Proposed Convolutional Neural Network Model Research Articles

Online Monitoring of Iron Ore Pellet Size Distribution Using Lightweight Convolutional Neural Network

An improved U-Net based convolutional neural network (CNN) is proposed in this paper for online size monitoring of iron ore pellets. The proposed CNN model is a lightweight version of U-Net. In the proposed model each convolution block of the encoder subnet consists of a concatenated <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1\times 1$</tex-math> </inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$3\times 3$</tex-math> </inline-formula> filter kernel, a batch normalization layer, and a ReLU nonlinearity. The proposed CNN model efficiently detects the pellets even under variable illumination conditions and images with overlapping pellets. The proposed model is evaluated using images of iron ore pellets acquired at the discharge end of a pelletizer disc. The proposed CNN model performs satisfactorily using <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim$</tex-math> </inline-formula> 39% less learnable parameters, and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\sim$</tex-math> </inline-formula> 16% reduced computational cost than the original U-Net model. The proposed model outperforms the conventional U-Net, different variants of U-Nets, FCN, and SegNet in weighted IoU, BF Score, global accuracy, SSIM, and PSNR. Experimental validation also shows a good agreement between the obtained pellet size distribution and the manual sieving result. This makes the proposed algorithm suitable for online pellet size-distribution measuring instruments. This method provides a more accurate and fast size monitoring system for iron ore pellets, ideal for real-time industrial applications. The image dataset and source codes are available at the below given link. https://github.com/aryadeo/Pellet_Size_Distribution. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Due to the advent of digitalization in industries, several attempts are being made to use innovative industrial monitoring systems in steel manufacturing plants. Most of the pellet plants in steel industries use human supervision for pellet growth monitoring. In this paper, a camera-based pellet size distribution monitoring method is proposed. A novel deep learning-based algorithm is used for the detection of pellets from the captured image followed by computation of pellet size analysis. Due to low computational complexity and better accuracy, the proposed method is suitable for online pellet size distribution system development compared to other previously proposed methods. However, protection from the harsh industrial environment is required for the uninterrupted and continuous operation of the system. As a future scope, the obtained pellet size information can be used as one of the control variables in designing a control system for the automated operation of the pelletizer disc.

Convolutional Neural Networks for Spherical Signal Processing via Area-Regular Spherical Haar Tight Framelets.

In this article, we develop a general theoretical framework for constructing Haar-type tight framelets on any compact set with a hierarchical partition. In particular, we construct a novel area-regular hierarchical partition on the two spheres and establish its corresponding spherical Haar tight framelets with directionality. We conclude by evaluating and illustrate the effectiveness of our area-regular spherical Haar tight framelets in several denoising experiments. Furthermore, we propose a convolutional neural network (CNN) model for spherical signal denoising, which employs fast framelet decomposition and reconstruction algorithms. Experiment results show that our proposed CNN model outperforms threshold methods and processes strong generalization and robustness.

Classification of Blood Cells with Convolutional Neural Network Model

Among the blood cells, white blood cells (WBC), which play a crucial role in forming our body's defense system, are essential components. Originating in the bone marrow, these cells serve as the fundamental components of the immune system, shouldering the responsibility of safeguarding the body against foreign microbes and diseases. Insufficient WBC counts may compromise the body's skill to resist infections, a status known as leukopenia. White blood cell counting is a specialty procedure that is usually carried out by qualified physicians and radiologists. Thanks to recent advances, image processing techniques are frequently used in biological systems to identify a wide spectrum of illnesses. In this work, image processing techniques were applied to enhance the white blood cell deep learning models' classification accuracy. To expedite the classification process, Convolutional Neural Network (CNN) models were combined with Ridge feature selection and Maximal Information Coefficient techniques. These tactics successfully determined the most important characteristics. The selected feature set was then applied to the classification procedure. ResNet-50, VGG19, and our suggested model were used as feature extractors in this study. The categorizing of white blood cells was completed with an amazing 98.27% success rate. Results from the experiments demonstrated a considerable improvement in classification accuracy using the proposed CNN model.

CNN-Based Approach for Non-Invasive Estimation of Breast Tumor Size and Location Using Thermographic Images

The characterization of tumors is crucial for guiding appropriate treatment strategies and enhancing patient survival rates. Surface thermography shows promise in the non-invasive detection of thermal patterns associated with the existence of breast tumors. Nevertheless, the precise prediction of both tumor size and location using temperature characteristics presents a critical challenge. This is due to the limited availability of thermal images labeled with the corresponding tumor size and location. This work proposes a deep learning approach based on convolutional neural networks (CNN) in combination with thermographic images for estimating breast tumor size and location. Successive COMSOL-based simulations are conducted, including a 3D breast model with various tumor scenarios. Thus, different noise levels were included in the development of the thermographic image dataset. Every image was accordingly labeled with the corresponding tumor location and size to train the CNN model. Mean absolute error (MAE) and the coefficient of determination (R²) were considered as evaluation metrics. The results show that the proposed CNN model achieved a reasonable prediction performance with MAE–R² values of 0.872–98.6% for tumor size, 1.161–96.8% for x location, 1.086–97.1% for y location, and 0.954–96.7% for z location. This study indicates that the combination of surface thermography and deep learning is a convenient tool for predicting breast tumor parameters.

Predicting Soil Quality Index with a Deep Regression Approach

ABSTRACT The detection, preservation and enhancement of soil quality is essential for ecosystem managers to offer the appropriate support after discovering factors that are linked to soil’s functional capability. In this study, soil quality indicators were combined to establish a soil quality index (SQI) by conducting an efficiency analysis for using Convolutional Neural Network (CNN), Gradient Boosting Methods (GBM) and Decision Tree (DT) approaches. For this purpose, soil’s intrinsic parameters, namely indicators, are utilized in case of fitting a deeper regression model. The experiments were carried out with analysis results of 545 soil samples obtained from previously studies conducted on different areas such as watershed, delta, pasture and farmland. The performance of each model is validated by the reported data. Compared to gradient boosting models, the proposed CNN model with mean absolute loss function achieves a lower error rate of 2.71 in Mean Absolute Percentage Error (MAPE) and best average correlation coefficient 0.90 in R2, which proves generalizability of CNN based regression. The findings show that CNNs may be utilized as an effective tool as giving a better prediction accuracy level and reliability in terms the establishing correlations and providing a conceptual framework for modeling of soil quality.

A CNN Hyperparameters Optimization Based on Particle Swarm Optimization for Mammography Breast Cancer Classification.

Breast cancer is considered one of the most-common types of cancers among females in the world, with a high mortality rate. Medical imaging is still one of the most-reliable tools to detect breast cancer. Unfortunately, manual image detection takes much time. This paper proposes a new deep learning method based on Convolutional Neural Networks (CNNs). Convolutional Neural Networks are widely used for image classification. However, the determination process for accurate hyperparameters and architectures is still a challenging task. In this work, a highly accurate CNN model to detect breast cancer by mammography was developed. The proposed method is based on the Particle Swarm Optimization (PSO) algorithm in order to look for suitable hyperparameters and the architecture for the CNN model. The CNN model using PSO achieved success rates of 98.23% and 97.98% on the DDSM and MIAS datasets, respectively. The experimental results proved that the proposed CNN model gave the best accuracy values in comparison with other studies in the field. As a result, CNN models for mammography classification can now be created automatically. The proposed method can be considered as a powerful technique for breast cancer prediction.

A Deep Learning Approach for the Automated Classification of Geomagnetically Induced Current Scalograms

During geomagnetic storms, which are a result of solar wind’s interaction with the Earth’s magnetosphere, geomagnetically induced currents (GICs) begin to flow in the long, high-voltage electrical networks on the Earth’s surface. It causes a number of negative phenomena that affect the normal operation of the entire electric power system. To investigate the nature of the phenomenon and its effects on transformers, a GIC monitoring system was created in 2011. The system consists of devices that are installed in the neutrals of autotransformers at five substations of the Kola–Karelian power transit in northwestern Russia. Considering the significant amount of data accumulated over 12 years of operating the GIC monitoring system, manual analysis becomes impractical. To analyze the constantly growing volume of recorded data effectively, a method for the automatic classification of GICs in autotransformer neutrals was proposed. The method is based on a continuous wavelet transform of the neutral current data combined with a convolutional neural network (CNN) to classify the obtained scalogram images. The classifier’s performance is evaluated using accuracy and binary cross-entropy loss metrics. As the result of comparing four CNN architectures, a model that showed high GIC classification performance on the validation set was chosen as the final model. The proposed CNN model, in addition to the main layers, includes pre-processing layers and a dropout layer.

Prediction of Ozone Depletion Levels using Intelligent CNN-SVM Classification System

&lt;p&gt;The concentration of ozone in the earth atmosphere has been steadily falling by 4% in the total amount since late 1970. With the widespread usage of modern industry chlorofluorocarbons, the rate at which ozone content decreases is escalating, resulting in an ozone hole. The depletion permits harmful UV into the earth surface which brings harmful hazards to earth living organisms. Increased UV radiation exposure can lead to skin cancer, cataracts, and ecological disruptions. The machine learning models face difficulties in accurately accounting for unpredictable events, such as sudden changes in emission patterns or unforeseen interactions, which limits their capacity to provide precise and reliable forecasts for future ozone depletion scenarios. To overcome this issue, a novel hybridization of Convolution Neural Network (CNN) and Support Vector Machine (SVM) is proposed to detect the variation in the ozone depletion around earth surfaces. The input images are collected from the thermosphere meteorological satellite and transformed into clean data in preprocessing. Then, the images are annotated and fed to the learning model for training. Followed by SVM classifier taken the CNN feature as an input and show the exact level of the ozone. The experimental findings show that the proposed CNN-SVM framework accomplishes satisfactory prediction accuracy of 99.44%. The overall accuracy range improves by 0.21%, 6.74%, and 4.44% with the CNN, SVM-IF, and Faster RCNN test outcomes, and by 2.59%, 3.52%, and 4.13% with the proposed CNN model, respectively. The proposed SVM model increases the total f1-Score by 2.3%, 3.19%, and 0.7%, respectively. The proposed CNN-SVM model obtains high accuracy rate than other existing models.&lt;/p&gt;&#x0D;

A deep learning model for brain age prediction using minimally preprocessed T1w images as input.

In the last few years, several models trying to calculate the biological brain age have been proposed based on structural magnetic resonance imaging scans (T1-weighted MRIs, T1w) using multivariate methods and machine learning. We developed and validated a convolutional neural network (CNN)-based biological brain age prediction model that uses one T1w MRI preprocessing step when applying the model to external datasets to simplify implementation and increase accessibility in research settings. Our model only requires rigid image registration to the MNI space, which is an advantage compared to previous methods that require more preprocessing steps, such as feature extraction. We used a multicohort dataset of cognitively healthy individuals (age range = 32.0-95.7 years) comprising 17,296 MRIs for training and evaluation. We compared our model using hold-out (CNN1) and cross-validation (CNN2-4) approaches. To verify generalisability, we used two external datasets with different populations and MRI scan characteristics to evaluate the model. To demonstrate its usability, we included the external dataset's images in the cross-validation training (CNN3). To ensure that our model used only the brain signal on the image, we also predicted brain age using skull-stripped images (CNN4). The trained models achieved a mean absolute error of 2.99, 2.67, 2.67, and 3.08 years for CNN1-4, respectively. The model's performance in the external dataset was in the typical range of mean absolute error (MAE) found in the literature for testing sets. Adding the external dataset to the training set (CNN3), overall, MAE is unaffected, but individual cohort MAE improves (5.63-2.25 years). Salience maps of predictions reveal that periventricular, temporal, and insular regions are the most important for age prediction. We provide indicators for using biological (predicted) brain age as a metric for age correction in neuroimaging studies as an alternative to the traditional chronological age. In conclusion, using different approaches, our CNN-based model showed good performance using one T1w brain MRI preprocessing step. The proposed CNN model is made publicly available for the research community to be easily implemented and used to study ageing and age-related disorders.

Application of light-weighted CNN for diagnosis of internal concrete defects using hammering sound

ABSTRACT In the past, diagnoses of the internal defects of ageing concrete members by sound tests have relied on the ability and experience of the inspector. However, with the development of deep neural networks, building diagnosis tools without the subjective judgements of humans is feasible. In this study, sound samples are collected from a tapping sound test on concrete slab specimens with internally embedded artificial defects. Spectrograms are generated from the sound samples and used to train a light-weighted convolutional neural network (CNN). Thereafter, the performance of the proposed CNN models at diagnosing the defects of the concrete slabs are examined and compared with convolutional autoencoder (CAE) and support vector regression (SVR). All the models performed well at distinguishing between healthy and defective concrete. Whereas noise can impair the performance of CAE and SVR, CNN is less affected, particularly when classifying sound samples with distinctive features. CNN also has other advantages: the physical area of the artificial defect can be output directly from CNN, and CNN performance is also less affected by the depth of the artificial defect and the rebar embedded in the concrete. At increased depths, the CNN is still able to identify the defect area.

Exponential Fusion of Interpolated Frames Network (EFIF-Net): Advancing Multi-Frame Image Super-Resolution with Convolutional Neural Networks.

Convolutional neural networks (CNNs) have become instrumental in advancing multi-frame image super-resolution (SR), a technique that merges multiple low-resolution images of the same scene into a high-resolution image. In this paper, a novel deep learning multi-frame SR algorithm is introduced. The proposed CNN model, named Exponential Fusion of Interpolated Frames Network (EFIF-Net), seamlessly integrates fusion and restoration within an end-to-end network. Key features of the new EFIF-Net include a custom exponentially weighted fusion (EWF) layer for image fusion and a modification of the Residual Channel Attention Network for restoration to deblur the fused image. Input frames are registered with subpixel accuracy using an affine motion model to capture the camera platform motion. The frames are externally upsampled using single-image interpolation. The interpolated frames are then fused with the custom EWF layer, employing subpixel registration information to give more weight to pixels with less interpolation error. Realistic image acquisition conditions are simulated to generate training and testing datasets with corresponding ground truths. The observation model captures optical degradation from diffraction and detector integration from the sensor. The experimental results demonstrate the efficacy of EFIF-Net using both simulated and real camera data. The real camera results use authentic, unaltered camera data without artificial downsampling or degradation.

Deep learning driven segmentation of maxillary impacted canine on cone beam computed tomography images

The process of creating virtual models of dentomaxillofacial structures through three-dimensional segmentation is a crucial component of most digital dental workflows. This process is typically performed using manual or semi-automated approaches, which can be time-consuming and subject to observer bias. The aim of this study was to train and assess the performance of a convolutional neural network (CNN)-based online cloud platform for automated segmentation of maxillary impacted canine on CBCT image. A total of 100 CBCT images with maxillary canine impactions were randomly allocated into two groups: a training set (n = 50) and a testing set (n = 50). The training set was used to train the CNN model and the testing set was employed to evaluate the model performance. Both tasks were performed on an online cloud-based platform, ‘Virtual patient creator’ (Relu, Leuven, Belgium). The performance was assessed using voxel- and surface-based comparison between automated and semi-automated ground truth segmentations. In addition, the time required for segmentation was also calculated. The automated tool showed high performance for segmenting impacted canines with a dice similarity coefficient of 0.99 ± 0.02. Moreover, it was 24 times faster than semi-automated approach. The proposed CNN model achieved fast, consistent, and precise segmentation of maxillary impacted canines.

Advancing Workplace Safety: A Proactive Approach with Convolutional Neural Network for Hand Pose Estimation in Press Machine Operations

Press machine operations are integral to goods production across industries, yet worker safety faces significant risks. Machine misuse and non-compliance with safety standards contribute substantially to these incidents. This study addresses the mounting concerns regarding workplace incidents through a proactive solution—a Convolutional Neural Network (CNN) model crafted to prevent press machine misuse by monitoring workers' hand placement during operation. The model that we suggest ensures adherence to safety standards. The CNN model does not replace the role of human operators but acts as a supportive layer, providing instant feedback and intervention when deviations from safety standards are detected. In conclusion, this research endeavors to pave the way for a safer and more secure industrial environment by leveraging the capabilities of advanced technology. The proposed CNN model addresses current concerns and sets a precedent for future advancements in ensuring workplace safety across diverse industries.

Artificial Intelligent-Based Wake Word Detection at Edge Device

Deep Neural Network based wake word (such as Hi Alexa or Hey Siri) systems allow increasingly accurate speech communication between humans and machines. However, this setup requires high processing power or cloud services which may not be accessible by edge devices. Currently, the accuracy of machine learning methods for cloudless edge devices in voice activation hovers below 90%. This paper explores wake word implementation on edge devices using a 2-Dimensional Convolutional Neural Network (CNN) with improved and balanced accuracy and latency. The proposed CNN model is created, trained and quantized using TensorFlow on a PC and exported to a Raspberry Pi Zero 2 W. The quantization method reduces the model size by 20% and spectral gating is adopted to lower wake word inaccuracy detection in moderately noisy environment. The proposed system achieved more than 90% wake word detection accuracy across 30 to 50 dB background noise with an average of 1.03 second of response time for the intended user. The result shows low-powered edge device still offers competitive performance for detecting wake word without cloud services.

CVINet: A deep learning based model for the diagnosis of chronic venous insufficiency in lower extremity using infrared thermal images

AbstractChronic venous insufficiency (CVI) is a venous disorder characterized by impaired blood flow from the lower extremities back to the heart, leading to various symptoms and complications. Accurate and timely diagnosis of CVI is critical for effective management and prevention of further complications. Deep learning (DL) models have shown results that are promising in the field of medical image analysis tasks over the past few years. This article presents CVINet, a enhanced DL‐based convolutional neural network (CNN) model that has been developed specifically for the purpose of diagnosing CVI utilizing thermal imaging data. The proposed CNN model extracts relevant features from input images using a multi‐layered architecture with convolutional layers and pooling layers. Following feature extraction, data are directed to fully connected layers for performing classification task. To enhance the performance of this model, we employ techniques such as dropout regularization and batch normalization. This model utilizes its ability to automatically learn discriminative features from raw thermal images. A large set of thermal images from both CVI patients and healthy individuals was acquired for training and testing of the model. A comparison between few conventional pre‐trained models was conducted, and the best performing model for classification was examined. Pre‐trained VGG‐16, EfficientNet‐B0, and ResNet‐152 models produced classification accuracies of 94.7%, 95.3%, and 95.8%, respectively. The Proposed CVINet model attained a classification accuracy of 96.8% on binary classification, demonstrating high performance compared with other state‐of‐the‐art networks. Overall, our proposed CNN model offers a promising solution for accurately classifying CVI and normal subjects based on thermal images which outperforms the diagnosis by clinician. The potential benefits include early detection of CVI and personalized treatment strategies that can improve patient outcomes. They improve the accuracy of patient diagnosis, reducing radiologist workload and providing them with a tool that can automatically assess the condition of the lower limb venous condition, lowering the risk of misdiagnosis. Furthermore, improving healthcare service quality and early detection can alter the course of the disease and reduce the morbidity and mortality rate of the disease.

The application of deep learning in computer vision: Facial emotion recognition based on convolutional neural network

Emotion recognition is an essential task in many fields, including affective computing, psychology, and human-computer interaction. The ability to accurately recognize emotions from facial expressions can help in the development of more personalized and responsive systems. The objective of this paper is to investigate the effectiveness of a Convolutional Neural Network (CNN) model in classifying emotions from facial expressions. We used the images classified into seven different categories from FER2013 dataset. The model is implemented using TensorFlow Keras, which consists of four CNN layers followed by two fully connected (FCN) layers and an output layer. In between each layer we use batch normalization, max pooling, and dropout to reduce calculation cost and prevent overfitting. Our model achieved an accuracy of 66.85% and a precision accuracy of 77.18% on the training set after 20 epochs. The recall and the F-1 score is 56.93% and 0.6545 respectively. This study demonstrates that the proposed CNN model can effectively recognize emotions in facial images. The availability of the FER2013 dataset provides researchers with an opportunity to further explore this area of research. The proposed model can be useful in various applications, such as affective computing, human-computer interaction, and psychology. Future work could involve tuning the hyperparameters of the model or using different datasets to explore the generalizability of the proposed model. Overall, our study provides insights into the effectiveness of CNNs for emotion recognition and highlights the potential for further research in this area.

SeedAI: a novel seed germination predictionsystem using dual stage deep learning framework

The detection of germinating seeds through automated means is a significant concern for seed testing agencies. Traditional approaches employ inspection manually. In recent years, there has been an increasing scientific focus on deep learning, particularly in the domain of seed detection, recognition, and germination in germination trays. In this paper, a novel two-stage network is proposed which leverages various Convolutional Neural Networks (CNN) to automate detection of seeds and the assessment of their germination state. In the first stage Mask R-CNN framework is used for instantaneous segmentation of seeds and in the next stage this Region of Interest (RoI) is given as input to the proposed CNN model for germination prediction. The proposed model is trained and tested on our own dataset. The experimental results proved that our proposed model is achieved better performance than state-of-the-art models with less trainable parameters.

Machine learning-based fault diagnosis for high-voltage transmission lines

In order to comply with the speed and diversification process of human economic and technological development, the power system gradually develops in the direction of intelligence and complexity, and it is urgent to combine transmission line fault diagnosis methods with machine learning pattern recognition problems in order to reflect the representative characteristics of transmission lines under different operating conditions and different operation modes. In this paper, a convolutional neural network (CNN) model is established for transmission line fault diagnosis, and a series of parameters such as weights, bias, learning rate, batch size and loss function of the proposed CNN model are debugged through experimental comparison, and the best CNN model structure is determined through experimental comparison and debugging, and the recognition accuracy is higher than other traditional machine learning algorithms, which can be as high as 98.38%, with validity, practicality and advancedness.

Photovoltaic cell defect classification based on integration of residual-inception network and spatial pyramid pooling in electroluminescence images

Electroluminescence (EL) imaging provides high spatial resolution and better identifies micro-defects for inspection of photovoltaic (PV) modules. However, the analysis of EL images could be typically a challenging process due to complex defect patterns and inhomogeneous background structure. In this study, a deep convolutional neural network (CNN) model using residual connections and spatial pyramid pooling (SPP) is proposed for the efficient classification of PV cell defects. The proposed CNN model is built on the Inception-v3 network. In this way, feature maps in inception modules are shared to reuse in deeper layers and the representation ability of features is enriched with the pooling process of the SPP in different sizes. Due to the imbalanced class distribution, offline data augmentation strategies are applied and network performance is further improved. The proposed method is evaluated on a publicly available dataset of 8 classes, of which 7 classes are defective and one class is defect-free images. In the comparative evaluation, while other approaches give accuracy values between 76.49% and 89.17%, this value is increased to 93.59% with the proposed method. The experimental results show that the proposed method exhibits more accurate and robust classification performance compared with other model combinations and CNN models.

Application of local climate zones combined with machine learning to predict the impact of urban structure patterns on thermal environment

The urban heat island effect is a pertinent concern and estimating the thermal stress in cities is a crucial research goal. Most relevant studies have focused on the relationship between urban structures and high air temperatures, ignoring the effect of different combination of urban structures on high air temperature identifications. In this study, an efficient method was developed for identifying the thermal risk based on combination of urban structures to explore the relationship between urban environment and meteorological conditions. After the preprocessing of LCZ and meteorological data, data were input into the convolutional neural network (CNN) model constructed in this study. After the training process, the accuracy rate of the proposed model increased as the sampling rate increased, and the model achieved a high accuracy rate of 81.97% at 50% sampling. Furthermore, the model performed particularly well at identifying low and medium level of thermal risk. This means that the model could estimate the classes of thermal risk in most areas in Taipei City. The feasibility of using the proposed CNN model to identify the level of thermal risk was proven; the model is a convenient tool for estimating thermal stress in different areas with incomplete air temperature data.