Short-term Model Research Articles

A unified framework for estimating country-specific cumulative incidence for 18 diseases stratified by polygenic risk

Polygenic scores (PGSs) offer the ability to predict genetic risk for complex diseases across the life course; a key benefit over short-term prediction models. To produce risk estimates relevant to clinical and public health decision-making, it is important to account for varying effects due to age and sex. Here, we develop a novel framework to estimate country-, age-, and sex-specific estimates of cumulative incidence stratified by PGS for 18 high-burden diseases. We integrate PGS associations from seven studies in four countries (N = 1,197,129) with disease incidences from the Global Burden of Disease. PGS has a significant sex-specific effect for asthma, hip osteoarthritis, gout, coronary heart disease and type 2 diabetes (T2D), with all but T2D exhibiting a larger effect in men. PGS has a larger effect in younger individuals for 13 diseases, with effects decreasing linearly with age. We show for breast cancer that, relative to individuals in the bottom 20% of polygenic risk, the top 5% attain an absolute risk for screening eligibility 16.3 years earlier. Our framework increases the generalizability of results from biobank studies and the accuracy of absolute risk estimates by appropriately accounting for age- and sex-specific PGS effects. Our results highlight the potential of PGS as a screening tool which may assist in the early prevention of common diseases.

Short-term thermal parameter prediction of building energy system based on MIE-JANET method

The precise prediction of thermal parameters in building energy systems is foundational for the efficient and stable operation of the system, aiding in the formulation of optimal building operation strategies. Currently, in the field of architecture, there is a lack of parameter prediction for thermal parameters that involve multiple devices and thermal processes. Moreover, the widely used long short-term memory (LSTM) algorithm in this field tends to have a large number of network parameters, leading to longer training times. Aiming at these problems, a short-term predictive method for thermal parameters named MIE-JANET is proposed. Mutual information entropy was employed to select relevant features from system operation data. Multiple short-term prediction models were constructed by JANET mdoel. The results indicate the superior predictive performance compared to similar algorithms. When considering insufficient data, the mean absolute error for the JANET decreases by 4.9% relative to LSTM. With the same structure, the training time of the JANET model was reduced by more than 40% compared to LSTM. Moreover, The accuracy of the room temperature model, return water temperature model, and supply water temperature model has significantly improved compared to the physical model. This approach provides a foundational model for the intelligent control of building energy systems.

Short-term wind power prediction based on improved sparrow search algorithm optimized long short-term memory with peephole connections

Accurate short-term wind power prediction is of great significance for the scheduling and management of wind farms. This paper proposes a model for short-term wind power prediction. Firstly, on the basis of traditional long short-term memory network, the peephole connections is added. The improved long short-term memory network is more stable compared to traditional long short-term memory neural networks and is suitable for regression prediction. Secondly, chaotic mapping, adaptive weights, Cauchy mutation, and opposition-based learning strategies are introduced to improve the sparrow search algorithm, and applied to optimize the four hyper-parameters of the long short-term memory network, greatly improving the prediction accuracy of the network. The effectiveness of the model is validated using two short-term wind power datasets with sampling times of 10 and 30 minutes respectively, combined with some fitting curves and performance indicators. The comparison results indicate that the proposed short-term wind power prediction model has high prediction accuracy.

Optimizing Emotional Insight through Unimodal and Multimodal Long Short-term Memory Models

The field of multimodal emotion recognition is increasingly gaining popularity as a research area. It involves analyzing human emotions across multiple modalities, such as acoustic, visual, and language. Emotion recognition is more effective as a multimodal learning task than relying on a single modality. In this paper, we present an unimodal and multimodal long short-term memory model with a class weight parameter technique for emotion recognition on the CMU-Multimodal Opinion Sentiment and Emotion Intensity dataset. In addition, a critical challenge lies in selecting the most effective fusion method for integrating multiple modalities. To address this, we applied four different fusion techniques: Early fusion, late fusion, deep fusion, and tensor fusion. These fusion methods improved the performance of multimodal emotion recognition compared to unimodal approaches. With the highly imbalanced number of samples per emotion class in the MOSEI dataset, adding a class weight parameter technique leads our model to outperform the state of the art on all three modalities — acoustic, visual, and language — as well as on all the fusion models. The challenges of class imbalance, which can lead to biased model performance, and using an effective fusion method for integrating multiple modalities often result in decreased accuracy in recognizing less frequent emotion classes. Our proposed model shows 2–3% performance improvement in the unimodal and 2% in the multimodal over the state-of-the-art achieved results.

Auscultation-Based Pulmonary Disease Detection through Parallel Transformation and Deep Learning.

Respiratory diseases are among the leading causes of death, with many individuals in a population frequently affected by various types of pulmonary disorders. Early diagnosis and patient monitoring (traditionally involving lung auscultation) are essential for the effective management of respiratory diseases. However, the interpretation of lung sounds is a subjective and labor-intensive process that demands considerable medical expertise, and there is a good chance of misclassification. To address this problem, we propose a hybrid deep learning technique that incorporates signal processing techniques. Parallel transformation is applied to adventitious respiratory sounds, transforming lung sound signals into two distinct time-frequency scalograms: the continuous wavelet transform and the mel spectrogram. Furthermore, parallel convolutional autoencoders are employed to extract features from scalograms, and the resulting latent space features are fused into a hybrid feature pool. Finally, leveraging a long short-term memory model, a feature from the latent space is used as input for classifying various types of respiratory diseases. Our work is evaluated using the ICBHI-2017 lung sound dataset. The experimental findings indicate that our proposed method achieves promising predictive performance, with average values for accuracy, sensitivity, specificity, and F1-score of 94.16%, 89.56%, 99.10%, and 89.56%, respectively, for eight-class respiratory diseases; 79.61%, 78.55%, 92.49%, and 78.67%, respectively, for four-class diseases; and 85.61%, 83.44%, 83.44%, and 84.21%, respectively, for binary-class (normal vs. abnormal) lung sounds.

Matching analysis of new energy vehicle charging demand and charging infrastructure power supply capacity: A case study of China's capital Beijing

The random charging behavior of new energy vehicles (NEVs) will bring new challenges to the matching between electric vehicle charging facilities (EVCF) and NEVs. In order to explore whether the power supply capacity of urban EVCF can meet the charging requirements of NEVs, using the progression of NEVs in Beijing as a basis, initially, the Monte Carlo simulation (MCS) approach simulates the power demand trajectory for NEVs in the region. Subsequently, to forecast the ownership trends of NEVs across three distinct scenarios from 2021 to 2030, the study employs Grey correlation analysis combined with the bidirectional long short-term memory model (GRA-BiLSTM), facilitating the determination of NEVs’ charging needs. Second, the charging supply of EVCF for the next 10 years is derived by analyzing different development scenarios with three growth rates of EVCF and three combinations of fast and slow pile ratios. The findings indicate a discrepancy between the rate of increase in ownership of NEVs and the rate of increase in charging infrastructure in Beijing between 2021 and 2030. Even under a scenario of high growth in NEV ownership, the balance between supply and demand for charging capacity is not achieved, resulting in suboptimal utilization of charging infrastructure.

Optimizing cascade Hydropower-VRE hybrid systems: A novel approach addressing whole-process vibration to enhance operational safety

The large-scale variable renewable energy (VRE) forces hydropower to smooth out more frequent and violent load/supply fluctuations in cascade hydropower-VRE hybrid systems (CHVHS), threatening the hydropower units safety. This paper proposes a short-term optimization operation model, considering the vibration in both the stable operation and regulation process, which minimizes the whole-process vibration for a CHVHS. Particularly, the traversing depth (TD) is defined for the first time and combined with the traversing time to quantify the cost of traversing vibration zone (VZ), and a complete vibration avoidance strategy applicable to multiple VZs of multiple units is proposed. Finally, the cascade hydropower stations in Hongshui River Basin are selected as a case study. The validity and superiority of the model are verified by comparing with two conventional operation models from the hydropower station and unit perspectives under different load curves, hydrology, wind speed and solar intensity scenarios. The proposed model enables the hydropower unit not to operate in the VZ, and its TD is reduced by 54.28 % and 55.28 % compared to the two conventional models respectively. The approach provides a safe and stable operation pattern that considers whole-process vibration for a CHVHS, mitigating exacerbated vibration from hydropower units compensating for VRE uncertainty.

Short-Term Flood Prediction Model Based on Pre-Training Enhancement

With the rapid advancement of deep learning techniques, deep learning-based flood prediction models have drawn significant attention. However, for short-term prediction in small- and medium-sized river basins, models typically rely on hydrological data spanning from the past several hours to one day, utilizing a fixed-length input window. Such input limits the models’ adaptability to diverse rainfall events and restricts their capability to comprehend historical temporal patterns. To address the underutilization of historical information by existing models, we introduce a Pre-training Enhanced Short-term Flood Prediction Method (PE-SFPM) to enrich the model’s temporal understanding without necessitating changes to the input window size. In the pre-training stage, the model uses a random masking and prediction strategy to learn segment features, capturing a more comprehensive evolutionary trend of historical floods. In the flow forecasting stage, temporal features and spatial features are captured and fused using the temporal attention, spatial attention, and gated fusion. Features are further enhanced by integrating segment features using a feed-forward network. Experimental results demonstrate that the proposed PE-SFPM model achieves excellent performance in short-term flood prediction tasks.

Numerical prediction model for long- and short-term concentration of indoor volatile organic compounds from building materials

ABSTRACT Emission models of volatile organic compounds (VOCs) from individual indoor building materials have been developed and validated. However, multiple indoor building materials release VOCs simultaneously, and neither single building material nor multiple building material emission models can predict the entire release cycle of VOCs accurately. This study established a long- and short-term numerical prediction model for indoor VOC concentration. The model includes an attenuation coefficient θ. To describe the decay rate of the total VOC content, which is mainly influenced by time, and by designing experiments and testing in environmental warehouses under different seasonal conditions, the value of θ was first obtained. Then, after successfully plotting the emission curve of indoor pollutant concentration over time through numerical solution and using θ, the VOC content was corrected for various seasonal conditions. On the basis of this model, an exposure dose integration algorithm was proposed to evaluate the environmental health risks, as an application of this model. In comparison with previous research results and experimental data, this model has better predictive performance.

Lightweight Violence Detection Model Based on 2D CNN with Bi-Directional Motion Attention

With the widespread deployment of surveillance cameras, automatic violence detection has attracted extensive attention from industry and academia. Though researchers have made great progress in video-based violence detection, it is still a challenging task to realize accurate violence detection in real time, especially with limited computing resources. In this paper, we propose a lightweight 2D CNN-based violence detection scheme, which takes advantage of frame-grouping to reduce data redundancy greatly and, meanwhile, enable short-term temporal modeling. In particular, a lightweight 2D CNN, named improved EfficientNet-B0, is constructed by integrating our proposed bi-directional long-term motion attention (Bi-LTMA) module and a temporal shift module (TSM) into the original EfficientNet-B0. The Bi-LTMA takes both spatial and channel dimensions into consideration and captures motion features in both forward and backward directions. The TSM is adopted to realize temporal feature interaction. Moreover, an auxiliary classifier is designed and employed to improve the classification capability and generalization performance of the proposed model. Experiment results demonstrate that the computational cost of the proposed model is 1.21 GFLOPS. Moreover, the proposed scheme achieves accuracies of 100%, 98.5%, 91.67%, and 90.25% on the Movie Fight dataset, the Hockey Fight dataset, the Surveillance Camera dataset, and the RWF-2000 dataset, respectively.

Genotoxicity and cytotoxicity evaluation of a heat-not-burn product

‘Heat-not-burn’ products (HnBP) contain lower levels of harmful substances than traditional cigarettes, but the use of these products warrants further toxicological evaluation. We have compared the cytotoxicity and genotoxicity of a heat-not burn product with conventional cigarettes, in vivo and in vitro. Male Sprague Dawley rats were exposed to mainstream smoke from conventional cigarettes or a HnBP, for 4 or 28 days, followed by isolation of bone marrow polychromatic erythrocytes (PCE) and histological examination of the testes. Chinese hamster lung fibroblast cells were exposed in vitro to total particulate matter from cigarette smoke obtained through Cambridge filters. The cytotoxicity and genotoxicity of total particulate matter were assessed by the neutral red uptake assay, chromosome aberration assay, in vitro micronucleus test, comet assay, and Ames assay. In the short-term exposure rat models, only the conventional-cigarettes group showed a significant increase in the ratio of micronuclei to total PCE. There was no significant difference in rat testis histology in the long-term exposure models. In vitro, in the neutral red uptake assay, the HnBP product showed lower cytotoxicity than conventional cigarettes. Conventional cigarettes showed greater genotoxicity in the chromosome aberration assay, high-dose Ames tests with exogenous metabolic activation, and micronucleus tests. In summary, our results suggest that HnBP have lower cytotoxicity and genotoxicity than conventional cigarettes.

Precipitation prediction based on variational mode decomposition combined with the crested porcupine optimization algorithm for long short-term memory model

Accurate precipitation prediction is very important for meteorological disaster prevention, water resources management, and agricultural decision making. To improve the accuracy of precipitation prediction, a hybrid model based on variational mode decomposition (VMD), crested porcupine optimization algorithm (CPO), and long short-term memory model (LSTM) is proposed in this paper. The model first uses VMD to decompose the precipitation time series into intrinsic mode functions of different frequencies to capture the multi-scale characteristics of precipitation data. Then, the CPO algorithm is used to optimize LSTM adaptive parameters to improve the global search ability and robustness of the model. Finally, the decomposed precipitation component is input into the LSTM network to learn the spatiotemporal dependence relationship and improve the ability of long-term prediction. The experimental results show that compared with the traditional LSTM model, CPO-LSTM model, and VMD-LSTM model, the hybrid model achieves better performance in many evaluation indices and effectively improves the accuracy of precipitation prediction. The application of the model can provide an effective tool for the fields of meteorology and water resources management, as well as provide new ideas for related research.

LSTEG: An evolutionary game model leveraging deep reinforcement learning for privacy behavior analysis on social networks

With the investment of third-party companies, various accurate recommendation services have emerged on social network platforms, making convenience and privacy concerns coexist for users. Platforms, users, and third-party companies have conflicts of interest around privacy issues, and privacy protection is not the only goal for them. For the analysis of multi-party behaviors related to privacy, a long short-term evolutionary game model (LSTEG) is proposed, where the long-term and short-term evolutionary processes describe the dynamics between three parties and between users, respectively. Their dynamic evolutionary processes are described by mean dynamic equations and all possible stationary-state conditions are analyzed theoretically. Deep reinforcement learning is adopted to solve these evolutionary stationary states and to reveal the rules of interdependence between long-term evolution and short-term evolution. Experiments conducted on real-world datasets show that this work can help platforms, users, and third-party companies to get a better sense of what is occurring in dynamic network environments.

Data-model Interactive Health Condition Assessment for Hydropower Unit

Abstract The health condition assessment (HCA) of hydropower unit plays an important role in enhancing safe operation of hydropower stations and reducing maintenance costs. Due to the harsh environment, there are some problems of sensor data during the unit operations, including abnormal data, missing data and high-noise data. Also, it is difficult to obtain complete monitoring data during run-to-failure maintenance. These issues definitely cause the low-confidence HCA. Thus, a data-model-interactive HCA for hydropower unit was proposed. First, a high-fidelity 3D mechanism simulation model, interacting with the actual unit, was built using unit drawing data provided by manufacturers. Average values of the volute inlet pressure and draft tube outlet pressure were fed into the dynamics simulation model to obtain the simulated pressure pulsation data under working conditions (water head H and power P). Then, a long short-term memory based healthy condition model was constructed using the power parameters, simulation and normal pressure pulsation. After model construction, difference values between simulated pressure pulsation dataset and degradation state pressure pulsation dataset were calculated to build the performance degradation index (PDI), describing the HCA of units. Finally, the PDI was fed into the convolutional neural networks and long short-term memory model to achieve degradation trend prediction. Validation experiment was conducted to verify the effectiveness of proposed method using actual monitoring data and operating parameters of 6# unit in the hydropower station.

Do multisource data matter for NGP prediction? Evidence from the G-LSTM model

Precisely predicting natural gas prices (NGPs) is important because it can provide the necessary decision-making basis for energy scheduling, planning and control. However, NGPs are affected by many factors and exhibit the characteristics of nonlinearity and randomness, which makes accurate predictions challenging. Therefore, in this paper, the information gain of multisource data and the global optimization ability of the gray wolf algorithm are used to build a multifactor-driven NGP hybrid forecasting model to improve the prediction performance. First, the emotional tendency and readability of news text are extracted and calculated by using VADER and textstat tools, respectively. Then the network search index is filtered and integrated by using the correlation coefficient method and the CRITIC method to form alternative variables of multisource data (news and search index). Second, the gray wolf optimization algorithm is used to find and determine the best key parameter group in long short-term memory model. Finally, the spot price of natural gas in Henry Hub from March 1, 2012 to February 28, 2022 is selected as the prediction object, and multi-scenario numerical experiments are carried out to verify the effectiveness of the proposed model. The ablation experiment results show that the information gain brought by multisource data can effectively improve the prediction effect of NGPs. Furthermore, the proposed model has the best prediction performance in different scenarios and can be regarded as a promising prediction tool.

An Interprofessional Graduate Student and Family Coaching Program in Naturalistic Communication Techniques.

Researchers implemented a short-term cascading coaching model focusing on naturalistic developmental behavioral intervention with three participant triads. Triads consisted of a graduate student clinician, a minimally verbal child with autism spectrum disorder, and the child's parent. Coaching and intervention occurred during an interprofessional summer clinic that included graduate student clinicians from special education and speech and hearing sciences departments. The efficacy of short-term instruction, researcher coaching for student clinicians, and student clinician coaching of parents was evaluated using a multiple baseline across participants' design. The dependent variables were student clinician's and parent's use of elicitation techniques (creating communication temptations, waiting, and prompting) and response techniques (naturally reinforcing children's communication and providing spoken language models). Following coaching, parents and student clinicians from all triads increased their use of elicitation and response techniques, with very large effect sizes across all variables. Visual analysis findings suggest individualized differences and variability across triads. Implications for graduate education and parent coaching programs are discussed.

Unsteady flow-field forecasting leveraging a hybrid deep-learning architecture

With the rapid development of data-driven technology, deep learning has been widely used to study unsteady flow phenomena, owing to its high-dimensional, nonlinear, and excellent big-data processing capabilities. Rapidly and accurately predicting unsteady flow fields has been a major challenge in fluid mechanics. Therefore, we designed a new U-shaped hybrid deep neural network (UDNN) framework using a multilayer convolution. Through the multilayer learning interaction of high-dimensional flow-field data, the temporal and spatial characteristics of the flow-field flow are captured, and the flow-field characteristics are predicted in an end-to-end form. The UDNN comprises a convolutional neural layer, deconvolutional layer, convolutional long-term and short-term layers, and attention-mechanism layer. First, based on computational fluid dynamics, we generated unsteady flow-field datasets of the flow around fixed and rotating cylinders at different Reynolds numbers, which were used as training samples for the network framework. Second, we designed a U-shaped convolutional layer, added horizontal time-series feature processing and attention-mechanism units, and fused the deep feature information predicted by the model with shallow semantic information to predict the flow-field features. In addition, we compared the UDNN, proper orthogonal decomposition – long short-term memory, and traditional convolutional autoencoder – long short-term memory models in terms of the flow-field prediction error, model training time, and inference speed. The final results showed that the proposed UDNN framework achieved high accuracy and strong robustness in predicting unsteady flow fields.

Machine learning-based model for predicting outcomes in cerebral hemorrhage patients with leukemia

Background and purposeIntracranial hemorrhage (ICH) in leukemia patients progresses rapidly with high mortality. Limited data are available on imaging studies in this population. The study aims to develop prediction models for 7-day and short-term mortality risk based on the non-contrast computed tomography (NCCT) image features. MethodsThe NCCT image features of ICH in 135 leukemia patients between 2007–2023 were retrospectively extracted using manual assessment and radiomics methods. After multiple imputation of missing laboratory data, univariate logistic regression and least absolute shrinkage and selection operator (LASSO) were used for feature selection. Random forest models were built with comprehensive evaluation and ranking of feature importance. Result135 and 129 patients were included in the studies for 7-day and short-term prognostic models, respectively. The median age of all enrolled patients was 35 years, and there were 86 male patients (63.7 %). Clinical models (validation: AUC [area under the curve] = 0.78, AUPRC [area under the precision-recall curve] = 0.73; AUC = 0.84, AUPRC = 0.86), radiomics models (validation: AUC = 0.82, AUPRC = 0.78; AUC = 0.75, AUPRC = 0.77), and the combined models (validation: AUC = 0.84, AUPRC = 0.83; AUC = 0.87, AUPRC = 0.89) predicted 7-day and short-term mortality with good predictive efficacy. Clinical decision curve analysis showed that the combined models predicted 7-day and 30-day risk of death would be more beneficial than other models. Shape features contributed significantly more than semantic features in both radiomics models and combined models (93.3 %, 52.1 %, as well as 85.2 %,37.4 %, respectively) for 7-day and 30-day mortality. ConclusionsCombined models constructed based on NCCT perform well in predicting the risk of 7-day and short-term mortality in ICH patients with leukemia. Shape features extracted by radiomics are important markers for modeling the prognosis.

Short-Term and Imminent Rainfall Prediction Model Based on ConvLSTM and SmaAT-UNet.

Short-term precipitation forecasting methods are mainly divided into statistical forecasting, numerical model-based forecasting, and radar image extrapolation techniques. The two methods based on statistical prediction and numerical model have the disadvantages of being unstable and generating large errors. Therefore, this study proposes the use of deep learning for radar image extrapolation for precipitation forecasting, in particular by developing algorithms for ConvLSTM and SmaAT-UNet. The ConvLSTM model is a fusion of a CNN (Convolutional Neural Network) and LSTM (Long Short-Term Memory network), which solves the challenge of processing spatial sequence data, which is a task that traditional LSTM models cannot accomplish. At the same time, SmaAT-UNet enhances the traditional UNet structure by incorporating the CBAM (Convolutional Block Attention Module) attention mechanism and replacing the standard convolutional layer with depthwise separable convolution. This innovative approach aims to improve the efficiency and accuracy of short-term precipitation forecasting by improving feature extraction and data processing techniques. Evaluation and analysis of experimental data show that both models exhibit good predictive ability, with the SmaAT-UNet model outperforming ConvLSTM in terms of accuracy. The results show that the performance indicators of precipitation prediction, especially detection probability (POD) and the Critical Success index (CSI), show a downward trend with the extension of the prediction time. This trend highlights the inherent challenges of maintaining predictive accuracy over longer periods of time and highlights the superior performance and resilience of the SmaAT-UNet model under these conditions. Compared with the statistical forecasting method and numerical model forecasting method, its accuracy in short-term rainfall forecasting is improved.

Optimization of the Load Command for a Coal-Fired Power Unit via Particle Swarm Optimization–Long Short-Term Memory Model

This study addresses the challenges faced by coal-fired power plants in adapting to energy fluctuations following the integration of renewable energy sources into the power grid. The flexible operation of thermal power plants has become a focal point in academic research. A numerical model of a coal-fired power plant was developed in this study using the Long Short-Term Memory (LSTM) algorithm and the Particle Swarm Optimization (PSO) algorithm based on actual operation data analysis. The combined PSO-LSTM approach improved the accuracy of the model by optimizing parameters. Validation of the model was performed using a Dymola physical simulation model, demonstrating that the PSO-LSTM coupled numerical model accurately simulates coal-fired power plant operations with a goodness of fit reaching 0.998. Overall system performance for comprehensively evaluating the rate and accuracy of unit operation is proposed. Furthermore, the model’s capability to simulate the load variation process of automatic generation control (AGC) under different load command groups was assessed, aiding in optimizing the best load command group. Optimization experiments show that the performance index of output power is optimal within the experimental range when the set load starts and stops are the same and the power of load command γ = 1.8. Specifically, the 50–75% Turbine Heat Acceptance (THA) load rise process enhanced the overall system performance index by 55.1%, while the 75–50% THA load fall process improved the overall system performance index by 54.2%. These findings highlight the effectiveness of the PSO-LSTM approach in optimizing thermal power plant operations and enhancing system performance under varying load conditions.