approach based on spectral-spatial non-local segment federated network (SSC-SFN) was developed in this study. In this framework, deconvolution is employed to recover the data size, while the lost spatial information is replaced by up-pooling. The spectral dimensional features are updated through the generation of non-Euclidean graph structures and the non-local segment smoothing technique. The convolutional neural network and graph convolutional network techniques are coupled to exploit the available spectral and spatial structure information fully. Extensive experimental results obtained using four public benchmark datasets show that the classification accuracy of SSC-SFN can exceed 90% for large-scale HSIs with limited samples.

An AI-enabled secure framework for enhanced elder healthcare

The healthcare sector has been revolutionized by Information and Communication Technology (ICT), leading to increased patient life expectancy and reduced healthcare costs. In the realm of cutting-edge research, Digital Twins (DT) technology holds great promise for improving healthcare. This study introduces a new approach to securing adult healthcare data by combining the Internet of Things (IoT), DT technology, and blockchain technology. Specifically, a context-aware physical activity monitoring framework is proposed for adult healthcare, incorporating an Artificial Intelligence-inspired Convolutional Neural Network (CNN) technique to analyze real-time abnormalities in the elderly. The CNN is trained on a large dataset, learning to recognize patterns and anomalies associated with abnormal conditions or behaviors in the elderly. The framework also ensures data security through the advanced features of blockchain, employing the Reputation-based Byzantine Fault Tolerance (RBFT) method for the consortium network. Experimental simulations validate the proposed technique, demonstrating its superior efficacy compared to state-of-the-art techniques. The results exhibit betters statistical measures of Delay Latency (121.23s), Prediction Efficacy (Precision (93.357%), Specificity (93.58%), Sensitivity (94.15%), and F-measure (94.58%)), Reliability (89.62%), and Stability (71%).

Performance analysis of hybrid deep learning framework using a vision transformer and convolutional neural network for handwritten digit recognition

Digitization created a demand for highly efficient handwritten document recognition systems. A handwritten document consists of digits, text, symbols, diagrams, etc. Digits are an essential element of handwritten documents. Accurate recognition of handwritten digits is vital for effective communication and data analysis. Various researchers have attempted to address this issue with modern convolutional neural network (CNN) techniques. Even after training, CNN filter weights remain unchanged despite the high identification accuracy. As a result, the process cannot flexibly adapt to input changes. Hence computer vision researchers have recently become interested in Vision Transformers (ViTs) and Multilayer Perceptrons (MLPs). The shortcomings of CNNs gave rise to a hybrid model revolution that combines the best elements of the two fields. This paper analyzes how the hybrid convolutional ViT model affects the ability to recognize handwritten digits. Also, the real-time data contains noise, distortions, and varying writing styles. Hence, cleaned and uncleaned handwritten digit images are used for evaluation in this paper. The accuracy of the proposed method is compared with the state-of-the-art techniques, and the result shows that the proposed model achieves the highest recognition accuracy. Also, the probable solutions for recognizing other aspects of handwritten documents are discussed in this paper.•Analyzed the effect of convolutional vision transformer on cleaned and real-time handwritten digit images.•The model's performance improved with the implication of cross-validation and hyper-parameter tuning.•The results show that the proposed model is robust, feasible, and effective on cleaned and uncleaned handwritten digits.

Designing of VehiNet Using Convolutional Neural Networks and Deep Learning Techniques

Traffic congestion has become a critical issue in metropolitan areas, inflicting significant hardships on individuals on a daily basis. This adverse situation poses multifaceted challenges, including increased air pollution, heightened fuel consumption, and compromised road safety. Deep learning algorithms, encompassing both Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) have showcased remarkable performance in areas such as computer vision, natural language processing, healthcare, finance, and autonomous systems. This research paper proposes a novel methodology to develop a vehicle detection model - VehiNet, which can subsequently be refined to create an automated traffic signal system. The study explores the effectiveness of various CNN, RNN, and deep learning algorithms and techniques in accomplishing this objective. The dataset picked for the study in addition to being compiled from internet resources, was also painstakingly assembled manually using a variety of methods to collect over 2000 photographs from various angles, lighting conditions, and locations within Bengaluru city. The main motive is to apply CNN, RNN, and other Deep Learning classification techniques for object detection and classification of Indian vehicles and see how well these deep learning algorithms and techniques affect prediction efficiency. This research stands out from others and makes its novelty clear thanks to the carefully collected dataset and the detailed analysis of the methodologies.

Transcription Factor Binding Site Prediction Using CnNet Approach.

Controlling the gene expression is the most important development in a living organism, which makes it easier to find different kinds of diseases and their causes. It's very difficult to know what factors control the gene expression. Transcription Factor (TF) is a protein that plays an important role in gene expression. Discovering the transcription factor has immense biological significance, however, it is challenging to develop novel techniques and evaluation for regulatory developments in biological structures. In this research, we mainly focus on 'sequence specificities' that can be ascertained from experimental data with 'deep learning' techniques, which offer a scalable, flexible and unified computational approach for predicting transcription factor binding. Specifically, Multiple Expression motifs for Motif Elicitation (MEME) technique with Convolution Neural Network (CNN) named as CnNet, has been used for discovering the 'sequence specificities' of DNA gene sequences dataset. This process involves two steps: a) discovering the motifs that are capable of identifying useful TF binding site by using MEME technique, and b) computing a score indicating the likelihood of a given sequence being a useful binding site by using CNN technique. The proposed CnNet approach predicts the TF binding score with much better accuracy compared to existing approaches. The source code and datasets used in this work are available at https://github.com/masoodbai/CnNet-Approach-for-TFBS.git.

Enhanced Face Detection in Videos Based on Integrating Spatial Features (LBP, CS-LBP) with CNN Technique

Face detection is a crucial aspect of computer vision and image processing, in order to enable the automatic detection and identification of human faces in video streams, face detection is an essential component of computer vision and image processing. Applications for facial recognition, video analytics, security systems, and surveillance all depend on it. Face identification techniques face many obstacles and issues, such as positional fluctuations, illumination changes, resolution and scale issues, facial emotions, and cosmetics. Robust algorithms are required for efficient face detection. This field looks at the feature extraction process using a variety of techniques. These consist of the center symmetric local binary patterns (CS_LBP) approach and the local binary patterns (LBP) method. The YouTube Face database provided the video frames that we used for our study. In order to train the convolutional neural network (CNN) to detect human faces in the video and draw a bounding box around them. The experimental results of the suggested approaches show that. The accuracy rate was 94% higher with the LBP techniques. However, the CS_LBP technique showed the best level of accuracy in both face detection and face rectangle recognition, with an accuracy rate of 95%.

Hand gesture recognition based on CNN and YOLO techniques

Communication is essential for humanity today and in the past. However, some individuals lack verbal communication due to their innate disability and physical losses from accidents. There are sign-language communication methods developed for such people to communicate. Artificial intelligence solutions are offered to remove the disadvantaged situations of people with disabilities due to communication in daily life. Nowadays, rapidly developing image processing and artificial intelligence methods are proper solutions for the problem focused on in this study. Convolution neural network techniques, which have become very popular recently, offer solutions to many problems. On the other hand, the YOLO algorithm shows very high performance in real-time object detection. In this study, we proposed a method for identifying the alphabets which each gesture delivers. This work studied hand detection on images and classification according to hand movements. The American Sign Language (ASL) standard was used as the sign language. The most recent version of YOLO, known as YOLOv5x, is used for gesture detection. Concentrating on the Static Sign-language problem, a study was conducted on the definition of hand movements. The letters “J” and “Z” are not included in the data set because movable hand signals are required. Apart from these two letters, a total number of 24 letters are classified. The proposed model achieved a training performance of 99.45% mAP@.5. Moreover, the proposed model has a performance of 97.9% mAP@.5 on the test dataset. The results demonstrate that the model's object detection performance is excellent. A statistical analysis of the training time shows that the training time has been drastically decreased, 4.5 hours with the current model as compared to the existing models in the literature.

Improvement of Brain Tumor Categorization using Deep Learning: A Comprehensive Investigation and Comparative Analysis

A brain tumor is a critically severe health disorder that requires an accurate and timely diagnosis for effective treatment. Advances in medical imaging and deep learning methods have shown potential for enhancing the identification and categorization of brain cancers throughout the years. In the present research, our study compares the accuracy of eight different deep learning models in the classification of brain tumors employing brain MRI data that involve Densenet121, EfficientNet B7, InceptionResNetV2, Inception_V3, RestNet50V2, VGG16, VGG19, and Xception. To further improve performance, we propose integrating a hybrid deep learning technique. Efficient and timely diagnosis of brain tumors is critical for the treatment of patients, and our study aims to achieve high recall, accuracy, and F1-score in this context. With a precision of 96.63%, our innovative convolutional neural network (CNN) technique achieved outstanding results in brain tumor diagnosis. Also, our study investigates the unique capabilities of certain models, such as VGG19 and InceptionResNetV2, and their possibilities for better glioma tumor detection efficiency. Our results, in particular, provide insight into possible uses of deep learning frameworks, including the integration of hybrid techniques, in medical imaging, offering an innovative approach for increased brain tumor detection and identification.

Software Reliability Analysis by Using the Bidirectional Attention Based Zeiler-Fergus Convolutional Neural Network

Software quality assurance relies heavily on software reliability as one of its primary metrics. Numerous studies have been conducted to identify the software reliability. Improved software dependability may be studied using a triangular approach that includes software modeling, measurement, and improvement. Each of these steps is critical to the development of a solid software system. Improved accuracy in calculating dependability is critical to managing the quality of software. It has been discovered that deep learning algorithms are excellent methods of assessing many aspects of software dependability. Software systems contain distinct characteristics that can be addressed using deep learning techniques. In this study, a deep-learning-based bidirectional attention-based Zeiler-Fergus convolutional neural network (BA-ZFCNN) technique has been suggested to assess software dependability. In the beginning, the data were standardized by using the scalable error splash method. This approach was then used to extract the software fault-related characteristics using hypertuned evolutionary salp swarm optimization (HESSO). Finally, the Zeiler-Fergus convolutional neural network based on bidirectional attention (BA-ZFCNN) may be used to assess software dependability. The suggested method is used to forecast how many defects or failures there are in a software product. AR1 software defect data is widely used to test the effectiveness of deep learning and traditional machine learning methods. The experimental results reveal that the proposed methods accuracy (96.7%) is higher than the current techniques accuracy.

Tomato Leaf Disease Detection Using CNN

One of the structure of economic development is farming involved with niche skills and technologies. More than 25% of total tomato crop production is lost annually because of various plant diseases. The farmers who grow tomatoes face huge economic losses every year, often due to various diseases that can infect tomatoes. The work carried aims to identify these diseases early and accurately, so can be informed well before the damage, which can minimize the waste. Convolution neural network (CNN) techniques, subset of Machine Learning (ML) are demonstrated to be very efficient for image datasets of various complex problems. Specifically, the work is focused to build and train a customized CNN model to classify the leaf images. Here we are using advanced deep learning architectures AlexNet and VGGNet-16 to recognize various diseases from image datasets collected from agricultural sources to develop models. Comparative analysis has resulted an improvement in accuracy by using deep learning architectures and CNN models. These models are responsible for helping to solve distribution problems, checking whether a leaf is healthy or not and, if so, what disease it is. Disease detected early and treated quickly minimizes the cost and improves the quality and quantity of the crop produced.

Research on Pedestrian Re-identification Techniques in Dynamic Scenes Using Convolutional Neural Networks

Abstract Pedestrian re-recognition is the process of retrieving pedestrians with the same identity information as a given pedestrian from a cross-domain view candidate image dataset or a non-overlapping surveillance video sequence using computer vision techniques. The goal of this paper is to use convolutional neural network techniques to re-recognize pedestrians in dynamic scenes. Through the use of convolutional calculations, activation function selection, and other techniques, this paper provides basic technical support for the research of pedestrian re-recognition technology. A Siamese network is obtained by applying convolutional neural networks to pedestrian recognition as the main discriminative model for subsequent research. In order to effectively solve the problem of occlusion, illumination, and other possible interference with the recognition effect in dynamic scenes, this paper adopts the image enhancement method of random erasure and introduces the attention mechanism to improve the robustness of the model to the occlusion of pedestrian images. Through the examination of the model on the dataset of the average accuracy mean (MAP) and other indicators and the actual application in the construction site and other scenes, it is proved that the pedestrian re-recognition model used in this paper has a more significant recognition performance compared with other models, and can still maintain more than 80% of the accuracy rate under the application of dynamic and complex scenes.

Enhancing Generalizability in Biomedical Entity Recognition: Self-Attention PCA-CLS Model.

One of the primary tasks in the early stages of data mining involves the identification of entities from biomedical corpora. Traditional approaches relying on robust feature engineering face challenges when learning from available (un-)annotated data using data-driven models like deep learning-based architectures. Despite leveraging large corpora and advanced deep learning models, domain generalization remains an issue. Attention mechanisms are effective in capturing longer sentence dependencies and extracting semantic and syntactic information from limited annotated datasets. To address out-of-vocabulary challenges in biomedical text, the PCA-CLS (Position and Contextual Attention with CNN-LSTM-Softmax) model combines global self-attention and character-level convolutional neural network techniques. The model's performance is evaluated on eight distinct biomedical domain datasets encompassing entities such as genes, drugs, diseases, and species. The PCA-CLS model outperforms several state-of-the-art models, achieving notable F1-scores, including 88.19% on BC2GM, 85.44% on JNLPBA, 90.80% on BC5CDR-chemical, 87.07% on BC5CDR-disease, 89.18% on BC4CHEMD, 88.81% on NCBI, and 91.59% on the s800 dataset.

Transformer Inrush Current and Internal Fault Discrimination Using Multitypes of Convolutional Neural Network Techniques

Transformer Inrush Current and Internal Fault Discrimination Using Multitypes of Convolutional Neural Network Techniques

Performance Evaluation of Deep Learning Techniques in The Detection of IOT Malware

Internet of Things (IoT) equipment is rapidly being used in a variety of businesses and for a variety of reasons (for example, sensing and collecting data from the environment in both public and military settings). Because of their expanding involvement in a wide range of applications and their rising computational and processing capabilities, they are a viable attack target for malware tailored to infect specific IoT devices. This study investigates the potential of detecting IoT malware using different deep learning techniques: the classic feedforward neural network (FNN), convolutional neural networks (CNN), long short-term memory (LSTM), and recurrent neural networks (RNN). The proposed method analyses the execution operation codes of IOT app sequences using modern NLP (natural language processing) methods. The current work utilized an IoT application dataset with 500 malware (collected from the IOTPOT dataset) and 500 goodware samples to train the proposed algorithms. The trained model is tested against 2971 fresh IoT malware and goodware samples. The samples were input into deep learning models, and performance metrics were obtained. The results demonstrate that the RNN model had the best accuracy (99.19%) in detecting fresh malware samples. On the other hand, the results were compared by the time required for training; the CNN model shows that it could achieve high accuracy (98.05%) with less training time. A comparison with various deep learning classifiers demonstrates that the RNN and CNN techniques produce the best results.

Optimized deep learning driven signal detection and adaptive channel estimation in underwater acoustic IoT networks

SummaryNowadays, multiple input multiple outputs with orthogonal frequency division multiplexing (MIMO‐OFDM) provide better communication performance that can be applied to the fast‐growing Internet of Things (IoTs). In underwater IoT, information fades away rapidly due to varying water conditions. Therefore, the MIMO model can be applied to the OFDM acoustic system, enabling high‐speed data transmission without affecting the channel effectively. However, detecting the underwater signal and estimating the channel is highly necessary for enhancing underwater acoustic communication (UWAC). Recently, many techniques have been introduced for effectively performing signal detection and channel estimation. However, those techniques face high time complexity due to increased channel interferences and noises during data transmission. Hence, this article brings a novel technique for SD and CE for the UWAC‐IoT‐enabled MIMO‐OFDM system. An adaptive recursive least square (ARLS) technique is proposed in this study for CE that aids in evaluating the acoustic channel parameters effectively. For performing SD, a bi‐directional deep pelican convolutional neural network (BDPCNN) technique is introduced to ensure the presence and absence of signals at the receiver end. The proposed method is analyzed via the MATLAB platform, and the performances are analyzed under different water types like turbid water, coastal water, clear ocean water, and pure seawater. Different performance metrics like bit error rate (BER), mean square error (MSE), energy efficiency (EE), and time complexity are analyzed with different existing techniques. The experimental section obtains the BER of 0.0086, 0.013, 0.017, and 0.021 for turbid, coastal, clear, and pure seawater, respectively.