Amount Of Training Data Research Articles

Deep-learning-based inverse design of colloidal quantum dots

Because optical properties of colloidal quantum dots (QDs) greatly depend on their layer thicknesses at the sub-nanometer scale, accurately predicting optical properties based on these structural parameters can help streamline the development process. However, most of traditional inverse design approaches require time-consuming numerical simulations and optimization processes. In this simulation-only paper, we propose a deep-learning-based inverse design model for colloidal InP/ZnSe/ZnS QDs based on the structure parameters of layer thicknesses and optical properties of the emission and absorption spectrum. Four different deep neural network (DNN) structures are implemented and compared. A tandem DNN structure with the simultaneous use of both emission and absorption spectra as input data shows the best accuracy due to its ability to alleviate the non-uniqueness problem in the inverse design of colloidal QDs. Our inverse design model enables the prediction of layer thicknesses for QDs that exhibit on-demand optical emission/absorption spectra, which are particularly enhanced at the specific target wavelength region. Moreover, the weights and biases of the well-trained tandem DNN for InP/ZnSe/ZnS QDs can be transferred and tuned to implement a transfer-learning-assisted inverse design model for CdSe/ZnSe/ZnS QDs, where the amount of training data to achieve the average prediction accuracy of 99.3 % is reduced by a maximum of 71.4 %.

Creating and Leveraging a Synthetic Dataset of Cloud Optical Thickness Measures for Cloud Detection in MSI

Cloud formations often obscure optical satellite-based monitoring of the Earth’s surface, thus limiting Earth observation (EO) activities such as land cover mapping, ocean color analysis, and cropland monitoring. The integration of machine learning (ML) methods within the remote sensing domain has significantly improved performance for a wide range of EO tasks, including cloud detection and filtering, but there is still much room for improvement. A key bottleneck is that ML methods typically depend on large amounts of annotated data for training, which are often difficult to come by in EO contexts. This is especially true when it comes to cloud optical thickness (COT) estimation. A reliable estimation of COT enables more fine-grained and application-dependent control compared to using pre-specified cloud categories, as is common practice. To alleviate the COT data scarcity problem, in this work, we propose a novel synthetic dataset for COT estimation, which we subsequently leverage for obtaining reliable and versatile cloud masks on real data. In our dataset, top-of-atmosphere radiances have been simulated for 12 of the spectral bands of the Multispectral Imagery (MSI) sensor onboard Sentinel-2 platforms. These data points have been simulated under consideration of different cloud types, COTs, and ground surface and atmospheric profiles. Extensive experimentation of training several ML models to predict COT from the measured reflectivity of the spectral bands demonstrates the usefulness of our proposed dataset. In particular, by thresholding COT estimates from our ML models, we show on two satellite image datasets (one that is publicly available, and one which we have collected and annotated) that reliable cloud masks can be obtained. The synthetic data, the newly collected real dataset, code and models have been made publicly available.

Learning Only on Boundaries: A Physics-Informed Neural Operator for Solving Parametric Partial Differential Equationsin Complex Geometries.

Recently, deep learning surrogates and neural operators have shown promise in solving partial differential equations (PDEs). However, they often require a large amount of training data and are limited to bounded domains. In this work, we present a novel physics-informed neural operator method to solve parameterized boundary value problems without labeled data. By reformulating the PDEs into boundary integral equations(BIEs), we can train the operator network solely on the boundary of the domain. This approach reduces the number of required sample points from O(Nd) to O(Nd-1), where d is the domain's dimension, leading to a significant acceleration of the training process. Additionally, our method can handle unbounded problems, which are unattainable for existing physics-informed neural networks (PINNs) and neural operators. Our numerical experiments show the effectiveness of parameterized complex geometries and unbounded problems.

Machine learning in high-entropy alloys: phase formation predictions with artificial neural networks

Due to their complex compositions, high entropy alloys (HEAs) offer a diverse range of material properties, making them highly adaptable for various applications, including those crucial for future sustainability. Phase engineering in HEAs presents a unique opportunity to tailor materials for environmentally friendly technologies and energy-efficient solutions. However, the challenge of predicting phase selection, a key aspect in harnessing the full potential of HEAs for sustainable applications, is compounded by the limited availability of HEA data. This study presents a distinctive approach by using a precisely produced and selected dataset to train an artificial neural network (ANN) model. This dataset, unlike prior studies, is uniquely constructed to contain an equal amount of training data for each phase in HEAs, which includes single-phase solid solutions (SS), amorphous (AM), and intermetallic compounds (IM). This methodology is relatively unexplored in the field and addresses the imbalanced data issue common in HEA research. To accurately assess the model's performance, rigorous cross-validation was employed to systematically adapt the model's hyperparameters for phase formation prediction. The assessment includes metrics such as phase-wise accuracy (AM 86.67% SS 81.25% & IM 82.35%), confusion matrix, and Micro-F1 score (0.83), all of which collectively demonstrate the effectiveness of this approach. The study highlights the importance of feature parameters in phase prediction for HEAs, shedding light on the factors influencing phase selection. Its balanced dataset and training method notably advance machine learning in HEA phase prediction, providing valuable insights for material design amidst challenges and data scarcity in the field.

A big data driven vegetation disease and pest region identification method based on self supervised convolutional neural networks and parallel extreme learning machines

A self supervised convolutional neural network-parallel extreme learning machine classification model based on big data is proposed to address the subjectivity and inaccuracy of traditional methods for identifying vegetation pests and diseases that rely on manual observation and empirical judgment. This model is constructed using convolutional neural networks and parallel extreme learning machines, and integrates feature extraction networks with dual attention mechanisms to improve the accuracy of identifying pests and diseases. The model utilized a large amount of big data for training, achieving a recall rate of 98.42 % on multispectral datasets, and an overall classification accuracy of 99.04 %. After optimizing the residual network, the overall accuracy of identifying vegetation pest and disease areas has been further improved to 99.77 %, and the recall rate has also reached 98.91 %. These results indicate that the method proposed in this study has high accuracy and efficiency in the application of big data, can meet the needs of disease and pest identification, and provides effective technical support for the monitoring and prevention of crop diseases and pests, which has important practical significance.

Exploring emergent syllables in end-to-end automatic speech recognizers through model explainability technique

Automatic speech recognition systems based on end-to-end models (E2E-ASRs) can achieve comparable performance to conventional ASR systems while reproducing all their essential parts automatically, from speech units to the language model. However, they hide the underlying perceptual processes modelled, if any, and they have lower adaptability to multiple application contexts, and, furthermore, they require powerful hardware and an extensive amount of training data. Model-explainability techniques can explore the internal dynamics of these ASR systems and possibly understand and explain the processes conducting to their decisions and outputs. Understanding these processes can help enhance ASR performance and reduce the required training data and hardware significantly. In this paper, we probe the internal dynamics of three E2E-ASRs pre-trained for English by building an acoustic-syllable boundary detector for Italian and Spanish based on the E2E-ASRs’ internal encoding layer outputs. We demonstrate that the shallower E2E-ASR layers spontaneously form a rhythmic component correlated with prominent syllables, central in human speech processing. This finding highlights a parallel between the analysed E2E-ASRs and human speech recognition. Our results contribute to the body of knowledge by providing a human-explainable insight into behaviours encoded in popular E2E-ASR systems.

Improving quantitative MRI using self-supervised deep learning with model reinforcement: Demonstration for rapid T1 mapping.

This paper proposes a novel self-supervised learning framework that uses model reinforcement, REference-free LAtent map eXtraction with MOdel REinforcement (RELAX-MORE), for accelerated quantitative MRI (qMRI) reconstruction. The proposed method uses an optimization algorithm to unroll an iterative model-based qMRI reconstruction into a deep learning framework, enabling accelerated MR parameter maps that are highly accurate and robust. Unlike conventional deep learning methods which require large amounts of training data, RELAX-MORE is a subject-specific method that can be trained on single-subject data through self-supervised learning, making it accessible and practically applicable to many qMRI studies. Using quantitative mapping as an example, the proposed method was applied to the brain, knee and phantom data. The proposed method generates high-quality MR parameter maps that correct for image artifacts, removes noise, and recovers image features in regions of imperfect image conditions. Compared with other state-of-the-art conventional and deep learning methods, RELAX-MORE significantly improves efficiency, accuracy, robustness, and generalizability for rapid MR parameter mapping. This work demonstrates the feasibility of a new self-supervised learning method for rapid MR parameter mapping, that is readily adaptable to the clinical translation of qMRI.

Semi-supervised angular super-resolution method for autostereoscopic 3D surface measurement.

Autostereoscopic 3D measuring systems are an accurate, rapid, and portable method for in situ measurements. These systems use a micro-lens array to record 3D information based on the light-field theory. However, the spatial-angular-resolution trade-off curtails their performance. Although learning models were developed for super-resolution, the scarcity of data hinders efficient training. To address this issue, a novel, to the best of our knowledge, semi-supervised learning paradigm for angular super-resolution is proposed for data-efficient training, benefiting both autostereoscopic and light-field devices. A convolutional neural network using motion estimation is developed for a view synthesis. Subsequently, a high-angular-resolution autostereoscopic system is presented for an accurate profile reconstruction. Experiments show that the semi-supervision enhances view reconstruction quality, while the amount of training data required is reduced by over 69%.

Improving machine translation and post-editing for Chinese tourism texts using transformer-based models

As the digital age and globalization continue to evolve, the demand for accurate machine translation of tourism texts has increased substantially. This paper investigates how to improve the quality of machine translation (MT) and machine translation post-editing (MTPE) of Chinese tourism texts for non-native speakers. A review of the machine translation literature reveals a significant progression in translation methods from rule-based to corpus-based, statistical, and finally to the current neural machine translation (NMT) models. Despite its advanced capabilities, NMT requires large amounts of parallel data for training, which often presents challenges. This study proposes the use of Transformer-based models for MT and MTPE to improve translation quality. A dataset was curated from online sources, mainly Chinese tourism websites. The methodology involved pre-processing the data, performing machine translation using the Transformer model, and post-editing the results. The experiment demonstrated an increase in the BLEU score, suggesting an improvement in translation quality. However, challenges such as the handling of synonyms and geographical nouns were encountered, indicating the need for further research and model optimization.

An Evaluation of Various Machine Learning Approaches for Detecting Leaf Diseases in Agriculture

Background: Machine learning has shown remarkable promise in recent years for use in areas such as pattern detection and categorization. The diagnosis of diseases is crucial in agriculture since they are a natural occurrence in plants. The easiest and most effective way to identify crop disease is through the use of image processing, computer vision and machine learning techniques. Methods: To identify and categorize cotton leaf diseases, the study compares the effectiveness of established techniques like Support Vector Machine (SVM) and random forest with state-of-the-art techniques like neural network (CNN) methods and architectures like Inceptionv3, VGG16 and RasNet50 with data augmentation and transfer learning. Result: The models were trained with four distinct types of plant photos that were manually gathered from a government agency and a farm. It was also noted that as the quantity of training data rose, so performed the resultant models.

Short-term ship roll motion prediction using the encoder–decoder Bi-LSTM with teacher forcing

The safety of maritime operations has become a paramount concern with the advancement of intelligent ships. Ship stability and safety are directly impacted by roll motion, making the prediction of short-term ship roll motion pivotal for assisting navigators in making timely adjustments and averting hazardous roll conditions. However, predicting ship roll motion poses challenges due to nonlinear dynamics. This study aims to predict short-term ship roll motion by leveraging the encoder–decoder structure of Bidirectional Long Short-Term Memory Networks (Bi-LSTM) with teacher forcing. The model is accomplished by employing an encoder–decoder structure to map input sequences to output sequences of varying lengths, and employing teacher forcing to enhance the network’s ability to extract information. To refine and analyze the prediction model, aspects such as the quantity of training data to guarantee model generalization, establishing apposite length relationships between input and output sequences, and assessing the model performance in various sea states are investigated. Additionally, comparative experiments assessing roll motion prediction for intervals of 10s, 30 s, 60 s, and 120 s are conducted to substantiate the necessity and effectiveness of the proposed network. The dataset originates from a commercial professional simulator developed by the Norwegian company Offshore Simulator Center AS (OSC).

A Rapid Single-view Radar Imaging Method with Window Functions

Monostatic rapid single-view radar imaging technology is a technique that employs single incidence angle and single frequency point information to implement rapid monostatic radar imaging within a small angular field. Owing to its analytical expression, this technique can substitute the traditional frequency-angle-scanning imaging in a small angular range, facilitating the rapid generation of highly realistic radar imaging data slices for complex targets and environments. This technology has been significantly applied in scatter hotspot diagnostics and target recognition. In order to achieve the windowing effect equivalent to that of frequency-angle-scanning imaging, and to enhance the scattering feature of monostatic imaging while controlling sidelobes, this paper derives analytic windowed imaging formulas for monostatic radar. It then obtains analytical expressions for various typical monostatic windowing rapid radar imaging scenarios. This enables the monostatic rapid imaging technology to maintain high efficiency in its analytical expressions while achieving the windowing effect equivalent to traditional imaging. The validity and correctness of the analytical formula and software implementation have been confirmed through 1D, 2D, and 3D imaging verifications. This technology can provide a vast amount of training data for modern radars.

VL-Few: Vision Language Alignment for Multimodal Few-Shot Meta Learning

Complex tasks in the real world involve different modal models, such as visual question answering (VQA). However, traditional multimodal learning requires a large amount of aligned data, such as image text pairs, and constructing a large amount of training data is a challenge for multimodal learning. Therefore, we propose VL-Few, which is a simple and effective method to solve the multimodal few-shot problem. VL-Few (1) proposes the modal alignment, which aligns visual features into language space through a lightweight model network and improves the multimodal understanding ability of the model; (2) adopts few-shot meta learning in the multimodal problem, which constructs a few-shot meta task pool to improve the generalization ability of the model; (3) proposes semantic alignment to enhance the semantic understanding ability of the model for the task, context, and demonstration; (4) proposes task alignment that constructs training data into the target task form and improves the task understanding ability of the model; (5) proposes generation alignment, which adopts the token-level training and multitask fusion loss to improve the generation ability of the model. Our experimental results show the effectiveness of VL-Few for multimodal few-shot problems.

Fibre orientation atlas guided rapid segmentation of white matter tracts.

Fibre tract delineation from diffusion magnetic resonance imaging (MRI) is a valuable clinical tool for neurosurgical planning and navigation, as well as in research neuroimaging pipelines. Several popular methods are used for this task, each with different strengths and weaknesses making them more or less suited to different contexts. For neurosurgical imaging, priorities include ease of use, computational efficiency, robustness to pathology and ability to generalise to new tracts of interest. Many existing methods use streamline tractography, which may require expert neuroimaging operators for setting parameters and delineating anatomical regions of interest, or suffer from as a lack of generalisability to clinical scans involving deforming tumours and other pathologies. More recently, data-driven approaches including deep-learning segmentation models and streamline clustering methods have improved reproducibility and automation, although they can require large amounts of training data and/or computationally intensive image processing at the point of application. We describe an atlas-based direct tract mapping technique called 'tractfinder', utilising tract-specific location and orientation priors. Our aim was to develop a clinically practical method avoiding streamline tractography at the point of application while utilising prior anatomical knowledge derived from only 10-20 training samples. Requiring few training samples allows emphasis to be placed on producing high quality, neuro-anatomically accurate training data, and enables rapid adaptation to new tracts of interest. Avoiding streamline tractography at the point of application reduces computational time, false positives and vulnerabilities to pathology such as tumour deformations or oedema. Carefully filtered training streamlines and track orientation distribution mapping are used to construct tract specific orientation and spatial probability atlases in standard space. Atlases are then transformed to target subject space using affine registration and compared with the subject's voxel-wise fibre orientation distribution data using a mathematical measure of distribution overlap, resulting in a map of the tract's likely spatial distribution. This work includes extensive performance evaluation and comparison with benchmark techniques, including streamline tractography and the deep-learning method TractSeg, in two publicly available healthy diffusion MRI datasets (from TractoInferno and the Human Connectome Project) in addition to a clinical dataset comprising paediatric and adult brain tumour scans. Tract segmentation results display high agreement with established techniques while requiring less than 3 min on average when applied to a new subject. Results also display higher robustness than compared methods when faced with clinical scans featuring brain tumours and resections. As well as describing and evaluating a novel proposed tract delineation technique, this work continues the discussion on the challenges surrounding the white matter segmentation task, including issues of anatomical definitions and the use of quantitative segmentation comparison metrics.

A framework for the detection of distributed denial of service attacks on network logs using ML and DL classifiers

Despite the promise of machine learning in DDoS mitigation, it is not without its challenges. Attackers can employ adversarial techniques to evade detection by machine learning models. Moreover, machine learning models require large amounts of high-quality data for training and continuous refinement. Security teams must also be vigilant in monitoring and fine-tuning these models to adapt to new attack vectors. Nonetheless, the integration of machine learning into cybersecurity strategies represents a powerful approach to countering the persistent threat of DDoS attacks in an increasingly interconnected world. This paper proposed Machine Learning (ML) models and a Deep Learning (DL) model for the detection of Distributed Denial of Service Attacks (DDOS) on network system. The DDOS dataset is highly imbalanced because the number of instances of the various classes of the dataset are different. To solve the imbalance problem, we performed random under-sampling using under sampling technique in python called random under-sampler. The down sampled dataset was used for the training of the ML and DL classifiers. The trained models are random forest, gradient boosting and recurrent neural network algorithms on the DDOS dataset. The model was trained on the DDOS dataset by fine tuning the hyper parameters. The models was used to make prediction in an unseen dataset to detect the various types of the DDOS attacks. The result of the models were evaluated in terms of accuracy. The results of the models show an accuracy result of 79% for random forest, 82%, for gradient boosting, and 99.47% for recurrent neural network. From the experimental results.

A Task-Adaptive Parameter Transformation Scheme for Model-Agnostic-Meta-Learning-Based Few-Shot Animal Sound Classification

Deep learning models that require vast amounts of training data struggle to achieve good animal sound classification (ASC) performance. Among recent few-shot ASC methods to address the data shortage problem regarding animals that are difficult to observe, model-agnostic meta-learning (MAML) has shown new possibilities by encoding common prior knowledge derived from different tasks into the model parameter initialization of target tasks. However, when the knowledge on animal sounds is difficult to generalize due to its diversity, MAML exhibits poor ASC performance due to the static initialization setting. In this paper, we propose a novel task-adaptive parameter transformation scheme called few-shot ASC. TAPT generates transformation variables while learning common knowledge and uses the variables to make parameters specific to the target task. Owing to this transformation, TAPT can reduce overfitting and enhance adaptability, training speed, and performance in heterogeneous tasks compared to MAML. In experiments on two public datasets on the same backbone network, we show that TAPT outperforms the existing few-shot ASC schemes in terms of classification accuracy, and in particular a performance improvement of 20.32% compared to the state-of-the-art scheme. In addition, we show that TAPT is robust to hyperparameters and efficient for training.

Scientific Deep Machine Learning Concepts for the Prediction of Concentration Profiles and Chemical Reaction Kinetics: Consideration of Reaction Conditions.

Emerging concepts from scientific deep machine learning such as physics-informed neural networks (PINNs) enable a data-driven approach for the study of complex kinetic problems. We present an extended framework that combines the advantages of PINNs with the detailed consideration of experimental parameter variations for the simulation and prediction of chemical reaction kinetics. The approach is based on truncated Taylor series expansions for the underlying fundamental equations, whereby the external variations can be interpreted as perturbations of the kinetic parameters. Accordingly, our method allows for an efficient consideration of experimental parameter settings and their influence on the concentration profiles and reaction kinetics. A particular advantage of our approach, in addition to the consideration of univariate and multivariate parameter variations, is the robust model-based exploration of the parameter space to determine optimal reaction conditions in combination with advanced reaction insights. The benefits of this concept are demonstrated for higher-order chemical reactions including catalytic and oscillatory systems in combination with small amounts of training data. All predicted values show a high level of accuracy, demonstrating the broad applicability and flexibility of our approach.

Monitoring Rubbish on Roads in Real Time by Deep Neural Network

Monitoring and managing litter on the roadways is important not only for preserving the cleanliness and esthetic appeal of our cities but also for safeguarding the overall health and sanitary environment of citizens. With the development of artificial intelligence, it is now possible to design algorithms capable of autonomously assessing the sanitation status of roadways. In this paper, we propose a method for detecting garbage on roads as our solution to tackle the issue. The proposed model is a deep learning model with an attention mechanism introduced to detect garbage in real-time scenarios. Furthermore, the object recognition capability of the model is enhanced through transfer learning to mitigate the influence of irrelevant content during training. The refined network can detect rubbish on roads with higher efficiency than the existing models. Also, compared with other methods, it consumes less amount of data for training. The experimental results demonstrate the efficiency of our proposed model, with a performance boost of 7.62% over the state-of-the-art methods.

Damage Location Determination with Data Augmentation of Guided Ultrasonic Wave Features and Explainable Neural Network Approach for Integrated Sensor Systems

Machine learning techniques such as deep learning have already been successfully applied in Structural Health Monitoring (SHM) for damage localization using Ultrasonic Guided Waves (UGW) at various temperatures. However, a common issue arises due to the time-consuming nature of collecting guided wave measurements at different temperatures, resulting in an insufficient amount of training data. Since SHM systems are predominantly employed in sensitive structures, there is a significant interest in utilizing methods and algorithms that are transparent and comprehensible. In this study, a method is presented to augment feature data by generating a large number of training features from a relatively limited set of measurements. In addition, robustness to environmental changes, e.g., temperature fluctuations, is improved. This is achieved by utilizing a known temperature compensation method called temperature scaling to determine the function of signal features as a function of temperature. These functions can then be used for data generation. To gain a better understanding of how the damage localization predictions are made, a known explainable neural network (XANN) architecture is employed and trained with the generated data. The trained XANN model was then used to examine and validate the artificially generated signal features and to improve the augmentation process. The presented method demonstrates a significant increase in the number of training data points. Furthermore, the use of the XANN architecture as a predictor model enables a deeper interpretation of the prediction methods employed by the network.

Public Sentiment towards the Medan-Binjai Water Pipeline Excavation using the Naïve Bayes Method

The work on this project received sharp scrutiny from Non-Governmental Organizations (NGOs) because it was suspected that it was not in accordance with the Work Operation Standards (SOP) and not in accordance with the Technical Instructions (Guidelines for Implementation) and Juknis (Technical Instructions) .Naive Bayes is based on a simplified estimate that attribute values are conditionally independent of each other when given output values. Obtain an accuracy value of 0.75, with a negative precision classification of 0.75, negative recall1.00 f1-score negative0.86 and a negative3 support value. Precision classification Positive 0.00 positive recall 0.00 f1-score positive 0.00 and positive support value 1. This means that the performance of the system's success in retrieving information that has a positive value in the document is very low. -Binjai using the Naive Bayes algorithm method, it can be concluded as follows: 1) The accuracy level produced by the naïve Bayes classifier is 75%. 2) The advantages of this study are that it has good accuracy, precision and recall values, so that it is enough to be used in a system. 3) The deficiency in this research is in the performance of the system in finding the success of the system to find back information in the positive class, which is equal to 0.00%. This is because the amount of training data in the positive class is less than the negative class or it can be said that the training data used in this study is not balanced.