Comparison of deep learning models for milk production forecasting at national scale

Comparison of deep learning models and a typical process-based model in glacio-hydrology simulation

This study develops and illustrates a hybrid k-medoids, random forest, and support vector regression (K-R-S) approach for predicting the lactation curves of individual primiparous cows within a targeted environment using monthly milk production data from their dams and paternal siblings. The model simulation and evaluation were based on historical test-day (TD) milk production data from 2010 to 2016 for 260 Wisconsin dairy farms. Data from older paternal siblings and dams were used to create family units (n = 6,400) of individual calves, from which their future performance was predicted. Test-day milk yield (MY) records from 2010 to 2014 were used for model training, whereas monthly milk production records of Holstein calves born in 2014 were used for model evaluation. The K-R-S hybrid approach was used to generate MY predictions for 5 randomly selected batches of 320 primiparous cows, which were used to evaluate model performance at the individual cow level by cross-validation. Across all 5 batches, the mean absolute error and the root mean square error of the K-R-S predictions were lower (by 24.2 and 23.4%, respectively) than that of the mean daily MY of paternal siblings. The K-R-S predictions of TD MY were closer to actual values 74.2 ± 2.0% of the time, as compared with means of paternal siblings'. The correlation between actual TD MY and K-R-S predictions was greater (0.34 ± 0.01) than the correlation between the actual yield and the mean of paternal siblings (0.08 ± 0.01). The results of this study demonstrate the effectiveness of the K-R-S hybrid approach for predicting future first-lactation MY of dairy calves in management applications, such as milk production forecasting or decision-support simulation, using only monthly TD yields of within-herd relatives and in the absence of detailed genomic data.

Due to technological advancement, agricultural production is increasingly dependent on electricity. At the same time, power delivery infrastructures are challenged by extreme weather events. Losses in primary food production due to electrical outages are still largely unquantified. This paper reports the effect of storm-induced power outages on milk production in Finland. The study used detailed, farm-level records of power cuts from 2010 to 2015 available from two power companies and contrasted them to the respective monthly milk production statistics collected at farm level. For each major storm event, deviation in the milk production compared to previous month was calculated for each farm. Effect of power outages onto milk production was estimated using linear mixed modeling. Power outages mainly occurred during and after storm events, and dairy farms experienced more outages than what was a national average for rural power customers. The power outages decreased the monthly milk yield of the most affected farms by 4.6% (farms experiencing outages longer than 72 h), and production recovered already for the month following the storm event. The results imply that milk production in Finland is prepared and resilient toward power outages shorter than 3 days and that the current magnitude of power outages in dairy farms is higher than what was known previously.

In recent years, deep learning models have demonstrated remarkable success in various image processing tasks, ranging from object recognition to medical image analysis. However, their performance often degrades in the presence of unseen data or adversarial attacks, highlighting the need for enhancing robustness and generalization. This paper explores innovative approaches to address these challenges, aiming to improve the reliability and applicability of deep learning models in real-world scenarios. The first section of the paper delves into the importance of robustness and generalization in deep learning models for image processing tasks. It discusses the implications of model vulnerabilities, such as overfitting to training data and susceptibility to adversarial perturbations, on the reliability of model predictions. [1] Through a comprehensive review of existing literature, various factors influencing robustness and generalization are identified, including dataset diversity, model architecture, regularization techniques, and adversarial training methods. The paper proposes novel methodologies to enhance the robustness and generalization capabilities of deep learning models. One key approach involves the integration of diverse training data sources, including synthetic data augmentation and domain adaptation techniques, to expose the model to a wider range of scenarios and improve its ability to generalize to unseen data. Additionally, advanced regularization techniques, such as dropout and batch normalization, are explored to mitigate overfitting and improve model generalization. The paper investigates the effectiveness of adversarial training strategies in enhancing model robustness against adversarial attacks. By incorporating adversarially generated examples during training, deep learning models can learn to better resist perturbations and maintain performance under adversarial conditions. Moreover, the paper explores the potential of incorporating uncertainty estimation methods, such as Bayesian neural networks and Monte Carlo dropout, to quantify model uncertainty and improve robustness in uncertain environments. This paper presents a comprehensive investigation into enhancing robustness and generalization in deep learning models for image processing tasks. By addressing key challenges such as overfitting, dataset bias, and adversarial vulnerabilities, the proposed methodologies offer promising avenues for improving the reliability and applicability of deep learning models in real-world scenarios. DOI: https://doi.org/10.52783/pst.193

Uncertainty quantification-based robust deep learning for building energy systems considering distribution shift problem

The automation of agricultural practices offers significant potential for boosting productivity while reducing labor requirements, particularly in fruit harvesting. However, accurately detecting tomatoes in dynamic and complex field environments remains a challenge due to issues such as high false positive rates, missed detections, variable illumination, occlusion, and heterogeneous foliage. In this research, tomato recognition for autonomous picking robots is conducted using the deep learning model Faster R-CNN (Region-based Convolutional Neural Network). Faster R-CNN excels in object detection tasks within complex scenes containing multiple objects and diverse backgrounds by generating region proposals and performing classifications, thereby addressing these challenges effectively. The Faster R-CNN model is trained and optimized on a comprehensive dataset of tomato plants collected under diverse field conditions for real-time detection. To enhance robustness and reliability in challenging environments, sensor fusion techniques integrating RGB and depth information are employed. This approach is expected to significantly reduce false positives and missed detections, improving the overall efficiency of autonomous picking robots. The proposed solution not only addresses critical inefficiencies in the tomato harvesting process but also advances the application of deep learning models in precision agriculture, promoting sustainable and efficient farming practices.

Recently, there is great interest to investigate the application of deep learning models for the prediction of clinical events using electronic health records (EHR) data. In EHR data, a patient's history is often represented as a sequence of visits, and each visit contains multiple events. As a result, deep learning models developed for sequence modeling, like recurrent neural networks (RNNs) are common architecture for EHR-based clinical events predictive models. While a large variety of RNN models were proposed in the literature, it is unclear if complex architecture innovations will offer superior predictive performance. In order to move this field forward, a rigorous evaluation of various methods is needed. In this study, we conducted a thorough benchmark of RNN architectures in modeling EHR data. We used two prediction tasks: the risk for developing heart failure and the risk of early readmission for inpatient hospitalization. We found that simple gated RNN models, including GRUs and LSTMs, often offer competitive results when properly tuned with Bayesian Optimization, which is in line with similar to findings in the natural language processing (NLP) domain. For reproducibility, Our codebase is shared at https://github.com/ZhiGroup/pytorch_ehr.

Detecting programmed death ligand 1 (PD-L1) expression based on immunohistochemical (IHC) staining is an important guide for the treatment of lung cancer with immune checkpoint inhibitors. However, this method has problems such as high staining costs, tumor heterogeneity, and subjective differences among pathologists. Therefore, the application of deep learning models to segment and quantitatively predict PD-L1 expression in digital sections of Hematoxylin and eosin (H&E) stained lung squamous cell carcinoma is of great significance. We constructed a dataset comprising H&E-stained digital sections of lung squamous cell carcinoma and used a Transformer Unet (TransUnet) deep learning network with an encoder-decoder design to segment PD-L1 negative and positive regions and quantitatively predict the tumor cell positive score (TPS). The results showed that the dice similarity coefficient (DSC) and intersection overunion (IoU) of deep learning for PD-L1 expression segmentation of H&E-stained digital slides of lung squamous cell carcinoma were 80 and 72%, respectively, which were better than the other seven cutting-edge segmentation models. The root mean square error (RMSE) of quantitative prediction TPS was 26.8, and the intra-group correlation coefficients with the gold standard was 0.92 (95% CI: 0.90-0.93), which was better than the consistency between the results of five pathologists and the gold standard. The deep learning model is capable of segmenting and quantitatively predicting PD-L1 expression in H&E-stained digital sections of lung squamous cell carcinoma, which has significant implications for the application and guidance of immune checkpoint inhibitor treatments. And the link to the code is https://github.com/Baron-Huang/PD-L1-prediction-via-HE-image.

Brain tumour detection is a critical medical procedure where early and accurate diagnosis significantly improves patient outcomes. This study explores the application of deep learning models, specifically VGG19 and InceptionV3, for detecting brain tumours in MRI images. We fine-tuned both models using transfer learning and evaluated them on a dataset of MRI scans. InceptionV3 achieved 100% validation accuracy, while VGG19 achieved 95%, demonstrating their high efficacy in medical image classification. In addition to deep learning, the study integrates insights from traditional image processing techniques, such as edge detection and probabilistic neural networks (PNNs), highlighting how combining deep learning with traditional methods can enhance image preprocessing and quality. The results underscore that while deep learning models are highly effective in brain tumour classification, traditional techniques still play a vital role in optimizing the overall detection process.

In environmental monitoring, deep learning models are used where we can either use past observations or extrapolated values with high uncertainty as input. The lag scheme is commonly applied during the modeling and construction process, in the application of deep learning models in multivariate time series prediction. For an adaptive feature engineering, an automated lag scheme is essential for improving the training efficiency. In multivariate time series (MTS) models, the predictive accuracy of artificial neural network ANN-type models can be improved by including more features. It is assumed that when processing a certain number of multivariate features, the timeliness and lag time of the inter-influencing between any pair of elements are different. This research aims to adopt an adaptive approach to solve it, namely, multi-level lag scheme. The research methods include literature review, searching for relevant technology frontiers, feasibility studies, selection and design solutions, modeling, data collection and pre-processing, experiments, evaluation, comprehensive analysis and conclusions. In proof of concept, we demonstrated a practical case of seasonal ANN type MTS model and public service on air quality. In terms of models, ANN type models were attempted with ARIMA as the comparing baseline. We used public data set of more than two base stations with pollution varying from low to high and including southern to northern district of a small city. Conclusions can be drawn from the analysis of multiple experimental results, proving that the proposed solution can effectively improve the training efficiency of the model. This is of great significance, so that most such models can be implemented to adaptively use lagged past measured data as input, instead of synchronously inputting future prediction values, which can greatly improve the practical application of the model in predictive ability.

Plant disease detection plays a critical role in ensuring agricultural productivity and food security. Accurate and efficient identification of plant diseases can aid in timely interventions, reducing potential crop losses. This paper presents a comprehensive study involving the application of deep learning models, namely CNN, ResNet, VGG, and Inception, to grayscale plant disease image datasets for apple, grape, and corn. The datasets consist of grayscale images divided into multiple disease classes. Initial experiments using standard deep learning models demonstrated reasonable accuracy. To further enhance performance, manual feature extraction techniques, including Histogram of Oriented Gradients (HOG), Oriented FAST and Rotated BRIEF (ORB), and Scale-Invariant Feature Transform (SIFT), were applied alongside deep features extracted using pretrained VGG and ResNet models. The extracted deep learning and handcrafted features were concatenated to form a comprehensive feature set. A Random Forest Classifier (RFC) was then applied to this combined feature set, resulting in improved accuracy compared to individual models.

IntroductionDrug safety has increasingly become a serious public health problem that threatens health and damages social economy. The common detection methods have the problem of high false positive rate. This study aims to introduce deep learning models into the adverse drug reaction (ADR) signal detection and compare different methods.MethodsThe data are based on adverse events collected by Center for ADR Monitoring of Guangdong. Traditional statistical methods were used for data preliminary screening. We transformed data into free text, extracted text information and made classification prediction by using the Long Short-Term Memory (LSTM) model. We compared it with the existing signal detection methods, including Logistic Regression, Random Forest, K-NearestNeighbor, and Multilayer Perceptron. The feature importance of the included variables was analyzed.ResultsA total of 2,376 ADR signals were identified between January 2018 and December 2019, comprising 448 positive signals and 1,928 negative signals. The sensitivity of the LSTM model based on free text reached 95.16%, and the F1-score was 0.9706. The sensitivity of Logistic Regression model based on feature variables was 86.83%, and the F1-score was 0.9063. The classification results of our model demonstrate superior sensitivity and F1-score compared to traditional methods. Several important variables “Reasons for taking medication”, “Serious ADR scenario 4”, “Adverse reaction analysis 5”, and “Dosage” had an important influence on the result.ConclusionThe application of deep learning models shows potential to improve the detection performance in ADR monitoring.

This paper focuses on pulse coupled neural network (PCNN) and digital image fusion. Aiming at the existing problems, this paper proposes a real-time deep learning model with dual-channel PCNN fusion algorithm based on image definition. It will also be helpful to digital image forensics. With the integration of the orthogonal color space that conforms to HVS, this algorithm simplifies the traditional PCNN model to a parallel dual-channel adaptive PCNN structure. Also, it can realize the adaptive processing by defining the image definition to be β, the coupled linking coefficient. As the dynamic threshold can be increased exponentially with this method, it can effectively solve the problems. The experimental result proves that our algorithm outperforms the traditional fusion algorithms according to the subjective visual effect or the objective assessment standard.

Double negative T (DNT) cells are a unique subset of CD3 + TCRαβ + T lymphocytes that lack CD4, CD8, or NK1.1 expression and constitute 3–5% of the total T cell population in C57BL/6 mice. They have increasingly gained recognition for their novel roles in the immune system, especially under autoimmune conditions. Conventional machine learning approaches such as principal component analysis have been employed in single-cell RNA sequencing (scRNA-seq) analysis to characterize DNT cells. However, advanced deep learning models such as Single Cell Variational Inference (scVI) have the capability to capture nonlinear gene expression patterns in the sequencing data. In this study, employing the deep learning methodology, we have revealed novel markers for splenic DNT cells in C57BL/6 mice which were validated with flow cytometry analysis. We classified DNT cells into two subgroups, naïve DNT (nDNT) cells differentiated by the expression of Ly6C and activated DNT (aDNT) cells differentiated by the expression of MHC-II. A prior study had predicted elevated expression of CD137/4-1BB encoded by Tnfrsf9 in nDNT cells; however, our analysis predicted and validated that CD137 was a marker for aDNT cells instead of nDNT cells. Innovatively, our data also identified CD30 encoded by Tnfrsf8 and CD153/CD30L encoded by Tnfsf8 as additional markers for aDNT cells. In addition, we classified three subgroups in nDNT cells and two subgroups in aDNT cells. Our scVI analysis suggested, and flow cytometry analysis confirmed, that Ly49G2 encoded by Klra7 was a marker for the nDNT0 subgroup. Importantly, we validated that MHC-II was indeed expressed by a subset of human DNT cells suggesting the presence of a human aDNT population. Furthermore, we found increased expression of CD30, CD153, and CD137 on aDNT cells in MRL/lpr mice compared to those in C57BL/6 mice suggesting potential pathogenic roles of these molecules in autoimmunity. Together, our comprehensive analysis has uncovered and validated novel markers for different subpopulations of DNT cells that can be used in the phenotypic and/or functional characterization of these relatively rare cells in health and disease.

There are some problems in feature extraction and representation of Chinese mental verbs, such as low accuracy and low efficiency. In order to further improve the computational efficiency and accuracy of Chinese mental verb text, based on deep learning theory, activation function and damage function were used to optimize the original model. Considering the calculation method of model gradient, the optimization model describing the characteristics of Chinese mental verbs is finally obtained. The model can be used to analyze the variation of the characteristic parameters of Chinese verbs and the method of representation. Finally, the model error is analyzed by the method of comparative verification. Relevant studies show that the number of outputs and output results corresponding to softmax function will influence the test results of the model. By comparing the curves, it can be seen that the curve corresponding to the output number has an obvious increasing trend, while the corresponding output result curve has an opposite changing trend. The linear and nonlinear characteristics of the two curves are obvious. The real value of the mean square error function shows a change of linear increase, while the corresponding output value shows a change trend of gradual decline, which indicates that the two kinds of data have different influences on the model under related algorithms. It can be seen from the error data that the gradual increase of independent variables will improve the accuracy of the test results. Five different Chinese mental verb parameters have different manifestations in the deep learning model: among them, declarative verbs fluctuate in a small range and have little corresponding influence. However, the fluctuation of nondeclarative verbs and positive and negative declarative verbs is relatively small, and the curve is relatively stable. Negative verbs have a positive influence on the test output. Double negative verbs have negative effects. Finally, the accuracy of the model is verified by calculating the difference between experimental data and model data. This research can provide theoretical support and model verification method for the application of deep learning model in other fields of Chinese language.