Effective training of nanopore callers for epigenetic marks with limited labelled data.

Nanopore sequencing platforms combined with supervised machine learning (ML) have been effective at detecting base modifications in DNA such as 5-methylcytosine (5mC) and N6-methyladenine (6mA). These ML-based nanopore callers have typically been trained on data that span all modifications on all possible DNA [Formula: see text]-mer backgrounds-a complete training dataset. However, as nanopore technology is pushed to more and more epigenetic modifications, such complete training data will not be feasible to obtain. Nanopore calling has historically been performed with hidden Markov models (HMMs) that cannot make successful calls for [Formula: see text]-mer contexts not seen during training because of their independent emission distributions. However, deep neural networks (DNNs), which share parameters across contexts, are increasingly being used as callers, often outperforming their HMM cousins. It stands to reason that a DNN approach should be able to better generalize to unseen [Formula: see text]-mer contexts. Indeed, herein we demonstrate that a common DNN approach (DeepSignal) outperforms a common HMM approach (Nanopolish) in the incomplete data setting. Furthermore, we propose a novel hybrid HMM-DNN approach, amortized-HMM, that outperforms both the pure HMM and DNN approaches on 5mC calling when the training data are incomplete. This type of approach is expected to be useful for calling other base modifications such as 5-hydroxymethylcytosine and for the simultaneous calling of different modifications, settings in which complete training data are not likely to be available.

Detecting fungi-affected multi-crop disease on heterogeneous region dataset using modified ResNeXt approach.

Crop diseases pose significant threats to agriculture, impacting crop production. Biotic factors contribute to various diseases, including fungal, bacterial, and viral infections. Recent advancements in deep learning present a novel approach to the detection and recognition of these crop diseases. While considerable research has focused on identifying and recognizing crop diseases, fungal disease-affected crops have received relatively less attention and also detecting disease on different region datasets. This paper is about spotting fungal diseases in crops across different regions with diverse climates. It emphasizes the need for tailored detection methods, addressing the risk of mycotoxin production by fungi, which can harm both humans and animals. Detecting fungal diseases in apple, guava, and custard apple crops such as spot, scab, rust, rot, leaf spot, and insect ate. In the proposed work, the modified ResNeXt variant of the convolution neural network (CNN) technique was employed to predict 3 major crop classes of fungal disease. Initially, using Inception-v7 and ResNet for fungal disease in crops did not yield satisfactory results. A modified ResNeXt CNN model was proposed, showing improved fungal disease prediction. The novel model underwent a comparison with established methodologies. The suggested model draws upon a benchmark dataset consisting of 14,408 images capturing fungal diseases, categorized into three distinct classes: apple, custard apple, and guava. Experimental outcomes show that the proposed mutated ResNeXt model outperformed the state-of-the-art approaches. The model achieved 98.92% accuracy and high performance across recall, precision, and F1-score (above 99%) for the benchmark dataset, which gained encouragement and was comparable with the state-of-the-art approach.

Cocrystal Prediction of Nifedipine Based on the Graph Neural Network and Molecular Electrostatic Potential Surface.

Nifedipine (NIF) is a dihydropyridine calcium channel blocker primarily used to treat conditions such as hypertension and angina. However, its low solubility and low bioavailability limit its effectiveness in clinical practice. Here, we developed a cocrystal prediction model based on Graph Neural Networks (CocrystalGNN) for the screening of cocrystals with NIF. And scoring 50 coformers using CocrystalGNN. To validate the reliability of the model, we used another prediction method, Molecular Electrostatic Potential Surface (MEPS), to verify the prediction results. Subsequently, we performed a second validation using experiments. The results indicate that our model achieved high performance. Ultimately, cocrystals of NIF were successfully obtained and all cocrystals exhibited better solubility and dissolution characteristics compared to the parent drug. This study lays a solid foundation for combining virtual prediction with experimental screening to discover novel water-insoluble drug cocrystals.

Image-based recognition of parasitoid wasps using advanced neural networks.

Hymenoptera has some of the highest diversity and number of individuals among insects. Many of these species potentially play key roles as food sources, pest controllers and pollinators. However, little is known about the diversity and biology and ~80% of the species have not yet been described. Classical taxonomy based on morphology is a rather slow process but DNA barcoding has already brought considerable progress in identification. Innovative methods such as image-based identification and automation can further speed up the process. We present a proof of concept for image data recognition of a parasitic wasp family, the Diapriidae (Hymenoptera), obtained as part of the GBOL III project. These tiny (1.2-4.5mm) wasps were photographed and identified using DNA barcoding to provide a solid ground truth for training a neural network. Taxonomic identification was used down to the genus level. Subsequently, three different neural network architectures were trained, evaluated and optimised. As a result, 11 different genera of diaprids and one mixed group of 'other Hymenoptera' can be classified with an average accuracy of 96%. Additionally, the sex of the specimen can be classified automatically with an accuracy of >97%.

ECG autoencoder based on low-rank attention.

The prevalence of cardiovascular disease (CVD) has surged in recent years, making it the foremost cause of mortality among humans. The Electrocardiogram (ECG), being one of the pivotal diagnostic tools for cardiovascular diseases, is increasingly gaining prominence in the field of machine learning. However, prevailing neural network models frequently disregard the spatial dimension features inherent in ECG signals. In this paper, we propose an ECG autoencoder network architecture incorporating low-rank attention (LRA-autoencoder). It is designed to capture potential spatial features of ECG signals by interpreting the signals from a spatial perspective and extracting correlations between different signal points. Additionally, the low-rank attention block (LRA-block) obtains spatial features of electrocardiogram signals through singular value decomposition, and then assigns these spatial features as weights to the electrocardiogram signals, thereby enhancing the differentiation of features among different categories. Finally, we utilize the ResNet-18 network classifier to assess the performance of the LRA-autoencoder on both the MIT-BIH Arrhythmia and PhysioNet Challenge 2017 datasets. The experimental results reveal that the proposed method demonstrates superior classification performance. The mean accuracy on the MIT-BIH Arrhythmia dataset is as high as 0.997, and the mean accuracy and F 1 -score on the PhysioNet Challenge 2017 dataset are 0.850 and 0.843.

Farmland pest recognition based on Cascade RCNN Combined with Swin-Transformer.

Agricultural pests and diseases pose major losses to agricultural productivity, leading to significant economic losses and food safety risks. However, accurately identifying and controlling these pests is still very challenging due to the scarcity of labeling data for agricultural pests and the wide variety of pest species with different morphologies. To this end, we propose a two-stage target detection method that combines Cascade RCNN and Swin Transformer models. To address the scarcity of labeled data, we employ random cut-and-paste and traditional online enhancement techniques to expand the pest dataset and use Swin Transformer for basic feature extraction. Subsequently, we designed the SCF-FPN module to enhance the basic features to extract richer pest features. Specifically, the SCF component provides a self-attentive mechanism with a flexible sliding window to enable adaptive feature extraction based on different pest features. Meanwhile, the feature pyramid network (FPN) enriches multiple levels of features and enhances the discriminative ability of the whole network. Finally, to further improve our detection results, we incorporated non-maximum suppression (Soft NMS) and Cascade R-CNN's cascade structure into the optimization process to ensure more accurate and reliable prediction results. In a detection task involving 28 pest species, our algorithm achieves 92.5%, 91.8%, and 93.7% precision in terms of accuracy, recall, and mean average precision (mAP), respectively, which is an improvement of 12.1%, 5.4%, and 7.6% compared to the original baseline model. The results demonstrate that our method can accurately identify and localize farmland pests, which can help improve farmland's ecological environment.

Signal automatic modulation based on AMC neural network fusion.

With the rapid development of modern communication technology, it has become a core problem in the field of communication to find new ways to effectively modulate signals and to classify and recognize the results of automatic modulation. To further improve the communication quality and system processing efficiency, this study combines two different neural network algorithms to optimize the traditional signal automatic modulation classification method. In this paper, the basic technology involved in the communication process, including automatic signal modulation technology and signal classification technology, is discussed. Then, combining parallel convolution and simple cyclic unit network, three different connection paths of automatic signal modulation classification model are constructed. The performance test results show that the classification model can achieve a stable training and verification state when the two networks are connected. After 20 and 29 iterations, the loss values are 0.13 and 0.18, respectively. In addition, when the signal-to-noise ratio (SNR) is 25dB, the classification accuracy of parallel convolutional neural network and simple cyclic unit network model is as high as 0.99. Finally, the classification models of parallel convolutional neural networks and simple cyclic unit networks have stable correct classification probabilities when Doppler shift conditions are introduced as interference in practical application environment. In summary, the neural network fusion classification model designed can significantly improve the shortcomings of traditional automatic modulation classification methods, and further improve the classification accuracy of modulated signals.

Anomaly detection in multivariate time series data using deep ensemble models.

Anomaly detection in time series data is essential for fraud detection and intrusion monitoring applications. However, it poses challenges due to data complexity and high dimensionality. Industrial applications struggle to process high-dimensional, complex data streams in real time despite existing solutions. This study introduces deep ensemble models to improve traditional time series analysis and anomaly detection methods. Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks effectively handle variable-length sequences and capture long-term relationships. Convolutional Neural Networks (CNNs) are also investigated, especially for univariate or multivariate time series forecasting. The Transformer, an architecture based on Artificial Neural Networks (ANN), has demonstrated promising results in various applications, including time series prediction and anomaly detection. Graph Neural Networks (GNNs) identify time series anomalies by capturing temporal connections and interdependencies between periods, leveraging the underlying graph structure of time series data. A novel feature selection approach is proposed to address challenges posed by high-dimensional data, improving anomaly detection by selecting different or more critical features from the data. This approach outperforms previous techniques in several aspects. Overall, this research introduces state-of-the-art algorithms for anomaly detection in time series data, offering advancements in real-time processing and decision-making across various industrial sectors.

Biologically meaningful genome interpretation models to address data underdetermination for the leaf and seed ionome prediction in Arabidopsis thaliana.

Genome interpretation (GI) encompasses the computational attempts to model the relationship between genotype and phenotype with the goal of understanding how the first leads to the second. While traditional approaches have focused on sub-problems such as predicting the effect of single nucleotide variants or finding genetic associations, recent advances in neural networks (NNs) have made it possible to develop end-to-end GI models that take genomic data as input and predict phenotypes as output. However, technical and modeling issues still need to be fixed for these models to be effective, including the widespread underdetermination of genomic datasets, making them unsuitable for training large, overfitting-prone, NNs. Here we propose novel GI models to address this issue, exploring the use of two types of transfer learning approaches and proposing a novel Biologically Meaningful Sparse NN layer specifically designed for end-to-end GI. Our models predict the leaf and seed ionome in A.thaliana, obtaining comparable results to our previous over-parameterized model while reducing the number of parameters by 8.8 folds. We also investigate how the effect of population stratification influences the evaluation of the performances, highlighting how it leads to (1) an instance of the Simpson's Paradox, and (2) model generalization limitations.

Role of artificial intelligence in multiple sclerosis management.

From a clinical viewpoint, there are enormous obstacles to early detection and diagnosis as well as treatment interventions for multiple sclerosis (MS). With the growing application of methods based on artificial intelligence (AI) to medical problems, there might be an opportunity for MS specialists and their patients. However, to develop accurate AI models, researchers must first examine large quantities of patient data (demographics, genetics-based information, clinical and radiological presentation) to identify the characteristics that distinguish illness from health. These are seen as promising approaches toward improved disease diagnosis, treatment individualization, and prognosis prediction. When applied to imaging data, the application of AI subdomains, such as machine learning (ML), deep learning (DL), and neural networks, have proven their value in healthcare. The application of AI in MS management marks a milestone within the healthcare sector. Now, as research and applications of AI continue to advance steadily, breakthroughs are coming at an ever-accelerating pace. As MS continues to develop, the integration of AI is more and more necessary for continuing progress in diagnosis and treatment as well as patient outcomes. In the field of multiple sclerosis, these algorithms have been used for many purposes, such as disease monitoring and therapy.

Human activity recognition using a single-photon direct time-of-flight sensor.

Single-Photon Avalanche Diode (SPAD) direct Time-of-Flight (dToF) sensors provide depth imaging over long distances, enabling the detection of objects even in the absence of contrast in colour or texture. However, distant objects are represented by just a few pixels and are subject to noise from solar interference, limiting the applicability of existing computer vision techniques for high-level scene interpretation. We present a new SPAD-based vision system for human activity recognition, based on convolutional and recurrent neural networks, which is trained entirely on synthetic data. In tests using real data from a 64×32 pixel SPAD, captured over a distance of 40 m, the scheme successfully overcomes the limited transverse resolution (in which human limbs are approximately one pixel across), achieving an average accuracy of 89% in distinguishing between seven different activities. The approach analyses continuous streams of video-rate depth data at a maximal rate of 66 FPS when executed on a GPU, making it well-suited for real-time applications such as surveillance or situational awareness in autonomous systems.

Surrogate gradient learning in spiking networks trained on event-based cytometry dataset.

Spiking neural networks (SNNs) are bio-inspired neural networks that - to an extent - mimic the workings of our brains. In a similar fashion, event-based vision sensors try to replicate a biological eye as closely as possible. In this work, we integrate both technologies for the purpose of classifying micro-particles in the context of label-free flow cytometry. We follow up on our previous work in which we used simple logistic regression with binary labels. Although this model was able to achieve an accuracy of over 98%, our goal is to utilize the system for a wider variety of cells, some of which may have less noticeable morphological variations. Therefore, a more advanced machine learning model like the SNNs discussed here would be required. This comes with the challenge of training such networks, since they typically suffer from vanishing gradients. We effectively apply the surrogate gradient method to overcome this issue achieving over 99% classification accuracy on test data for a four-class problem. Finally, rather than treating the neural network as a black box, we explore the dynamics inside the network and make use of that to enhance its accuracy and sparsity.

Deep learning restores speech intelligibility in multi-talker interference for cochlear implant users.

Cochlear implants (CIs) do not offer the same level of effectiveness in noisy environments as in quiet settings. Current single-microphone noise reduction algorithms in hearing aids and CIs only remove predictable, stationary noise, and are ineffective against realistic, non-stationary noise such as multi-talker interference. Recent developments in deep neural network (DNN) algorithms have achieved noteworthy performance in speech enhancement and separation, especially in removing speech noise. However, more work is needed to investigate the potential of DNN algorithms in removing speech noise when tested with listeners fitted with CIs. Here, we implemented two DNN algorithms that are well suited for applications in speech audio processing: (1) recurrent neural network (RNN) and (2) SepFormer. The algorithms were trained with a customized dataset ( ∼ 30 h), and then tested with thirteen CI listeners. Both RNN and SepFormer algorithms significantly improved CI listener's speech intelligibility in noise without compromising the perceived quality of speech overall. These algorithms not only increased the intelligibility in stationary non-speech noise, but also introduced a substantial improvement in non-stationary noise, where conventional signal processing strategies fall short with little benefits. These results show the promise of using DNN algorithms as a solution for listening challenges in multi-talker noise interference.

Preliminary study on AI-assisted diagnosis of bone remodeling in chronic maxillary sinusitis.

OBJECTIVE: To construct the deep learning convolution neural network (CNN) model and machine learning support vector machine (SVM) model of bone remodeling of chronic maxillary sinusitis (CMS) based on CT image data to improve the accuracy of image diagnosis. METHODS: Maxillary sinus CT data of 1000 samples in 500 patients from January 2018 to December 2021 in our hospital was collected. The first part is the establishment and testing of chronic maxillary sinusitis detection model by 461 images. The second part is the establishment and testing of the detection model of chronic maxillary sinusitis with bone remodeling by 802 images. The sensitivity, specificity and accuracy and area under the curve (AUC) value of the test set were recorded, respectively. RESULTS: Preliminary application results of CT based AI in the diagnosis of chronic maxillary sinusitis and bone remodeling. The sensitivity, specificity and accuracy of the test set of 93 samples of CMS, were 0.9796, 0.8636 and 0.9247, respectively. Simultaneously, the value of AUC was 0.94. And the sensitivity, specificity and accuracy of the test set of 161 samples of CMS with bone remodeling were 0.7353, 0.9685 and 0.9193, respectively. Simultaneously, the value of AUC was 0.89. CONCLUSION: It is feasible to use artificial intelligence research methods such as deep learning and machine learning to automatically identify CMS and bone remodeling in MSCT images of paranasal sinuses, which is helpful to standardize imaging diagnosis and meet the needs of clinical application.

Epilepsy detection based on multi-head self-attention mechanism.

CNN has demonstrated remarkable performance in EEG signal detection, yet it still faces limitations in terms of global perception. Additionally, due to individual differences in EEG signals, the generalization ability of epilepsy detection models is week. To address this issue, this paper presents a cross-patient epilepsy detection method utilizing a multi-head self-attention mechanism. This method first utilizes Short-Time Fourier Transform (STFT) to transform the original EEG signals into time-frequency features, then models local information using Convolutional Neural Network (CNN), subsequently captures global dependency relationships between features using the multi-head self-attention mechanism of Transformer, and finally performs epilepsy detection using these features. Meanwhile, this model employs a light multi-head attention mechanism module with an alternating structure, which can comprehensively extract multi-scale features while significantly reducing computational costs. Experimental results on the CHB-MIT dataset show that the proposed model achieves accuracy, sensitivity, specificity, F1 score, and AUC of 92.89%, 96.17%, 92.99%, 94.41%, and 96.77%, respectively. Compared to the existing methods, the method proposed in this paper obtains better performance along with better generalization.

Seismic resolution improving by a sequential convolutional neural network.

Thin-bed soft rock is one of the main factors causing large deformations of tunnels. In addition to relying on some innovative construction techniques, detecting thin beds early during surface geological exploration and advanced geological prediction can provide a basis for planning and implementing effective coping measures. The commonly used seismic methods cannot meet the requirement for thin beds detection accuracy. A high-resolution (HR) seismic signal processing method is proposed by introducing a sequential convolutional neural network (SCNN). The deep learning dataset including low-resolution (LR) and HR seismic is firstly prepared through forward modeling. Then, a one-dimension (1D) SCNN architecture is proposed to establish the mapping relationship between LR and HR sequences. Training on the prepared dataset, the HR seismic processing model with high accuracy is achieved and applied to some practical seismic data. The applications on both poststack and prestack seismic data demonstrate that the trained HR processing model can effectively improve the seismic resolution and restore the high-frequency seismic energy so that to recognize the thin-bed rocks.

Synergistic information supports modality integration and flexible learning in neural networks solving multiple tasks.

Striking progress has been made in understanding cognition by analyzing how the brain is engaged in different modes of information processing. For instance, so-called synergistic information (information encoded by a set of neurons but not by any subset) plays a key role in areas of the human brain linked with complex cognition. However, two questions remain unanswered: (a) how and why a cognitive system can become highly synergistic; and (b) how informational states map onto artificial neural networks in various learning modes. Here we employ an information-decomposition framework to investigate neural networks performing cognitive tasks. Our results show that synergy increases as networks learn multiple diverse tasks, and that in tasks requiring integration of multiple sources, performance critically relies on synergistic neurons. Overall, our results suggest that synergy is used to combine information from multiple modalities-and more generally for flexible and efficient learning. These findings reveal new ways of investigating how and why learning systems employ specific information-processing strategies, and support the principle that the capacity for general-purpose learning critically relies on the system's information dynamics.

Low-dose CT reconstruction using dataset-free learning.

Low-Dose computer tomography (LDCT) is an ideal alternative to reduce radiation risk in clinical applications. Although supervised-deep-learning-based reconstruction methods have demonstrated superior performance compared to conventional model-driven reconstruction algorithms, they require collecting massive pairs of low-dose and norm-dose CT images for neural network training, which limits their practical application in LDCT imaging. In this paper, we propose an unsupervised and training data-free learning reconstruction method for LDCT imaging that avoids the requirement for training data. The proposed method is a post-processing technique that aims to enhance the initial low-quality reconstruction results, and it reconstructs the high-quality images by neural work training that minimizes the ℓ1-norm distance between the CT measurements and their corresponding simulated sinogram data, as well as the total variation (TV) value of the reconstructed image. Moreover, the proposed method does not require to set the weights for both the data fidelity term and the plenty term. Experimental results on the AAPM challenge data and LoDoPab-CT data demonstrate that the proposed method is able to effectively suppress the noise and preserve the tiny structures. Also, these results demonstrate the rapid convergence and low computational cost of the proposed method. The source code is available at https://github.com/linfengyu77/IRLDCT.

Deep Neural Networks for Automated Outer Plexiform Layer Subsidence Detection on Retinal OCT of Patients With Intermediate AMD.

Purpose: The subsidence of the outer plexiform layer (OPL) is an important imaging biomarker on optical coherence tomography (OCT) associated with early outer retinal atrophy and a risk factor for progression to geographic atrophy in patients with intermediate age-related macular degeneration (AMD). Deep neural networks (DNNs) for OCT can support automated detection and localization of this biomarker. Methods: The method predicts potential OPL subsidence locations on retinal OCTs. A detection module (DM) infers bounding boxes around subsidences with a likelihood score, and a classification module (CM) assesses subsidence presence at the B-scan level. Overlapping boxes between B-scans are combined and scored by the product of the DM and CM predictions. The volume-wise score is the maximum prediction across all B-scans. One development and one independent external data set were used with 140 and 26 patients with AMD, respectively. Results: The system detected more than 85% of OPL subsidences with less than one false-positive (FP)/scan. The average area under the curve was 0.94 ± 0.03 for volume-level detection. Similar or better performance was achieved on the independent external data set. Conclusions: DNN systems can efficiently perform automated retinal layer subsidence detection in retinal OCT images. In particular, the proposed DNN system detects OPL subsidence with high sensitivity and a very limited number of FP detections. Translational Relevance: DNNs enable objective identification of early signs associated with high risk of progression to the atrophic late stage of AMD, ideally suited for screening and assessing the efficacy of the interventions aiming to slow disease progression.

Detection of Parkinson disease using multiclass machine learning approach.

Parkinson's Disease (PD) is a prevalent neurological condition characterized by motor and cognitive impairments, typically manifesting around the age of 50 and presenting symptoms such as gait difficulties and speech impairments. Although a cure remains elusive, symptom management through medication is possible. Timely detection is pivotal for effective disease management. In this study, we leverage Machine Learning (ML) and Deep Learning (DL) techniques, specifically K-Nearest Neighbor (KNN) and Feed-forward Neural Network (FNN) models, to differentiate between individuals with PD and healthy individuals based on voice signal characteristics. Our dataset, sourced from the University of California at Irvine (UCI), comprises 195 voice recordings collected from 31 patients. To optimize model performance, we employ various strategies including Synthetic Minority Over-sampling Technique (SMOTE) for addressing class imbalance, Feature Selection to identify the most relevant features, and hyperparameter tuning using RandomizedSearchCV. Our experimentation reveals that the FNN and KSVM models, trained on an 80-20 split of the dataset for training and testing respectively, yield the most promising results. The FNN model achieves an impressive overall accuracy of 99.11%, with 98.78% recall, 99.96% precision, and a 99.23% f1-score. Similarly, the KSVM model demonstrates strong performance with an overall accuracy of 95.89%, recall of 96.88%, precision of 98.71%, and an f1-score of 97.62%. Overall, our study showcases the efficacy of ML and DL techniques in accurately identifying PD from voice signals, underscoring the potential for these approaches to contribute significantly to early diagnosis and intervention strategies for Parkinson's Disease.