CNN For Detection Research Articles

A novel multi-information fusion CNN for defect detection in laser soldering of SAC305

Identification of laser soldering of lead-free solder Sn-3.0Ag-0.5Cu (SAC305) in electronic packaging was still an enormous challenge. It was difficult to detect defects in large-scale production. This work proposed an identification model based on multi-information fusion convolutional neural network (MIFCNN) for inspecting laser soldering process. In this method, the forty images in chronological order and the temperature data were combined as the input to be utilized in detecting defects. The results demonstrated that MIFCNN had best accuracy for three types of joints with accuracy of 98.28 % due to the combination of images and temperature information. The ICNN and TCNN had poor recognition accuracy for the warpage defect with 73.9 % and the poor wetting defect with 66.5 %, respectively. This was because the images and temperature information were the key to identifying the poor wetting defects and warpage defects, respectively. The poor wetting defect could be recognized by difference of contact angle, while the warpage defect could be significantly detected by maximum temperature. This work could help detecting defects of laser soldering in the actual production and widen the application of MIFCNN in the field of laser soldering.

AUDIOSIGNAL BASED EVENT DETECTION USING DEEP LEARNING TECHNIQUES

Deep learning has garnered significant interest from researchers for performing pattern recognition tasks. In particular, the detection of events based on audio signals and the recognition of natural sounds in the environment stand out. The DCASE challenge – Detection and Classification of Acoustic Scenes and Events – has further highlighted the efficiency of deep learning in accomplishing these tasks. This paper reviews the works of other researchers that applied various deep learning techniques to detect emergency events based on audio signals. It focuses on the complexity and specific challenges of recognizing polyphonic sound-based events. The use and structures of neural networks are presented, with an emphasis on the application of CNN and RNN for event detection based on audio signals. Evaluation metrics and an overview of datasets are also provided.

Stress and Mental Health Detection using Machine Learning

Abstract: The precise determination of psychological health and stress levels substantial involvement in the course of a patient's therapy, Especially during the initial phases of the condition, it's crucial to remain vigilant as there's a potential for health risks to emerge for the patient. Deep Learning (DL) has emerged as a prevalent technique utilized to detect stress and mental health conditions, aiding in their identification. in a timely manner. Here, we provide mental health prediction utilizing KNN, Random Forest, and Logistic Regression whereas CNN for stress detection to aid in the timely identification of the illness. The website we created compiles the patient/person dataset. It aids When forecasting the outcome of the event, patient's or person's mental health and stress levels once the necessary training procedures have been completed.

A Framework of Grasp Detection and Operation for Quadruped Robot with a Manipulator

Quadruped robots equipped with manipulators need fast and precise grasping and detection algorithms for the transportation of disaster relief supplies. To address this, we developed a framework for these robots, comprising a Grasp Detection Controller (GDC), a Joint Trajectory Planner (JTP), a Leg Joint Controller (LJC), and a Manipulator Joint Controller (MJC). In the GDC, we proposed a lightweight grasp detection CNN based on DenseBlock called DES-LGCNN, which reduced algorithm complexity while maintaining accuracy by incorporating UP and DOWN modules with DenseBlock. For JTP, we optimized the model based on quadruped robot kinematics to enhance wrist camera visibility in dynamic environments. We integrated the network and model into our homemade robot control system and verified our framework through multiple experiments. First, we evaluated the accuracy of the grasp detection algorithm using the Cornell and Jacquard datasets. On the Jacquard dataset, we achieved a detection accuracy of 92.49% for grasp points within 6 ms. Second, we verified its visibility through simulation. Finally, we conducted dynamic scene experiments which consisted of a dynamic target scenario (DTS), a dynamic base scenario (DBS), and a dynamic target and base scenario (DTBS) using an SDU-150 physical robot. In all three scenarios, the object was successfully grasped. The results demonstrate the effectiveness of our framework in managing dynamic environments throughout task execution.

ACCIDENT DETECTION USING TENSOR FLOW AND CNN

Accident detection is a critical aspect of road safety management, with timely identification and response being paramount to minimizing casualties and damage. In this project, a comprehensive approach to accident detection utilizing Deep learning techniques is proposed. The system aims to automatically detect accidents in real time using information obtained from diverse sources like video feeds, sensor inputs, and audio signals. The project involves the development and implementation of Deep learning models trained on labeled datasets containing examples of accident and non-accident scenarios. Supervised learning techniques like classification, regression and advanced neural network architecture like convolution, recurrent neural network are considered to effectively process and analyze the data. The deployed system continuously monitors the environment, processing incoming data streams to identify patterns indicative of accidents. Upon detection, the system triggers appropriate response mechanisms, such as alerting emergency services or nearby vehicles, facilitating swift intervention. The project aims to contribute to road safety initiatives by providing a scalable and efficient solution for accident detection. Additionally, the insights gained from the data collected by the system can inform policymakers and urban planners in implementing measures to prevent accidents and improve overall road safety. Through this project, the students gain valuable experience in applying Deep learning techniques to address real-world challenges and contribute to societal welfare.

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.

A Novel Hybrid Vision Transformer CNN for COVID-19 Detection from ECG Images

The emergence of the novel coronavirus in Wuhan, China since 2019, has put the world in an exotic state of emergency and affected millions of lives. It is five times more deadly than Influenza and causes significant morbidity and mortality. COVID-19 mainly affects the pulmonary system leading to respiratory disorders. However, earlier studies indicated that COVID-19 infection may cause cardiovascular diseases, which can be detected using an electrocardiogram (ECG). This work introduces an advanced deep learning architecture for the automatic detection of COVID-19 and heart diseases from ECG images. In particular, a hybrid combination of the EfficientNet-B0 CNN model and Vision Transformer is adopted in the proposed architecture. To our knowledge, this study is the first research endeavor to investigate the potential of the vision transformer model to identify COVID-19 in ECG data. We carry out two classification schemes, a binary classification to identify COVID-19 cases, and a multi-class classification, to differentiate COVID-19 cases from normal cases and other cardiovascular diseases. The proposed method surpasses existing state-of-the-art approaches, demonstrating an accuracy of 100% and 95.10% for binary and multiclass levels, respectively. These results prove that artificial intelligence can potentially be used to detect cardiovascular anomalies caused by COVID-19, which may help clinicians overcome the limitations of traditional diagnosis.

A Cloud-Based Deep Learning Framework for Downy Mildew Detection in Viticulture Using Real-Time Image Acquisition from Embedded Devices and Drones

In viticulture, downy mildew is one of the most common diseases that, if not adequately treated, can diminish production yield. However, the uncontrolled use of pesticides to alleviate its occurrence can pose significant risks for farmers, consumers, and the environment. This paper presents a new framework for the early detection and estimation of the mildew’s appearance in viticulture fields. The framework utilizes a protocol for the real-time acquisition of drones’ high-resolution RGB images and a cloud-docker-based video or image inference process using object detection CNN models. The authors implemented their framework proposition using open-source tools and experimented with their proposed implementation on the debina grape variety in Zitsa, Greece, during downy mildew outbursts. The authors present evaluation results of deep learning Faster R-CNN object detection models trained on their downy mildew annotated dataset, using the different object classifiers of VGG16, ViTDet, MobileNetV3, EfficientNet, SqueezeNet, and ResNet. The authors compare Faster R-CNN and YOLO object detectors in terms of accuracy and speed. From their experimentation, the embedded device model ViTDet showed the worst accuracy results compared to the fast inferences of YOLOv8, while MobileNetV3 significantly outperformed YOLOv8 in terms of both accuracy and speed. Regarding cloud inferences, large ResNet models performed well in terms of accuracy, while YOLOv5 faster inferences presented significant object classification losses.

Quantitative Detection of Pipeline Cracks Based on Ultrasonic Guided Waves and Convolutional Neural Network.

In this study, a quantitative detection method of pipeline cracks based on a one-dimensional convolutional neural network (1D-CNN) was developed using the time-domain signal of ultrasonic guided waves and the crack size of the pipeline as the input and output, respectively. Pipeline ultrasonic guided wave detection signals under different crack defect conditions were obtained via numerical simulations and experiments, and these signals were input as features into a multi-layer perceptron and one-dimensional convolutional neural network (1D-CNN) for training. The results revealed that the 1D-CNN performed better in the quantitative analysis of pipeline crack defects, with an error of less than 2% in the simulated and experimental data, and it could effectively evaluate the size of crack defects from the echo signals under different frequency excitations. Thus, by combining the ultrasonic guided wave detection technology and CNN, a quantitative analysis of pipeline crack defects can be effectively realized.

Fusion between an Algorithm Based on the Characterization of Melanocytic Lesions' Asymmetry with an Ensemble of Convolutional Neural Networks for Melanoma Detection

Melanoma is still a major health problem worldwide. Early diagnosis is the first step toward reducing its mortality, but it remains a challenge even for experienced dermatologists. Although computer-aided systems have been developed to help diagnosis, the lack of insight into their predictions is still a significant limitation toward acceptance by the medical community. To tackle this issue, we designed handcrafted expert features representing color asymmetry within the lesions, which are parts of the approach used by dermatologists in their daily practice. These features are given to an artificial neural network classifying between nevi and melanoma. We compare our results with an ensemble of 7 state-of-the-art convolutional neural networks and merge the 2 approaches by computing the average prediction. Our experiments are done on a subset of the International Skin Imaging Collaboration 2019 dataset (6296 nevi, 1361 melanomas). The artificial neural network based on asymmetry achieved an area under the curve of 0.873, sensitivity of 90%, and specificity of 67%; the convolutional neural network approach achieved an area under the curve of 0.938, sensitivity of 91%, and specificity of 82%; and the fusion of both approaches achieved an area under the curve of 0.942, sensitivity of 92%, and specificity of 82%. Merging the knowledge of dermatologists with convolutional neural networks showed high performance for melanoma detection, encouraging collaboration between computer science and medical fields.

不変情報クラスタリングと良品画像のみを用いて訓練された欠陥検知用CNNの提案

不変情報クラスタリングと良品画像のみを用いて訓練された欠陥検知用CNNの提案

Recent Trends and advances in deep learning techniques for the classification of landslides using satellite images: comprehensive survey

A landslide is a geographical catastrophe that occurs frequently in monsoon season and has a formidable impact over a wide range to pose risks to human lives and infrastructure worldwide. Traditional methods to classify and identify landslides are more time-consuming and less reliable. In the past few years artificial intelligence algorithms mainly, deep learning algorithms were used in many fields to detect and identify automatic disasters like landslides and earthquakes. Numerous research and classification approaches have been implemented in satellite image processing for the detection and prediction of landslides. The most challenging task in the classification and prediction of landslides from satellite imagery is to train the model with appropriate techniques and datasets which predict “accurately”. Limited work has been done on high-resolution satellite images using convolution techniques. This article presents a comprehensive study of recent deep-learning approaches based on convolutional neural networks to achieve efficient classification of landslide satellite images. A few selected research articles on deep learning approaches based on CNN for automatic detection of landside from peer reviews journals etc. are considered for this study. “The performance of all surveyed articles is evaluated using accuracy recall precision and F 1 score parameters”. This study illustrates the viability of deep learning approaches in learning complex and high-resolution satellite images for the classification and prediction of landslides.

A Novel Architecture of Depthwise Separable CNN and Multi-Level Pooling for Detection and Classification of Myopic Maculopathy

A Novel Architecture of Depthwise Separable CNN and Multi-Level Pooling for Detection and Classification of Myopic Maculopathy

Attention-based deep learning approach for detecting IoT botnetbased distributed denial of service attacks

Internet of Things (IoT) technology has evolved rapidly to become an integral part of our daily life. The numerous number of IoT devices and the limited security measures that could be applied on such devices attracted attackers to exploit these devices to act as botnets, generating massive Distributed Denial of Service (DDoS) attacks. IoT botnet-based DDoS attacks are growing dramatically both in frequency and sophistication and thus call for urgent development of powerful detection mechanism and deploy those mechanisms in an efficient way.In this paper, we propose attention-based deep learning approach for IoT botnet-based DDoS attacks. Specifically, we apply deep learning attention mechanism on two popular deep learning models LSTM and CNN for detection of IoT botnet DDoS attacks. We also examine the effect of using the deep Autoencoder for feature reduction and examine its effect on training time and data size needed to be exchanged through the network for training and updating the model, especially for solutions deployed at the Edge computing network. Performance evaluation shows that combining attention mechanism with LSTM model achieves superior performance with an accuracy reaching 100% which is due to combining the memorizing ability by the LSTM and the focusing ability of the attention in one model. In addition, results show that using Autoencoder for feature reduction resulted in reducing the training time up to 66.25%, 64.39%, 72.30% and 78.64% for ALSTM, LSTM, ACNN, CNN models respectively. Also achieved reduction in size of the dataset up to 67%.

A Novel Secured Deep Learning Model for COVID Detection Using Chest X-Rays

Automatic detection of a medical disease is a need of the hour as it helps doctors diagnose diseases and provide fast medical reports. COVID-19 is a deadly disease for which an automated detection system may be helpful. This study proposes a unique hybrid deep learning model, COVIDet, based on CNN and the speeded-up robust features (SURF) extraction approach to diagnose COVID-19 using chest x-ray images. SURF is utilized in this work to extract features, and the output is then transferred to a 25-layer CNN for detection using the extracted features. This investigation employed 4623 COVID-19 positive X-ray pictures or 8055 total. The suggested hybrid model also contrasts with the study's VGG19, Resnet50, Inception, Xception, and traditional CNN models. The proposed model had a 98.01% accuracy, a 97.03% F1-score, a 98.65% sensitivity, a 99% precision, and a 95.65% specificity. The proposed model can be further improved when more datasets are available and can help doctors to diagnose patients quickly and efficiently. Using chest X-ray pictures, a secured web application is also developed to identify COVID-19. The user sends the application a chest X-ray image, and in return, it determines whether an individual is COVID-19 positive or not, cutting down on testing time. In Covid times, when people are standing in long queues and waiting for their turns, this application would greatly help. The application uses the pre-trained COVIDet model in the backend.

Optimized vision transformer encoder with cnn for automatic psoriasis disease detection

Optimized vision transformer encoder with cnn for automatic psoriasis disease detection

Evaluating a Periapical Lesion Detection CNN on a Clinically Representative CBCT Dataset-A Validation Study.

The aim of this validation study was to comprehensively evaluate the performance and generalization capability of a deep learning-based periapical lesion detection algorithm on a clinically representative cone-beam computed tomography (CBCT) dataset and test for non-inferiority. The evaluation involved 195 CBCT images of adult upper and lower jaws, where sensitivity and specificity metrics were calculated for all teeth, stratified by jaw, and stratified by tooth type. Furthermore, each lesion was assigned a periapical index score based on its size to enable a score-based evaluation. Non-inferiority tests were conducted with proportions of 90% for sensitivity and 82% for specificity. The algorithm achieved an overall sensitivity of 86.7% and a specificity of 84.3%. The non-inferiority test indicated the rejection of the null hypothesis for specificity but not for sensitivity. However, when excluding lesions with a periapical index score of one (i.e., very small lesions), the sensitivity improved to 90.4%. Despite the challenges posed by the dataset, the algorithm demonstrated promising results. Nevertheless, further improvements are needed to enhance the algorithm's robustness, particularly in detecting very small lesions and the handling of artifacts and outliers commonly encountered in real-world clinical scenarios.

Efficient Feature Selection Using CNN, VGG16 and PCA for Breast Cancer Ultrasound Detection

Efficient Feature Selection Using CNN, VGG16 and PCA for Breast Cancer Ultrasound Detection

Combining wavelet transforms features and high-level features using CNN for face morphing attack detection

Combining wavelet transforms features and high-level features using CNN for face morphing attack detection

Multi‐input fully CNN for joint pilot decontamination and symbol detection in 5G massive MIMO

AbstractThis paper presents a multi‐input deep learning‐based joint pilot decontamination and symbol detection (SD) technique for 5G massive multiple‐input multiple‐output (MAMIMO) systems. It consists of a fully convolutional neural network (FCNN) that finds the 5G channel coefficients using pre‐known sounding reference signals (SRSs) under pilot contamination and a symbol detector derived from projected gradient descent iterations. The study considers pilot contamination caused by inter‐cell interferences between SRSs during channel estimation (CE). The proposed scheme accepts entire 5G orthogonal frequency modulated (OFDM) data and least square estimates and produces the transmitted OFDM signal. Simulation experiments demonstrated that the proposed technique has better CE and SD performance with reduced trainable parameters. Moreover, it is faster due to the lowest elapsed time during end‐to‐end OFDM symbol detection. This paper proposes a joint pilot decontamination and signal detection for 5G MAMIMO systems. It achieves better detection performance with the lowest number of trainable parameters and memory requirements. It is applicable in 5G OFDM symbol detection and channel estimation under pilot contamination.