Inadequate Datasets Research Articles

Improving WSN-based dataset using data augmentation for TSCH protocol performance modeling

This study addresses the problem of inadequate datasets in Time-Slotted Channel Hopping (TSCH) protocol in Wireless Sensor Networks (WSN) by introducing a viable machine learning (ML) approach that explicitly tackles the limitations associated with the scarcity of data samples. The dataset employed in this research is derived from actual sensor node implementations, ensuring authenticity and relevance. To counteract overfitting, Variational Auto-Encoder (VAE) and Generative Adversarial Network (GAN) algorithms are utilized for data augmentation during the modeling phase, alongside the incorporation of Random Forest (RF) and Artificial Neural Network (ANN) algorithms. Results reveal a notable improvement in the performance of the ML models through the implementation of data augmentation techniques. A comparative analysis of various ML models underscores the superiority of the RF model, augmented by the GAN technique. This model exhibits enhanced predictive capabilities for TSCH latency, underscoring its efficacy in modeling network protocol performance.

Meta-2OM: A multi-classifier meta-model for the accurate prediction of RNA 2'-O-methylation sites in human RNA.

2'-O-methylation (2-OM or Nm) is a widespread RNA modification observed in various RNA types like tRNA, mRNA, rRNA, miRNA, piRNA, and snRNA, which plays a crucial role in several biological functional mechanisms and innate immunity. To comprehend its modification mechanisms and potential epigenetic regulation, it is necessary to accurately identify 2-OM sites. However, biological experiments can be tedious, time-consuming, and expensive. Furthermore, currently available computational methods face challenges due to inadequate datasets and limited classification capabilities. To address these challenges, we proposed Meta-2OM, a cutting-edge predictor that can accurately identify 2-OM sites in human RNA. In brief, we applied a meta-learning approach that considered eight conventional machine learning algorithms, including tree-based classifiers and decision boundary-based classifiers, and eighteen different feature encoding algorithms that cover physicochemical, compositional, position-specific and natural language processing information. The predicted probabilities of 2-OM sites from the baseline models are then combined and trained using logistic regression to generate the final prediction. Consequently, Meta-2OM achieved excellent performance in both 5-fold cross-validation training and independent testing, outperforming all existing state-of-the-art methods. Specifically, on the independent test set, Meta-2OM achieved an overall accuracy of 0.870, sensitivity of 0.836, specificity of 0.904, and Matthew's correlation coefficient of 0.743. To facilitate its use, a user-friendly web server and standalone program have been developed and freely available at http://kurata35.bio.kyutech.ac.jp/Meta-2OM and https://github.com/kuratahiroyuki/Meta-2OM.

Surrogate models for seismic and pushover response prediction of steel special moment resisting frames

For structural engineers, existing surrogate models of buildings present challenges due to inadequate datasets, exclusion of significant input variables impacting nonlinear building response, and failure to consider uncertainties associated with input parameters. Moreover, there are no surrogate models for the prediction of both pushover and nonlinear time history analysis (NLTHA) outputs. To overcome these challenges, the present study proposes a novel framework for surrogate modelling of steel structures, considering crucial structural factors impacting engineering demand parameters (EDPs). The first phase involves the development of a process by which 30,000 random steel special moment resisting frames (SMRFs) for low to high-rise buildings are generated, considering the material and geometrical uncertainties embedded in the design of structures. In the second phase, a surrogate model is developed to predict the seismic EDPs of SMRFs when exposed to various earthquake levels. This is accomplished by leveraging the results obtained from phase one. Moreover, separate surrogate models are developed for the prediction of SMRFs’ essential pushover parameters. Various machine learning (ML) methods are examined, and the outcomes are presented as user-friendly GUI tools. The findings highlighted the substantial influence of pushover parameters as well as beams and columns’ plastic hinges properties on the prediction of NLTHA, factors that have been overlooked in prior studies. Moreover, CatBoost has been acknowledged as the superior ML technique for predicting both pushover and NLTHA parameters for all buildings. This framework offers engineers the ability to estimate building responses without the necessity of conducting NLTHA, pushover, or even modal analysis which is computationally intensive.

A neural network approach for population synthesis

This work explores techniques and metrics applied to the process of population synthesis used in activity-based modeling for traffic and transport simulation. The paper presents a novel population synthesis approach based on applying artificial neural networks (ANNs) and evaluates the approach against techniques derived from iterative proportional fitting (IPF), Bayesian networks, and data sampling methods. The documented research also investigates the appropriateness of goodness-of-fit measures and the need to consider similarity measures in assessing technique effectiveness with a focus on measures derived from Jaccard similarity coefficient. We established that IPF techniques should be preferred when datasets with the required composition are available, targeting few output variables and in relatively large zones of 5% region size. However, in smaller zones with sparser datasets, or inadequate dataset composition, the proposed ANN technique and identified sampling method are favorable. The proposed ANN method shows suitability for the population synthesis problem compared with the examined methods, but further work is required to improve model fitting speed, explore mixture models of multiple ANNs, and apply data reduction techniques to reduce the observation–decision space. The research findings also established that comparing scenarios of varying sizes and variable numbers is challenging when employing specific goodness-of-fit measures. Furthermore, the mentioned similarity measures can reveal concerns regarding inconsistent archetypes and low-quality populations that can remain concealed when using error metrics.

GLCM-Based FBLS: A Novel Broad Learning System for Knee Osteopenia and Osteoprosis Screening in Athletes

Due to the physical strain experienced during intense workouts, athletes are at a heightened risk of developing osteopenia and osteoporosis. These conditions not only impact their overall health but also their athletic performance. The current clinical screening methods for osteoporosis are limited by their high radiation dose, complex post-processing requirements, and the significant time and resources needed for implementation. This makes it challenging to incorporate them into athletes’ daily training routines. Consequently, our objective was to develop an innovative automated screening approach for detecting osteopenia and osteoporosis using X-ray image data. Although several automated screening methods based on deep learning have achieved notable results, they often suffer from overfitting and inadequate datasets. To address these limitations, we proposed a novel model called the GLCM-based fuzzy broad learning system (GLCM-based FBLS). Initially, texture features of X-ray images were extracted using the gray-level co-occurrence matrix (GLCM). Subsequently, these features were combined with the fuzzy broad learning system to extract crucial information and enhance the accuracy of predicting osteoporotic conditions. Finally, we applied the proposed method to the field of osteopenia and osteoporosis screening. By comparing this model with three advanced deep learning models, we have verified the effectiveness of GLCM-based FBLS in the automatic screening of osteoporosis for athletes.

A Multilabel Active Learning Framework for Microcontroller Performance Screening

In safety-critical applications, microcontrollers have to be tested to satisfy strict quality and performances constraints. It has been demonstrated that on-chip ring oscillators can be used as speed monitors to reliably predict the performances. However, any machine-learning model is likely to be inaccurate if trained on an inadequate dataset, and labeling data for training is quite a costly process. In this paper, we present a methodology based on active learning to select the best samples to be included in the training set, significantly reducing the time and cost required. Moreover, since different speed measurements are available, we designed a multi-label technique to take advantage of their correlations. Experimental results demonstrate that the approach halves the training-set size, with respect to a random-labelling, while it increases the predictive accuracy, with respect to standard single-label machine-learning models.

Hybrid LSTM Model to Predict the Level of Air Pollution in Montenegro

Air pollution is a critical environmental concern that poses significant health risks and affects multiple aspects of human life. ML algorithms provide promising results for air pollution prediction. In the existing scientific literature, Long Short-Term Memory (LSTM) predictive models, as well as their combination with other statistical and machine learning approaches, have been utilized for air pollution prediction. However, these combined algorithms may not always provide suitable results due to the stochastic nature of the factors that influence air pollution, improper hyperparameter configurations, or inadequate datasets and data characterized by great variability and extreme dispersion. The focus of this paper is applying and comparing the performance of Support Vector Machine and hybrid LSTM regression models for air pollution prediction. To identify optimal hyperparameters for the LSTM model, a hybridization with the Genetic Algorithm is proposed. To mitigate the risk of overfitting, the bagging technique is employed on the best LSTM model. The proposed predicitive model aims to determine the Common Air Quality Index level for the next hour in Niksic, Montenegro. With the hybridization of the LSTM algorithm and by applying the bagging technique, our approach aims to significantly enhance the accuracy and reliability of hourly air pollution prediction. The major contribution of this paper is in the application of advanced machine learning analysis and the combination of the LSTM, Genetic Algorithm, and bagging techniques, which have not been previously employed in the analysis of air pollution in Montenegro. The proposed model will be made available to interested management structures, local governments, national entities, or other relevant institutions, empowering them to make effective pollution level predictions and take appropriate measures.

A Day-Ahead Photovoltaic Power Prediction via Transfer Learning and Deep Neural Networks

Climate change and global warming drive many governments and scientists to investigate new renewable and green energy sources. Special attention is on solar panel technology, since solar energy is considered one of the primary renewable sources and solar panels can be installed in domestic neighborhoods. Photovoltaic (PV) power prediction is essential to match supply and demand and ensure grid stability. However, the PV system has assertive stochastic behavior, requiring advanced forecasting methods, such as machine learning and deep learning, to predict day-ahead PV power accurately. Machine learning models need a rich historical dataset that includes years of PV power outputs to capture hidden patterns between essential variables to predict day-ahead PV power production accurately. Therefore, this study presents a framework based on the transfer learning method to use reliable trained deep learning models of old PV plants in newly installed PV plants in the same neighborhoods. The numerical results show the effectiveness of transfer learning in day-ahead PV prediction in newly established PV plants where a sizable historical dataset of them is unavailable. Among all nine models presented in this study, the LSTM models have better performance in PV power prediction. The new LSTM model using the inadequate dataset has 0.55 mean square error (MSE) and 47.07% weighted mean absolute percentage error (wMAPE), while the transferred LSTM model improves prediction accuracy to 0.168 MSE and 32.04% wMAPE.

Federated machine learning for privacy preserving, collective supply chain risk prediction

The use of Artificial Intelligence (AI) for predicting supply chain risk has gained popularity. However, proposed approaches are based on the premise that organisations act alone, rather than a collective when predicting risk, despite the interconnected nature of supply chains. This yields a problem: organisations that have inadequate datasets cannot predict risk. While data-sharing has been proposed to evaluate risk, in practice this does not happen due to privacy concerns. We propose a federated learning approach for collective risk prediction without the risk of data exposure. We ask: Can organisations who have inadequate datasets tap into collective knowledge? This raises a second question: Under what circumstances would collective risk prediction be beneficial? We present an empirical case study where buyers predict order delays from their shared suppliers before and after Covid-19. Results show that federated learning can indeed help supply chain members predict risk effectively, especially for buyers with limited datasets. Training data-imbalance, disruptions, and algorithm choice are significant factors in the efficacy of this approach. Interestingly, data-sharing or collective risk prediction is not always the best choice for buyers with disproportionately larger order-books. We thus call for further research on on local and collective learning paradigms in supply chains.

Artificial Intelligence Model in Predicting Geomechanical Properties for Shale Formation: A Field Case in Permian Basin

Due to complexities in geologic structure, heterogeneity, and insufficient borehole information, shale formation faces challenges in accurately estimating the elastic properties of rock which triggers severe technical challenges in safe drilling and completion. These geomechanical properties could be computed from acoustic logs, however, accurate estimation is critical due to log deficit and a higher recovery expense of inadequate datasets. To fill the gap, this study focuses on predicting the sonic properties of rock using deep neural network (Bi-directional long short-time memory, Bi-LSTM) and random forest (RF) algorithms to estimate and evaluate the geomechanical properties of the potential unconventional formation, Permian Basin, situated in West Texas. A total of three wells were examined using both single-well and cross-well prediction algorithms. Log-derived single-well prediction models include a 75:25 ratio for training and testing the data whereas the cross-well includes two wells for training and the remaining well was used for testing. The selected well input logs include compressional wave slowness, resistivity, gamma-ray, porosity, and bulk density to predict shear wave slowness. The results using RF and Bi-LSTM show a promising prediction of geomechanical properties for Permian Basin wells. RF algorithm performed superior for both single and grouped well prediction. The single-well prediction method using the RF algorithm provided the highest accuracy of 99.90% whereas Bi-LSTM gave 93.60%. The best accuracy for a grouped well prediction was achieved employing Bi-LSTM and RF models, i.e., 96.01% and 93.80%. The average prediction including RF and Bi-LSTM algorithms demonstrated that accuracy for single well and cross well prediction is 96% and 94% respectively with an error below 7%. These outcomes show the astonishing capability of artificial intelligence (AI) models trained to create a realistic prediction to unlock unconventional potential when datasets are inadequate. Given adequate training data, operators could leverage these efficient tools by utilizing them to examine fracture interpretations with reduced cost and time when datasets are incomplete and thus increase the hydrocarbon recovery potential.

FGCM: Noisy Label Learning via Fine-Grained Confidence Modeling

A small portion of mislabeled data can easily limit the performance of deep neural networks (DNNs) due to their high capacity for memorizing random labels. Thus, robust learning from noisy labels has become a key challenge for deep learning due to inadequate datasets with high-quality annotations. Most existing methods involve training models on clean sets by dividing clean samples from noisy ones, resulting in large amounts of mislabeled data being unused. To address this problem, we propose categorizing training samples into five fine-grained clusters based on the difficulty experienced by DNN models when learning them and label correctness. A novel fine-grained confidence modeling (FGCM) framework is proposed to cluster samples into these five categories; with each cluster, FGCM decides whether to accept the cluster data as they are, accept them with label correction, or accept them as unlabeled data. By applying different strategies to the fine-grained clusters, FGCM can better exploit training data than previous methods. Extensive experiments on widely used benchmarks CIFAR-10, CIFAR-100, clothing1M, and WebVision with different ratios and types of label noise demonstrate the superiority of our FGCM.

Revisiting b-value for extended Kopili region of Northeast India and probabilistic estimation of seismic hazard attributes thereof

Kopili fault and its' surroundings of northeast India have remained witness to some devastating earthquakes. The complex tectonic feature of this region incurs a high seismicity rate relative to other regions. Very recently, an earthquake of magnitude 6.4 (MW) has jolted this region. Considering the persistently rising seismicity pattern of this region, the present study intends to integrate the frequency magnitude distribution of earthquakes with other pertinent seismic hazard parameters. This work presents the estimation of the return period and probability of non-exceedance of medium to large earthquakes for the Kopili fault and its' surroundings via the extreme value method. Two statistical methods, namely the Gutenberg-Richter(G-R) power law and Gumbel extreme value method (GEVM), are applied for the correct estimation of the b-value for the Kopili fault and its' surrounding region. The uniform and homogenous magnitude scale dataset consisting of 550 events observed within a limit of 350 km from the Kopili fault (1964 to 2022) are used in the study. The b-value computed using GR relation was found to be unsatisfactory (0.73) due to an inadequate dataset—thus Gumbel's extreme value method is used for the estimation of the b-value (0.97). Gumbel's extreme value method is used for the calculation of the probability of occurrence of earthquakes, return period, and the most probable earthquake magnitude for the study region. The most probable annual earthquake is found to be ∼ MW 4.99. The return period and probability of occurrence of design-based earthquakes are also calculated. The correlation between b-value, seismic moment, and fractal dimension for seismic hazard analysis is also investigated. The antithetical relationship between seismic moment and b-value is observed for the region while the deep-root character of the Kopili fault and the strong, unfractured character of the Shillong plateau is highlighted with the spatial distribution of fractal dimension in the study region.

A hierarchical deep convolutional regression framework with sensor network fail-safe adaptation for acoustic-emission-based structural health monitoring

Lamb wave-based signals from sparse-distributed sensors are complicated and difficult to process for structural health monitoring (SHM), not only due to their dispersive and multi-mode nature, but also due to the increasing complexity of materials and structures. Deep learning (DL) has attracted huge attention to help solve physical problems with a high level of automation and accuracy. However, its reliability and robustness are still questioned when performing the case-by-case model trained by inadequate datasets for practical scenarios, where many variables exist. In this study, a hierarchical deep convolutional regression framework is proposed to solve the impact source localization problem by acoustic emission signals. One-dimensional (1D) network is used due to its capability to process fast with raw time-series data. The window length of input data and the target of output results are discussed to improve the over-fitting issue. The sensor network fail-safe mechanism is designed via generalizing the model to handle abnormal situations with random faulty channels. Data augmentation and transfer learning techniques are utilized to train the fail-safe model without the need for additional experimental data. Pristine case and multiple random-faulty-channel cases are used to test and validate the adaptation performance of the fail-safe model. The whole framework combines both pristine and fail-safe models to achieve high accuracy of impact localization results of both a simple homogeneous plate and a complex inhomogeneous plate with geometric features. The proposed DL framework of greatly improved reliability and robustness, also short processing time, is well suitable for real-time and in-situ SHM applications.

Combining Numerical Simulation and Deep Learning for Landslide Displacement Prediction: An Attempt to Expand the Deep Learning Dataset

Effective landslide hazard prevention requires accurate landslide prediction models, and the data-driven approaches based on deep learning models are gradually becoming a hot research topic. When training deep learning models, it is always preferable to have a large dataset, while most available landslide monitoring data are limited. For data missing or data sparseness problems, conventional interpolation methods based on mathematical knowledge lack mechanism interpretability. This paper proposes that numerical simulations can be used to expand the deep learning dataset we need. Taking the Jiuxianping landslide in the Three Gorges Reservoir Area (TGRA) as the geological background, a finite element numerical model was established, and the landslide displacement time series data were solved considering the boundary conditions of reservoir water level change and precipitation. Next, based on three metrics: Euclidean distance, cosine similarity, and dynamic time warping (DTW) distance, the time series similarity between the displacement data obtained from simulation and data obtained from actual monitoring were verified. Finally, the combined deep learning model was built to predict the displacement of the Jiuxianping landslide. The model was trained on both the simulated and monitored datasets and tested by the last 12 monitored data points. Prediction results with the testing set showed that the models trained using the expanded training set from numerical simulations exhibited lower prediction errors, and the errors had a more concentrated distribution. The results suggest that this landslide displacement prediction method combining numerical simulation and deep learning can solve the problem of inadequate datasets due to low monitoring frequency, as well as provide an interpretation of the physical mechanism for data vacancy filling.

DETECTION OF COVID FROM CHEST X-RAYS USING GAN

A great deal of lung-related infections including COVID-19 can be diagnosed in the early stages by examining the x-ray images. With the advancement in deep learning techniques, we can back this up to a great extent. For the formulation of such models, the complexion of the dataset used for them plays a key role. An inadequate dataset with an imbalanced class of samples adversely affects the performance of such models. Through this research work, we introduce an improved version of Auxiliary Classifier GAN (ACGAN) which is computationally much more efficient than the prior model for the augmentation of the dataset. The dataset used in this research work is highly imbalanced due to the lack of availability of covid-19 infected samples. The proposed GAN architecture has done a great job in solving this issue. After the augmentation phase, the dataset including the spawned new samples is fed into the detection network to evaluate the performance of the model. The use of pre-existing ImageNet weights and Adam as an optimizer helped to train the model at a quicker rate and the overall accuracy achieved was 95.67 and validation accuracy of 92.57 with a loss value reduced to 0.675. KEYWORDS: Transfer Learning, Convolutional Neural Network (CNN), Data Augmentation, Deep Learning, Multiple perceptrons(MLP), ACGAN

Analysing corpus of office documents for macro-based attacks using Machine Learning

Macro-based malware attacks are on the rise in recent cyber-attacks using malicious code written in visual basic code which can be used to target computers to achieve various exploitations. Macro malware can be obfuscated using various tools and easily evade antivirus software. To detect this macro malware, several methods of machine learning techniques have been proposed with an inadequate dataset for both benign and malicious macro codes which are not reproducible and evaluated on unbalanced datasets. In this paper, use of word embedding technique such as Word2Vec embedding is used for code analysis is proposed to analyze and process macro code written in visual basic language to understand and detect the attack vector before opening the documents. The proposed word embedding technique, called Obfuscated-Word2vec is proposed to detect obfuscated keywords, Obfuscated function names from the macro code and classify them as obfuscated or benign function calls which are later used as feature vectors to train models to extract the most relevant features from macro code and even to help the classifiers to detect more accurately as a downloader, dropper malware, shellcode, PowerShell exploits, etc. Experimental results show that proposed method is reproducible and could detect completely new macro malware by analyzing the macro code by the help of Random forest classifier with 82.65 percent accuracy.

Inadequate dataset learning for major depressive disorder MRI semantic classification

Inadequate dataset learning for major depressive disorder MRI semantic classification

Curating Cyberbullying Datasets: a Human-AI Collaborative Approach.

Cyberbullying is the use of digital communication tools and spaces to inflict physical, mental, or emotional distress. This serious form of aggression is frequently targeted at, but not limited to, vulnerable populations. A common problem when creating machine learning models to identify cyberbullying is the availability of accurately annotated, reliable, relevant, and diverse datasets. Datasets intended to train models for cyberbullying detection are typically annotated by human participants, which can introduce the following issues: (1) annotator bias, (2) incorrect annotation due to language and cultural barriers, and (3) the inherent subjectivity of the task can naturally create multiple valid labels for a given comment. The result can be a potentially inadequate dataset with one or more of these overlapping issues. We propose two machine learning approaches to identify and filter unambiguous comments in a cyberbullying dataset of roughly 19,000 comments collected from YouTube that was initially annotated using Amazon Mechanical Turk (AMT). Using consensus filtering methods, comments were classified as unambiguous when an agreement occurred between the AMT workers’ majority label and the unanimous algorithmic filtering label. Comments identified as unambiguous were extracted and used to curate new datasets. We then used an artificial neural network to test for performance on these datasets. Compared to the original dataset, the classifier exhibits a large improvement in performance on modified versions of the dataset and can yield insight into the type of data that is consistently classified as bullying or non-bullying. This annotation approach can be expanded from cyberbullying datasets onto any classification corpus that has a similar complexity in scope.

Leveraging advances in immunopathology and artificial intelligence to analyze in vitro tumor models in composition and space.

Cancer is the leading cause of death worldwide. Unfortunately, efforts to understand this disease are confounded by the complex, heterogenous tumor microenvironment (TME). Better understanding of the TME could lead to novel diagnostic, prognostic, and therapeutic discoveries. One way to achieve this involves in vitro tumor models that recapitulate the in vivo TME composition and spatial arrangement. Here, we review the potential of harnessing in vitro tumor models and artificial intelligence to delineate the TME. This includes (i) identification of novel features, (ii) investigation of higher-order relationships, and (iii) analysis and interpretation of multiomics data in a (iv) holistic, objective, reproducible, and efficient manner, which surpasses previous methods of TME analysis. We also discuss limitations of this approach, namely inadequate datasets, indeterminate biological correlations, ethical concerns, and logistical constraints; finally, we speculate on future avenues of research that could overcome these limitations, ultimately translating to improved clinical outcomes.

Transfer Learning and Semisupervised Adversarial Detection and Classification of COVID-19 in CT Images

The ongoing coronavirus 2019 (COVID-19) pandemic caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has resulted in a severe ramification on the global healthcare system, principally because of its easy transmission and the extended period of the virus survival on contaminated surfaces. With the advances in computer-aided diagnosis and artificial intelligence, this paper presents the application of deep learning and adversarial network for the automatic identification of COVID-19 pneumonia in computed tomography (CT) scans of the lungs. The complexity and time limitation of the reverse transcription-polymerase chain reaction (RT-PCR) swab test makes it disadvantageous to depend solely on as COVID-19’s central diagnostic mechanism. Since CT imaging systems are of low cost and widely available, we demonstrate that the drawback of the RT-PCR can be alleviated with a faster, automated, and reduced contact diagnostic process via the use of a neural network model for the classification of infected and noninfected CT scans. In our proposed model, we explore the benefit of transfer learning as a means of resolving the problem of inadequate dataset and the importance of semisupervised generative adversarial network for the extraction of well-mapped features and generation of image data. Our experimental evaluation indicates that the proposed semisupervised model achieves reliable classification, taking advantage of the reflective loss distance between the real data sample space and the generated data.