Feature Sequence Research Articles

Recovering Permuted Sequential Features for effective Reinforcement Learning.

When applying Reinforcement Learning (RL) to the real-world visual tasks, two major challenges necessitate consideration: sample inefficiency and limited generalization. To address the above two challenges, previous works focus primarily on learning semantic information from the visual state for improving sample efficiency, but they do not explicitly learn other valuable aspects, such as spatial information. Moreover, they improve generalization by learning representations that are invariant to alterations of task-irrelevant variables, without considering task-relevant variables. To enhance sample efficiency and generalization of the base RL algorithm in visual tasks, we propose an auxiliary task called Recovering Permuted Sequential Features (RPSF). Our method enhances generalization by learning the spatial structure information of the agent, which can mitigate the effects of changes in both task-relevant and task-irrelevant variables. Moreover, it explicitly learns both semantic and spatial information from the visual state by disordering and subsequently recovering a sequence of features to generate more holistic representations, thereby improving sample efficiency. Extensive experiments demonstrate that our method significantly improves the sample efficiency and generalization of the base RL algorithm and outperforms various state-of-the-art baselines across diverse tasks in unseen environments. Furthermore, our method exhibits compatibility with both CNN and Transformer architectures.

Road Pothole Detection Model Based on Local Attention Resnet18-CNN-LSTM

Abstract. In response to the low detection accuracy and slow speed of existing road pothole detection methods, a road pothole classification detection model based on local attention Resnet18-CNN-LSTM (Long Short-Term Memory network) is proposed. On the basis of Resnet18, a local attention mechanism and a CNN-LSTM combined model are added to propose a road pothole detection model based on local attention Resnet18-CNN-LSTM. The local attention mechanism is used to accurately extract specific target feature values, CNN is used to extract the spatial features of the input data, and LSTM enhances the detection model's extraction of sequential features and performs classification, thereby improving the accuracy of the road and pothole model. Experimental results show that on the training set, the accuracy of the local attention mechanism-based ResNet18-CNN-LSTM model reached 99.2188%, which is an increase of 0.7813% and 2.3438% compared to the ResNet34-CNN-LSTM and ResNet50-CNN-LSTM models under the same conditions, respectively. On the test set, the model's accuracy was 93.4437%, an increase of 0.5437% and 1.9867% compared to the ResNet34-CNN-LSTM and ResNet50-CNN-LSTM models, respectively. After dealing with overfitting issues through early stopping, the detection accuracy of this model has significantly improved compared to the detection models based on ResNet34 and ResNet50, with an increase of 1.2% and 1.49% respectively. The model shows faster processing speed in identification time, effectively retains the correlation and sequence features of the data, overcomes the problem of gradient disappearance in deep networks, and thereby enhances the extraction capability of local target features of road pothole images. The above results indicate that the local attention mechanism-based ResNet18-CNN-LSTM model shows superior performance in road pothole detection.

Program Equivalence in the Erlang Actor Model

This paper presents the formal semantics of concurrency in Core Erlang, an intermediate language for Erlang, along with a notion of program equivalence (based on barbed bisimulation) that is able to model equivalence between programs that have different communication structures but the same observable behaviour. The novelty in our formalisation is its extent: it includes semantics for messages and exit and link signals, in addition to most of Core Erlang’s sequential features. Furthermore, unlike previous studies, this work formalises message receipt using primitive operations, consistent with the standard as of Erlang/OTP 23. In this novel formalisation, we show some generally applicable program equivalences (such as process identifier renaming and silent evaluation) and present a practical case study featuring the equivalence of sequential and concurrent list processing.

Ensembling methods for protein-ligand binding affinity prediction

Protein-ligand binding affinity prediction is a key element of computer-aided drug discovery. Most of the existing deep learning methods for protein-ligand binding affinity prediction utilize single models and suffer from low accuracy and generalization capability. In this paper, we train 13 deep learning models from combinations of 5 input features. Then, we explore all possible ensembles of the trained models to find the best ensembles. Our deep learning models use cross-attention and self-attention layers to extract short and long-range interactions. Our method is named Ensemble Binding Affinity (EBA). EBA extracts information from various models using different combinations of input features, such as simple 1D sequential and structural features of the protein-ligand complexes rather than 3D complex features. EBA is implemented to accurately predict the binding affinity of a protein-ligand complex. One of our ensembles achieves the highest Pearson correlation coefficient (R) value of 0.914 and the lowest root mean square error (RMSE) value of 0.957 on the well-known benchmark test set CASF2016. Our ensembles show significant improvements of more than 15% in R-value and 19% in RMSE on both well-known benchmark CSAR-HiQ test sets over the second-best predictor named CAPLA. Furthermore, the superior performance of the ensembles across all metrics compared to existing state-of-the-art protein-ligand binding affinity prediction methods on all five benchmark test datasets demonstrates the effectiveness and robustness of our approach. Therefore, our approach to improving binding affinity prediction between proteins and ligands can contribute to improving the success rate of potential drugs and accelerate the drug development process.

Investigating TCR-pMHC interactions for TCRs without identified epitopes by constructing a computational pipeline

The molecular mechanisms underlying epitope recognition by T cell receptors (TCRs) are critical for activating T cell immune responses and rationally designing TCR-based therapeutics. Single-cell sequencing techniques vastly boost the accumulation of TCR sequences, while the limitation of available TCR-pMHC structures hampers further investigations. In this study, we proposed a computational pipeline that incorporates structural information and single-cell sequencing data to investigate the epitope-recognition mechanisms for TCRs without identified epitopes. By antigen specificity clustering, we mapped the epitope sequences between epitope-known and epitope-unknown TCRs from COVID-19 patients. One reported SARS-CoV-2 epitope, NQKLIANQF (S919–927), was identified for a TCR expressed by 614 T cells (TCR-614). Epitope screening also identified a potential cross-reactive epitope, KLKTLVATA (NSP31790–1798), for a TCR expressed by 204 T cells (TCR-204). By molecular dynamics (MD) simulations, we revealed the detailed epitope-recognition mechanisms for both TCRs. The structural motifs responsible for epitope recognition revealed by the MD simulations are consistent with the sequential features recognized by the sequence-based clustering method. We hope that this strategy could facilitate the discovery and optimization of TCR-based therapeutics.

Comparing ensemble learning algorithms and severity of illness scoring systems in cardiac intensive care units: a retrospective study.

Beatriz Nistal-Nuño designed a machine learning system type of ensemble learning for patients undergoing cardiac surgery and intensive care unit cardiology patients, based on sequences of cardiovascular physiological measurements and other intensive care unit physiological measurements in addition to static features, which generates a score for prediction of mortality of cardiac intensive care unit patients. ■ Gradient Boosting Machine and Random Forest models were built for prediction of mortality at cardiac intensive care units. ■ A total of 9,761 intensive care unit stays of patients admitted under a Cardiac Surgery and Cardiac Medical services were studied. ■ The AUROC and AUPRC values were significantly superior to seven conventional systems compared. ■ The machine learning models' calibration curves were substantially closer to the ideal line. Logistic Regression has been used traditionally for the development of most predictor tools of intensive care unit mortality. The purpose of this study is to combine shared risk factors between patients undergoing cardiac surgery and intensive care unit cardiology patients to develop a risk score for prediction of mortality in cardiac intensive care unit patients, using machine learning. Gradient Boosting Machine and Distributed Random Forest models were developed based on 9,761 intensive care unit-stays from the MIMIC-III database. Sequential and static features were collected. The primary endpoint was intensive care unit mortality prediction. Discrimination, calibration, and accuracy statistics were evaluated. The predictive performance of traditional scoring systems was compared. Machine learning models' AUROC and AUPRC were significantly superior to all conventional systems for the primary endpoint (p<0.05), with AUROC of 0.9413 for Gradient Boosting Machine and 0.9311 for Distributed Random Forest. Sensitivity was 0.6421 for Gradient Boosting Machine, 0.6 for Distributed Random Forest, and <0.3 for all conventional systems except for serial SOFA (0.6316). Precision was 0.574 for Gradient Boosting Machine, 0.566 for Distributed Random Forest, and <0.5 for all conventional systems. Diagnostic odds ratio was 58.8144 for Gradient Boosting Machine, 51.2926 for Distributed Random Forest and <34 for all conventional systems. Brier score was 0.025 for Gradient Boosting Machine and 0.028 for Distributed Random Forest, being worse for the traditional systems. Calibration curves of Gradient Boosting Machine and Distributed Random Forest were substantially closer to the ideal line. The machine learning models showed superiority over the traditional scoring systems compared, with Gradient Boosting Machine having the best performance. Discrimination and calibration were excellent for Gradient Boosting Machine, followed by Distributed Random Forest. The machine learning methods exhibited better capacity for most accuracy statistics.

Tone classification of online medical services based on 1DCNN-BiLSTM

In order to improve the recognition rate of the tone classification of doctors in online medical services scenarios, we propose a model that integrates a one-dimensional convolutional neural network (1DCNN) with a bidirectional long short-term memory network (BiLSTM). Firstly, significant tone types within online medical services scenarios were identified through a survey questionnaire. Secondly, 68 features in both the time and frequency domains of doctors’ tone were extracted using Librosa, serving as the initial input for the model. We utilize the 1DCNN branch to extract local features in the time and frequency domains, while the BiLSTM branch captures the global sequential features of the audio, and a feature-level fusion is performed to enhance tone classification effectiveness. When applied in online medical services scenarios, experimental results show that the model achieved an average recognition rate of 84.4% and an F1 score of 84.4%, significantly outperforming other models and effectively improving the efficiency of doctor-patient communication. Additionally, a series of ablation experiments were conducted to validate the effectiveness of the 1DCNN and BiLSTM modules and the parameter settings.

Detection Method for Three-Phase Electricity Theft Based on Multi-Dimensional Feature Extraction.

The advent of smart grids has facilitated data-driven methods for detecting electricity theft, with a preponderance of research efforts focused on user electricity consumption data. The multi-dimensional power state data captured by Advanced Metering Infrastructure (AMI) encompasses rich information, the exploration of which, in relation to electricity usage behaviors, holds immense potential for enhancing the efficiency of theft detection. In light of this, we propose the Catch22-Conv-Transformer method, a multi-dimensional feature extraction-based approach tailored for the detection of anomalous electricity usage patterns. This methodology leverages both the Catch22 feature set and complementary features to extract sequential features, subsequently employing convolutional networks and the Transformer architecture to discern various types of theft behaviors. Our evaluation, utilizing a three-phase power state and daily electricity usage data provided by the State Grid Corporation of China, demonstrates the efficacy of our approach in accurately identifying theft modalities, including evasion, tampering, and data manipulation.

Explainable Machine Learning Model to Accurately Predict Protein-Binding Peptides

Enzymes play key roles in the biological functions of living organisms, which serve as catalysts to and regulate biochemical reaction pathways. Recent studies suggest that peptides are promising molecules for modulating enzyme function due to their advantages in large chemical diversity and well-established methods for library synthesis. Experimental approaches to identify protein-binding peptides are time-consuming and costly. Hence, there is a demand to develop a fast and accurate computational approach to tackle this problem. Another challenge in developing a computational approach is the lack of a large and reliable dataset. In this study, we develop a new machine learning approach called PepBind-SVM to predict protein-binding peptides. To build this model, we extract different sequential and physicochemical features from peptides and use a Support Vector Machine (SVM) as the classification technique. We train this model on the dataset that we also introduce in this study. PepBind-SVM achieves 92.1% prediction accuracy, outperforming other classifiers at predicting protein-binding peptides.

A Deep Learning Method for Human Sleeping Pose Estimation with Millimeter Wave Radar.

Recognizing sleep posture is crucial for the monitoring of people with sleeping disorders. Existing contact-based systems might interfere with sleeping, while camera-based systems may raise privacy concerns. In contrast, radar-based sensors offer a promising solution with high penetration ability and the capability to detect vital bio-signals. This study propose a deep learning method for human sleep pose recognition from signals acquired from single-antenna Frequency-Modulated Continuous Wave (FMCW) radar device. To capture both frequency features and sequential features, we introduce ResTCN, an effective architecture combining Residual blocks and Temporal Convolution Network (TCN) to recognize different sleeping postures, from augmented statistical motion features of the radar time series. We rigorously evaluated our method with an experimentally acquired data set which contains sleeping radar sequences from 16 volunteers. We report a classification accuracy of 82.74% on average, which outperforms the state-of-the-art methods.

Prediction of PM10 Concentration in Dry Bulk Ports Using a Combined Deep Learning Model Considering Feature Meteorological Factors

Accurate prediction of PM10 concentration is important for effectively managing PM10 exposure and mitigating health and economic risks posed to humans in dry bulk ports. However, accurately capturing the time-series nonlinear variation characteristics of PM10 concentration is challenging owing to the specific intensity of port operation activities and the influence of meteorological factors. To address such challenges, a novel combined deep learning model （CLAF） was proposed, merging cascaded convolutional neural networks （CNN）, long short-term memory （LSTM）, and an attention mechanism （AM）. This integrated model aimed to forecast hourly PM10 concentration in dry bulk ports. First, using the random forest characteristic importance algorithm, the distinct meteorological factors were identified among the selected five meteorological factors. These selected factors were incorporated into the prediction model along with the PM10 concentration. Subsequently, the CNN layer was employed to extract high-dimensional time-varying features from the input variables, while the LSTM layer captured sequential features and long-term dependencies. In the AM layer, different weights were assigned to the output components of the LSTM layer to amplify the effects of important information. Finally, three evaluation metrics were applied to compare the performance of the CLAF model with three basic models and three commonly used prediction models. Real-case data was collected and used in this study. Comparison results demonstrated that considering the meteorological factors could improve the prediction accuracy and fitting performance of PM10 concentration in ports. The CLAF model reduced the mean absolute error statistic by 13.92%-56.9%, decreased the mean square error statistic by 45.99%-81.02%, and improved the goodness-of-fit statistic by 3.2%-15.5%.

A coordinated adaptive multiscale enhanced spatio-temporal fusion network for multi-lead electrocardiogram arrhythmia detection

The multi-lead electrocardiogram (ECG) is widely utilized in clinical diagnosis and monitoring of cardiac conditions. The advancement of deep learning has led to the emergence of automated multi-lead ECG diagnostic networks, which have become essential in the fields of biomedical engineering and clinical cardiac disease diagnosis. Intelligent ECG diagnosis techniques encompass Recurrent Neural Networks (RNN), Transformers, and Convolutional Neural Networks (CNN). While CNN is capable of extracting local spatial information from images, it lacks the ability to learn global spatial features and temporal memory features. Conversely, RNN relies on time and can retain significant sequential features. However, they are not proficient in extracting lengthy dependencies of sequence data in practical scenarios. The self-attention mechanism in the Transformer model has the capability of global feature extraction, but it does not adequately prioritize local features and cannot extract spatial and channel features. This paper proposes STFAC-ECGNet, a model that incorporates CAMV-RNN block, CBMV-CNN block, and TSEF block to enhance the performance of the model by integrating the strengths of CNN, RNN, and Transformer. The CAMV-RNN block incorporates a coordinated adaptive simplified self-attention module that adaptively carries out global sequence feature retention and enhances spatial–temporal information. The CBMV-CNN block integrates spatial and channel attentional mechanism modules in a skip connection, enabling the fusion of spatial and channel information. The TSEF block implements enhanced multi-scale fusion of image spatial and sequence temporal features. In this study, comprehensive experiments were conducted using the PTB-XL large publicly available ECG dataset and the China Physiological Signal Challenge 2018 (CPSC2018) database. The results indicate that STFAC-ECGNet surpasses other cutting-edge techniques in multiple tasks, showcasing robustness and generalization.

Doppler Radar Sensor-Based Fall Detection Using a Convolutional Bidirectional Long Short-Term Memory Model.

Falls among the elderly are a common and serious health risk that can lead to physical injuries and other complications. To promptly detect and respond to fall events, radar-based fall detection systems have gained widespread attention. In this paper, a deep learning model is proposed based on the frequency spectrum of radar signals, called the convolutional bidirectional long short-term memory (CB-LSTM) model. The introduction of the CB-LSTM model enables the fall detection system to capture both temporal sequential and spatial features simultaneously, thereby enhancing the accuracy and reliability of the detection. Extensive comparison experiments demonstrate that our model achieves an accuracy of 98.83% in detecting falls, surpassing other relevant methods currently available. In summary, this study provides effective technical support using the frequency spectrum and deep learning methods to monitor falls among the elderly through the design and experimental validation of a radar-based fall detection system, which has great potential for improving quality of life for the elderly and providing timely rescue measures.

StackedEnC-AOP: prediction of antioxidant proteins using transform evolutionary and sequential features based multi-scale vector with stacked ensemble learning

BackgroundAntioxidant proteins are involved in several biological processes and can protect DNA and cells from the damage of free radicals. These proteins regulate the body's oxidative stress and perform a significant role in many antioxidant-based drugs. The current invitro-based medications are costly, time-consuming, and unable to efficiently screen and identify the targeted motif of antioxidant proteins.MethodsIn this model, we proposed an accurate prediction method to discriminate antioxidant proteins namely StackedEnC-AOP. The training sequences are formulation encoded via incorporating a discrete wavelet transform (DWT) into the evolutionary matrix to decompose the PSSM-based images via two levels of DWT to form a Pseudo position-specific scoring matrix (PsePSSM-DWT) based embedded vector. Additionally, the Evolutionary difference formula and composite physiochemical properties methods are also employed to collect the structural and sequential descriptors. Then the combined vector of sequential features, evolutionary descriptors, and physiochemical properties is produced to cover the flaws of individual encoding schemes. To reduce the computational cost of the combined features vector, the optimal features are chosen using Minimum redundancy and maximum relevance (mRMR). The optimal feature vector is trained using a stacking-based ensemble meta-model.ResultsOur developed StackedEnC-AOP method reported a prediction accuracy of 98.40% and an AUC of 0.99 via training sequences. To evaluate model validation, the StackedEnC-AOP training model using an independent set achieved an accuracy of 96.92% and an AUC of 0.98.ConclusionOur proposed StackedEnC-AOP strategy performed significantly better than current computational models with a ~ 5% and ~ 3% improved accuracy via training and independent sets, respectively. The efficacy and consistency of our proposed StackedEnC-AOP make it a valuable tool for data scientists and can execute a key role in research academia and drug design.

Multi-time scales prediction of aggregated schedulable capacity of electric vehicle fleets based on enhanced Prophet-LGBM algorithm

The fast-increasing applications of renewable energy and electric vehicles (EVs) pose significant challenges to the safe and economic operation of the power grid. However, through Virtual Power Plant (VPP) technology, EV fleets can be aggregated into large-scale EV generalized energy storage systems, providing scarce dispatchable flexible resources for the future power system. Rapid and accurate prediction of the Aggregated Schedulable Capacity of EV (EVASC) fleets is a crucial technology for VPP with Electric Vehicles (EV-VPP) to participate in various ancillary services of the power system. In this paper, orienting for various dispatch scenarios in the power system, a multi-time scale prediction model of the EVASC for EV-VPPs is presented based on the enhanced Prophet algorithm combining a light gradient boosting machine (LGBM) algorithm. The enhanced Prophet-LGBM algorithm is initially proposed here by incorporating the LGBM algorithm into the traditional Prophet algorithm in series and adding extra sequential features in its input, such as temperature, weather, and alike. In this way, the problem of overfitting and low capability in addressing additional input features in the traditional Prophet is overcome. The proposed enhanced Prophet-LGBM-based prediction method of the EVASC for EV-VPPs is validated using 1.8 million actual charging records of over 4000 charging piles for half a year at the provincial level. The 30-day simulation results of the day ahead and intraday predictions of the EVASC for EV-VPPs show that much higher performances in the prediction accuracy can be achieved, specifically in holidays.

Neural Collaborative Learning for User Preference Discovery From Biased Behavior Sequences

The rapid increase of the data of user behaviors on the Internet brings a promising chance to better discover user preferences. Recommender systems have become a popular tool for the discovery of user preferences. One key issue is how to employ user behavior sequences to develop effective sequential recommendations, especially when behavior sequences are biased. The current sequential recommendation methods either can only mine data dependencies but ignores bias or only can learn bias but cannot mine data dependencies. To solve these problems, in this article, we propose a neural collaborative sequential learning mechanism, which learns sequential information from user behavior sequences that contain bias. We propose a neural collaborative filtering (NCF) model that fully takes advantage of all data dependencies among users, items, and biased sequential behaviors. Our sequential learning mechanism employs a self-attention mechanism to learn sequential features into an embedding space and inputs this sequential embedding into the generalized matrix factorization (GMF) model and the multilayer perceptron (MLP) model. We performed experiments on two real-world datasets and compared our model with many well-known baselines. The experimental results demonstrate that our model achieves superior performance. We also give a thorough analysis through ablation experiments and sensitivity experiments.

Assessment of Interactional Competence in L2 German: Integrating an innovative rubric to help language teachers effectively evaluate pragmatics

Research on the development of second language (L2) interactional competence (IC) has shown that IC is vital for L2 speakers' participation in the social world of the L2 and thus an important aspect of pragmatic competence. To date, however, there is little work on the education of future language teachers in the assessment of their learners' IC. More specifically, there is no research on language teachers' experiences using a rubric that focuses on specific interactional sequential features. We address this gap by presenting a study on training L2 German instructors to assess German response tokens — e.g., achso or echt. Building on a prior study on L2 German students' use of response tokens, this paper presents a study on devising a new, specific IC rubric on response tokens. By having L2 instructors use this new IC rubric, we show the advantages and disadvantages of the rubric concentrated around response tokens. Moreover, by collecting L2 instructors’ feedback via survey data on their experience, opinions, and concerns, we illustrate the importance of integrating response tokens into rubrics. We conclude the paper by considering pedagogical implications for language teacher education. The findings show that language instructors need input on the interactional function of response tokens and that instructors view assessing L2 interaction using a sequentially focused rubric as generally positive.

ML-Based Online Transaction Fraud Detection

This paper focuses on fraud detection and the measures necessary to fully automate this process, which has become crucial for banks. With fraud on the rise, it poses significant threats and can result in substantial damages to financial institutions. Transaction data presents unique challenges for fraud detection due to the lack of short-term processing capabilities. The primary objective is to conduct a feasibility study on the selected fraud detection methods. Using various models, we aim to test each transaction individually and proceed accordingly.Initially, we define the detection task, outlining the dataset attributes, metric choices, and techniques to manage unbalanced datasets. This analysis helps identify underlying patterns within the dataset, such as how cardholders' purchasing habits may evolve over time and how fraudsters may adapt their tactics. We then explore various methods used to derive sequential features from credit card transactions. Financial fraud, the practice of gaining financial benefits through deceitful and unlawful means, has become a significant threat to businesses and organizations. Despite numerous efforts to combat financial fraud, it continues to inflict substantial economic and societal harm, with daily losses reaching significant amounts. Traditional methods for fraud detection, introduced years ago, were predominantly manual, making them time- consuming, costly, and prone to errors. Although more research is being conducted, current approaches have not effectively reduced the financial losses associated with fraud. Conventional fraud detection methods, such as manual verifications and inspections, are inefficient, costly, and inaccurate. Keywords: Transaction data, cardholders' purchasing.

Diversification of von Willebrand Factor A and Chitin-Binding Domains in Pif/BMSPs Among Mollusks

Pif is a shell matrix protein (SMP) identified in the nacreous layer of Pinctada fucata (Pfu) comprised two proteins, Pif97 and Pif 80. Pif97 contains a von Willebrand factor A (VWA) and chitin-binding domains, whereas Pif80 can bind calcium carbonate crystals. The VWA domain is conserved in the SMPs of various mollusk species; however, their phylogenetic relationship remains obscure. Furthermore, although the VWA domain participates in protein–protein interactions, its role in shell formation has not been established. Accordingly, in the current study, we investigate the phylogenetic relationship between PfuPif and other VWA domain-containing proteins in major mollusk species. The shell-related proteins containing VWA domains formed a large clade (the Pif/BMSP family) and were classified into eight subfamilies with unique sequential features, expression patterns, and taxa diversity. Furthermore, a pull-down assay using recombinant proteins containing the VWA domain of PfuPif 97 revealed that the VWA domain interacts with five nacreous layer-related SMPs of P. fucata, including Pif 80 and nacrein. Collectively, these results suggest that the VWA domain is important in the formation of organic complexes and participates in shell mineralisation.

Combining an improved Apriori algorithm and Social Network analysis to identify the unique sequential features of individual household electricity consumption behaviours

ABSTRACT The household’s electricity consumption behaviour follows a unique sequential pattern and can be identified by analyzing the electricity consumption data with fine granularity in a smart home context. This particular sequence is concretely embodied in a series of electrical activities with temporal association relationships, thus forming a unique household electrical appliance activity-based chain (EAAC). In this study, we propose a method that combines an improved Apriori algorithm and Social Network to construct a household EAACs. First, we improved the Apriori algorithm (Apriori (1,1)) by combining the temporal and transactional sequences and used it to mine the time-series activity associations among different household appliances. After that, we used the Sliding Window concept to splice the time-series associations and obtain the unique EAACs for each household. Next, we visualized the EAACs using the Social Network analysis to reflect the unique sequential features of household electricity consumption behaviours. Finally, the model was validated by analyzing two families’ actual household electricity consumption data, and future research directions were given.