Insufficient Historical Data Research Articles

Hybrid model for robust and accurate forecasting building electricity demand combining physical and data-driven methods

The high-precision prediction of building electrical demand is paramount significance for optimal control of building systems and the reduction of operational energy consumption. The pure physical simulation software struggles to depict buildings' energy usage behavior accurately; while purely data-driven methods lack the interpretability in real-world physical scenarios. To address the challenges existing in current models and algorithms, this paper proposes a hybrid model that combines physical mechanism simulation and machine learning to complement each other. Empirical Mode Decomposition (EMD) is utilized to decompose complex data into simple components in pre-processing (RMSE, MAE, and SMAPE all decreased by around 0.2–0.3). And K-means clustering algorithm is used to extract features of building electrical data and determine employee working states (R2 increased from 0.3 to 0.85). Shapley Additive explanations (SHAP) values and Pearson correlation coefficients are used for model interpretability analysis. Combining weather forecasts, the Monte Carlo method is employed to obtain prediction intervals. Furthermore, this study explores the use of transfer learning to save computational costs and reduce the amount of data needed for predicting, especially for high-rise buildings or floors with insufficient historical data. The hybrid model results indicate that the R2 can exceed 0.85, up to 0.9, while pure physical simulation can only achieve 0.3. MAE, MSE, and RMSE remain below 0.07, while SMAPE stays around 0.2. The R2 value of the transfer learning model can surpass 0.8 (MSE, MAE. MAE, MSE, and RMSE remain below 0.2, while SMAPE stays around 0.4). The model's residuals obey normal distribution, indicating the model has strong generalization capabilities.

Three-layered location recommendation algorithm using spectral clustering

Users utilize Location-Based Social Networks (LBSNs) to check into diverse venues and share their experiences through ratings and comments. However, these platforms typically feature a considerably larger number of locations than users, resulting in a challenge known as insufficient historical data or user-location matrix sparsity. This sparsity arises because not all users can check into all available locations on a given LBSN, such as Yelp. To address this challenge, this paper proposes combining Spectral Clustering with a three-layered location recommendation model to develop a recommender system named LSC, applied to Yelp datasets. LSC leverages various information, including users’ check-in data, demographics, location demographics, and users’ friendship network data, to train the recommender system and generate recommendations. Evaluation of LSC’s performance utilizes the Yelp dataset and several comparison metrics, such as accuracy, RMSE, and F1-score. The results demonstrate that our proposed algorithm delivers reliable and significant performance improvements across various evaluation metrics compared to competing algorithms.

Identifying Strategies for Effective Biodiversity Preservation and Species Status of Chilean Amphibians.

Resources are limited in global biodiversity conservation efforts, which emphasizes the significance of setting conservation priorities. Using standardized criteria, we evaluated 58 amphibian species in Chile to determine their conservation priority (CP). Species with insufficient historical data had their values marked as missing. With a median value of p = 1.67, the results demonstrated CP values ranging from p = 0.48 to p = 3.0, classifying species into priority and non-priority groups. Four levels were established for the priority categories: no priority, low priority, medium priority, and high priority. Additionally, the Telmatobiidae and Alsodidae families were identified as two more priority families. Notably, the species with the highest priority were found to be T. halli, T. fronteriensis, T. philippii, T. chusmisensis, A. pehuenche, and Alsodes tumultuosus, where T. philippii and T. fronteriensis have equal priority for conservation at the national level according to the conservation priority analysis. Eight priority families-the Alsodidae, Batrachylidae, Bufonidae, Ceratophryidae, Leptodactylidae, Rhinodermatidae, and Telmatobiidae-were determined, and 14 species-or 24% of the species examined-need further study. Based on the conservation priority analysis, the species T. fronteriensis and T. philippii share the highest priority for conservation at the national level (p = 2.50). With 70% of the amphibians under study being threatened mainly by habitat loss, pollution, and emerging diseases, the creation of conservation categories made the threat assessment process easier. Due to a lack of information on geographic distribution and abundance, quantitatively classifying amphibians in Chile remains difficult. The analysis of conservation priorities and potential extinction threats informs appropriate management strategies.

Assessment of Factors Affecting the Implementation of Occupational Health and Safety Measures in the Construction Industry in Somaliland

Purpose. The success of construction projects heavily depends on the occupational health and safety (OHS) of the workers. In Somaliland, however, this is not given much consideration. Therefore, the present study aimed to assess the factors affecting the implementation of OHS measures on building construction projects (BCPs) in Somaliland. Design/Methodology/Approach. A cross‐sectional research design was employed and 80 questionnaires were distributed to the intended respondents as part of the descriptive survey study, which used a census to determine that the total population was equal to the accessible population. Additionally, data were gathered through observations and interviews. Quantitative data were analyzed using frequency analysis and relative importance index, while qualitative data from interviews and observation were explored through narrative analysis. Findings. The majority of the construction industries do not use Occupational Health Safety Assessment Series 45001 to increase safety performance since the relevant laws are not enforced. The study also found that the construction companies did not consider the factors influencing the implementation of OHS: unavailability of personal protective equipment, lack of local guidelines on the standard procedure of OHS, limited expertise, and insufficient historical data availability are the main challenges on the implementation of OHS measures on BCPs in Somaliland. Originality/Value. The study concludes that the implementation of the current stage of OHS in construction industries in Somaliland is 2.5%, which shows very poor and the safety management system was not developed; there were challenging factors to implement this OHS in construction industries in Somaliland. The researchers make several recommendations, including increased OHS awareness, training and retraining of construction employees on OHS, and enforcing the use of protective safety wear and equipment on building sites.

Impact assessment of shared storage and peer-to-peer trading on industrial buildings in the presence of electric vehicle parking lots: A hybrid robust-CVaR analysis

Local power markets and peer-to-peer (P2P) power transaction plans between the clients have lately received attractions as a cost-effective approach to encourage flexible energy options and sharing the internal power resources. For the integration of industrial consumers (ICs) in the presence of electric vehicle parking lot, this study modeled local power markets to share the surplus power of ICs between each other. Other hands, shared storage is modeled in the proposed system to benefit consumers. In order to investigate the proposed system under uncertain conditions, a hybrid optimization method is proposed for uncertainty modeling. In this paper, the well-known uncertainty modeling tools, including the robust optimization and Conditional Value at Risk (CVaR) embedded stochastic optimization approach, are proposed to model the uncertainties. The markets price uncertainty is one of the important uncertain parameters assumed as an unknown-distribution parameter due to insufficient historical data or not following a specific distribution; thus, the risks of this parameter are modeled by robust optimization, which has no need for big historical data of uncertain parameter. The other uncertain parameter is solar irradiation. The corresponding risks of solar irradiation is modeled by CVaR modeling because of the following Beta distribution. Thus, the financial risks of different uncertain parameters can be modeled effectively using the proposed hybrid optimization framework. According to obtained results, using peer-to-peer trading reduces the operation cost by 7.94%, while using the shared storage along with peer-to-peer trading reduces the operation cost by 21.49%.

Numerical Modelling and Sensitivity Analysis of the Pitztal Valley Debris Flow Event

Debris flows characterized by their rapid velocity and composition of water, mud, soil, and boulders, have the potential to inflict significant harm and present hazards to human life, infrastructure, and the natural surroundings. Numerical simulations provide a cost-effective approach for investigating different scenarios, hence boosting comprehension of flow dynamics and interactions. However, accurate modelling of these flows typically face difficult challenges arising from inherent modeling constraints and insufficient historical event data. The primary objective of the present study is to conduct numerical modeling and sensitivity analysis of the debris flow event that occurred in the Pitztal Valley, Austria in August of 2009, based on a multi-phase model for debris flows. The validation of the simulation results involves the comparison with the observed deposition patterns in the field. Various validation factors are employed to evaluate the accuracy of the simulated deposit and demonstrate a satisfactory level of precision in predicting deposition patterns. A sensitivity analysis is also conducted to examine the influence of in situ conditions on the effects of debris flow. The results demonstrate that numerical modelling can play an important role in engineering hazard assessment by analyzing the existing model’s effectiveness in simulating both historical and projected debris flow events.

Optimized Transfer Learning Based Short-term Electrical Load Interval Prediction

Electrical load forecasting is an essential foundation for power reliable and economical operation of the power grid. Most forecasting models regard the prediction results as deterministic variables, which ignores the randomness and volatility of the power load. At the same time, insufficient historical load data often lead to undertrained models, which affects the accuracy of capturing uncertain information. Therefore, we proposed an optimized transfer learning-based method for short-term load-interval prediction. A deep learning quantile regression model would be constructed by source domain data in the method, and the weights of the source model would be optimized to avoid negative transfer. Then, the target model is constructed by parameter transfer based on key layers and is tuned with hyperparameters by target domain data. From the experimental discussion, it is known that the model with an optimized transfer learning strategy can accurately quantify the fluctuation range of future power load.

Multi-source weighted source-free domain transfer method for rotating machinery fault diagnosis

The mainstream approach to addressing the issues of insufficient historical data and high annotation costs in the domain of rotating machinery is to build transfer learning models based on labeled multi-source data. However, the practical diagnosis of failure cases often relies on data privacy, thereby limiting the widespread application of current multi-source domain transfer approaches for the ‘data silos’ problem of. In view of the above problem, a multi-source weighted source-free domain transfer approach is designed for rotating machinery fault diagnosis, and the designed scheme can efficiently achieve data privacy and domain transfer. Specifically, the proposed approach achieves knowledge transfer from the source to the target during the training process of the unlabeled target data without accessing the source data. This is accomplished through the utilization of a designed reinforced information maximization strategy and improved self-training mechanism. Additionally, a weighted strategy is devised to automatically apply optimal values to all source domains based on their relevance to the target domain. The proposed framework demonstrates accuracy exceeding 96% across eight cross-domain diagnostic cases in two sets of rotating machinery data, with an average accuracy of 98.26%. These results underscore the exceptional ability of the proposed method to address cross-domain fault diagnosis in rotating machinery while ensuring privacy protection.

Capacity estimation of Li-ion battery based on transformer-adversarial discriminative domain adaptation

Lithium-ion batteries are widely used in various electronic devices as well as electric vehicles, and accurate estimation of the battery capacity is important to ensure safe and reliable operation of the system. However, in practice, the complex working conditions and the limitation of the number of charge/discharge cycles lead to insufficient historical data and inaccurate capacity estimation. In order to improve the adaptability as well as accuracy under different operating conditions, this paper proposes a lithium-ion battery capacity estimation model based on Transformer-Adversarial Discriminative Domain Adaptation (T-ADDA). The model takes charging voltage, charging current, and charging temperature as inputs and uses a transformer network to extract the time series features from the data. Then, adversarial domain adaptation is trained on the source and target domain data by the domain discrimination network of the ADDA model so as to find the domain invariant features between the source and target domains. Finally, the regression network of ADDA is used to achieve cross-domain prediction for the target domain data. The experimental results show that the T-ADDA model can accurately achieve cross-domain prediction and that the average error of prediction under different operating conditions is only 3.9225%. Therefore, the T-ADDA model has good adaptability and accuracy, and it can significantly improve the performance of lithium-ion battery capacity estimation.

Predicting Demands of COVID-19 Prevention and Control Materials via Co-Evolutionary Transfer Learning.

The novel coronavirus pneumonia (COVID-19) has created great demands for medical resources. Determining these demands timely and accurately is critically important for the prevention and control of the pandemic. However, even if the infection rate has been estimated, the demands of many medical materials are still difficult to estimate due to their complex relationships with the infection rate and insufficient historical data. To alleviate the difficulties, we propose a co-evolutionary transfer learning (CETL) method for predicting the demands of a set of medical materials, which is important in COVID-19 prevention and control. CETL reuses material demand knowledge not only from other epidemics, such as severe acute respiratory syndrome (SARS) and bird flu but also from natural and manmade disasters. The knowledge or data of these related tasks can also be relatively few and imbalanced. In CETL, each prediction task is implemented by a fuzzy deep contractive autoencoder (CAE), and all prediction networks are cooperatively evolved, simultaneously using intrapopulation evolution to learn task-specific knowledge in each domain and using interpopulation evolution to learn common knowledge shared across the domains. Experimental results show that CETL achieves high prediction accuracies compared to selected state-of-the-art transfer learning and multitask learning models on datasets during two stages of COVID-19 spreading in China.

Slope stability assessment of a major trunk road at Scrabster Harbour, Scotland, UK

In 2017 two landslides resulted in a temporary closure of the main access road to Scrabster Harbour, located in the north of the Scottish mainland. A slope stability assessment was commissioned to investigate the occurrence, causes and mechanisms of historical landslides, and their associated consequences to inform future landslide hazard potential. Within Scotland, most slope stability studies are undertaken using qualitative rather than quantitative methods, largely due to insufficient historical data. This paper presents a case study where a semi-quantitative risk assessment was used to assess the stability of coastal slopes above the A9 trunk road at Scrabster Harbour. A database of historical landslides and slope characteristics was compiled and used in a semi-quantitative risk assessment to provide the client with targeted information on which areas of the slope can be stabilized most effectively. This was based on ranking the slopes in terms of relative risk, thus providing the road operator and maintenance contractor with an indication of those slopes presenting a higher risk so that these areas could be prioritized for remedial works. The analysis showed that surface-water drainage intersecting the slopes and locally oversteepened slopes were primary controls for the observed landslides.

Urban waterlogging prediction and risk analysis based on rainfall time series features: A case study of Shenzhen

In recent years, the frequency of extreme weather has increased, and urban waterlogging caused by sudden rainfall has occurred from time to time. With the development of urbanization, a large amount of land has been developed and the proportion of impervious area has increased, intensifying the risk of urban waterlogging. How to use the available meteorological data for accurate prediction and early warning of waterlogging hazards has become a key issue in the field of disaster prevention and risk assessment. In this paper, based on historical meteorological data, we combine domain knowledge and model parameters to experimentally extract rainfall time series related features for future waterlogging depth prediction. A novel waterlogging depth prediction model that applies only rainfall data as input is proposed by machine learning algorithms. By analyzing a large amount of historical flooding monitoring data, a “rainfall-waterlogging amplification factor” based on the geographical features of monitoring stations is constructed to quantify the mapping relationship between rainfall and waterlogging depths at different locations. After the model is trained and corrected by the measured data, the prediction error for short-time rainfall basically reaches within 2 cm. This method improves prediction performance by a factor of 2.5–3 over featureless time series methods. It effectively overcomes the limitations of small coverage of monitoring stations and insufficient historical waterlogging data, and can achieve more accurate short-term waterlogging prediction. At the same time, it can provide reference suggestions for the government to conduct waterlogging risk analysis and add new sensor stations by counting the amplification factor of other locations.

Subjective Attack Trees

Subjective attack trees (SATs) extend traditional attack trees by taking into account the uncertainty about the probability values of security events. Assigning precise values is often difficult due to lack of knowledge, or insufficient historical data, making the evaluation of risk in existing approaches unreliable, and therefore unreliable security decisions. With SATs, the author seeks to better reflect the reality underpinning the model and offer a better approach to decision-making via the modeling of uncertainty about the probability distributions in the form of subjective opinions, resulting in a model taking second-order uncertainty into account. The author further discusses how to conduct security analysis, such as risk measuring and security investments analysis, under the proposed model. Security investments analysis requires first to incorporate the model with countermeasures and then study how these countermeasures reduce risk in the presence of uncertainty about probability values. The importance and advantage of the SAT model are demonstrated through extended examples.

RAC-GAN-Based Scenario Generation for Newly Built Wind Farm

Due to the lack of historical output data of new wind farms, there are difficulties in the scheduling and planning of power grid and wind power output scenario generation. The randomness and uncertainty of meteorological factors lead to the results of traditional scenario generation methods not having the ability to accurately reflect their uncertainty. This article proposes a RAC-GAN-based scenario generation method for a new wind farm output. First, the Pearson coefficient is adopted in this method to screen the meteorological factors and obtain the ones that have larger impact on wind power output; Second, based on the obtained meteorological factors, the Grey Relation Analysis (GRA) is used to analyze the meteorological correlation between multiple wind farms with sufficient output data and new wind farms (target power stations), so that the wind farm with high meteorological correlation is selected as the source power station. Then, the K-means method is adopted to cluster the meteorological data of the source power station, thus generating the target power station scenario in which the cluster information serves as the label of the robust auxiliary classifier generative adversarial network (RAC-GAN) model and the output data of the source power station is considered as the basis. Finally, the actual wind farm output and meteorological data of a region in northeast China are employed for arithmetic analysis to verify the effectiveness of the proposed method. It is proved that the proposed method can effectively reflect the characteristics of wind power output and solve the problem of insufficient historical data of new wind farm output.

Evaluating Prediction Models for Airport Passenger Throughput Using a Hybrid Method

This paper proposes a hybrid evaluation method to assess the prediction models for airport passenger throughput (APT). By analyzing two hundred three airports in China, five types of models are evaluated to study the applicability to different airports with various airport passenger throughput and developing conditions. The models were fitted using the historical data before 2014 and were verified by using the data from 2015–2019. The evaluating results show that the models employed for evaluating perform well in general except that there are insufficient historical data for modelling, or the APT of the airports changes abruptly owing to expansion, relocation or other kinds of external forces such as earthquakes. The more the APT of an airport is, the more suitable the models are for the airport. Particularly, there is no direct relation between the complexity and the predicting accuracy of the models. If the parameters of the models are properly set, time series models, causal models, market share methods and analogy-based methods can be utilized to predict the APT of 88% of studied airports effectively.

Photovoltaic power prediction under insufficient historical data based on dendrite network and coupled information analysis

In recent years, the installed capacity of photovoltaic solar energy has been increasing year by year. The existing power prediction methods are difficult to achieve reliable power generation prediction for PV equipment that has just been put into service. This poses great difficulties for power system management and dispatching. Therefore, establishing a reliable PV power prediction model for this situation is important for the rapid integration of new-built PV installations into the power system for energy management and dispatching. In this paper, an ultra-short-term PV power prediction method based on coupled information analysis and a dendritic network is proposed. First, an improved Hampel filter is proposed to improve the accuracy of anomaly data processing by analyzing the information between strongly coupled variables. In addition, a dendritic network modeling method is introduced for PV generation prediction. Compared to other solutions, this prediction approach relies on very little historical data to achieve reliable predictions and also features a simple model structure and high generalization. Forty different sets of tests were conducted according to different weather conditions and data conditions. The experimental results show that the proposed method can achieve higher prediction performance and stability compared with the benchmark model.

Fuzzy logic-based vehicle safety estimation using V2V communications and on-board embedded ROS-based architecture for safe traffic management system in hail city

<abstract> <p>Estimating the state of surrounding vehicles is crucial to either prevent or avoid collisions with other road users. However, due to insufficient historical data and the unpredictability of future driving tactics, estimating the safety status is a difficult undertaking. To address this problem, an intelligent and autonomous traffic management system based on V2V technology is proposed. The main contribution of this work is to design a new system that uses a real-time control system and a fuzzy logic algorithm to estimate safety. The robot operating system (ROS) is the foundation of the control architechture, which connects all the various system nodes and generates the decision in the form of a speech and graphical message. The safe path is determined by a safety evaluation system that combines sensor data with a fuzzy classifier. Moreover, the suitable information processed by each vehicle unit is shared in the group to avoid unexpected problems related to speed, sudden braking, unplanned deviation, street holes, road bumps, and any kind of street issues. The connection is provided through a network based on the ZigBee protocol. The results of vehicle tests show that the proposed method provides a more reliable estimate of safety as compared to other methods.</p> </abstract>

Distribution-Free Approaches for an Integrated Cargo Routing and Empty Container Repositioning Problem with Repacking Operations in Liner Shipping Networks

Cargo (laden container) routing and empty container repositioning are crucial components in liner shipping, which are closely relevant. However, most existing works focus on cargo routing and empty container repositioning separately, which cannot optimize the global shipping cost. In addition, (1) appropriate repacking operations for laden containers can curtail the total handling costs, and (2) the perfect information for uncertain laden and empty container demands may be difficult to obtain due to insufficient historical data. This work investigates an integrated cargo routing and empty container repositioning problem with repacking operations in which only partial information about uncertain laden and empty container demands is known. The objective is to minimize the total costs including repacking operation cost and laden and empty container transportation costs. For the problem, a new chance-constrained programming model based on moment-based ambiguous sets is formulated. Then, four distribution-free solution approaches are adopted to solve the investigated problem. Numerical experiments are conducted to compare the proposed methods.

Remaining useful life prediction of lithium-ion batteries based on attention mechanism and bidirectional long short-term memory network

Accurate prediction of the remaining useful life of lithium-ion batteries is beneficial to prolong the battery's life and increase safety. However, there is insufficient historical data available because of the limitation of charge and discharge cycles of lithium-ion batteries. To enhance the prediction accuracy, a hybrid model based on an attention mechanism and a bidirectional long short-term memory network is proposed, which can acquire good prediction results with early data of the target battery. Multiple temporal features, which strongly correlate with the capacity considered the main feature of battery health, are used as input to train and test the proposed model. The attention mechanism is added in the bidirectional long short-term memory network to precisely decide the attention distribution of multiple features to extract useful information. It helps the bidirectional long short-term memory networks to make a better prognosis and overcome the vanishing and exploding gradient problems. The experimental results show that the proposed framework can decrease the uncertainty for multi-step prediction and outperforms other machine learning models in prediction accuracy.

Bayesian Decision Making of an Imperfect Debugging Software Reliability Growth Model with Consideration of Debuggers’ Learning and Negligence Factors

In this study, an imperfect debugging software reliability growth model (SRGM) with Bayesian analysis was proposed to determine an optimal software release in order to minimize software testing costs and also enhance the practicability. Generally, it is not easy to estimate the model parameters by applying MLE (maximum likelihood estimation) or LSE (least squares estimation) with insufficient historical data. Therefore, in the situation of insufficient data, the proposed Bayesian method can adopt domain experts’ prior judgments and utilize few software testing data to forecast the reliability and the cost to proceed with the prior analysis and the posterior analysis. Moreover, the debugging efficiency involves testing staff’s learning and negligent factors, and therefore, the human factors and the nature of debugging process are taken into consideration in developing the fundamental model. Based on this, the estimation of the model’s parameters would be more intuitive and can be easily evaluated by domain experts, which is the major advantage for extending the related applications in practice. Finally, numerical examples and sensitivity analyses are performed to provide managerial insights and useful directions for software release strategies.