Individual Models Research Articles

A review on evaluating mental stress by deep learning using EEG signals

AbstractMental stress is a common problem that affects individuals all over the world. Stress reduces human functionality during routine work and may lead to severe health defects. Early detection of stress is important for preventing diseases and other negative health-related consequences of stress. Several neuroimaging techniques have been utilized to assess mental stress, however, due to its ease of use, robustness, and non-invasiveness, electroencephalography (EEG) is commonly used. This paper aims to fill a knowledge gap by reviewing the different EEG-related deep learning algorithms with a focus on Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs) for the evaluation of mental stress. The review focuses on data representation, individual deep neural network model architectures, hybrid models, and results amongst others. The contributions of the paper address important issues such as data representation and model architectures. Out of all reviewed papers, 67% used CNN, 9% LSTM, and 24% hybrid models. Based on the reviewed literature, we found that dataset size and different representations contributed to the performance of the proposed networks. Raw EEG data produced classification accuracy around 62% while using spectral and topographical representation produced up to 88%. Nevertheless, the roles of generalizability across different deep learning models and individual differences remain key areas of inquiry. The review encourages the exploration of innovative avenues, such as EEG data image representations concurrently with graph convolutional neural networks (GCN), to mitigate the impact of inter-subject variability. This novel approach not only allows us to harmonize structural nuances within the data but also facilitates the integration of temporal dynamics, thereby enabling a more comprehensive assessment of mental stress levels.

Effective creation of ESG reporting using data from financial accounting in the food industry company

Environmental, social, and governance (ESG) reports in the synergy of the accounting system of the company. In building a system for ESG reporting, it is necessary to comply with valid transnational and national levels and at the same time create a system that will be able to fulfil its tasks in the future. This study presents an analysis possibility of using the company's accounting system for the efficient creation of ESG reporting. The paper presents the focused on the investigation of factors that influence the tendency to using the financial data for effective ESG reporting. Next step of the conducted analysis was the estimation of individual model to investigate specific factors and to identify differences between selected companies of food industry in region of western Slovakia. We used Binary logit model for estimated, based on the data coming from questionary survey in selection company. In this study strongly significant variable DocFA with a positive effect on the dependent variable referred to the agreement of respondents to use documentation from financial accounting for effective ESG reporting. For instance, respondents from the selected western region of Slovakia in the field of food industry have an 82% higher chance of using this documentation for effective ESG reporting. Significant variable AccountS is strongly significant (p-value less than 0.01) in selected companies in western region of Slovakia in field of food industry, which has positive impact to use financial data for effective ESG reporting.

Social role normativity: from individualism to institutionalism

ABSTRACT In her book Social Goodness, Charlotte Witt gives an account of the normativity of social norms, crucially appealing to (and naming) social role normativity. Social role normativity is a distinctive kind of normativity that follows from social roles. For example, teachers ought to teach and students ought to do their homework. According to Witt's artisanal model of social role normativity, we should make sense of social role normativity by reference to artisanal roles, like being a carpenter. Just as carpenters have skills, techniques, and expertise associated with their craft, social roles have skills, techniques, and expertise associated with them. The artisanal model presents the individual craftsperson, taught by a uniquely qualified expert, as the paradigm. Because of this, I argue that the artisanal model struggles to capture the messiness of the actual world, where expertise is distributed, unstable, and contested. To accommodate the real world, we should move away from Witt's individualistic artisanal model. Instead of focusing on individual artisans, our account of social role normativity should focus on communities and institutions that promote artisanal practices.

In-situ particle analysis with heterogeneous background: a machine learning approach

We propose a novel framework that combines state-of-the-art deep learning approaches with pre- and post-processing algorithms for particle detection in complex/heterogeneous backgrounds common in the manufacturing domain. Traditional methods, like size analyzers and those based on dilution, image processing, or deep learning, typically excel with homogeneous backgrounds. Yet, they often fall short in accurately detecting particles against the intricate and varied backgrounds characteristic of heterogeneous particle–substrate (HPS) interfaces in manufacturing. To address this, we've developed a flexible framework designed to detect particles in diverse environments and input types. Our modular framework hinges on model selection and AI-guided particle detection as its core, with preprocessing and postprocessing as integral components, creating a four-step process. This system is versatile, allowing for various preprocessing, AI model selections, and post-processing strategies. We demonstrate this with an entrainment-based particle delivery method, transferring various particles onto substrates that mimic the HPS interface. By altering particle and substrate properties (e.g., material type, size, roughness, shape) and process parameters (e.g., capillary number) during particle entrainment, we capture images under different ambient lighting conditions, introducing a range of HPS background complexities. In the preprocessing phase, we apply image enhancement and sharpening techniques to improve detection accuracy. Specifically, image enhancement adjusts the dynamic range and histogram, while sharpening increases contrast by combining the high pass filter output with the base image. We introduce an image classifier model (based on the type of heterogeneity), employing Transfer Learning with MobileNet as a Model Selector, to identify the most appropriate AI model (i.e., YOLO model) for analyzing each specific image, thereby enhancing detection accuracy across particle–substrate variations. Following image classification based on heterogeneity, the relevant YOLO model is employed for particle identification, with a distinct YOLO model generated for each heterogeneity type, improving overall classification performance. In the post-processing phase, domain knowledge is used to minimize false positives. Our analysis indicates that the AI-guided framework maintains consistent precision and recall across various HPS conditions, with the harmonic mean of these metrics comparable to those of individual AI model outcomes. This tool shows potential for advancing in-situ process monitoring across multiple manufacturing operations, including high-density powder-based 3D printing, powder metallurgy, extreme environment coatings, particle categorization, and semiconductor manufacturing.

An Assessment of Convergence of Climate Reanalyses from Two Coupled Data Assimilation Systems with Identical High-Efficiently Filtering

Abstract Coupled data assimilation (CDA) uses coupled model dynamics and physics to extract observational information from measured data in multiple Earth system domains to reconstruct historical states of the Earth system, forming a reanalysis of climate variability. Due to imperfect numerical schemes in modeling dynamics and physics, models are usually biased from the real world. Such model bias is a critical obstacle in the reconstruction of historical variability by combining model and observations, and, to some degree, causes divergence of CDA results because of individual model behavior in each system. Here, based on a multitimescale high-efficiency filtering algorithm which includes a deep ocean bias relaxing scheme, we first develop a high-efficiency online CDA system with the Community Earth System Model (CESM-MSHea-CDA). Then, together with the other previously-established CDA system (CM2-MSHea-CDA) within the Coupled Model version 2.1 model that is developed by Geophysical Fluid Dynamics Laboratory, we conduct climate reanalysis for the past four decades (1978–2018). Evaluations show that due to improved representation for multiscale background statistics and effective deep ocean model bias relaxing, both CDA systems produce convergent estimation of variability for major climate signals such as variability of basin-scale ocean heat content, ENSO, PDO, etc. Particularly, both CDA systems generate similar time-mean of global and Atlantic meridional overturning circulations that converge to the geostrophic velocity estimate from climatological temperature and salinity data. The CDA-estimated mass transport at typical measurement sections is mostly consistent with the observations.

An Age–Period–Cohort Framework for Profit and Profit Volatility Modeling

The greatest source of failure in portfolio analytics is not individual models that perform poorly, but rather an inability to integrate models quantitatively across management functions. The separable components of age–period–cohort models provide a framework for integrated credit risk modeling across an organization. Using a panel data structure, credit risk scores can be integrated with an APC framework using either logistic regression or machine learning. Such APC scores for default, payoff, and other key rates fit naturally into forward-looking cash flow estimates. Given an economic scenario, every applicant at the time of origination can be assigned profit and profit volatility estimates so that underwriting can truly be account-level. This process optimizes the most fallible part of underwriting, which is setting cutoff scores and assigning loan pricing and terms. This article provides a summary of applications of APC models across portfolio management roles, with a description of how to create the models to be directly integrated. As a consequence, cash flow calculations are available for each account, and cutoff scores can be set directly from portfolio financial targets.

A prediction model for water absorption in sublayers based on stacking ensemble learning method

The water absorption profile can reflect the difference in the waterflooding status of each sublayer in the injection well, and predicting the water absorption profile has important guiding significance for formulating and adjusting the waterflood development plan. Currently, numerical simulation and radioisotope logging techniques are commonly used to obtain the water absorption in sublayers. However, the complex and increasingly heterogeneous subsurface formations in China's oilfields have made it impossible for the numerical simulation to reflect the actual reservoir water injection status by splitting the water absorption into sublayers. Although the radioisotope method is more accurate, it is more expensive and has less actual test data in oilfields. In addition, the water absorption prediction model built by traditional machine learning only applies to injection wells with a small amount of water absorption profile data, and its prediction accuracy needs further improvement. In this paper, a new machine learning prediction method is proposed to build a water absorption profile prediction model by stacking ensemble learning algorithm, which achieves the prediction of water absorption in sublayers for injection wells without historical data of water absorption profiles during the development period. In our model, based on the oilfield's static geological data and dynamic production data, the input feature parameters are comprehensively selected by a hybrid feature selection method to analyze the importance of each feature. The robust base-learners are extracted from the sub-model pool by comparing and analyzing the comprehensive prediction performance of each individual model, including ANN, KNN, SVR, RF, XGBoost, LightGBM, etc. The stacking ensemble model was trained using K-fold cross-validation on a randomly divided dataset, which improves the predictive performance of an individual model by combining the advantages of multiple base-learners so that it can accurately reflect the dynamic changes of the water absorption profile. Finally, a case study from the MG study area of the DG oilfield was conducted to verify the model's predictive effect. This case shows that the stacking model proposed in this paper has better performance in predicting the water absorption in sublayers compared with the traditional single model and other ensemble models, and the model has a strong generalization ability, which proves that the method can be used in studying the prediction of the water absorption in sublayers of injection wells.

Challenges of COVID-19 Case Forecasting in the US, 2020-2021.

During the COVID-19 pandemic, forecasting COVID-19 trends to support planning and response was a priority for scientists and decision makers alike. In the United States, COVID-19 forecasting was coordinated by a large group of universities, companies, and government entities led by the Centers for Disease Control and Prevention and the US COVID-19 Forecast Hub (https://covid19forecasthub.org). We evaluated approximately 9.7 million forecasts of weekly state-level COVID-19 cases for predictions 1-4 weeks into the future submitted by 24 teams from August 2020 to December 2021. We assessed coverage of central prediction intervals and weighted interval scores (WIS), adjusting for missing forecasts relative to a baseline forecast, and used a Gaussian generalized estimating equation (GEE) model to evaluate differences in skill across epidemic phases that were defined by the effective reproduction number. Overall, we found high variation in skill across individual models, with ensemble-based forecasts outperforming other approaches. Forecast skill relative to the baseline was generally higher for larger jurisdictions (e.g., states compared to counties). Over time, forecasts generally performed worst in periods of rapid changes in reported cases (either in increasing or decreasing epidemic phases) with 95% prediction interval coverage dropping below 50% during the growth phases of the winter 2020, Delta, and Omicron waves. Ideally, case forecasts could serve as a leading indicator of changes in transmission dynamics. However, while most COVID-19 case forecasts outperformed a naïve baseline model, even the most accurate case forecasts were unreliable in key phases. Further research could improve forecasts of leading indicators, like COVID-19 cases, by leveraging additional real-time data, addressing performance across phases, improving the characterization of forecast confidence, and ensuring that forecasts were coherent across spatial scales. In the meantime, it is critical for forecast users to appreciate current limitations and use a broad set of indicators to inform pandemic-related decision making.

Traffic crash prediction model in Kano State, Nigeria: a multivariate LSTM approach

Accurate traffic crash prediction is crucial for implementing effective road safety measures. This study compares the performance of Long Short-Term Memory (LSTM) and Multivariate LSTM (MLSTM) models in forecasting total crash count data in Kano State, Nigeria. Human and vehicle factors, including speed violation, tire burst, brake failure, sign light violation, and phone use while driving, are incorporated as covariates in the MLSTM model. An ARIMAX model is employed to investigate the effects of the covariates. The MLSTM model outperforms both the basic LSTM model and individual covariate models, emphasizing the synergistic effect of considering a broad range of factors. The ARIMAX model results reveal that speed violation is significantly positively correlated with total crashes, while other covariates show positive correlations but do not reach the statistical significance. The findings underscore the importance of a multivariate approach in enhancing traffic crash prediction. The MLSTM model's superior performance highlights the value of considering a comprehensive range of factors that influence crash occurrence to achieve more accurate predictions. Practical applications of these models could involve leveraging them for proactive traffic safety measures, which include increased enforcement of traffic rules, targeted driver education and campaigns, and improvements to road infrastructure.

Understanding the alleviation of “Double-ITCZ” bias in CMIP6 models from the perspective of atmospheric energy balance

Understanding the alleviation of “Double-ITCZ” bias in CMIP6 models from the perspective of atmospheric energy balance

Comparative analysis of modern technologies of additive production

In today's conditions, 3D printing is used to create unique models, prototypes, and equipment necessary for conducting experiments and studying various phenomena and processes, for the rapid prototyping of various parts and devices in scientific and engineering research. 3D printing technologies are actively used to create individual medical implants, prostheses, and organ models for training and planning operations, which significantly improves the quality of medical care. In the aerospace and automotive industries, additive manufacturing is used to create lightweight and durable parts helping to reduce weight and improve vehicle efficiency. The use of additive manufacturing methods, technologies, and tools allows you to check and test designs and concepts before mass production. In this work, a detailed analysis of various existing 3D printers is carried out depending on the tasks, and modern technologies of additive manufacturing are investigated depending on the set goals and scientific and applied tasks. Such technologies include Fused Deposition Modeling, Stereolithography, Selective Laser Sintering, Direct Metal Laser Sintering, and Digital Light Processing. In the work, a comparative analysis of these technologies was carried out according to various criteria, such as principle of operation, materials, resolution, surface finish, accuracy, speed, strength, application, cost, complexity of parts, and post-processing. For each technology, the advantages and disadvantages of its use are determined depending on the goals and objectives. It should be noted that some materials may not be suitable for printing complex parts or require additional support during the printing process. This can lead to complexity in the processing of products and increase the time and costs of printing. Improper selection of materials for 3D printing can be harmful to the environment or human health when used incorrectly. For example, some plastic materials may emit toxic elements or have low biodegradability. Also, using excess expensive material unnecessarily can increase the cost of the project. Keywords: additive manufacturing, 3D printing, additive manufacturing technologies, Fused Deposition Modeling, Stereolithography, Selective Laser Sintering, Direct Metal Laser Sintering, Digital Light Processing.

Minimally Invasive Plate Osteosynthesis (MIPO) of Comminuted Radial Fractures Using a Locking Plate Contoured on a 3D-Printed Model of the Feline Antebrachium: A Cadaveric Study.

(1) Background: Due to the unique structural and functional characteristics of the forelimb in cats, fractures of the radius and ulna are best repaired using internal fixation and stabilization in accordance with AO principles. This study presents the results of reduction of 42 cadaveric comminuted feline radial fractures reduced by minimally invasive plate osteosynthesis (MIPO). (2) Methods: Radius fractures were created on 21 pairs of forelimbs with intact bones. MIPO was then performed using two locking bone plates pre-contoured on 3D-printed bone models of the antebrachium of a male and a female cat. Pre- and postoperative radiographs were taken, and radius length and anatomical lateral distal radial angle (aLDRA) were measured. (3) Results: All fractures were classified as complex diaphyseal fractures of the radius. The radial bone length did not change significantly after surgery (F1,18 = 0.01, p = 0.933). However, the aLDRA was modified after surgery (F1,18 = 7.51, p = 0.013), but this change was only observed in females, in whom the aLDRA was significantly reduced (p = 0.035) compared to the value determined by the shape of the plate. In males, the pre- and postoperative aLDRA values were similar (p = 0.824). In 40 cases, alignment, adjacency of bone fragments, and apparatus were judged to be satisfactory. In two cases, the plate was fixed to the proximal radius and distal ulna due to misidentification of the distal radius. In both cases, revision surgery and correct fixation of the radius gave proper alignment, adjacency, and apparatus. (4) Conclusion: A pre-contoured plate on a 3D-printed model of the male and female domestic cat antebrachium was suitable for the reduction and stabilization of comminuted radial fractures in a cohort of domestic cat cadavers without the need to print individual antebrachial bone models for each patient.

Federated Multiple Tensor-on-Tensor Regression (FedMTOT) for Multimodal Data Under Data-Sharing Constraints

In recent years, diversified measurements reflect the system dynamics from a more comprehensive perspective in system modeling and analysis, such as scalars, waveform signals, images, and structured point clouds. To handle such multimodal structured high-dimensional (SHD) data, combining a large amount of data from multiple sites is necessary (i) to reduce the inherent population bias from a single site and (ii) to increase the model accuracy. However, impeded by data management policies and storage costs, data could not be easily shared or directly exchanged among different sites. Instead of simplifying or facilitating the data query process, we propose a federated multiple tensor-on-tensor regression (FedMTOT) framework to train the individual system model locally using (i) its own data and (ii) data features (not data itself) from other sites. Specifically, federated computation is executed based on alternating direction method of multipliers (ADMM) to satisfy data-sharing requirements, while the individual model at each site can still benefit from feature knowledge from other sites to improve its own model accuracy. Finally, two simulations and two case studies validate the superiority of the proposed FedMTOT framework.

Rural community response to accidental toxic gas release: An individual emergency response model during self-organized evacuations

The emergency response ability in rural areas is weaker than in urban areas. Once a major accident occurs in a rural area, it is more likely to cause serious consequences. Thus, we propose a individual emergency response model during self-organized evacuations after accidental toxic gas releases in rural areas. The proposed model can reproduce emergency information dissemination and individual emergency decision-making in self-organized evacuations. We propose an improved susceptible infected recovered model for emergency information dissemination process. At the same time, we propose a emergency decision-making mechanism to simulate individual emergency actions. In this model, individual personality characteristics will affect the accessing and disseminating individual emergency information. Then, we conduct a simulation experiment based on methanol leakage in a rural community. Through comparative experiments, we found that the traditional model may be too pessimistic in estimating emergency information dissemination results, underestimating shadow evacuation. In noncompliance evacuation areas, loudspeakers can inhibit individuals from unnecessarily evacuating who are close to it, and may cause individuals far away from it to evacuate unnecessarily. When formulating emergency response strategies, managers should focus on groups with weak access to information and consider the impact of loudspeaker locations on individual emergency response actions.

Multi-Model Workload Specifications and their application to Cyber-Physical Systems

Abstract To address the question of how to deliver time-sensitive software for Cyber-Physical Systems (CPS) requires a range of modelling and analysis techniques to be developed and integrated. A number of these required techniques are unique to time-sensitive software where timeliness is a correctness property rather than a performance attribute. This paper focuses on how to obtain worst-case estimates of the software’s execution time; in particular, it considers how workload models are derived from assumptions about the system’s run-time behaviour. The specific contribution of this paper is the exploration of the notion that a system can be subject to more than one workload model. Examples illustrate how such multi-models can lead to improved schedulability, and hence more efficient CPS. An important property of the approach is that the derived analysis exhibits model-bounded behaviour. This ensures that the maximum load on the system is never higher than that implied by the individual models.

External Validation of Updated Prediction Models for Neurological Outcomes at 90 Days in Patients With Out-of-Hospital Cardiac Arrest.

Few prediction models for individuals with early-stage out-of-hospital cardiac arrest (OHCA) have undergone external validation. This study aimed to externally validate updated prediction models for OHCA outcomes using a large nationwide dataset. We performed a secondary analysis of the JAAM-OHCA (Comprehensive Registry of In-Hospital Intensive Care for Out-of-Hospital Cardiac Arrest Survival and the Japanese Association for Acute Medicine Out-of-Hospital Cardiac Arrest) registry. Previously developed prediction models for patients with cardiac arrest who achieved the return of spontaneous circulation were updated. External validation was conducted using data from 56 institutions from the JAAM-OHCA registry. The primary outcome was a dichotomized 90-day cerebral performance category score. Two models were updated using the derivation set (n=3337). Model 1 included patient demographics, prehospital information, and the initial rhythm upon hospital admission; Model 2 included information obtained in the hospital immediately after the return of spontaneous circulation. In the validation set (n=4250), Models 1 and 2 exhibited a C-statistic of 0.945 (95% CI, 0.935-0.955) and 0.958 (95% CI, 0.951-0.960), respectively. Both models were well-calibrated to the observed outcomes. The decision curve analysis showed that Model 2 demonstrated higher net benefits at all risk thresholds than Model 1. A web-based calculator was developed to estimate the probability of poor outcomes (https://pcas-prediction.shinyapps.io/90d_lasso/). The updated models offer valuable information to medical professionals in the prediction of long-term neurological outcomes for patients with OHCA, potentially playing a vital role in clinical decision-making processes.

Evaluation and projection of circulation conditions tied to summertime compound drought and heatwave frequency over the Yangtze River Delta, China, for the carbon neutrality period based on CMIP6 GCMs

AbstractFrequent occurrences of compound droughts and heatwaves (CDHWs) may have considerable adverse impacts on human health and socioeconomic development. To project future summertime CDHWs over the Yangtze River Delta (YRD) of China under carbon neutrality (CN) for policymakers, we used nine global climate models (GCMs) from the Coupled Model Intercomparison Project Phase 6 (CMIP6) and evaluated and projected circulation conditions tied to the summer YRD CDHW frequency in the boreal summer. The results show that a marked mid‐tropospheric regional‐scale anticyclonic anomaly centred over the East China Sea can be deemed the dominant system linking the more frequent occurrence of YRD CDHWs. Our selected nine CMIP6 GCMs better captured the observed climatological and anomalous spatial circulation patterns connected to the summer YRD CDHW frequency. Moreover, the nine models' multi‐model ensemble mean (9MME) was better than most of the individual models regarding the related climatological circulation simulations. The 9MME‐projected changes in circulation conditions tied to summer YRD CDHWs during the carbon neutrality period (2050–2060) under SSP119 favour the comparable occurrence of the YRD with that for the same period under the medium greenhouse gas (GHG) warming scenario (SSP245), but the intensities of the CDHWs are the least severe. However, the highest number of YRD CDHWs is driven by the high GHG warming scenario (SSP585), and these CDHWs feature the most severe intensity. Our research identified a new paradigm regarding the frequency and intensity of the summer YRD CDHW under SSP119, highlighting the potential role of the newly accessible CN‐oriented sustainable development pathway in alleviating compound extremes.

Enhancing machining accuracy of banana fiber-reinforced composites with ensemble machine learning

Through innovative predictive modeling, this study advances Abrasive Water Jet Machining (AWJM) for banana fiber-reinforced biocomposites. Utilizing Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) models, hyperparameters are meticulously tuned for predicting Surface Roughness (Ra), Material Removal Rate (MRR), and Kerf Angle (Ka). Optimal configurations are identified, such as 3–6-6–4-1, 3–5-5–4-1, and 3–5–4–4-1 for ANN models, and 250, 100, and 50 units for LSTM models. Beyond individual models, the study explores stacking ensemble models, merging ANN and LSTM strengths with a Linear Regression final estimator, showcasing robust performance validated with high R-squared values. Regression models from Design Expert 13 contribute to understanding process parameter-outcome relationships. Optimized input parameters offer insights into minimizing surface roughness and kerf angle while maximizing MRR. This holistic approach, integrating advanced machine learning and ensemble learning, enhances predictive accuracy for banana-reinforced biocomposites, providing a versatile framework for diverse materials processing applications.

Pruning Self-Attentions Into Convolutional Layers in Single Path.

Vision Transformers (ViTs) have achieved impressive performance over various computer vision tasks. However, modeling global correlations with multi-head self-attention (MSA) layers leads to two widely recognized issues: the massive computational resource consumption and the lack of intrinsic inductive bias for modeling local visual patterns. To solve both issues, we devise a simple yet effective method named Single-Path Vision Transformer pruning (SPViT), to efficiently and automatically compress the pre-trained ViTs into compact models with proper locality added. Specifically, we first propose a novel weight-sharing scheme between MSA and convolutional operations, delivering a single-path space to encode all candidate operations. In this way, we cast the operation search problem as finding which subset of parameters to use in each MSA layer, which significantly reduces the computational cost and optimization difficulty, and the convolution kernels can be well initialized using pre-trained MSA parameters. Relying on the single-path space, we introduce learnable binary gates to encode the operation choices in MSA layers. Similarly, we further employ learnable gates to encode the fine-grained MLP expansion ratios of FFN layers. In this way, our SPViT optimizes the learnable gates to automatically explore from a vast and unified search space and flexibly adjust the MSA-FFN pruning proportions for each individual dense model. We conduct extensive experiments on two representative ViTs showing that our SPViT achieves a new SOTA for pruning on ImageNet-1 k. For example, our SPViT can trim 52.0% FLOPs for DeiT-B and get an impressive 0.6% top-1 accuracy gain simultaneously.

Short-term energy consumption prediction for university dormitory buildings based on energy consumption grouping by considering meteorological factors and teaching schedules

Accurate short-term energy consumption prediction is essential for studying renewable energy utilization in building technologies. University dormitory energy consumption is affected by meteorological factors and teaching schedules, presenting a more complex time series compared to residential buildings, rendering traditional methods unsuitable. Therefore, in the present study, we developed a model called energy consumption grouping-Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise-Bi-directional Long Short-Term Memory (ECG-ICEEMDAN-BILSTM) for predicting short-term energy consumption in university dormitory buildings. Model was tested using electricity consumption data from university dormitory buildings in cold regions of China. Based on the energy consumption characteristics, we identified two consumption patterns comprising high power energy consumption (HPEC) and low power energy consumption (LPEC). Using the ECG method, data with similar daily energy consumption distributions for HPEC and LPEC were grouped. Subsequently, individual prediction models were constructed based on ICEEMDAN-BILSTM for each specific energy consumption group. The experimental results showed the ECG-ICEEMDAN-BILSTM model obtained more accurate predictions compared with other neural network models. In addition, the model was more effective at forecasting the complex distribution of the HPEC pattern, with reductions of at least 16.21% and 15.82% in MAPE and PRMSE, respectively. Thus, study still can obtain valuable insights to address the problem of short-term prediction using complex time series.