GANSamples-ac4C: Enhancing ac4C site prediction via generative adversarial networks and transfer learning

RNA modification, N4-acetylcytidine (ac4C), is enzymatically catalyzed by N-acetyltransferase 10 (NAT10) and plays an essential role across tRNA, rRNA, and mRNA. It influences various cellular functions, including mRNA stability and rRNA biosynthesis. Wet-lab detection of ac4C modification sites is highly resource-intensive and costly. Therefore, various machine learning and deep learning techniques have been employed for computational detection of ac4C modification sites. The known ac4C modification sites are limited for training an accurate and stable prediction model. This study introduces GANSamples-ac4C, a novel framework that synergizes transfer learning and generative adversarial network (GAN) to generate synthetic RNA sequences to train a better ac4C modification site prediction model. Comparative analysis reveals that GANSamples-ac4C outperforms existing state-of-the-art methods in identifying ac4C sites. Moreover, our result underscores the potential of synthetic data in mitigating the issue of data scarcity for biological sequence prediction tasks. Another major advantage of GANSamples-ac4C is its interpretable decision logic. Multi-faceted interpretability analyses detect key regions in the ac4C sequences influencing the discriminating decision between positive and negative samples, a pronounced enrichment of G in this region, and ac4C-associated motifs. These findings may offer novel insights for ac4C research. The GANSamples-ac4C framework and its source code are publicly accessible at http://www.healthinformaticslab.org/supp/.

Synthesizing affective neurophysiological signals using generative models: A review paper

The integration of emotional intelligence in machines is an important step in advancing human-computer interaction. This demands the development of reliable end-to-end emotion recognition systems. However, the scarcity of public affective datasets presents a challenge. In this literature review, we emphasize the use of generative models to address this issue in neurophysiological signals, particularly Electroencephalogram (EEG) and Functional Near-Infrared Spectroscopy (fNIRS). We provide a comprehensive analysis of different generative models used in the field, examining their input formulation, deployment strategies, and methodologies for evaluating the quality of synthesized data. This review serves as a comprehensive overview, offering insights into the advantages, challenges, and promising future directions in the application of generative models in emotion recognition systems. Through this review, we aim to facilitate the progression of neurophysiological data augmentation, thereby supporting the development of more efficient and reliable emotion recognition systems.

Overcoming data scarcity in radiomics/radiogenomics using synthetic radiomic features

PURPOSE

To evaluate the potential of synthetic radiomic data generation in addressing data scarcity in radiomics/radiogenomics models.

METHODS

This study was conducted on a retrospectively collected cohort of 386 colorectal cancer patients (n = 2570 lesions) for whom matched contrast-enhanced CT images and gene TP53 mutational status were available. The full cohort data was divided into a training cohort (n = 2055 lesions) and an independent and fixed test set (n = 515 lesions). Differently sized training sets were subsampled from the training cohort to measure the impact of sample size on model performance and assess the added value of synthetic radiomic augmentation at different sizes. Five different tabular synthetic data generation models were used to generate synthetic radiomic data based on "real-world" radiomics data extracted from this cohort. The quality and reproducibility of the generated synthetic radiomic data were assessed. Synthetic radiomics were then combined with "real-world" radiomic training data to evaluate their impact on the predictive model's performance.

RESULTS

A prediction model was generated using only "real-world" radiomic data, revealing the impact of data scarcity in this particular data set through a lack of predictive performance at low training sample numbers (n = 200, 400, 1000 lesions with average AUC = 0.52, 0.53, and 0.56 respectively, compared to 0.64 when using 2055 training lesions). Synthetic tabular data generation models created reproducible synthetic radiomic data with properties highly similar to "real-world" data (for n = 1000 lesions, average Chi-square = 0.932, average basic statistical correlation = 0.844). The integration of synthetic radiomic data consistently enhanced the performance of predictive models trained with small sample size sets (AUC enhanced by 9.6%, 11.3%, and 16.7% for models trained on n_samples = 200, 400, and 1000 lesions, respectively). In contrast, synthetic data generated from randomised/noisy radiomic data failed to enhance predictive performance underlining the requirement of true signal data to do so.

CONCLUSION

Synthetic radiomic data, when combined with real radiomics, could enhance the performance of predictive models. Tabular synthetic data generation might help to overcome limitations in medical AI stemming from data scarcity.

Deep Generative Models: The winning key for large and easily accessible ECG datasets?

Large high-quality datasets are essential for building powerful artificial intelligence (AI) algorithms capable of supporting advancement in cardiac clinical research. However, researchers working with electrocardiogram (ECG) signals struggle to get access and/or to build one. The aim of the present work is to shed light on a potential solution to address the lack of large and easily accessible ECG datasets. Firstly, the main causes of such a lack are identified and examined. Afterward, the potentials and limitations of cardiac data generation via deep generative models (DGMs) are deeply analyzed. These very promising algorithms have been found capable not only of generating large quantities of ECG signals but also of supporting data anonymization processes, to simplify data sharing while respecting patients' privacy. Their application could help research progress and cooperation in the name of open science. However several aspects, such as a standardized synthetic data quality evaluation and algorithm stability, need to be further explored.

Bayesian Convolutional Neural Networks in Medical Imaging Classification: A Promising Solution for Deep Learning Limits in Data Scarcity Scenarios

Deep neural networks (DNNs) have already impacted the field of medicine in data analysis, classification, and image processing. Unfortunately, their performance is drastically reduced when datasets are scarce in nature (e.g., rare diseases or early-research data). In such scenarios, DNNs display poor capacity for generalization and often lead to highly biased estimates and silent failures. Moreover, deterministic systems cannot provide epistemic uncertainty, a key component to asserting the model's reliability. In this work, we developed a probabilistic system for classification as a framework for addressing the aforementioned criticalities. Specifically, we implemented a Bayesian convolutional neural network (BCNN) for the classification of cardiac amyloidosis (CA) subtypes. We prepared four different CNNs: base-deterministic, dropout-deterministic, dropout-Bayesian, and Bayesian. We then trained them on a dataset of 1107 PET images from 47 CA and control patients (data scarcity scenario). The Bayesian model achieved performances (78.28 (1.99) % test accuracy) comparable to the base-deterministic, dropout-deterministic, and dropout-Bayesian ones, while showing strongly increased "Out of Distribution" input detection (validation-test accuracy mismatch reduction). Additionally, both the dropout-Bayesian and the Bayesian models enriched the classification through confidence estimates, while reducing the criticalities of the dropout-deterministic and base-deterministic approaches. This in turn increased the model's reliability, also providing much needed insights into the network's estimates. The obtained results suggest that a Bayesian CNN can be a promising solution for addressing the challenges posed by data scarcity in medical imaging classification tasks.

Estimation of the impact of combined sewer overflows on surface water quality in a sparsely monitored area

Combined sewer overflows (CSOs) can have a severe negative, local impact on surface water systems. To assure good ecological surface water quality and drinking water production that meets the demands, the impact of sewer system overflows on the surrounding water bodies for current and future climate conditions needs to be assessed. Typically, integrated, detailed hydrological and hydrodynamic water quantity and quality models are used for this purpose, but often data and computational resource requirements limit their applicability. Therefore, an alternative computationally efficient, integrated water quantity and quality model of sewer systems and their receiving surface waters is proposed to assess the impact of CSOs on surface water quality in a sparsely observed area. A conceptual model approach to estimate CSO discharges is combined with an empirical model for estimating CSO pollutant concentrations based on waste water treatment plant influent observations. Both methods are compared with observations and independent results of established reference methods as to evaluate their performance. The methodology is demonstrated by modelling the current impact of CSOs on the water abstraction area of a major drinking water production centre in Flanders, Belgium. It is concluded that the proposed conceptual models achieve similar results for daily WWTP effluent and CSO frequency, whereby the accumulated CSO volume is similar to more detailed full hydrodynamic models. Further, the estimated pollutant concentrations correspond with another dataset based on high resolution sampled overflows. As a result, the proposed computational efficient method can give insights in the impact of CSOs on the water quality at a catchment level and can be used for planning monitoring campaigns or performing analyses of e.g. the current and future water availability for a data scarce areas.

Monitoring Kikuletwa river levels in northern Tanzania: A data set unlocking insights for effective flood early warning systems

Floods are a recurring natural disaster that pose significant risks to communities and infrastructure. The lack of reliable and accurate data on river systems in developing countries has hindered the development of effective flood early warning systems. This paper presents a data set collected using ultrasonic distance sensors installed at two locations along the Kikuletwa River in the Pangani River Basin, Northern Tanzania. The dataset consists of hourly measurements of river water levels, providing a high-resolution time series that can be used to study trends in water level changes and to develop more accurate flood early warning systems. The Kikuletwa River dataset has significant potential applications for flood management, including the calibration and validation of hydrological models, the identification of critical thresholds for flood warning, and the evaluation of flood forecasting techniques. The dataset can also be used to study the hydrological processes in the basin, such as the relationship between rainfall and river discharge, and to develop more efficient and effective flood management strategies. The ultrasonic distance sensors were configured to record river level data at hourly intervals, providing a continuous time series of river levels. The data was subjected to quality control procedures to ensure accuracy and consistency, and missing or erroneous data was corrected or removed where necessary.

Graph Spatio-Temporal Networks for Manufacturing Sales Forecast and Prevention Policies in Pandemic Era

Worldwide manufacturing industries are significantly affected by COVID-19 pandemic because of their production characteristics with low-cost country sourcing, globalization, and inventory level. To analyze the correlated time series, spatial-temporal model becomes more attractive, and the graph convolution network (GCN) is also commonly used to provide more information to the nodes and its neighbors in the graph. Recently, attention-adjusted graph spatio-temporal network (AGSTN) was proposed to address the problem of pre-defined graph in GCN by combining multi-graph convolution and attention adjustment to learn spatial and temporal correlations over time. However, AGSTN may show potential problem with limited small non-sensor data; particularly, convergence issue. This study proposes several variants of AGSTN and applies them to non-sensor data. We suggest data augmentation and regularization techniques such as edge selection, time series decomposition, prevention policies to improve AGSTN. An empirical study of worldwide manufacturing industries in pandemic era was conducted to validate the proposed variants. The results show that the proposed variants significantly improve the prediction performance at least around 20% on mean squared error (MSE) and convergence problem.

Data scarce modelling the impact of present and future groundwater development on Jordan multiaquifer groundwater resources

Rapidly growing demands and climate change stresses water resources worldwide and leads to highly competitive situations between the environment and socio-economic development of a region, calling for a smart and modelling driven water resources management. However, data scarcity often prevents the realisation of a comprehensive, nation-wide resources model, which provides reliable and spatially discretized results of water resources development. We present a workflow approach to set up a large-scale multi-aquifer model, overcoming data shortage by stepwise calibration and integrating hydrological and numerical groundwater flow modelling into a coupled system. The study aims to develop such a system to assess how groundwater resources react on anthropogenic impacts on the example of the Kingdom of Jordan, one of the water poorest countries on globe. Simulated heads reliably resembled the monitored ones in >70 % of the observation wells. That makes us confident, the model represents all the states well from 1970, prior to the intense development of the country until 2015. The water balance shows an annual deficit of 1.16 million cubic meter (MCM) due to an overdraft. The discharge to the Dead Sea increased from 564 MCM/yr to 696 MCM/yr over the time period. Regional drawdowns of >250 m and groundwater depression with an extension of approx.100 km are observable in both large aquifer complexes. Most severe areas in the upper calcareous aquifer are located in the north of Amman and practically in all urban and agricultural agglomerations across the country. Groundwater tables in the deeper sandstone aquifer are particularly affected in the south as well as in the wider vicinity of the Dead Sea as consequence of its continuous dropping. Simulations of the future development of the groundwater tables indicate a severe deterioration of the situation with further declines in groundwater levels of up to 70 m.

Comparing critical source areas for the sediment and nutrients of calibrated and uncalibrated models in a plateau watershed in southwest China

Controlling non-point source pollution is often difficult and costly. Therefore, focusing on areas that contribute the most, so-called critical source areas (CSAs), can have economic and ecological benefits. CSAs are often determined using a modelling approach, yet it has proved difficult to calibrate the models in regions with limited data availability. Since identifying CSAs is based on the relative contributions of sub-basins to the total load, it has been suggested that uncalibrated models could be used to identify CSAs to overcome data scarcity issues. Here, we use the SWAT model to study the extent to which an uncalibrated model can be applied to determine CSAs. We classify and rank sub-basins to identify CSAs for sediment, total nitrogen (TN), and total phosphorus (TP) in the Fengyu River Watershed (China) with and without model calibration. The results show high similarity (81%-93%) between the identified sediment and TP CSA number and locations before and after calibration both on the yearly and seasonal scale. For TN alone, the results show moderate similarity on the yearly scale (73%). This may be because, in our study area, TN is determined more by groundwater flow after calibration than by surface water flow. We conclude that CSA identification with the uncalibrated model for TP is always good because its CSA number and locations changed least, and for sediment, it is generally satisfactory. The use of the uncalibrated model for TN is acceptable, as its CSA locations did not change after calibration; however, the TN CSA number changed by over 60% compared to the figures before calibration on both yearly and seasonal scales. Therefore, we advise using an uncalibrated model to identify CSAs for TN only if water yield composition changes are expected to be limited. This study shows that CSAs can be identified based on relative loading estimates with uncalibrated models in data-deficient regions.

Transfer learning in deep neural network-based receiver coil sensitivity map estimation

INTRODUCTION

The success of parallel Magnetic Resonance Imaging algorithms like SENSitivity Encoding (SENSE) depends on an accurate estimation of the receiver coil sensitivity maps. Deep learning-based receiver coil sensitivity map estimation depends upon the size of training dataset and generalization capabilities of the trained neural network. When there is a mismatch between the training and testing datasets, retraining of the neural networks is required from a scratch which is costly and time consuming.

MATERIALS AND METHODS

A transfer learning approach, i.e., end-to-end fine-tuning is proposed to address the data scarcity and generalization problems of deep learning-based receiver coil sensitivity map estimation. First, generalization capabilities of a pre-trained U-Net (initially trained on 1.5T receiver coil sensitivity maps) are thoroughly assessed for 3T receiver coil sensitivity map estimation. Later, end-to-end fine-tuning is performed on the pre-trained U-Net to estimate the 3T receiver coil sensitivity maps.

RESULT AND CONCLUSION

Peak Signal-to-Noise Ratio, Root Mean Square Error and central line profiles (of the SENSE reconstructed images) show a successful SENSE reconstruction by utilizing the receiver coil sensitivity maps estimated by the proposed method.

Transfer learning in deep neural network based under-sampled MR image reconstruction

In Magnetic Resonance Imaging (MRI), the success of deep learning-based under-sampled MR image reconstruction depends on: (i) size of the training dataset, (ii) generalization capabilities of the trained neural network. Whenever there is a mismatch between the training and testing data, there is a need to retrain the neural network from scratch with thousands of MR images obtained using the same protocol. This may not be possible in MRI as it is costly and time consuming to acquire data. In this research, a transfer learning approach i.e. end-to-end fine tuning is proposed for U-Net to address the data scarcity and generalization problems of deep learning-based MR image reconstruction. First the generalization capabilities of a pre-trained U-Net (initially trained on the human brain images of 1.5 T scanner) are assessed for: (a) MR images acquired from MRI scanners of different magnetic field strengths, (b) MR images of different anatomies and (c) MR images under-sampled by different acceleration factors. Later, end-to-end fine tuning of the pre-trained U-Net is proposed for the reconstruction of the above-mentioned MR images (i.e. (a), (b) and (c)). The results show successful reconstructions obtained from the proposed method as reflected by the Structural SIMilarity index, Root Mean Square Error, Peak Signal-to-Noise Ratio and central line profile of the reconstructed images.

Energy optimization of a wastewater treatment plant based on energy audit data: small investment with high return

Ambitious energy targets in the 2020 European climate and energy package have encouraged many stakeholders to explore and implement measures improving the energy efficiency of water and wastewater treatment facilities. Model-based process optimization can improve the energy efficiency of wastewater treatment plants (WWTP) with modest investment and a short payback period. However, such methods are not widely practiced due to the labor-intensive workload required for monitoring and data collection processes. This study offers a multi-step simulation-based methodology to evaluate and optimize the energy consumption of the largest Italian WWTP using limited, preliminary energy audit data. An integrated modeling platform linking wastewater treatment processes, energy demand, and production sub-models is developed. The model is calibrated using a stepwise procedure based on available data. Further, a scenario-based optimization approach is proposed to obtain the non-dominated and optimized performance of the WWTP. The results confirmed that up to 5000 MWh annual energy saving in addition to improved effluent quality could be achieved in the studied case through operational changes only.

Fuzzy-based assessment of groundwater intrinsic vulnerability of a volcanic aquifer in the Chilean Andean Valley

A fuzzy logic approach has been proposed to face the uncertainty caused by sparse data in the assessment of the intrinsic vulnerability of a groundwater system with parametric methods in Las Trancas Valley, Andean Mountain, south-central Chile, a popular touristic place in Chile, but lacking of a centralized drinking and sewage water public systems; this situation is a potentially source of groundwater pollution. Based on DRASTIC, GOD, and EKv and the expert knowledge of the study area, the Mamdani fuzzy approach was generated and the spatial data were processed by ArcGIS. The groundwater system exhibited areas with high, medium, and low intrinsic vulnerability indices. The fuzzy approach results were compared with traditional methods results, which, in general, have shown a good spatial agreement even though significant changes were also identified in the spatial distribution of the indices. The Mamdani logic approach has shown to be a useful and practical tool to assess the intrinsic vulnerability of an aquifer under sparse data conditions.

Using an ensemble of regional climate models to assess climate change impacts on water scarcity in European river basins

Climate change will likely increase pressure on the water balances of Mediterranean basins due to decreasing precipitation and rising temperatures. To overcome the issue of data scarcity the hydrological relevant variables total runoff, surface evaporation, precipitation and air temperature are taken from climate model simulations. The ensemble applied in this study consists of 22 simulations, derived from different combinations of four General Circulation Models (GCMs) forcing different Regional Climate Models (RCMs) and two Representative Concentration Pathways (RCPs) at ~12km horizontal resolution provided through the EURO-CORDEX initiative. Four river basins (Adige, Ebro, Evrotas and Sava) are selected and climate change signals for the future period 2035-2065 as compared to the reference period 1981-2010 are investigated. Decreased runoff and evaporation indicate increased water scarcity over the Ebro and the Evrotas, as well as the southern parts of the Adige and the Sava, resulting from a temperature increase of 1-3° and precipitation decrease of up to 30%. Most severe changes are projected for the summer months indicating further pressure on the river basins already at least partly characterized by flow intermittency. The widely used Falkenmark indicator is presented and confirms this tendency and shows the necessity for spatially distributed analysis and high resolution projections. Related uncertainties are addressed by the means of a variance decomposition and model agreement to determine the robustness of the projections. The study highlights the importance of high resolution climate projections and represents a feasible approach to assess climate impacts on water scarcity also in regions that suffer from data scarcity.