Historical Data Research Articles

Pre-Assessment Research of Regional Spatial Planning from the Perspective of Spatial Evolution

As an important policy tool for guiding the development and protection of territorial space, the specific impact of spatial planning on the evolution of territorial space and the effects of its implementation have not yet been fully recognized. At the planning formulation stage, the feedback cycle of the implementation effect of planning is too long, and the adjustment is too slow to take effect. This directly affects the effectiveness and relevance of planning implementation. In this study, we propose a framework for pre-assessment of regional spatial planning based on the evolution of territorial space. We construct an indicator system from four dimensions to pre-assess the effectiveness of territorial spatial planning. The results show that the land use change simulation model, based on historical data coupled with planning elements, achieves an accuracy of 0.8457, which can accurately reflect the impact of planning on the evolution of land space. The results of the evaluation show that: (1) Planning elements such as concentrated urban construction areas, schools, and other public service facilities are the main driving forces behind the future evolution of territorial space. (2) Regional spatial planning has a significant effect on adjusting the spatial layout and optimizing the spatial form, and it has a certain effect on restricting the total scale of the construction area, improving the efficiency of land use, and lowering carbon emissions. (3) Existing planning strategies are still too rigid, so further enhancement of “flexibility” and “blank space” in planning is necessary. Additionally, guidance for improving the efficiency of land development needs to be further strengthened. The main contribution of this study is to provide a reliable pre-evaluation framework for policymakers and scholars. This will help identify problems and shortcomings at the planning formulation stage, allowing them to be optimized and adjusted in a timely manner. Under the guidance of scientific and reasonable planning, it will further promote the green and high-quality development and protection of territorial space.

Product pricing based on customer perception quality and service convenience using interval type-2 fuzzy logic system

In the competitive landscape of customer goods, particularly in the wrapping paper industry, pricing strategies are critical to achieving market success. This study presents a novel approach to product pricing by integrating customer perception quality and service and convenience factors using interval type-2 fuzzy logic system (IT2FLS). The customer perception quality factor is subdivided into material quality and aesthetics design sub-factors while the service and convenience factor comprise web-based ordering system as well as the web-based post-sale customer engagement. The methodology involves collecting data through customer surveys and expert evaluations to quantify the perceived importance and performance of each sub-factor. The IT2FLS is employed to handle the inherent uncertainty and imprecision in experts’ judgment, providing a robust framework for aggregating these qualitative assessments into a comprehensive pricing model. This IT2FLS allows for the dynamic adjustment of pricing based on fluctuating customer perceptions and service levels. The outcome of the proposed IT2FLS is a pricing factor that serves as a multiplier for the standard product price established by the company. The new product prices have been validated also considering historical data and it was found that the prices remain acceptable to customers without drastically impacting sales. This study contributes to the body of knowledge on pricing strategies by offering a sophisticated, mathematically grounded approach that accounts for the complex, fuzzy nature of customer preferences. The proposed model not only enhances pricing accuracy but also provides a flexible tool for managers to adapt pricing strategies in real-time based on customer feedback and service performance.

An Efficient Data Collection Method by UAV Based on Data Recovery

As a crucial component of crowdsensing networks, unmanned aerial vehicles (UAVs) typically serve as data collectors. Utilizing UAVs for data acquisition in designated areas holds significant potential for military and industrial applications. To effectively reduce the time and cost of UAV-based data collection, this invention proposes a UAV data collection and completion method based on the importance of data. First, reinforcement learning is employed to identify the importance of data regions using historical data, enabling the recovery of data for the entire region by collecting data from only these critical areas, thereby reducing costs. Subsequently, an algorithm for optimizing UAV trajectories is introduced to minimize the flight distance while ensuring coverage of all important regions. Finally, data completion methods are utilized to obtain data for the entire region based on the data collected by the UAVs. The proposed method in this invention aims to achieve reduced collection costs while ensuring data accuracy.

Research on Photovoltaic Power Prediction Method Based on Dynamic Similar Selection and Bidirectional Gated Recurrent Unit

AbstractPhotovoltaic (PV) power generation is vital for sustainable energy development, yet its inherent randomness and volatility challenge grid stability. Accurate short‐term PV power prediction is essential for reliable operation. This paper proposes an integrated prediction method combining dynamic similar selection (DSS), variational mode decomposition (VMD), bidirectional gated recurrent unit (BiGRU), and an improved sparrow search algorithm (ISSA). First, DSS selects training data based on local meteorological similarity, reducing randomness interference. VMD then decomposes PV power data into smooth components, mitigating volatility. The Pearson correlation coefficient is used to filter highly relevant meteorological variables, enhancing input quality. BiGRU captures temporal evolution patterns, with ISSA optimizing key parameters for robust forecasting. Validated on historical Australian PV data under diverse weather conditions, the proposed method effectively reduces randomness and volatility, significantly improving prediction accuracy and reliability. These advancements support stable PV power supply and efficient grid operation.

Prediction analysis of retail store sales level using neural network algorithm method based on customer segments

Marketing activities are of significant importance to business operations, as they are uniquely positioned to provide value to consumers. The marketing mix represents one of the strategic approaches employed to attain these organizational objectives. However, the company's sales data is only available for consultation in the archives. By understanding customer preferences and requirements, the company can readily develop an effective marketing strategy to compete with similar businesses. Accordingly, this study employs the neural network methodology to forecast sales based on the company's historical sales data. The research method employs a neural network due to its capacity for processing substantial data sets with flexibility. Moreover, the Root Mean Square Error (RMSE) must be employed to ascertain the precision of the utilized model. The findings of this study indicate that the discrepancy between the actual and predicted values is minimal, suggesting that the model is able to accurately represent the data. Similarly, the results of the RMSE (Root Mean Square Error) demonstrate that the model's accuracy is improving, with minimal values observed in each segment. A 4P marketing mix strategy may be employed to enhance the company's sales potential. Based on the findings of the research, it can be posited that the results of the prediction data set, the visual prediction results, and the RMSE using the Neural Network method can be utilized effectively and accurately to forecast sales and assist company owners and management in considering target sales levels in the future.

Research on Load Forecasting Model for Distribution Network Based on Virtual Definition of Internet of Things

In the process of smart grid construction, the increasing demand for electricity in power-consuming areas often leads to the operation of distribution network equipment at full load or even overload, which puts great pressure on the protection of the power system. At present, equipment load forecasting models are mainly used to predict and analyze various data-related factors of equipment, which are divided into temporal factors and nonsequential factors, to reduce the complexity of equipment management on embedded platforms. According to the original intention of ubiquitous power Internet of Things (IoT) construction, this paper uses the embedded platform of distribution network equipment to build a fog network. It also adopts a virtual defined network to manage the data communication of each node, and effectively utilizes edge computing to complete data processing tasks. A lightweight load forecasting scheme with both time series and nontime characteristics is proposed, and a neural network feature model is pre-trained. For the sensing parameters extracted from embedded systems of power equipment and load prediction, the unidirectional continuous cyclic long short-term memory (LSTM) connection is regarded as a time series neural network modeling. We then consider the determining factors of historical data on equipment operation capability to predict the effectiveness of load capacity, and extract load data feature vectors to compare potential relationships. Simulation tests have shown that the research method proposed in this paper is more effective in predicting load capacity and analyzing different temporal patterns of loads, facilitating the decomposition of data in the initial stage. Software-defined virtual networks use lightweight structures to reduce network operational pressure and minimize data space occupation. The research results can achieve the important function of early warning of abnormal operation of the power grid system, reduce the operational risks of the power grid system, and have significant implications for improving the economic and social benefits of the power system.

Saliency-aware Foveated Path Tracing for Virtual Reality Rendering.

Foveated rendering reduces computational load by distributing resources based on the human visual system. This enables the implementation of ray tracing in virtual reality applications, where a high frame rate is essential to achieve visual immersion. However, traditional foveation methods based solely on eccentricity cannot adequately account for the complex behavior of visual attention. This is one of the main reasons that leads to lower perceived quality compared to non-foveated techniques. In this study, we introduce a novel rendering pipeline that incorporates ocular attention through the use of visual saliency. Based on foveation saliency, our approach facilitates the real-time production of high-quality images utilizing path tracing by distributing samples according to saliency metrics derived from geometric and historical data. To further augment image quality, an adaptive filtering process, aligned with the saliency metrics, is employed to reduce visible artifacts in non-foveal regions. Our experiments prove that this novel approach can demonstrate superior performance compared to previous methods, both in terms of quantitative metrics and perceived visual quality.

Multitask Deep Learning Models of Combined Industrial Absorption, Distribution, Metabolism, and Excretion Datasets to Improve Generalization.

The optimization of absorption, distribution, metabolism, and excretion (ADME) profiles of compounds is critical to the drug discovery process. As such, machine learning (ML) models for ADME are widely used for prioritizing the design and synthesis of compounds. The effectiveness of ML models for ADME depends on the availability of high-quality experimental data for a diverse set of compounds that is relevant to the emerging chemical space being explored by the drug discovery teams. To that end, ADME data sets from Genentech and Roche were combined to evaluate the impact of expanding the chemical space on the performance of ML models, a first experiment of its kind for large-scale, historical ADME data sets. The combined ADME data set consisted of over 1 million individual measurements distributed across 11 assay end points. We utilized a multitask (MT) neural network architecture that enables the modeling of multiple end points simultaneously and thereby exploits information transfer between interconnected ADME end points. Both single- and cross-site MT models were trained and compared against single-site, single-task baseline models. Given the differences in assay protocols across the two sites, the data for corresponding end points across sites were modeled as separate tasks. Models were evaluated against test sets representing varying degrees of extrapolation difficulty, including cluster-based, temporal, and external test sets. We found that cross-site MT models appeared to provide a greater generalization capacity compared to single-site models. The performance improvement of the cross-site MT models was more pronounced for the relatively "distant" external and temporal test sets, suggesting an expanded applicability domain. The data exchange exercise described here demonstrates the value of expanding the learning from ADME data from multiple sources without the need to aggregate such data when the experimental methods are disparate.

Predicting Thai stock index trend using deep neural network based on technical indicators

In this study, we aimed to find a suitable model for predicting the direction of the Stock Exchange of Thailand index (SET50 index) by developing a deep neural network model that builds upon the advancements of a hybrid model of an artificial neural network and genetic algorithm. Due to the complexity of stock data and the challenging predictability, a single hidden layer may not be sufficient. Therefore, we proposed a deep neural network model with three hidden layers, optimizing the number of nodes in each layer to achieve accurate predictions of the movement of the index. The input data consists of technical indicators widely used by technical stock analysts. These indicators are calculated over four different lookback periods of 3, 5, 10, and 15 days. The data was collected from the SETSMART system, which can retrieve historical data and real-time data via an API. We focused on data from the period of 2015–2019, comprising 1,220 records. Our test results showed that the proposed model achieved the highest average accuracy at 82.94%, outperforming the previous model.

Adaptive Non-Stationary Fuzzy Time Series Forecasting with Bayesian Networks.

Despite its interpretability and excellence in time series forecasting, the fuzzy time series forecasting model (FTSFM) faces significant challenges when handling non-stationary time series. This paper proposes a novel hybrid non-stationary FTSFM that integrates time-variant FTSFM, Bayesian network (BN), and non-stationary fuzzy sets. We first apply first-order differencing to extract the fluctuation information of the time series while reducing non-stationarity. A novel time-variant FTSFM updating method is proposed to effectively merge historical knowledge with new observations, enhancing model stability while maintaining sensitivity to time series changes. The updating of fuzzy sets is achieved by incorporating non-stationary fuzzy sets and prediction residuals. Based on updated fuzzy sets, the system reconstructs fuzzy logical relationship groups by combining historical and new data. This approach implements dynamic quantitative modeling of fuzzy relationships between historical and predicted moments, integrating valuable historical temporal fuzzy patterns with emerging temporal fuzzy characteristics. This paper further develops an adaptive BN structure learning method with an adaptive scoring function to update temporal dependence relationships between any two moments while building upon existing dependence relationships. Experimental results indicate that the proposed model significantly outperforms benchmark algorithms.

Museum insights for conservation: Unraveling the Extinction Factors in the Jambato Harlequin Frog, Atelopus ignescens .

Natural history museums harbor invaluable resources for conserving endangered species by providing insights into the mechanism of historical population declines. We conducted data synthesis to better understand the extinction factors of the iconic Jambato Harlequin frog, Atelopus ignescens, which was widespread in the Ecuadorian Andes before 1985 but vanished in 1988. We synthesized historical data from natural history museums, the Global Biodiversity Information Facility (GBIF), and mtDNA sequences to examine whether Batrachochytrium dendrobatidis (Bd) fungus infection, climate change, and/or their interaction contributed to the rapid population decline. We found excessive rare alleles reflected in the negative Tajima's D estimated from the mtDNA samples from 1984, indicating a selective sweep or population bottleneck. Sex and geography showed stronger effects on adult body sizes than Bd epizootic timing. The body sizes of adult males formed a geographic cline. Species distribution modeling based on temperature and precipitation accurately predicted the occupancy of A. ignescens in 1960-69, which further projected a rapid decline in species distribution between 1970-2020. This investigation revealed strong climate effect and weak epizootics effect on A. ignescens extinction, and inspires future museum genomic studies to dissect the potential climatic maladaptation behind dramatic historical extinctions.

New extra-Amazonian records of the Black-billed Cuckoo <i>Coccyzus erythropthalmus</i> (Cuculidae) for Brazil

The breeding grounds of the Black-billed Cuckoo Coccyzus erythropthalmus encompass a wide area in northern North America. During the austral winter individuals migrate to non-breeding areas in South America. There had been only three known locations for the species in Brazil, two in the Amazon Forest and one in the Atlantic Forest. Here, we aim to present new records in Brazil and to organize the available literature recovering historical data. The new records are in the Southeast and South regions and thus represent the first documented records outside the Brazilian Amazon. These findings indicate an expansion of the area considered nomadic for the species. All extra-Amazonian records were made in strong El Niño years, a climate phenomenon that may be changing bird migration patterns in South America, which requires further investigation.

An Express Management System With Graph Recurrent Neural Network for Estimated Time of Arrival

Estimated Time of Arrival (ETA) is a crucial task in the logistics and transportation industry, aiding businesses and individuals in optimizing time management and improving operational efficiency. This study proposes a novel Graph Recurrent Neural Network (GRNN) model that integrates external factor data. The model first employs a Multilayer Perceptron (MLP)-based external factor data embedding layer to categorize and combine influencing factors into a vector representation. A Graph Recurrent Neural Network, combining Long Short-Term Memory (LSTM) and GNN models, is then used to predict ETA based on historical data. The model undergoes both offline and online evaluation experiments. Specifically, the offline experiments demonstrate a 5.3% reduction in RMSE on the BikeNYC dataset and a 6.1% reduction on the DidiShenzhen dataset, compared to baseline models. Online evaluation using Baidu Maps data further validates the model's effectiveness in real-time scenarios. These results underscore the model's potential in improving ETA predictions for urban traffic systems.

Efficient and assured reinforcement learning-based building HVAC control with heterogeneous expert-guided training

Building heating, ventilation, and air conditioning (HVAC) systems account for nearly half of building energy consumption and of total energy consumption in the US. Their operation is also crucial for ensuring the physical and mental health of building occupants. Compared with traditional model-based HVAC control methods, the recent model-free deep reinforcement learning (DRL) based methods have shown good performance while do not require the development of detailed and costly physical models. However, these model-free DRL approaches often suffer from long training time to reach a good performance, which is a major obstacle for their practical deployment. In this work, we present a systematic approach to accelerate online reinforcement learning for HVAC control by taking full advantage of the knowledge from domain experts in various forms. Specifically, the algorithm stages include learning expert functions from existing abstract physical models and from historical data via offline reinforcement learning, integrating the expert functions with rule-based guidelines, conducting training guided by the integrated expert function and performing policy initialization from distilled expert function. Moreover, to ensure that the learned DRL-based HVAC controller can effectively keep room temperature within the comfortable range for occupants, we design a runtime shielding framework to reduce the temperature violation rate and incorporate the learned controller into it. Experimental results demonstrate up to 8.8X speedup in DRL training from our approach over previous methods, with low temperature violation rate.

Machine learning-based model predictive control for multizone building automation: A case study

In Singapore’s hot and humid climate, air-conditioning and mechanical ventilation (ACMV) systems account for over 60% of commercial building energy consumption, driving efforts to enhance energy efficiency through predictive control strategies such as model predictive control (MPC) to overcome the limitations of conventional reactive building automation systems. This paper presents a multizone MPC system designed to optimize energy consumption and thermal comfort in a commercial building’s ACMV system in Singapore. The system was implemented in a multi-use test building with real occupancy and a deployment area of approximately 850 m2, partitioned into six learning zones, two office spaces, and three open spaces. The ACMV system serving the deployment area consisted of two primary air-handling units and 16 fan coil units, where chilled water was supplied to the cooling coils, and conditioned air was distributed through motorized diffusers. To facilitate predictive control, data-driven thermal prediction models were developed for each zone using a non-linear autoregressive exogenous network with exogenous inputs trained on historical data and disturbances. Thermal comfort optimization was guided by the predictive mean vote, which was targeted at 0, representing thermal neutrality (as per ASHRAE 55 standards), and constrained within a range of −0.5 – 0.5. Performance comparisons demonstrated that the MPC system achieved over 42% energy savings compared to the original thermostat-based control while enhancing thermal comfort. Despite its advantageous control performances, challenges for large-scale deployment remain, including implementation costs, scalability, and model accuracy. Future work can address these challenges by developing comfort models that leverage existing building sensors.

A Review of Informal Economy in China’s Urban-Rural Interfaces (URIs)—Analysis from the Angle of Historical Geography

With accelerated urbanization in China, urban-rural interfaces (URIs) of varied characteristics emerge across the nation. As the frontline and a crucial link between urban and rural areas, URIs have provided an alternate position for urbanization and economic expansion. Among all the economic forms there, informal economy brings both opportunities and threats. From historical geography, this paper explored the historical development of informal economy in URIs, and reviewed previous works on the economy of URIs. Based on historical data, the features and problems of informal economy in URIs are analyzed to provide a basis for healthy development of informal economy in URIs as well as design and practice of relevant policies.

Hybrid graph convolutional LSTM model for spatio-temporal air quality transfer learning

Abstract The short-term air quality forecasting models serve as an early warning system for local agencies, aiding in preparing mitigation strategies against severe pollution episodes. This paper explores the application of Transfer Learning to enhance short-term air quality forecasting model accuracy when labelled data is limited or missing, as often occurs with newly installed monitoring stations or due to sensor malfunctions. These monitoring stations are typically installed in areas of high exposure, like roads or urban/industrial areas, due to recurrent peak episodes or to monitor background pollutant levels generally. Forecasts with greater reliability, even when there is limited historical data available due to the recent installation of the monitoring station for example, are expected to enable the swift implementation of proactive measures to prevent significant pollution episodes from happening. The proposed method leverages knowledge from spatially neighbouring air quality monitoring stations to achieve the multi-modal spatial-temporal transfer learning to the target station, exploring multivariate time series data available from neighbouring monitoring stations. This study employed historical air quality data from spatially adjacent monitoring stations identified in South Wales, UK. The study evaluates the predictive capabilities of four base models and their corresponding transfer learning variants for estimating NO2 and PM10 pollutant levels, which are the most difficult pollutants to meet objectives and limit values in the UK’s air quality strategy. The paper highlights the importance of capturing spatial patterns from different monitoring stations along with temporal trends when it comes to air quality prediction. Our experiments demonstrate that transfer learning models outperform models trained from scratch on air quality multivariate time series prediction problems in a low data environment. The proposed hybrid Graph Convolutional-LSTM model, making use of a novel Granger causality-based adjacency matrix for the new site, has significantly outperformed other baseline models in predicting pollutants, achieving notable improvements in prediction accuracy of approximately 8% for PM10 and 7% for NO2 values, as reflected in the RMSE values. It has also demonstrated the potential for data-efficient approaches in spatial transfer learning by reducing the need for large datasets by incorporating prior causal information.

Multifeature-Driven Multistep Wind Speed Forecasting Using NARXR and Modified VMD Approaches

The global demand for clean and sustainable energy has driven the rapid growth of wind power. However, wind farm managers face the challenge of forecasting wind power for efficient power generation and management. Accurate wind speed forecasting (WSF) is vital for predicting wind power; yet, the variability and intermittency of the wind make forecasting wind speeds difficult. Consequently, WSF remains a challenging area of wind research, driving continuous improvement in the field. This study aimed to enhance the optimization of multifeature-driven short multistep WSF. The primary contributions of this research include the integration of ReliefF feature selection (RFFS), a novel approach to variational mode decomposition for multifeature decomposition (NAMD), and a recursive non-linear autoregressive with exogenous inputs (NARXR) neural network. In particular, RFFS aids in identifying meteorological features that significantly influence wind speed variations, thus ensuring the selection of the most impactful features; NAMD improves the accuracy of neural network training on historical data; and NARXR enhances the overall robustness and stability of the wind speed forecasting results. The experimental results demonstrate that the predictive accuracy of the proposed NAMD–NARXR hybrid model surpasses that of the models used for comparison, as evidenced by the forecasting error and statistical metrics. Integrating the strengths of RFFS, NAMD, and NARXR enhanced the forecasting performance of the proposed NAMD–NARXR model, highlighting its potential suitability for applications requiring multifeature-driven short-term multistep WSF.

Prediction and Spatiotemporal Dynamics of Vegetation Index Based on Deep Learning and Environmental Factors in the Yangtze River Basin

Accurately predicting the vegetation index (VI) of the Yangtze River Basin and analyzing its spatiotemporal trends are essential for assessing vegetation dynamics and providing recommendations for environmental resource management in the region. This study selected the key climate factors most strongly correlated with three vegetation indexes (VI): the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), and kernel Normalized Difference Vegetation Index (kNDVI). Historical VI and climate data (2001–2020) were used to train, validate, and test a CNN-BiLSTM-AM deep learning model, which integrates the strengths of Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and Attention Mechanism (AM). The performance of this model was compared with CNN-BiLSTM, LSTM, and BiLSTM-AM models to validate its superiority in predicting the VI. Finally, climate simulation data under three Shared Socioeconomic Pathway (SSP) scenarios (SSP1-1.9, SSP2-4.5, and SSP5-8.5) were used as inputs to the CNN-BiLSTM-AM model to predict the VI for the next 20 years (2021–2040), aiming to analyze spatiotemporal trends. The results showed the following: (1) Temperature, precipitation, and evapotranspiration had the highest correlation with VI data and were used as inputs to the time series VI model. (2) The CNN-BiLSTM-AM model combined with the EVI achieved the best performance (R2 = 0.981, RMSE = 0.022, MAE = 0.019). (3) Under all three scenarios, the EVI over the next 20 years showed an upward trend compared to the previous 20 years, with the most significant growth observed under SSP5-8.5. Vegetation in the source region and the western part of the upper reaches increased slowly, while significant increases were observed in the eastern part of the upper reaches, middle reaches, lower reaches, and estuary. The analysis of the predicted EVI time series indicates that the vegetation growth conditions in the Yangtze River Basin will continue to improve over the next 20 years.

PRICE SENSITIVITY AND BOOKING PATTERNS: UNDERSTANDING CONSUMER PREFERENCES IN DESTINATION HOTELS

This research explores how factors like price sensitivity, how far in advance bookings are made, seasonal trends, and discount promotions affect the way customers book hotels. By combining survey responses from 275 people with historical booking data, the study examines how strategic pricing can balance maximizing revenue and keeping customers happy. The research shows that price sensitivity is of significant effect on frequency of booking and from where one books. The price-sensitive individuals will book from OTAs and search for discount offers, whereas others who are indifferent about the prices will book from the hotels themselves and remain loyal to specific brands. However, the study also found that practices like dynamic pricing (where prices change based on demand), personalized offers, and loyalty programs can increase both revenue (as measured by RevPAR) and guest satisfaction. It underlines the significance of transparent pricing and being in good health with OTAs, providing hands-on tips for hotel managers to optimize their pricing strategies. Although the research is limited to a smaller number of participants and a geographic locality, it nevertheless provides intriguing insights into how customers act when they reserve hotels in well-known places. It further provides a foundation for more research into how pricing effects can drive customer loyalty and a hotel’s profitability in the long run.