Shallow Neural Network Model Research Articles

Demand forecasting model for time-series pharmaceutical data using shallow and deep neural network model.

Demand forecasting is a scientific and methodical assessment of future demand for a critical product.The effective Demand Forecast Model (DFM) enables pharmaceutical companies to be successful in the global market. The purpose of this research paper is to validate various shallow and deep neural network methods for demand forecasting, with the aim of recommending sales and marketing strategies based on the trend/seasonal effects of eight different groups of pharmaceutical products with different characteristics. The root mean squared error (RMSE) is used as the predictive accuracy of DFMs. This study also found that the mean RMSE value of the shallow neural network-based DFMs was 6.27 for all drug categories, which was lower than deep neural network models. According to the findings, DFMs based on shallow neural networks can effectively estimate future demand for pharmaceutical products.

A Comparative Study of the Accuracy of Machine Learning Models for Predicting Tempered Martensite Hardness According to Model Complexity

We investigated various numerical methods including a physical-based empirical equation, linear regression, shallow neural network, and deep learning approaches, to compare their accuracy for predicting the hardness of tempered martensite in low alloy steels. The physical-based empirical equation, which had been previously proposed with experimental data, was labelled and used in the present study. While it had a smaller number of coefficients, the prediction accuracy of the physical-based empirical equation was almost similar to that of the regression model based on the response surface method. The prediction accuracy of the machine learning models clearly improved as the number of layers increased and became more complicated in structure before the model began to overfit. The key point we found was that a single layered neural network model with optimized hyperparameters resulted in similar or better hardness prediction performance compared to deep learning models with a more complex architecture. We also analyzed 18 research papers from the literature which used neural network models to predict the hardness of steels. Only two recent papers adopted a convolutional neural network, as a kind of deep learning model, in a new attempt to predict hardness. The other 16 papers from 1998 to 2021 commonly chose shallow neural network models because a more complicated model is less effective than a simple model for regression problems with well-labeled experimental data in materials science and engineering.

MNet-10: A robust shallow convolutional neural network model performing ablation study on medical images assessing the effectiveness of applying optimal data augmentation technique.

Interpretation of medical images with a computer-aided diagnosis (CAD) system is arduous because of the complex structure of cancerous lesions in different imaging modalities, high degree of resemblance between inter-classes, presence of dissimilar characteristics in intra-classes, scarcity of medical data, and presence of artifacts and noises. In this study, these challenges are addressed by developing a shallow convolutional neural network (CNN) model with optimal configuration performing ablation study by altering layer structure and hyper-parameters and utilizing a suitable augmentation technique. Eight medical datasets with different modalities are investigated where the proposed model, named MNet-10, with low computational complexity is able to yield optimal performance across all datasets. The impact of photometric and geometric augmentation techniques on different datasets is also evaluated. We selected the mammogram dataset to proceed with the ablation study for being one of the most challenging imaging modalities. Before generating the model, the dataset is augmented using the two approaches. A base CNN model is constructed first and applied to both the augmented and non-augmented mammogram datasets where the highest accuracy is obtained with the photometric dataset. Therefore, the architecture and hyper-parameters of the model are determined by performing an ablation study on the base model using the mammogram photometric dataset. Afterward, the robustness of the network and the impact of different augmentation techniques are assessed by training the model with the rest of the seven datasets. We obtain a test accuracy of 97.34% on the mammogram, 98.43% on the skin cancer, 99.54% on the brain tumor magnetic resonance imaging (MRI), 97.29% on the COVID chest X-ray, 96.31% on the tympanic membrane, 99.82% on the chest computed tomography (CT) scan, and 98.75% on the breast cancer ultrasound datasets by photometric augmentation and 96.76% on the breast cancer microscopic biopsy dataset by geometric augmentation. Moreover, some elastic deformation augmentation methods are explored with the proposed model using all the datasets to evaluate their effectiveness. Finally, VGG16, InceptionV3, and ResNet50 were trained on the best-performing augmented datasets, and their performance consistency was compared with that of the MNet-10 model. The findings may aid future researchers in medical data analysis involving ablation studies and augmentation techniques.

A shallow deep learning approach to classify skin cancer using down-scaling method to minimize time and space complexity.

The complex feature characteristics and low contrast of cancer lesions, a high degree of inter-class resemblance between malignant and benign lesions, and the presence of various artifacts including hairs make automated melanoma recognition in dermoscopy images quite challenging. To date, various computer-aided solutions have been proposed to identify and classify skin cancer. In this paper, a deep learning model with a shallow architecture is proposed to classify the lesions into benign and malignant. To achieve effective training while limiting overfitting problems due to limited training data, image preprocessing and data augmentation processes are introduced. After this, the 'box blur' down-scaling method is employed, which adds efficiency to our study by reducing the overall training time and space complexity significantly. Our proposed shallow convolutional neural network (SCNN_12) model is trained and evaluated on the Kaggle skin cancer data ISIC archive which was augmented to 16485 images by implementing different augmentation techniques. The model was able to achieve an accuracy of 98.87% with optimizer Adam and a learning rate of 0.001. In this regard, parameter and hyper-parameters of the model are determined by performing ablation studies. To assert no occurrence of overfitting, experiments are carried out exploring k-fold cross-validation and different dataset split ratios. Furthermore, to affirm the robustness the model is evaluated on noisy data to examine the performance when the image quality gets corrupted.This research corroborates that effective training for medical image analysis, addressing training time and space complexity, is possible even with a lightweighted network using a limited amount of training data.

Spectral Ranking Regression

We study the problem of ranking regression, in which a dataset of rankings is used to learn Plackett–Luce scores as functions of sample features. We propose a novel spectral algorithm to accelerate learning in ranking regression. Our main technical contribution is to show that the Plackett–Luce negative log-likelihood augmented with a proximal penalty has stationary points that satisfy the balance equations of a Markov Chain. This allows us to tackle the ranking regression problem via an efficient spectral algorithm by using the Alternating Directions Method of Multipliers (ADMM). ADMM separates the learning of scores and model parameters, and in turn, enables us to devise fast spectral algorithms for ranking regression via both shallow and deep neural network (DNN) models. For shallow models, our algorithms are up to 579 times faster than the Newton’s method. For DNN models, we extend the standard ADMM via a Kullback–Leibler proximal penalty and show that this is still amenable to fast inference via a spectral approach. Compared to a state-of-the-art siamese network, our resulting algorithms are up to 175 times faster and attain better predictions by up to 26% Top-1 Accuracy and 6% Kendall-Tau correlation over five real-life ranking datasets.

Needle in a Haystack: Spotting and recognising micro-expressions “in the wild”

Computational research on facial micro-expressions has long focused on videos captured under constrained laboratory conditions due to the challenging elicitation process and limited samples that are publicly available. Moreover, processing micro-expressions is extremely challenging under unconstrained scenarios. This paper introduces, for the first time, a completely automatic micro-expression “spot-and-recognize” framework that is performed on in-the-wild videos, such as in poker games and political interviews. The proposed method first spots the apex frame from a video by handling head movements and unconscious actions which are typically larger in motion intensity, with alignment employed to enforce a canonical face pose. Optical flow guided features play a central role in our method: they can robustly identify the location of the apex frame, and are used to learn a shallow neural network model for emotion classification. Experimental results demonstrate the feasibility of the proposed methodology, establishing good baselines for both spotting and recognition tasks – ASR of 0.33 and F1-score of 0.6758 respectively on the MEVIEW micro-expression database. In addition, we present comprehensive qualitative and quantitative analyses to further show the effectiveness of the proposed framework, with new suggestion for an appropriate evaluation protocol. In a nutshell, this paper provides a new benchmark for apex spotting and emotion recognition in an in-the-wild setting.

Shallow neural networks trained to detect collisions recover features of visual loom-selective neurons.

Animals have evolved sophisticated visual circuits to solve a vital inference problem: detecting whether or not a visual signal corresponds to an object on a collision course. Such events are detected by specific circuits sensitive to visual looming, or objects increasing in size. Various computational models have been developed for these circuits, but how the collision-detection inference problem itself shapes the computational structures of these circuits remains unknown. Here, inspired by the distinctive structures of LPLC2 neurons in the visual system of Drosophila, we build anatomically-constrained shallow neural network models and train them to identify visual signals that correspond to impending collisions. Surprisingly, the optimization arrives at two distinct, opposing solutions, only one of which matches the actual dendritic weighting of LPLC2 neurons. Both solutions can solve the inference problem with high accuracy when the population size is large enough. The LPLC2-like solutions reproduces experimentally observed LPLC2 neuron responses for many stimuli, and reproduces canonical tuning of loom sensitive neurons, even though the models are never trained on neural data. Thus, LPLC2 neuron properties and tuning are predicted by optimizing an anatomically-constrained neural network to detect impending collisions. More generally, these results illustrate how optimizing inference tasks that are important for an animal's perceptual goals can reveal and explain computational properties of specific sensory neurons.

Deep Learning with Backtracking Search Optimization Based Skin Lesion Diagnosis Model

Nowadays, quality improvement and increased accessibility to patient data, at a reasonable cost, are highly challenging tasks in healthcare sector. Internet of Things (IoT) and Cloud Computing (CC) architectures are utilized in the development of smart healthcare systems. These entities can support real-time applications by exploiting massive volumes of data, produced by wearable sensor devices. The advent of evolutionary computation algorithms and Deep Learning (DL) models has gained significant attention in healthcare diagnosis, especially in decision making process. Skin cancer is the deadliest disease which affects people across the globe. Automatic skin lesion classification model has a highly important application due to its fine-grained variability in the presence of skin lesions. The current research article presents a new skin lesion diagnosis model i.e., Deep Learning with Evolutionary Algorithm based Image Segmentation (DL-EAIS) for IoT and cloud-based smart healthcare environments. Primarily, the dermoscopic images are captured using IoT devices, which are then transmitted to cloud servers for further diagnosis. Besides, Backtracking Search optimization Algorithm (BSA) with Entropy-Based Thresholding (EBT) i.e., BSA-EBT technique is applied in image segmentation. Followed by, Shallow Convolutional Neural Network (SCNN) model is utilized as a feature extractor. In addition, Deep-Kernel Extreme Learning Machine (D-KELM) model is employed as a classification model to determine the class labels of dermoscopic images. An extensive set of simulations was conducted to validate the performance of the presented method using benchmark dataset. The experimental outcome infers that the proposed model demonstrated optimal performance over the compared techniques under diverse measures.

Symbolic Regression Based Feature Extraction of Shallow Neural-Networks for Identification and Prediction

This paper proposes a feature extraction method to improve the performance of shallow neural-network models with less number of parameters to apply especially on embedded system design at remote applications. Feature extraction method is designed using fuzzy c-means clustering based fuzzy system design cascaded a layer of symbolic operators and functions, respectively. During the training stage of neural-networks, symbolic operators and functions are selected using random-learning theory with the unity internal weights such that based on the prediction performance, optimal sequences are recorded for feature extraction to be utilized on testing phase. Extracted features are here used to empower the single-layer neural-network (SLNN) with sigmoid hyperbolic activation functions, functional-link neural- network (FLNN) with Chebyshev polynomials and Pi-Sigma higher-order neural-network (PSNN) with sigmoid activation functions, respectively. The internal and output parameters of the appended shallow neural-networks are optimized using batch optimization methods. Proposed regression models are first tested on identification of an artificial discrete-time dynamic system and real-time inverted pendulum then also for prediction of the sunspot time-series and traffic density estimation. As a result, the prediction performance of shallow neural networks is improved to be used in future applications.

Pathological categorization of lung carcinoma from multimodality images using convolutional neural networks

Accurate diagnosis and treatment of lung carcinoma depend on its pathological type and staging. Normally, pathological analysis is performed either by needle biopsy or surgery. Therefore, a noninvasive method to detect pathological types would be a good alternative. Hence, this work aims at categorizing different types of lung cancer from multimodality images. The proposed approach involves two stages. Initially, a Blind/Referenceless Image Spatial Quality Evaluator-based approach is adopted to extract the slices having lung abnormalities from the dataset. The slices then are transferred to a novel shallow convolutional neural network model to detect adenocarcinoma, squamous cell carcinoma, and small cell carcinoma from multimodality images. The classifier efficacy is then investigated by comparing precision, recall, area under curve, and accuracy with pretrained models and existing methods. The results narrate that the suggested system outperformed with a testing accuracy of 95% in Positron emission tomography/computed tomography (PET/CT), 93% in CT images of the Lung-PET-CT-DX dataset, and 98% in the Lung3 dataset. Furthermore, a kappa score of 0.92 in PET/CT of Lung-PETCT-DX and 0.98 in CT of Lung3 exhibited the effectiveness of the presented system in the field of lung cancer classification.

Machine learning predicts fretting and fatigue key mechanical properties

The present work uses machine learning to predict fretting crack lengths and corresponding stress intensity factors (SIF) under partial slip conditions resulting in crack arrest. Plain fretting tests were first performed on cylinder/flat configurations in partial slip, in which the test sample was flat. Adjusting contact pressure and cylinder radius, both short and long crack arrest responses were achieved for the studied C-Mn steel. Finite element (FE) analysis was then used to compute the fretting SIF threshold ΔKth for each arrested cylinder/plane fretting crack condition. Under elastic fretting conditions, a coupled approach combining complete FE simulations modeling the crack and Rice's fracture integrals was used. When plasticity needed to be considered, an indirect method was applied, using FE simulations without the crack and classical weight functions once elastic shakedown was reached (decoupled approach). The fretting SIF threshold ΔKth could then be extrapolated to estimate the fatigue long crack SIF threshold ΔK0 when the fretting crack was long enough. The novelty of this research work resides in the use of Machine Learning to predict the key mechanical parameters introduced above. A backpropagation algorithm with Bayesian regularization was used to identify a shallow neural network model based on just fourteen experiments. A neural network-based model was then employed to describe fretting crack lengths and corresponding SIF of the studied alloy as a function of the fretting contact radius, the maximum surface pressure, and shear traction. Perfect correlations were obtained to predict both crack depth and associated SIF threshold. An investigation was performed to determine the reliability with which samples sizes matching the count of the available experimental points can be used to predict fretting crack lengths and corresponding SIF. A Monte-Carlo bootstrapping method was used to estimate the output confidence interval corresponding to specific target inputs. This analysis provided optimistic results as relatively small datasets may be sufficient for accurate predictions. The neural network described short to long crack behaviors under elastic or elastoplastic conditions, making it a valuable tool for predicting fatigue long crack ΔK0 based on fretting experiments.

Electrical impedance guides electrode array in cochlear implantation using machine learning and robotic feeder

Cochlear Implant provides an electronic substitute for hearing to severely or profoundly deaf patients. However, postoperative hearing outcomes significantly depend on the proper placement of electrode array (EA) into scala tympani (ST) during cochlear implant surgery. Due to limited intra-operative methods to access array placement, the objective of the current study was to evaluate the relationship between EA complex impedance and different insertion trajectories in a plastic ST model. A prototype system was designed to measure bipolar complex impedance (magnitude and phase) and its resistive and reactive components of electrodes. A 3-DoF actuation system was used as an insertion feeder. 137 insertions were performed from 3 different directions at a speed of 0.08 mm/s. Complex impedance data of 8 electrode pairs were sequentially recorded in each experiment. Machine learning algorithms were employed to classify both the full and partial insertion lengths. Support Vector Machine (SVM) gave the highest 97.1% accuracy for full insertion. When a real-time prediction was tested, Shallow Neural Network (SNN) model performed better than other algorithms using partial insertion data. The highest accuracy was found at 86.1% when 4 time samples and 2 apical electrode pairs were used. Direction prediction using partial data has the potential of online control of the insertion feeder for better EA placement. Accessing the position of the electrode array during the insertion has the potential to optimize its intraoperative placement that will result in improved hearing outcomes.

Electrocardiogram Quality Assessment with a Generalized Deep Learning Model Assisted by Conditional Generative Adversarial Networks.

The electrocardiogram (ECG) is widely used for cardiovascular disease diagnosis and daily health monitoring. Before ECG analysis, ECG quality screening is an essential but time-consuming and experience-dependent work for technicians. An automatic ECG quality assessment method can reduce unnecessary time loss to help cardiologists perform diagnosis. This study aims to develop an automatic quality assessment system to search qualified ECGs for interpretation. The proposed system consists of data augmentation and quality assessment parts. For data augmentation, we train a conditional generative adversarial networks model to get an ECG segment generator, and thus to increase the number of training data. Then, we pre-train a deep quality assessment model based on a training dataset composed of real and generated ECG. Finally, we fine-tune the proposed model using real ECG and validate it on two different datasets composed of real ECG. The proposed system has a generalized performance on the two validation datasets. The model’s accuracy is 97.1% and 96.4%, respectively for the two datasets. The proposed method outperforms a shallow neural network model, and also a deep neural network models without being pre-trained by generated ECG. The proposed system demonstrates improved performance in the ECG quality assessment, and it has the potential to be an initial ECG quality screening tool in clinical practice.

Computer-aided detection of breast cancer on the Wisconsin dataset: An artificial neural networks approach

The early detection of breast cancer (BC) has a significant impact on reducing the disease’s mortality rate. As an effective cost- and time-saving tool, computer-aided diagnosis (CAD) systems have been developed in this research field, aiding clinicians and radiologists’ decision-making process by offering highly accurate information. In this study, a shallow artificial neural network (ANN) model with one hidden layer is used to diagnose and predict BC using the Wisconsin breast cancer dataset (WBCD) and the Wisconsin diagnostic breast cancer (WDBC) dataset without employing feature optimization or selection algorithms. The datasets are divided into 80% for training and 20% for testing using five-fold cross-validation. The model’s effectiveness and efficiency are evaluated based on sensitivity, specificity, precision, accuracy, and F1 score, along with the area under the receiver-operating characteristic curve (AUC). In the task of classifying benign and malignant tumours using the WBCD, the shallow ANN model showed promising performance with an average accuracy of 99.85%, specificity of 99.72%, sensitivity of 100%, precision of 99.69%, and F1 score of 99.84%. For BC detection using WDBC, it achieved an average accuracy of 99.47%, specificity of 99.53%, sensitivity of 99.59%, precision of 98.71%, and F1 score of 99.13%. The AUC of the proposed model was 99.86% and 99.56% for the WBCD and the WDBC dataset, respectively, illustrating the model’s discrimination capacity. Moreover, the ANN model outperformed state-of-the-art models that integrate feature optimization and selection algorithms to classify BC tumours using WBCD and WDBC. Hence, the shallow ANN model presented here demonstrates significant potential for diagnosing BC using WBCD and WDBC without the need for feature optimization or selection algorithms.

An Ensemble Learning Algorithm for Machinery Fault Diagnosis Based on Convolutional Neural Network and Gradient Boosting Decision Tree

In the massive mechanical fault data, the value density of fault information is low, and the data quality is uneven. What’s more, the multi-source signals collected by different sampling methods are different. At present, the expert system or shallow neural network model with weak self-learning ability cannot meet the requirements. Therefore, aiming at the characteristics of coupling, uncertainty and concurrency of mechanical faults, this paper constructs two kinds of 2D-CNN fault feature data sets, and uses Convolutional Neural Network (CNN) with strong self-learning ability to build two kinds of fault diagnosis models: CNN-Z and CNN-F. With CNN-Z and CNN-F models as base learners, this paper utilizes the ensemble algorithm Gradient Boosting Decision Tree (GBDT) to combine multiple bases. Compared with the results of the single base learner, the outcomes have higher accuracy and lower generalization error. Through the analysis and comparison of the performance indicators of the algorithm, this paper concludes that the diagnosis error of the fault diagnosis algorithm based on CNN and GBDT is the lowest with 1.79%, and the effectiveness, reliability and accuracy of the proposed algorithm in mining hidden fault state information are verified.

Simultaneous quantification of Au and Ag composition from Au–Ag bi-metallic LIBS spectra combined with shallow neural network model for multi-output regression

Simultaneous quantification of Au and Ag composition from Au–Ag bi-metallic LIBS spectra combined with shallow neural network model for multi-output regression

Penetration Depth Modeling and Process Parameter Maps for Laser Welds Using Machine Learning

Penetration control is an important factor in determining the weld quality in keyhole mode laser welding, which enables deep penetration. In this study, machine learning models and neural network models were developed by using 380 published welding data which were constructed for steel base metals under the following welding conditions: a laser power of 0.3-16.7 kW, a welding speed of 0.3-20.0 m/min, and a bead diameter of 0.05-0.78 mm. A machine learning model SVM (supported vector machine) could accurately predict the penetration depth with a coefficient of determination, R2 of 0.95. A shallow neural network model with five nodes in only one hidden layer was developed with a slightly improved accuracy with R2 of 0.98. It was confirmed that neither model was overfitted, and process parameters (welding speed and beam diameter) maps with penetration depth contours were provided for a laser power of 2-8 kW.

The detection of mild traumatic brain injury in paediatrics using artificial neural networks

Head computed tomography (CT) is the gold standard in emergency departments (EDs) to evaluate mild traumatic brain injury (mTBI) patients, especially for paediatrics. Data-driven models for successfully classifying head CT scans that have mTBI will be valuable in terms of timeliness and cost-effectiveness for TBI diagnosis. This study applied two different machine learning (ML) models to diagnose mTBI in a paediatric population collected as part of the paediatric emergency care applied research network (PECARN) study between 2004 and 2006. The models were conducted using 15,271 patients under the age of 18 years with mTBI and had a head CT report. In the conventional model, random forest (RF) ranked the features to reduce data dimensionality and the top ranked features were used to train a shallow artificial neural network (ANN) model. In the second model, a deep ANN applied to classify positive and negative mTBI patients using the entirety of the features available. The dataset was divided into two subsets: 80% for training and 20% for testing using five-fold cross-validation. Accuracy, sensitivity, precision, and specificity were calculated by comparing the model's prediction outcome to the actual diagnosis for each patient. RF ranked ten clinical demographic features and twelve CT-findings; the hybrid RF-ANN model achieved an average specificity of 99.96%, sensitivity of 95.98%, precision of 99.25%, and accuracy of 99.74% in identifying positive mTBI from negative mTBI subjects. The deep ANN proved its ability to carry out the task efficiently with an average specificity of 99.9%, sensitivity of 99.2%, precision of 99.9%, and accuracy of 99.9%. The performance of the two proposed models demonstrated the feasibility of using ANN to diagnose mTBI in a paediatric population. This is the first study to investigate deep ANN in a paediatric cohort with mTBI using clinical and non-imaging data and diagnose mTBI with balanced sensitivity and specificity using shallow and deep ML models. This method, if validated, would have the potential to reduce the burden of TBI evaluation in EDs and aide clinicians in the decision-making process.

Maria: Accurate Prediction of MHC-II Peptide Presentation with Deep-Learning and Lymphoma Patient MHC-II Ligandome

Background: The presentation of antigens by Major Histocompatibility Complex Class II (MHC-II) is an essential component of adaptive immune response. By combining whole exome sequencing and tandem mass spectrometry (LC-MS/MS), we recently demonstrated that MHC-II presented immunoglobulin neoantigens are common recognition targets in mantle cell lymphoma (MCL) [Khodadoust et al 2017 Nature]. While patient proteomic data can be difficult to obtain, computational methods can learn from these data to predict cancer neoantigen presentation informing personalized immunotherapeutic strategies across cancers. Unfortunately, current tools for predicting peptide presentation by MHC-II have major limitations due to the complexity of presentation pathways and the promiscuity of binding motifs for MHC-II alleles. We hypothesized that a method trained on naturally presented MHC-II ligandomes integrating both sequence and gene expression features could better predict presentation of tumor neoantigens.Method: We trained a recurrent neural network (RNN) model on 19 mantle cell lymphoma MHC-II ligandomes (>30,000 sequences) to build MARIA (MHC Analysis with RNN Integrated Architecture). MARIA is a deep learning algorithm that predicts peptide MHC-II presentation probabilities based on peptide sequences, neighboring context in each protein (cleavage signatures), patient MHC alleles, and gene expression levels. We evaluated the performance of MARIA with 10-fold cross-validation and also using held out data from both B-cell lymphoma and melanoma patients.Results: Gene expression levels and cleavage signatures of corresponding peptides have a profound influence on MHC-II peptide presentation but are not incorporated in standard prediction algorithms (Figure 1a). MARIA presentation scores achieved over 0.93 AUC under cross-validation on validated MHC-II ligands from our lymphoma dataset (Figure 1a). In comparison, predicted binding scores alone gave only 0.70 AUC, and conventional shallow neural network models (e.g., NetMHCIIpan3.1) gave 0.87 AUC when trained on the same dataset. When tested on held-out lymphoma and melanoma empirical ligandome data, MARIA sustained over 70% sensitivity with 90% specificity for detection of MHC-II ligands. Though MARIA was exclusively trained on non-immunoglobulin human sequences, it correctly predicted IgM presentation hot spots discovered by direct antigen presentation profiling using LC-MS/MS (Figure 1b), as well as hotspots in alpha-gliadin, a known Celiac Disease antigen, in an HLA-restricted fashion.Conclusion: MARIA enables high throughput antigen screening with higher accuracy than other methods. It can be applied to immunology applications such as vaccine design, patient profiling, and neo- and auto-antigen identification.Figure 1. Performance of MARIA predicting human MHC-II peptide presentation. a) Five different predictors of MHC-II peptide presentation were used to differentiate 3290 validation MHC-II peptides from 7500 random human decoy peptides. MARIA scores that incorporate sequence information, gene expression levels, binding scores, and cleavage signatures outperformed other methods with an aggregate AUC=0.93. b) MARIA predicted MHC-II presentation of lymphoma IgM (left) compared to experimentally recovered MHC-II peptides (right). MARIA highlighted MHC-II presentation hot spots on IgM FR3 and CH2 regions, consistent with the experimental heat-map (Spearman R=0.63, p-value<0.0001). [Display omitted] DisclosuresDavis:Vir Biotechnology: Consultancy, Equity Ownership, Honoraria; PACT Bio: Consultancy, Equity Ownership, Honoraria; Adicet Inc: Consultancy, Equity Ownership, Honoraria; Chuga Pharmabody: Consultancy, Honoraria; Amgen: Consultancy, Research Funding; Atreca: Consultancy, Equity Ownership, Honoraria; Juno: Consultancy, Equity Ownership, Honoraria. Altman:Karius: Consultancy; Personalis: Consultancy; Pfizer: Consultancy.

Using convolutional neural networks for tick image recognition - a preliminary exploration.

Smartphone cameras and digital devices are increasingly used in the capture of tick images by the public as citizen scientists, and rapid advances in deep learning and computer vision has enabled brand new image recognition models to be trained. However, there is currently no web-based or mobile application that supports automated classification of tick images. The purpose of this study was to compare the accuracy of a deep learning model pre-trained with millions of annotated images in Imagenet, against a shallow custom-build convolutional neural network (CNN) model for the classification of common hard ticks present in anthropic areas from northeastern USA. We created a dataset of approximately 2000 images of four tick species (Ixodes scapularis, Dermacentor variabilis, Amblyomma americanum and Haemaphysalis sp.), two sexes (male, female) and two life stages (adult, nymph). We used these tick images to train two separate CNN models - ResNet-50 and a simple shallow custom-built. We evaluated our models' performance on an independent subset of tick images not seen during training. Compared to the ResNet-50 model, the small shallow custom-built model had higher training (99.7%) and validation (99.1%) accuracies. When tested with new tick image data, the shallow custom-built model yielded higher mean prediction accuracy (80%), greater confidence of true detection (88.7%) and lower mean response time (3.64s). These results demonstrate that, with limited data size for model training, a simple shallow custom-built CNN model has great prospects for use in the classification of common hard ticks present in anthropic areas from northeastern USA.