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.

Editorial for Special Issue on Commonsense Knowledge and Reasoning:Representation,Acquisition and Applications

Commonsense knowledge is an important resource for humans to understand the meanings or semantics of the data.The ability to learn and own commonsense knowledge is one of the major gaps between humans and machines.Although recent research progresses about deep learning,like Transformer,pre-trained models,etc.,have made amazing breakthroughs in many fields,including computer version,natural language learning,etc.,letting the machines have rich commonsense knowledge and possess the reasoning ability is still difficult and under-resolved.

Event detection and evolution in multi-lingual social streams

Real-life events are emerging and evolving in social and news streams.Recent methods have succeeded in capturing designed features of monolingual events,but lack of interpretability and multi-lingual considerations.To this end,we propose a multi-lingual event mining model,namely MLEM,to automatically detect events and generate evolution graph in multilingual hybrid-length text streams including English,Chinese,French,German,Russian and Japanese.Specially,we merge the same entities and similar phrases and present multiple similarity measures by incremental word2vec model.We propose an 8-tuple to describe event for correlation analysis and evolution graph generation.We evaluate the MLEM model using a massive human-generated dataset containing real world events.Experimental results show that our new model MLEM outperforms the baseline method both in efficiency and effectiveness.

Find truth in the hands of the few:acquiring specific knowledge with crowdsourcing

Crowdsourcing has been a helpful mechanism to leverage human intelligence to acquire useful knowledge.However,when we aggregate the crowd knowledge based on the currently developed voting algorithms,it often results in common knowledge that may not be expected.In this paper,we consider the problem of collecting specific knowledge via crowdsourcing.With the help of using external knowledge base such as WordNet,we incorporate the semantic relations between the alternative answers into a probabilisticmodel to determine which answer is more specific.We formulate the probabilistic model considering both worker’s ability and task’s difficulty from the basic assumption,and solve it by the expectation-maximization(EM)algorithm.To increase algorithm compatibility,we also refine our method into semi-supervised one.Experimental results show that our approach is robust with hyper-parameters and achieves better improvement thanmajority voting and other algorithms when more specific answers are expected,especially for sparse data.

Semiparametric Preference Learning

Unlike traditional supervised learning problems,preference learning learns from data available in the form of pairwise preference relations between instances.Existing preference learning methods are either parametric or nonparametric in nature.We propose in this paper a semiparametric preference learning model,abbreviated as SPPL,with the aim of combining the strengths of the parametric and nonparametric approaches.SPPL uses multiple Gaussian processes which are linearly coupled to determine the preference relations between instances.SPPL is more powerful than previous models while keeping the computational complexity low （linear in the number of distinct instances）.We devise an efficient algorithm for model learning.Empirical studies have been conducted on two real-world data sets showing that SPPL outperforms related preference learning methods.

Semi-supervised Gaussian random field transduction and induction

This paper proposes a semi-supervised inductive algorithm adopting a Gaussian random field(GRF)and Gaussian process.We introduce the prior based on graph regularization.This regularization term measures the p-smoothness over the graph.A new conditional probability called the extended Bernoulli model(EBM)is also proposed.EBM generalizes the logistic regression to the semi-supervised case,and especially,it can naturally represent the margin.In the training phase,a novel solution is given to the discrete regularization framework defined on the graphs.For the new test data,we present the prediction formulation,and explain how the margin model affects the classification boundary.A hyper-parameter estimation method is also developed.Experimental results show that our method is competitive with the existing semi-supervised inductive and transductive methods.