Explore the vast range of titles available.

Building energy consumption prediction plays an important role in improving the energy utilization rate through helping building managers to make better decisions. However, as a result of randomness and noisy disturbance, it is not an easy task to realize accurate prediction of the building energy consumption. In order to obtain better building energy consumption prediction accuracy, an extreme deep learning approach is presented in this paper. The proposed approach combines stacked autoencoders (SAEs) with the extreme learning machine (ELM) to take advantage of their respective characteristics. In this proposed approach, the SAE is used to extract the building energy consumption features, while the ELM is utilized as a predictor to obtain accurate prediction results. To determine the input variables of the extreme deep learning model, the partial autocorrelation analysis method is adopted. Additionally, in order to examine the performances of the proposed approach, it is compared with some popular machine learning methods, such as the backward propagation neural network (BPNN), support vector regression (SVR), the generalized radial basis function neural network (GRBFNN) and multiple linear regression (MLR). Experimental results demonstrate that the proposed method has the best prediction performance in different cases of the building energy consumption.

Generative pretrained transformer (GPT) tools have been thriving, as ignited by the remarkable success of OpenAI’s recent chatbot product. GPT technology offers countless opportunities to significantly improve or renovate current health care research and practice paradigms, especially digital health interventions and digital health–enabled clinical care, and a future of smarter digital health can thus be expected. In particular, GPT technology can be incorporated through various digital health platforms in homes and hospitals embedded with numerous sensors, wearables, and remote monitoring devices. In this viewpoint paper, we highlight recent research progress that depicts the future picture of a smarter digital health ecosystem through GPT-facilitated centralized communications, automated analytics, personalized health care, and instant decision-making.

This study developed and validated a multimodal MRI-based radiomics model to assess brain changes in a rat model of autism spectrum disorder (ASD) following selenium intervention. ASD was induced in Sprague-Dawley rats via prenatal valproic acid administration, with sodium selenite used for intervention. MRI modalities included T2-weighted imaging, T1 and T2 relaxation mapping, diffusion tensor imaging, and diffusion kurtosis imaging. Radiomics features were extracted, correlated with behavioral metrics, and analyzed using clustering and radiomics scoring. Logistic regression models incorporating single-modality and multimodal radiomics features were developed and evaluated using receiver operating characteristic (ROC) curve analysis. Subgroup analyses assessed predictive performance and correlations with behavioral and developmental indices. ASD model rats exhibited growth retardation, anxiety-like behavior, and deficits in social interaction and memory, which were alleviated by selenium supplementation. The multimodal radiomics model outperformed single-modality models, achieving the highest area under the ROC curve and strong predictive capability in subgroup analyses. Significant correlations were identified between multimodal radiomics scores and behavioral as well as developmental measures. The cerebellum was a key region affected in ASD, whereas the visual-auditory cortex showed notable responses to selenium treatment. In conclusion, the multimodal radiomics model demonstrates high diagnostic efficacy, highlights the cerebellum as a key region affected in ASD, and suggests the visual-auditory cortex as a primary target of selenium intervention, enhancing predictive accuracy for structural and functional brain improvements post-treatment.

To enhance the prediction performance for building energy consumption, this paper presents a modified deep belief network (DBN) based hybrid model. The proposed hybrid model combines the outputs from the DBN model with the energy-consuming pattern to yield the final prediction results. The energy-consuming pattern in this study represents the periodicity property of building energy consumption and can be extracted from the observed historical energy consumption data. The residual data generated by removing the energy-consuming pattern from the original data are utilized to train the modified DBN model. The training of the modified DBN includes two steps, the first one of which adopts the contrastive divergence (CD) algorithm to optimize the hidden parameters in a pre-train way, while the second one determines the output weighting vector by the least squares method. The proposed hybrid model is applied to two kinds of building energy consumption data sets that have different energy-consuming patterns (daily-periodicity and weekly-periodicity). In order to examine the advantages of the proposed model, four popular artificial intelligence methods—the backward propagation neural network (BPNN), the generalized radial basis function neural network (GRBFNN), the extreme learning machine (ELM), and the support vector regressor (SVR) are chosen as the comparative approaches. Experimental results demonstrate that the proposed DBN based hybrid model has the best performance compared with the comparative techniques. Another thing to be mentioned is that all the predictors constructed by utilizing the energy-consuming patterns perform better than those designed only by the original data. This verifies the usefulness of the incorporation of the energy-consuming patterns. The proposed approach can also be extended and applied to some other similar prediction problems that have periodicity patterns, e.g., the traffic flow forecasting and the electricity consumption prediction.

In Al–Fe alloys, the mechanical properties are determined by the morphology of iron-rich phases. In this work, AA8176(Al-1Fe)-nY (n = 0, 0.3, 0.5, 0.7, and 0.9 wt.%) alloys were prepared by the cast method. The effects of yttrium (Y) addition on the microstructure and mechanical properties of AA8176 alloy were studied using various techniques including optical microscopy (OM), scanning electron microscopy (SEM), transmission electron microscopy (TEM), X-ray diffraction (XRD), cooling curve analysis and tensile tests. The results revealed that the optimal refinement effect was achieved when the amount of Y content was 0.5 wt.%. When the Y content increased from 0 to 0.5 wt.%, the coarse needle-like Al13Fe4 phases were gradually transformed into short rod-like morphology and some fine Al10Fe2Y phases were formed around the Al13Fe4 phases. The average length of iron-rich phases was decreased from 10.01 μm to 2.65 μm. Additionally, as the Y content increased from 0 to 0.5 wt.%, the secondary dendrite arm spacing (SDAS) of AA8176 alloy was reduced from 31.33 μm to 20.24 μm. Furthermore, the mechanical properties of the AA8176 alloy were improved due to the modified microstructure. With the addition of 0.5 wt.% Y, the ultimate tensile strength, yield strength, elongation, and Vickers hardness were improved to 96.86 MPa, 57.21 MPa, 23.1%, and 30.55 HV, respectively, compared to 84.47 MPa, 50.71 MPa, 18.6%, and 27.28 HV for the unmodified AA8176 alloy. It is proposed that the growth of α-Al dendrite and Al13Fe4 phases were effectively inhibited by segregation of Y atoms around α-Al dendrite and Al13Fe4 phases during solidification. And the Al10Fe2Y phases were formed by these Y atoms with Al and Fe elements. However, the formation of coarse Al10Fe2Y phases was promoted by excessive Y content, resulting in a substantial degradation in mechanical properties.

The surface cleaning of metals plays a pivotal role in ensuring their overall performance and functionality. Dielectric barrier discharge (DBD) plasma, due to its unique properties, has been considered to be a good alternative to traditional cleaning methods. The confinement of DBD plasma in microreactors brings additional benefits, including excellent stability at high pressures, enhanced density of reactive species, reduced safety risks, and less gas and energy consumption. In the present work, we demonstrated a DBD plasma-based method for the degradation of stains from metal surfaces in a microreactor. Aluminum plates with capsanthin stains were used to investigate the influence of operational parameters on the decolorization efficiency, including plasma discharge power, plasma processing time, and O2 content in the atmosphere. The results revealed that an increase in plasma discharge power and plasma processing time together with an appropriate amount of O2 in the atmosphere promote the degradation of capsanthin stains. The optimum processing condition was determined to be the following: plasma power of 11.3 W, processing time of 3 min, and Ar/O2 flow rate of 48/2 sccm. The evolution of composition, morphology, bonding configuration, and wettability of aluminum plates with capsanthin and lycopene stains before and after plasma treatment were systematically investigated, indicating DBD plasma can efficiently degrade stains from the surface of metals without damage. On this basis, the DBD plasma cleaning approach was extended to degrade rhodamine B and malachite green stains from different metals, suggesting it has good versatility. Our work provides a simple, efficient, and solvent-free approach for the surface cleaning of metals.

IntroductionCOVID-19 vaccination is crucial for vulnerable people with underlying chronic conditions such as Alzheimer’s disease and related dementias (ADRD) and mild cognitive impairment (MCI). These individuals face unique challenges, including higher risk of COVID-19, difficulties in adopting preventive behaviours and vaccine hesitancy due to concerns about adverse reactions. Therefore, efforts to promote vaccination, including boosters tailored to the currently circulating virus, are essential for people with ADRD/MCI.ObjectiveThe primary purpose of this study protocol is to conduct a comprehensive analysis of COVID-19 vaccination coverage and adverse reactions among individuals with ADRD/MCI in comparison to those without ADRD/MCI. Additionally, the proposed study aims to investigate the impact of social determinants of health on COVID-19 vaccination and vaccine hesitancy in individuals with ADRD/MCI.Methods and analysisA retrospective cross-sectional study will be conducted utilising data from the All of Us (AoU) Researcher Workbench. Relevant data fields are extracted from sources including demographic information, COVID-19 Vaccine Survey, Basic Survey, Health Access & Utilization, Social Determinants of Health, and Electronic Health Record (EHR) data. Data on vaccination, adverse reactions and vaccine hesitancy will be collected through COVID-19 vaccine survey questionnaires. Propensity score matching and binary logistic regression will be applied to assess the vaccination rates and vaccine hesitancy, while controlling for demographic characteristics and social determinants of health factors.Ethics and disseminationThis study protocol received approval from the Institutional Review Board at Florida State University (STUDY00004571). Results will be disseminated through publication in peer-reviewed journals and presented at scientific conferences.

Achieving clinically significant weight loss through lifestyle interventions for obesity management is challenging for most individuals. Improving intervention effectiveness involves early identification of intervention nonresponders and providing them with timely, tailored interventions. Early and frequent self-monitoring (SM) adherence predicts later weight loss success, making it a potential indicator for identifying nonresponders in the initial phase. This study aims to identify clinically meaningful participant subgroups based on longitudinal adherence to SM of diet, activity, and weight over 6 months as well as psychological predictors of participant subgroups from a self-determination theory (SDT) perspective. This was a secondary data analysis of a 6-month digital lifestyle intervention for adults with overweight or obesity. The participants were instructed to perform daily SM on 3 targets: diet, activity, and weight. Data from 50 participants (mean age: 53.0, SD 12.6 y) were analyzed. Group-based multitrajectory modeling was performed to identify subgroups with distinct trajectories of SM adherence across the 3 SM targets. Differences between subgroups were examined for changes in clinical outcomes (ie, body weight, hemoglobin A ) and SDT constructs (ie, eating-related autonomous motivation and perceived competence for diet) over 6 months using linear mixed models. Two distinct SM trajectory subgroups emerged: the Lower SM group (21/50, 42%), characterized by all-around low and rapidly declining SM, and the Higher SM group (29/50, 58%), characterized by moderate and declining diet and weight SM with high activity SM. Since week 2, participants in the Lower SM group exhibited significantly lower levels of diet (P=.003), activity (P=.002), and weight SM (P=.02) compared with the Higher SM group. In terms of clinical outcomes, the Higher SM group achieved a significant reduction in body weight (estimate: -6.06, SD 0.87 kg; P<.001) and hemoglobin A (estimate: -0.38, SD 0.11%; P=.02), whereas the Lower SM group exhibited no improvements. For SDT constructs, both groups maintained high levels of autonomous motivation for over 6 months. However, the Lower SM group experienced a significant decline in perceived competence (P=.005) compared with the Higher SM group, which maintained a high level of perceived competence throughout the intervention (P=.09). The presence of the Lower SM group highlights the value of using longitudinal SM adherence trajectories as an intervention response indicator. Future adaptive trials should identify nonresponders within the initial 2 weeks based on their SM adherence and integrate intervention strategies to enhance perceived competence in diet to benefit nonresponders. ClinicalTrials.gov NCT05071287; https://clinicaltrials.gov/study/NCT05071287. RR2-10.1016/j.cct.2022.106845.

Accurate and practical modelling of the scroll expander is essential to improve energy conversion efficiency and reduce energy losses. To improve the generalizability and physical consistency of the data-driven models for the scroll expander under noisy and data scarcity conditions, a novel mechanism-guided residual network (MGResNet) model is proposed in this study. Firstly, the overall framework of MGResNet is presented. This framework is based on the architecture of residual network, where the mechanistic laws are embedded as constraints in the training of the network through an improved loss function. Then, a hybrid optimization algorithm is detailed, which can achieve efficient and accurate updating of the parameters of the network and mechanistic equations. Finally, comparative prediction experiments are carried out to validate the proposed MGResNet. It has the ability to incorporate mechanistic constraints within the data-driven approach, setting it apart from conventional machine learning and deep learning methods that often disregard underlying physical laws. Experimental results demonstrate that MGResNet significantly outperforms traditional models, achieving over 14.324% improvement in volume flow rate prediction and 3.937% in torque prediction under noisy conditions. Even with a 90% reduction in training data, MGResNet maintains superior accuracy, showing up to 45.983% better performance than other models. This proves that the proposed MGResNet exhibits better forecasting accuracy and stronger robustness in the noisy environments and data sparse conditions due to embedded mechanistic constraints, while generating outputs consistently with physical laws.

Short-term electrical load forecasting is of great significance to the safe operation, efficient management, and reasonable scheduling of the power grid. However, the electrical load can be affected by different kinds of external disturbances, thus, there exist high levels of uncertainties in the electrical load time series data. As a result, it is a challenging task to obtain accurate forecasting of the short-term electrical load. In order to further improve the forecasting accuracy, this study combines the data-driven long-short-term memory network (LSTM) and extreme learning machine (ELM) to present a hybrid model-based forecasting method for the prediction of short-term electrical loads. In this hybrid model, the LSTM is adopted to extract the deep features of the electrical load while the ELM is used to model the shallow patterns. In order to generate the final forecasting result, the predicted results of the LSTM and ELM are ensembled by the linear regression method. Finally, the proposed method is applied to two real-world electrical load forecasting problems, and detailed experiments are conducted. In order to verify the superiority and advantages of the proposed hybrid model, it is compared with the LSTM model, the ELM model, and the support vector regression (SVR). Experimental and comparison results demonstrate that the proposed hybrid model can give satisfactory performance and can achieve much better performance than the comparative methods in this short-term electrical load forecasting application.