Deep learning analysis of smart meter data from a small sample of room air conditioners facilitates routine assessment of their operational efficiency

Room air conditioners (RACs) are crucial household appliances that consume substantial amounts of electricity. Their efficiency tends to deteriorate over time, resulting in unnecessary energy wastage. Smart meters have become popular to monitor electricity use of home appliances, offering underexplored opportunities to evaluate RAC operational efficiency. Traditional supervised data-driven analysis methods necessitate a large sample size of RACs and their efficiency, which can be challenging to acquire. Additionally, the prevalence of zero values when RACs are off can skew training. To overcome these challenges, we assembled a dataset comprising a limited number of window-type RACs with measured operational efficiencies from 2021. We devised an intuitive zero filter and resampling protocol to process smart meter data and increase training samples. A deep learning-based encoder–decoder model was developed to evaluate RAC efficiency. Our findings suggest that our protocol and model accurately classify and regress RAC operational efficiency. We verified the usefulness of our approach by evaluating the RACs replaced in 2022 using 2022 smart meter data. Our case study demonstrates that repairing or replacing an inefficient RAC can save electricity by up to 17 %. Overall, our study offers a potential energy conservation solution by leveraging smart meters for regularly assessing RAC operational efficiency and facilitating smart preventive maintenance.

Key findings of the 2016 symposium on the frontiers of chemical science and engineering： Environment and sustainable development

There were 30 speakers and the proceedings contained 28 abstracts that discussed the start-of-the art applications of sustainable chemical engineering [1]. We summarized topics that were discussed in the 28 abstracts using the non-negative matrix factorization （NMF） algorithm. The ＂topics＂ were synthesized without reading the abstracts. Here we will not discuss the algorithm of NMF in detail because of the space limitation and please refer to references for the description of NMF [2,3]. Topic modeling will be more valuable as the number of the abstracts increases.

Convergent synaptic and circuit substrates underlying autism genetic risks

There has been a surge of diagnosis of autism spectrum disorders （ASD） over the past decade. While large, high powered genome screening studies of children with ASD have identified numerous genetic risk factors, research efforts to understanding how each of these risk factors contributes to the development autism has met with limited success. Revealing the mechanisms by which these genetic risk factors affect brain development and predispose a child to autism requires mechanistic understanding of the neurobiological changes underlying this devastating group of developmental disorders at multifaceted molecular, cellular and system levels. It has been increasingly clear that the normal trajectory of neurodevelopment is compromised in autism, in multiple domains as much as aberrant neuronal production, growth, functional maturation, patterned connectivity, and balanced excitation and inhibition of brain networks. Many autism risk factors identified in humans have been now reconstituted in experimental mouse models to allow mechanistic interrogation of the biological role of the risk gene. Studies utilizing these mouse models have revealed that underlying the enormous heterogeneity of perturbed cellular events, mechanisms directing synaptic and circuit assembly may provide a unifying explanation for the pathophysiological changes and behavioral endophenotypes seen in autism, although synaptic perturbations are far from being the only alterations relevant for ASD. In this review, we discuss synaptic and circuit abnormalities obtained from several prevalent mouse models, particularly those reflecting syndromic forms of ASD that are caused by single gene perturbations. These compiled results reveal that ASD risk genes contribute to proper signaling of the developing gene networks that maintain synaptic and circuit homeostasis, which is fundamental to normal brain development.

Data-driven integrated assessment of global wild-caught seafood exported to Hong Kong by 2030 in different representative concentration and shared socioeconomic pathways

Wild-caught seafood is an important commodity traded globally.As elimate change and socioeconomic development is affecting global marine capture fisheries,the impact on regional supply remains unexplored,especially for areas like Hong Kong relying on global trading to meet high seafood consumption.However,it is challenging to assess the global marine capture fisheries production using complex process-based models.In this study,a data-driven integrated assessment approach was developed to evaluate the change of global seafood supply from wild catch.With the catch data available from 1990 to 2014,machine learning models were trained and tested including environmental,socioeconomic,geographic,and technological features to estimate the catch by ocean grid cells for individual species.Nine popular seafood categories in Hong Kong were studied,which include 68 species in total.Important input features for estimating the catch were compared across species and the impacts of these input features were interpreted using partial dependence plots.The global marine wild catch of the 68 species by countries and the export to Hong Kong were projected by 2030 in RCP2.6-SSPi,RCP4.5-SSP2,RCP7.0-SSP3,and RCP8.5-SSP5.Performances of machine learning models demonstrate the reliability of data-driven methods to estimate the catch by ocean grid cells.The importance of geographic features rank top for the estimate while that of climate change and socioeconomic development varies significantly across species.The projection reflects a drop of squid exported to Hong Kong due to the reduction of squid supply from China's mainland during 2015-2019.The export of wild-caught seafood of the nine categories to Hong Kong willhave a slight decline by about 16%from the 2020 level by 2030.The projection also suggests no significant differences among the four climatic-socioeconomically interrelated scenarios regarding the export to Hong Kong before 2030.Top producers include China's mainland,United States,and Japan.However,China's mainland and Japan will suffer from the decline.The data-driven integrated assessment approach can be improved to provide more insights into the long-term change and sustainable management.