Deep Learning Convolutional Neural Network Research Articles

An ergonomic evaluation using a deep learning approach for assessing postural risks in a virtual reality-based smart manufacturing context

This study proposes an integrated ergonomic evaluation designed to identify unsafe postures, whereby postural risks during industrial work are assessed in the context of virtual reality-based smart manufacturing. Unsafe postures were recognised by identifying the displacements of the centre of mass (COM) of body keypoints using a computer vision-based deep learning (DL) convolutional neural network approach. The risk levels for the identified unsafe postures were calculated using ergonomic risk assessment tools rapid upper limb assessment and rapid whole-body assessment. An analysis of variance was conducted to determine significant differences between the vertical and horizontal directions of postural movements associated with the most unsafe postures. The findings assess the ergonomic risk levels and identify the most unsafe postures during industrial work in smart manufacturing using DL method. The identified postural risks can help industry managers and researchers acquire a better understanding of unsafe postures.

Machine Learning Approaches for ADHD Detection

This report explores the application of deep learning convolutional neural networks (CNNs) for analyzing brain MRI scans to assist in the diagnosis of Attention Deficit Hyperactivity Disorder (ADHD) syndrome. ADHD is a neuro developmental disorder that affects millions of individuals worldwide, characterized by difficulties in attention, hyperactivity, and impulsivity. Traditional methods of diagnosis rely on subjective assessments and behavioral observations, leading to inaccuracies and delays in treatment. Leveraging the power of deep learning CNNs for MRI analysis offers the potential for more objective and efficient diagnosis, facilitating timely intervention and personalized treatment strategies

An Update on the Use of Artificial Intelligence in Digital Pathology for Oral Epithelial Dysplasia Research.

Oral epithelial dysplasia (OED) is a precancerous histopathological finding which is considered the most important prognostic indicator for determining the risk of malignant transformation into oral squamous cell carcinoma (OSCC). The gold standard for diagnosis and grading of OED is through histopathological examination, which is subject to inter- and intra-observer variability, impacting accurate diagnosis and prognosis. The aim of this review article is to examine the current advances in digital pathology for artificial intelligence (AI) applications used for OED diagnosis. We included studies that used AI for diagnosis, grading, or prognosis of OED on histopathology images or intraoral clinical images. Studies utilizing imaging modalities other than routine light microscopy (e.g., scanning electron microscopy), or immunohistochemistry-stained histology slides, or immunofluorescence were excluded from the study. Studies not focusing on oral dysplasia grading and diagnosis, e.g., to discriminate OSCC from normal epithelial tissue were also excluded. A total of 24studies were included in this review. Nineteen studies utilized deep learning (DL) convolutional neural networks for histopathological OED analysis, and 4 used machine learning (ML) models. Studies were summarized by AI method, main study outcomes, predictive value for malignant transformation, strengths, and limitations. ML/DL studies for OED grading and prediction of malignant transformation are emerging as promising adjunctive tools in the field of digital pathology. These adjunctive objective tools can ultimately aid the pathologist in more accurate diagnosis and prognosis prediction. However, further supportive studies that focus on generalization, explainable decisions, and prognosis prediction are needed.

Near-Real Prediction of Earthquake-Triggered Landslides on the Southeastern Margin of the Tibetan Plateau

Earthquake-triggered landslides (ETLs) feature large quantities, extensive distributions, and enormous losses to human lives and critical infrastructures. Near-real spatial prediction of ETLs can rapidly predict the locations of coseismic landslides just after a violent earthquake and is a vital technical support for emergency response. However, near-real prediction of ETLs has always been a great challenge with relatively low accuracy. This work proposes an ensemble prediction model of EnPr by integrating machine learning tree models and a deep learning convolutional neural network. EnPr exhibits relatively strong prediction and generalization performance and achieves relatively accurate prediction of ETLs. Six great seismic events occurring from 2008 to 2022 on the southeastern margin of the Tibetan Plateau are selected to conduct ETL prediction. In a chronological order, the 2008 Ms 8.0 Wenchuan, 2010 Ms 7.1 Yushu, 2013 Ms 7.0 Lushan, and 2014 Ms 6.5 Ludian earthquakes are employed for model training and learning. The 2017 Ms 7.0 Jiuzhaigou and 2022 Ms 6.1 Lushan earthquakes are adopted for ETL prediction. The prediction accuracy merits of ACC and AUC attain 91.28% and 0.85, respectively, for the Jiuzhaigou earthquake. The values of ACC and AUC achieve 93.78% and 0.88, respectively, for the Lushan earthquake. The proposed EnPr algorithm outperforms the algorithms of XGBoost, random forest (RF), extremely randomized trees (ET), convolutional neural network (CNN), and Transformer. Moreover, this work reveals that seismic intensity, high and steep relief, pre-seismic fault tectonics, and pre-earthquake road construction have played significant roles in coseismic landslide occurrence and distribution. The EnPr model uses globally accessible open datasets and can therefore be used worldwide for new large seismic events in the future.

An Artificial Intelligence Driven Approach for Classification of Ophthalmic Images using Convolutional Neural Network: An Experimental Study.

Early disease detection is emphasized within ophthalmology now more than ever, and as a result, clinicians and innovators turn to deep learning to expedite accurate diagnosis and mitigate treatment delay. Efforts concentrate on the creation of deep learning systems that analyze clinical image data to detect disease-specific features with maximum sensitivity. Moreover, these systems hold promise of early accurate diagnosis and treatment of patients with common progressive diseases. DenseNet, ResNet, and VGG-16 are among a few of the deep learning Convolutional Neural Network (CNN) algorithms that have been introduced and are being investigated for potential application within ophthalmology. In this study, the authors sought to create and evaluate a novel ensembled deep learning CNN model that analyzes a dataset of shuffled retinal color fundus images (RCFIs) from eyes with various ocular disease features (cataract, glaucoma, diabetic retinopathy). Our aim was to determine (1) the relative performance of our finalized model in classifying RCFIs according to disease and (2) the diagnostic potential of the finalized model to serve as a screening test for specific diseases (cataract, glaucoma, diabetic retinopathy) upon presentation of RCFIs with diverse disease manifestations. We found adding convolutional layers to an existing VGG-16 model, which was named as a proposed model in this article that, resulted in significantly increased performance with 98% accuracy (p<0.05), including good diagnostic potential for binary disease detection in cataract, glaucoma, diabetic retinopathy. The proposed model was found to be suitable and accurate for a decision support system in Ophthalmology Clinical Framework.

An Evaluation Method of Dental Treatment Quality Combined with Deep Learning and Multi-index Decomposition

ABSTRACT Dentists judge that the quality of dental treatment for each patient is very time-consuming and inefficient, lacks quantitative evaluation criteria, and is easy to cause errors. At the same time, the traditional method of extracting tooth and root canal image features based on experience is difficult to accurately extract the tooth area and root canal filling area, resulting in low accuracy of tooth and root canal segmentation, which in turn affects the accuracy of tooth treatment quality evaluation. In this paper, a deep learning convolutional neural network is used to segment the root canal filling area, tooth boundary, and the boundary between tooth and soft tissue for the real patient ‘s root canal treatment and filling image. Finally, the segmented image is quantitatively evaluated according to the multi-evaluation index of professional doctors. The experimental results show that the intelligent evaluation method of dental treatment quality combined with deep learning and multi-index decomposition proposed in this paper not only unifies the evaluation criteria of dental treatment quality but also the therapeutic effect of quantitative scoring can effectively improve the work efficiency of doctors, which has reference significance for the application of artificial intelligence in the medical field.

Deep learning based event reconstruction for cyclotron radiation emission spectroscopy

The objective of the cyclotron radiation emission spectroscopy (CRES) technology is to build precise particle energy spectra. This is achieved by identifying the start frequencies of charged particle trajectories which, when exposed to an external magnetic field, leave semi-linear profiles (called tracks) in the time–frequency plane. Due to the need for excellent instrumental energy resolution in application, highly efficient and accurate track reconstruction methods are desired. Deep learning convolutional neural networks (CNNs) - particularly suited to deal with information-sparse data and which offer precise foreground localization—may be utilized to extract track properties from measured CRES signals (called events) with relative computational ease. In this work, we develop a novel machine learning based model which operates a CNN and a support vector machine in tandem to perform this reconstruction. A primary application of our method is shown on simulated CRES signals which mimic those of the Project 8 experiment—a novel effort to extract the unknown absolute neutrino mass value from a precise measurement of tritium β −-decay energy spectrum. When compared to a point-clustering based technique used as a baseline, we show a relative gain of 24.1% in event reconstruction efficiency and comparable performance in accuracy of track parameter reconstruction.

Ensembles of Multiple Models for Soil Moisture Retrieval from Remote Sensing Data over Agricultural Areas: A Deep Learning-based Framework

In agricultural areas, most surface soil moisture (SM) retrieval models are unstable in terms of their accuracy and performance during crop growth. As a result, there is no consensus on which model performs optimally during the agricultural season. This is because of the uncertainties associated with model physics, initial conditions, model inversion processes, input data, vegetation attenuation and soil characteristics. To better deal with these practical concerns, we propose a simple, but robust SM retrieval method of using combination of multiple models based on deep learning and multi-model ensemble approach, called the DL-MME method, which makes use of the ‘collective intelligence’ and ‘wisdom of crowds’ concepts. The advantages of this method are: (1) robustness to model selection, and (2) robustness to model calibration during the growing season. In addition, this method is less dependent on one type of data across various agricultural areas compared to the single model approach. Firstly, the coupled water cloud model (WCM) and soil backscattering models (Oh model or advanced integral equation model (AIEM)) with different vegetation descriptors were calibrated and validated during the growing season in sugarcane and winter wheat fields for Sentinel-1 backscattering coefficients (VV and VH). SM was also retrieved by employing the trapezoid model (OPTRAM) with different parameters from Sentinel-2 images. To optimize SM retrieval computations, we used the outputs from optical and SAR models, auxiliary features, and reliable in situ SM measurements as inputs to a deep learning convolutional neural network (DL-CNN). For sugarcane and wheat fields in the early stages of crop growth, WCM models retrieved more accurate time-series SM than optical models. OPTRAM soil moisture retrievals showed greater accuracy in the late crop growing season. Time-series SM retrieval accuracy using DL-MME was higher than for the optical and semi-empirical SAR models. According to the results of the in situ validation for wheat (sugarcane) fields, the minimum MAE by an optimal combination of models was around 0.01 (0.02) m3m-3 (RMSE= 0.036 (0.074) m3m-3; R= 0.87 (0.71)). The findings demonstrate that our method is reliable and feasible for SM retrieval. Additionally, our method provides a way to select an optimal model for retrieving time-series SM during the crop growing season.

Enhancing Arabic Sign Language Recognition using Deep Learning

The present time, Sign language is very important for people who suffer from hearing loss or who cannot speak. Normal humans tend to disregard the significance of signal language, which is a mere supply of communique to mute and deaf societies. So, this study proposes a developed model for sign Language Recognition for Arabic using the Deep learning Convolutional Neural Network (CNN) algorithm. Then set the algorithm by developing programming on Open-CV, using Python language. The dataset contains 54049 snapshots of Arabic signal language alphabets. The 32 folders were created, and each one of them included 1500 images incorporating hand gestures in at-variance environments. The data set was divided into a training section with a percentage of 70 %, a section for testing with a percentage of 20 %, and a section for validation with a percentage of 10 %. The results show that the suggested model achieved an accuracy rate of 94.8%, and it has proven its effectiveness and success, especially after being tried and tested by several users and obtaining their comments and feedback.

An efficient tomato diseases detection and classification methodology using CNN Deep Learning Network

In this paper, an efficient methodology for detecting and classifying tomato diseases using a Convolutional Neural Network (CNN) deep learning network is presented as an efficient aided tool to classify different tomato diseases based on their leaf appearence, where plant diseases and insects are considered as a main challenges for farmers to overcome. The proposed methodology structure is based on 20 layers using convolution, Maxpooling, Batch normalization and ReLU process as main operations in the adopted architecture. The obtained results using Plant Village database show that our proposed methodology outclasses the best recent methods of tomato diseases detection and classification with scores of 97.3% 96.8% 97.0% and 97.5% for precision, Recall, F1-Score and accuracy coefficient criteria respectively. Our methodology of tomato diseases detection and classification is found as effective, accurate and aided diagnostic tool that aims to aid farmers to make a precise plant treatments and enhancing productivity while promoting environmental sustainability.

Initial Fire Detection Method for Intelligent CCTV Using Deep Learning Technology

Pre-prediction and early detection are important for the prevention of fires. Hence, the integration of intelligent CCTV image analysis technology, deep learning, and artificial intelligence is actively being studied. Intelligent CCTV can analyze visible light images of fires, but the accuracies of the detection targets are low. To solve this problem, a dual sensing experimental device was constructed by combining a visible light sensor and a thermal image sensor, and an algorithm was implemented to predict fire events. An algorithm was constructed to detect three classes (Fire, Smoke, and Person) through RGB sensors and thermal imaging sensors. Additionally, a CNN deep learning method and the YOLOv5 method were used to build a classification neural network. The dual sensing device was able to act as a trigger to predict and detect a fire based on the size of the flame and changes in temperature.

Forecasting Gas Well Classification Based on a Two-Dimensional Convolutional Neural Network Deep Learning Model

In response to the limitations of existing evaluation methods for gas well types in tight sandstone gas reservoirs, characterized by low indicator dimensions and a reliance on traditional methods with low prediction accuracy, therefore, a novel approach based on a two-dimensional convolutional neural network (2D-CNN) is proposed for predicting gas well types. First, gas well features are hierarchically selected using variance filtering, correlation coefficients, and the XGBoost algorithm. Then, gas well types are determined via spectral clustering, with each gas well labeled accordingly. Finally, the selected features are inputted, and classification labels are outputted into the 2D-CNN, where convolutional layers extract features of gas well indicators, and the pooling layer, which, trained by the backpropagation of CNN, performs secondary dimensionality reduction. A 2D-CNN gas well classification prediction model is constructed, and the softmax function is employed to determine well classifications. This methodology is applied to a specific tight gas reservoir. The study findings indicate the following: (1) Via two rounds of feature selection using the new algorithm, the number of gas well indicator dimensions is reduced from 29 to 15, thereby reducing the computational complexity of the model. (2) Gas wells are categorized into high, medium, and low types, addressing a deep learning multi-class prediction problem. (3) The new method achieves an accuracy of 0.99 and a loss value of 0.03, outperforming BP neural networks, XGBoost, LightGBM, long short-term memory networks (LSTMs), and one-dimensional convolutional neural networks (1D-CNNs). Overall, this innovative approach demonstrates superior efficacy in predicting gas well types, which is particularly valuable for tight sandstone gas reservoirs.

Stellar populations with optical spectra: deep learning versus popular spectrum fitting codes

ABSTRACT We compare the performance of several popular spectrum fitting codes (firefly, starlight, pypipe3d, and ppxf), and a deep-learning convolutional neural network (starnet), in recovering known stellar population properties (mean stellar age, stellar metallicity, stellar mass-to-light ratio M*/Lr and the internal E(B−V)) of simulated galaxy spectra in optical wavelengths. Our mock spectra are constructed from star-formation histories from the IllustrisTNG100-1 simulation. These spectra mimic the Sloan Digital Sky Survey (SDSS) through a novel method of including the noise, sky residuals, and emission lines taken directly from SDSS. We find that starnet vastly outperforms all conventional codes in both speed and recovery of stellar population properties (error scatter &amp;lt;0.08 dex, average biases &amp;lt;0.02 dex for all tested quantities), but it requires an appropriate training set. Of the non-machine-learning codes, ppxf was a factor of 3–4 times faster than the other codes, and was the best in recovering stellar population properties (error scatter of &amp;lt;0.11 dex, average biases &amp;lt;0.08 dex). However, the errors and biases are strongly dependent on both true and predicted values of stellar age and metallicity, and signal-to-noise ratio. The biases of all codes can approach 0.15 dex in stellar ages, metallicities and log M*/Lr, but remain ≲0.05 for E(B−V). Using unrealistic Gaussian noise in the construction of mock spectra will underestimate the errors in the metallicities by a factor of 2 or more, and mocks without emission lines will underestimate the errors in stellar age and M*/Lr by a factor of 2.

Robust Deepfake Detection System with Deep Learning Techniques

This comprehensive study investigates the pervasive issue of deep fakes within the context of deep learning applications, focusing on their detection and production. Utilizing a diverse array of deep learning algorithms, including InceptionResnetV2, VGG19, CNN, Xception, InceptionV3, EfficientNetB1, DenseNet121, Hybrid Model, LSTM, ResNext-LSTM, and MRI-GAN, the research systematically evaluates their effectiveness in detecting deep fakes. Results reveal varying levels of accuracy, with Xception emerging as the most precise algorithm, achieving an accuracy of 99.32%. Notably, InceptionResnetV2 and DenseNet121 also demonstrate robust performance, with accuracies surpassing 99%. However, certain models like VGG19 and LSTM exhibit lower accuracy rates, underscoring the need for further refinement. These findings underscore the urgent necessity for robust detection mechanisms amidst the proliferation of malicious deep fakes, safeguarding against potential societal ramifications such as misinformation and privacy breaches.

An End-to-End Lightweight Multi-Scale CNN for the Classification of Lung and Colon Cancer with XAI Integration

To effectively treat lung and colon cancer and save lives, early and accurate identification is essential. Conventional diagnosis takes a long time and requires the manual expertise of radiologists. The rising number of new cancer cases makes it challenging to process massive volumes of data quickly. Different machine learning approaches to the classification and detection of lung and colon cancer have been proposed by multiple research studies. However, when it comes to self-learning classification and detection tasks, deep learning (DL) excels. This paper suggests a novel DL convolutional neural network (CNN) model for detecting lung and colon cancer. The proposed model is lightweight and multi-scale since it uses only 1.1 million parameters, making it appropriate for real-time applications as it provides an end-to-end solution. By incorporating features extracted at multiple scales, the model can effectively capture both local and global patterns within the input data. The explainability tools such as gradient-weighted class activation mapping and Shapley additive explanation can identify potential problems by highlighting the specific input data areas that have an impact on the model’s choice. The experimental findings demonstrate that for lung and colon cancer detection, the proposed model was outperformed by the competition and accuracy rates of 99.20% have been achieved for multi-class (containing five classes) predictions.

Deep learning radiomics-based prediction model of metachronous distant metastasis following curative resection for retroperitoneal leiomyosarcoma: a bicentric study

BackgroundCombining conventional radiomics models with deep learning features can result in superior performance in predicting the prognosis of patients with tumors; however, this approach has never been evaluated for the prediction of metachronous distant metastasis (MDM) among patients with retroperitoneal leiomyosarcoma (RLS). Thus, the purpose of this study was to develop and validate a preoperative contrast-enhanced computed tomography (CECT)-based deep learning radiomics model for predicting the occurrence of MDM in patients with RLS undergoing complete surgical resection.MethodsA total of 179 patients who had undergone surgery for the treatment of histologically confirmed RLS were retrospectively recruited from two tertiary sarcoma centers. Semantic segmentation features derived from a convolutional neural network deep learning model as well as conventional hand-crafted radiomics features were extracted from preoperative three-phase CECT images to quantify the sarcoma phenotypes. A conventional radiomics signature (RS) and a deep learning radiomics signature (DLRS) that incorporated hand-crafted radiomics and deep learning features were developed to predict the risk of MDM. Additionally, a deep learning radiomics nomogram (DLRN) was established to evaluate the incremental prognostic significance of the DLRS in combination with clinico-radiological predictors.ResultsThe comparison of the area under the curve (AUC) values in the external validation set, as determined by the DeLong test, demonstrated that the integrated DLRN, DLRS, and RS models all exhibited superior predictive performance compared with that of the clinical model (AUC 0.786 [95% confidence interval 0.649–0.923] vs. 0.822 [0.692–0.952] vs. 0.733 [0.573–0.892] vs. 0.511 [0.359–0.662]; both P < 0.05). The decision curve analyses graphically indicated that utilizing the DLRN for risk stratification provided greater net benefits than those achieved using the DLRS, RS and clinical models. Good alignment with the calibration curve indicated that the DLRN also exhibited good performance.ConclusionsThe novel CECT-based DLRN developed in this study demonstrated promising performance in the preoperative prediction of the risk of MDM following curative resection in patients with RLS. The DLRN, which outperformed the other three models, could provide valuable information for predicting surgical efficacy and tailoring individualized treatment plans in this patient population.Trial registration: Not applicable.

IOT based Waste Segregation Using Deep Learning

In the rapidly urbanizing world, effective waste management is crucial to maintain environmental sustainability. This project presents an innovative solution utilizing Internet of Things (IoT) technology and deep learning Convolutional Neural Networks (CNN) algorithm for automated waste segregation. We propose a smart waste segregation system equipped with sensors to detect the level of waste in bins. The system utilizes a CNN model trained using Deep Learning to classify waste items into different categories, ensuring proper segregation. When a bin reaches its full capacity, the IoT sensors trigger an alert mechanism, sending real-time notifications to the concerned authorities or waste management personnel. This proactive approach not only optimizes waste collection but also promotes recycling by ensuring the segregated waste reaches the appropriate recycling facilities. The integration of IoT devices and deep learning algorithms enhances the efficiency of waste management processes, reducing environmental pollution and promoting a sustainable future. Key Words: IoT, waste management, deep learning, CNN algorithm, waste segregation, environmental sustainability, real-time monitoring, sensor technology, recycling, smart cities, automation.

A Bidirectional Arabic Sign Language Framework Using Deep Learning and Fuzzy Matching Score

Sign language is widely used to facilitate the communication process between deaf people and their surrounding environment. Sign language, like most other languages, is considered a complex language which cannot be mastered easily. Thus, technology can be used as an assistive tool to solve the difficulties and challenges that deaf people face during interactions with society. In this study, an automatic bidirectional translation framework for Arabic Sign Language (ArSL) is designed to assist both deaf and ordinary people to communicate and express themselves easily. Two main modules were intended to translate Arabic sign images into text by utilizing different transfer learning models and to translate the input text into Arabic sign images. A prototype was implemented based on the proposed framework by using several pre-trained convolutional neural network (CNN)-based deep learning models, including the DenseNet121, ResNet152, MobileNetV2, Xception, InceptionV3, NASNetLarge, VGG19, and VGG16 models. A fuzzy string matching score method, as a novel concept, was employed to translate the input text from ordinary people into appropriate sign language images. The dataset was constructed with specific criteria to obtain 7030 images for 14 classes captured from both deaf and ordinary people locally. The prototype was developed to conduct the experiments on the collected ArSL dataset using the utilized CNN deep learning models. The experimental results were evaluated using standard measurement metrics such as accuracy, precision, recall, and F1-score. The performance and efficiency of the ArSL prototype were assessed using a test set of an 80:20 splitting procedure, obtaining accuracy results from the highest to the lowest rates with average classification time in seconds for each utilized model, including (VGG16, 98.65%, 72.5), (MobileNetV2, 98.51%, 100.19), (VGG19, 98.22%, 77.16), (DenseNet121, 98.15%, 80.44), (Xception, 96.44%, 72.54), (NASNetLarge, 96.23%, 84.96), (InceptionV3, 94.31%, 76.98), and (ResNet152, 47.23%, 98.51). The fuzzy matching score is mathematically validated by computing the distance between the input and associative dictionary words. The study results showed the prototype’s ability to successfully translate Arabic sign images into Arabic text and vice versa, with the highest accuracy. This study proves the ability to develop a robust and efficient real-time bidirectional ArSL translation system using deep learning models and the fuzzy string matching score method.

Denoising Seismic Waveforms Using a Wavelet-Transform-Based Machine-Learning Method

ABSTRACT Seismic waveform data recorded at stations can be thought of as a superposition of the signal from a source of interest and noise from other sources. Frequency-based filtering methods for waveform denoising do not result in desired outcomes when the targeted signal and noise occupy similar frequency bands. Recently, denoising techniques based on deep-learning convolutional neural networks (CNNs), in which a recorded waveform is decomposed into signal and noise components, have led to improved results. These CNN methods, which use short-time Fourier transform representations of the time series, provide signal and noise masks for the input waveform. These masks are used to create denoised signal and designaled noise waveforms, respectively. However, advancements in the field of image denoising have shown the benefits of incorporating discrete wavelet transforms (DWTs) into CNN architectures to create multilevel wavelet CNN (MWCNN) models. The MWCNN model preserves the details of the input due to the good time–frequency localization of the DWT. Here, we use a data set of over 382,000 constructed seismograms recorded by the University of Utah Seismograph Stations network to compare the performance of CNN and MWCNN-based denoising models. Evaluation of both models on constructed test data shows that the MWCNN model outperforms the CNN model in the ability to recover the ground-truth signal component in terms of both waveform similarity and preservation of amplitude information. Model evaluation of real-world data shows that both the CNN and MWCNN models outperform standard band-pass filtering (BPF; average improvement in signal-to-noise ratio of 9.6 and 19.7 dB, respectively, with respect to BPF). Evaluation of continuous data suggests the MWCNN denoiser can improve both signal detection capabilities and phase arrival time estimates.

Udder thermogram-based deep learning approach for mastitis detection in Murrah buffaloes

Mastitis, a production disease with multiple etiologies, inflicts significant economic losses among dairy farmers around the globe. In this study, an attempt has been made to detect mastitis through a Convolutional Neural Networks (CNN)-based deep learning model using 7615 udder thermograms of 40 Murrah buffaloes. The thermograms were grouped separately as healthy, sub-clinical (SCM), and clinical mastitis (CM) affected udder quarters based on California Mastitis Test (CMT) scores, Somatic Cell Count (SCC) values and thermal image analysis. Results of thermogram analysis revealed a significant increase (p < 0.01) in the mean values of udder skin surface temperature (USST) among SCM and CM-affected quarters compared to healthy quarters to the tune of 1.32 and 2.61 °C, respectively. The USST showed a strong positive correlation with the CMT score (r = 0.87, p < 0.01) and log10SCC value (r = 0.88, p < 0.01). The sequential (Normal vs. Clinical and Normal vs. Sub-clinical) models had training accuracy and validation accuracy of 0.999 and 0.988, 0.991 and 0.978, respectively. The confusion matrix for Normal vs. Clinical and Normal vs. Sub-clinical models reflected a loss of 0.009 and 0.029, precision of 0.947 and 0.980, and recall of 0.996 and 0.904, respectively. Consequently, the sequential (Normal vs. Clinical and Normal vs. Sub-clinical) models achieved a testing accuracy of 0.970 and 0.943, respectively. Thus, the improved deep-learning CNN models efficiently predicted SCM and CM cases in Murrah buffaloes.