Window Method Research Articles

A Hybrid CNN-LSTM Model for Predicting Energy Consumption and Production Across Multiple Energy Sources

This study utilizes a robust dataset provided by Energy Exchange Istanbul (EXIST), a leading authority in energy data, which contains hourly energy consumption and production data from 01/01/2018 to 31/12/2023 across Turkey. Various machine learning and deep learning methods such as linear regression (LR), random forest (RF), support vector machines (SVR), convolutional neural networks (CNN), long short-term memory networks (LSTM), and the proposed hybrid CNN-LSTM model are applied to predict energy consumption and production more accurately. This study transforms time series data into a regression problem using the sliding window method. The experimental results show that the hybrid CNN-LSTM model outperforms the other models in forecasting total energy consumption and natural gas, hydro dam, lignite, hydro river, wind, and fuel oil production. The CNN-LSTM model achieved the lowest RMSE and MAE values and the highest R² scores. The success of the proposed hybrid approach is due to the combination of CNN's ability to identify local patterns and LSTM's ability to learn long-term dependencies. This study demonstrates the hybrid CNN-LSTM model's effectiveness in accurately forecasting energy consumption and production. It makes an important contribution to more efficient use of energy resources.

Analysis on Innovation Efficiency of High-tech Industries in the Three Coastal Economic Zones in Eastern China

The high-tech industry is an important force in promoting the upgrading of traditional industries and the transformation of economic growth mode. Its technological innovation directly affects the innovation efficiency and economic development level of the region. The three major economic zones of Bohai Rim, Yangtze River Delta, and Pan Pearl River Delta are the most active areas for China's economic development and independent innovation, with a level of technological development far exceeding the average level of China, becoming the three growth poles driving China's economic growth. This article first uses the three-stage DEA Windows method to measure the innovation efficiency of high-tech industries in China's Yangtze River Delta, Pan Pearl River Delta, and Bohai Rim economic zones from 2016 to 2022, and considers the dynamic evolution characteristics of innovation efficiency in each region over time. Secondly, the impact of environmental variables on the redundancy of input variables in high-tech industries in the three major economic zones was studied. Finally, the differences of innovation efficiency values among the three major economic zones were examined. Research has found that after controlling for environmental factors and random errors, the overall innovation efficiency values of the three major regions have not reached the forefront of production, and have shown an increasing trend year by year. Low scale efficiency is the main factor affecting the R&D efficiency of the three regions, and further coordinated planning is urgently needed.

Tightly Coupled SLAM Algorithm Based on Similarity Detection Using LiDAR-IMU Sensor Fusion for Autonomous Navigation

In recent years, the rise of unmanned technology has made Simultaneous Localization and Mapping (SLAM) algorithms a focal point of research in the field of robotics. SLAM algorithms are primarily categorized into visual SLAM and laser SLAM, based on the type of external sensors employed. Laser SLAM algorithms have become essential in robotics and autonomous driving due to their insensitivity to lighting conditions, precise distance measurements, and ease of generating navigation maps. Throughout the development of SLAM technology, numerous effective algorithms have been introduced. However, existing algorithms still encounter challenges, such as localization errors and suboptimal utilization of sensor data. To address these issues, this paper proposes a tightly coupled SLAM algorithm based on similarity detection. The algorithm integrates Inertial Measurement Unit (IMU) and LiDAR odometry modules, employs a tightly coupled processing approach for sensor data, and utilizes curvature feature optimization extraction methods to enhance the accuracy and robustness of inter-frame matching. Additionally, the algorithm incorporates a local keyframe sliding window method and introduces a similarity detection mechanism, which reduces the real-time computational load and improves efficiency. Experimental results demonstrate that the algorithm achieves superior performance, with reduced positioning errors and enhanced global consistency, in tests conducted on the KITTI dataset. The accuracy of the real trajectory data compared to the ground truth is evaluated using metrics such as ATE (absolute trajectory error) and RMSE (root mean square error).

Footprint of soil erosion effects on pedodiversity at different hierarchical levels: A study across China's water erosion-prone areas.

Pedodiversity conservation is critical for the sustainable use of soil resources and the regulation of ecological security. To explore the relationship between pedodiversity and soil erosion over a prolonged history. In this paper, the response of the regional measurement factor for erosion (RMFE) to pedodiversity at different hierarchical levels was investigated using the optimal window method and structural equation modeling on the basis of water erosion-prone zones. The results suggest that variations in the factors used for soil classification at different hierarchical levels was the main cause of spatial heterogeneity in pedodiversity. Significant impacts of the RMFE on pedodiversity occurred mainly in the Middle reaches of Yangtze River low mountains, hills, plains and basins sub-region (IIC), the Southern China low mountains, hills and plains sub-region (IID) and the Southwestern Yunnan middle and high mountains sub-region (VE) at the Group, Subgroup and Genus levels. Notably, at the Subgroup and Genus levels, the impacts of soil erosion begin to be significant in the Wanda Mt and Sanjiang Plain low mountains and hills sub-region (IA), the Zhejiang and Fujian middle and low mountains, hills and valleys sub-region (IIA), and Taiwan plains and mountains of sub-region (IIE). The regional distribution revealed that pedodiversity in the southeast was more sensitive and positively correlated with the RMFE, with parent material, temperature and anthropogenic activities being the main influences. However, the negatively correlated effects of RMFE on pedodiversity were concentrated in the northeast, where the roles of parent material and vegetation were more critical. The findings of this study are of great practical value and scientific importance for the protection of soil ecological functions and the improvement of regional ecosystem quality and stability.

Adaptive Route Memory Sequences for Insect-Inspired Visual Route Navigation

Visual navigation is a key capability for robots and animals. Inspired by the navigational prowess of social insects, a family of insect-inspired route navigation algorithms—familiarity-based algorithms—have been developed that use stored panoramic images collected during a training route to subsequently derive directional information during route recapitulation. However, unlike the ants that inspire them, these algorithms ignore the sequence in which the training images are acquired so that all temporal information/correlation is lost. In this paper, the benefits of incorporating sequence information in familiarity-based algorithms are tested. To do this, instead of comparing a test view to all the training route images, a window of memories is used to restrict the number of comparisons that need to be made. As ants are able to visually navigate when odometric information is removed, the window position is updated via visual matching information only and not odometry. The performance of an algorithm without sequence information is compared to the performance of window methods with different fixed lengths as well as a method that adapts the window size dynamically. All algorithms were benchmarked on a simulation of an environment used for ant navigation experiments and showed that sequence information can boost performance and reduce computation. A detailed analysis of successes and failures highlights the interaction between the length of the route memory sequence and environment type and shows the benefits of an adaptive method.

Early-stage identification of indoor leakage sources in factories

Identifying the leakage source in industrial factories as soon as an incident happens is crucial for controlling the leak in time and safeguarding lives and property. This study developed a rapid source identification method for factories, aiming to identify the characteristics of leakage sources at the early stage of the leakage event. The approach integrates pollutant diffusion theory, sliding window method, correlation coefficient method, and data fitting method. Based on an experimental cabin, 162 verification conditions were established, encompassing constant sources as well as two time-varying sources: linear and non-linear ones. Additionally, various aspects of the method were evaluated. It was found that considering the error and noise in sensor monitoring data, the method exhibits identification accuracies of 83.3%, 79.6%, and 74.1% for constant sources, linear sources, and non-linear sources, respectively. In the case of non-linear sources, the coefficient “b” must be taken into account when generating the dimensionless concentration vector. A sliding window containing 50 to 60 valid data points can achieve the highest source identification accuracy. This research can provide help in quickly locating leakage sources in factories, help with the timely control of leaks, and protect workers’ health and property safety.

Deep learning insights into distinct patterns of polygenic adaptation across human populations.

Response to spatiotemporal variation in selection gradients resulted in signatures of polygenic adaptation in human genomes. We introduce RAISING, a two-stage deep learning framework that optimizes neural network architecture through hyperparameter tuning before performing feature selection and prediction tasks. We tested RAISING on published and newly designed simulations that incorporate the complex interplay between demographic history and selection gradients. RAISING outperformed Phylogenetic Generalized Least Squares (PGLS), ridge regression and DeepGenomeScan, with significantly higher true positive rates (TPR) in detecting genetic adaptation. It reduced computational time by 60-fold and increased TPR by up to 28% compared to DeepGenomeScan on published data. In more complex demographic simulations, RAISING showed lower false discoveries and significantly higher TPR, up to 17-fold, compared to other methods. RAISING demonstrated robustness with least sensitivity to demographic history, selection gradient and their interactions. We developed a sliding window method for genome-wide implementation of RAISING to overcome the computational challenges of high-dimensional genomic data. Applied to African, European, South Asian and East Asian populations, we identified multiple genomic regions undergoing polygenic selection. Notably, ∼70% of the regions identified in Africans are unique, with broad patterns distinguishing them from non-Africans, corroborating the Out of Africa dispersal model.

Altered Dynamic Brain Functional Network Connectivity Related to Visual Network in Spinal Cord Injury.

Visual feedback training (VFT) plays an important role in the motor rehabilitation of patients with spinal cord injury (SCI). However, the neural mechanisms are unclear. We aimed to investigate the changes in dynamic functional network connectivity (FNC) related to visual networks (VN) in patients with SCI and to reveal the neural mechanism of VFT promoting motor function rehabilitation. Dynamic FNC and the sliding window method were performed in 18 complete SCI (CSCI), 16 patients with incomplete SCI (ISCI), and 42 healthy controls (HCs). Then, k-mean clustering was implemented to identify discrete FNC states, and temporal properties were computed. The correlations between these dynamic features and neurological parameters in all patients with SCI were calculated. The majority of aberrant FNC was manifested between VN and executive control network (ECN). In addition, compared with HCs, temporal metrics derived from state transition vectors were decreased in patients with CSCI including the mean dwell time and the fraction of time spent in state 3. Furthermore, the disrupted FNC between salience network and ECN in state 2 and the number of transitions were all positively correlated with neurological scores in patients with SCI. Our findings indicated that SCI could result in VN-related FNC alterations, revealing the possible mechanism for VFT in rehabilitation of patients with SCI and increasing the training efficacy and promoting rehabilitation for SCI.

Medium and long-term regional water demand prediction using Harris hawks optimisation–backpropagation neural network model

Precise water demand prediction is essential for the efficient allocation and rational utilisation of regional water resources. This study addressed the challenge associated with medium and long-term water demand prediction by introducing a novel coupled model, HHO-BPNN (Harris Hawks Optimisation–Backpropagation Neural Network). Principal component analysis was employed to reduce the dimensionality of potential water demand factors. The performance of the forecasting models was compared through mean square error (MSE), mean absolute percentage error (MAPE), mean absolute error (MAE), and coefficient of determination (R2). The findings indicated that the HHO-BPNN outperformed traditional methods, such as BPNN, support vector machines, and grey prediction model. The study utilised the sliding window method to predict water demand for the next 1, 3, and 5 years for five prefecture-level cities in northern Jiangsu Province, China. High prediction accuracy was achieved across various categories of water demand (agricultural, industrial, domestic, and ecological), with the overall accuracy being impressive at 97%. Additionally, the forecasts aligned well with local developmental plans, suggesting practical applicability for urban planning. This study elucidates the key drivers impacting water demand, providing an effective tool for regional water demand forecasting, facilitating efficient and precise water management and decision-making in the future.

Large-scale gene expression data clustering through incremental ensemble approach

Abstract DNA microarray technology monitors gene activity in real-time in living organisms. It creates a large amount of data that helps scientists learn about how genes work. Clustering this data helps understand gene interactions and uncover important biological processes. However, the traditional clustering techniques have difficulties due to the enormous dimensionality of gene expression data and the intricacy of biological networks. Although ensemble clustering is a viable strategy, such high-dimensional data may not lend itself well to traditional approaches. This study introduces a novel technique for gene expression data clustering called incremental ensemble clustering for gene expression data (IECG). There are two steps in the IECG. A technique for grouping gene expression data into windows is presented in the first step, producing a tree of clusters. This procedure is carried out again for succeeding windows that have distinct feature sets. The base clusterings of two consecutive windows are ensembled using a new goal function to form a new clustering solution. By repeating this step-by-step method for further windows, reliable patterns that are beneficial for medical applications can be extracted. The results from both biological and non-biological data demonstrate that the proposed algorithm outperformed the state-of-the-art algorithms. Additionally, the running time of the proposed algorithm has been examined.

Landslide Displacement Prediction Stacking Deep Learning Algorithms: A Case Study of Shengjibao Landslide in the Three Gorges Reservoir Area of China

Computational models enable accurate, timely prediction of landslides based on the monitoring data on-site as the development of artificial intelligence technology. The most existing prediction methods focus on finding a single prediction algorithm with excellent performance or an integrated and efficient hyperparameter optimization algorithm with a highly accurate regression prediction algorithm. In order to break through the limitation of generalization of prediction models, this paper proposes an ensemble model that combines deep learning algorithms, with a stacking framework optimized with the sliding window method. Multiple deep learning algorithms are set as the first layer of the stacking framework, which is optimized with the sliding window method to avoid confusion in the time order of datasets based on time series analysis. The Shengjibao landslide in the Three Gorges Reservoir is used as a case study. First, the cumulative displacement is decomposed into a trend and a periodic term using a moving average method. A single-factor and a multi-factor superposition model based on multiple deep learning algorithms are used to predict the trend and periodic term of the displacement, respectively. Finally, the predicted values of the trend and periodic terms are added to obtain the total predicted landslide displacement. For monitoring point ZK2-3, the values of RMSE and MAPE of the total displacement prediction with the stacking model are 15.93 mm and 0.54%, and the values of RMSE and MAPE of the best-performing individual deep learning model are 20.00 mm and 0.64%. The results show that the stacking model outperforms other models by combining the advantages of each individual deep learning algorithm. This study provides a framework for integrating landslide displacement prediction models. It can serve as a reference for the geological disaster prediction and the establishment of an early warning system in the Three Gorges Reservoir Area.

Флуктуации корреляционных характеристик в шумовой системе радиосвязи

Ultra-wideband noise communication system using the transmitted reference technique with the time diversity is proposed for a covert data transmission through additive white Gaussian noise channel. Spectrum modulation of transmitted signals is performed as a result from linear superposition between the noise references and informative noise carriers delayed at the time diversity significantly exceeding the coherent time. The delayed noise carriers are multiplied by antipodal symbols at the same rate of binary data stream. Spectral power density of result noise signals is modulated by antipodal harmonic functions with the period in inverse proportion to diversity time delay. The time delay in the correlation receiver corresponds to the diversity time delay of informative noise signals. The correlation estimation problem appears in the case of data transmitting on the base of continuous noise carriers. Fluctuation analysis of correlation estimations with nonstationary trend at the data rate is performed. The intersystem jamming occurring in digital noise communications increase the correlation fluctuations at the receiver output and initiate asymptotic limitation of correlation performances without thermal noise in a wireless channel. Nonstationary trends of output correlation estimations become little if the informative time delay significantly exceeds the coherent times as noise carriers as additive white Gaussian noise. The forming of digital noise carriers is produced by the time window method. Simulation of noise communications shows that utilizing continuously noise carriers with time windows permits to decrease randomly fluctuations of correlation performances in the case when the product of noise signal bandwidth by bit duration exceeds one hundred units.

Flight Trajectory Prediction Based on LSTM

Track prediction is a key technology to avoid potential navigation dangers and provide reliable scheduling. Due to the insufficient processing ability of traditional neural networks for long sequence data such as track data, the prediction error of aircraft trajectories is relatively large. In this paper, the Long Short-Term Memory network (LSTM) is used for 4D track prediction, and the excessive dependence between adjacent data is reduced through the sliding window method. The ADS-B track data is standardized, outliers are processed using the 3σ Principle, and the smoothness of the time series is ensured through cubic spline interpolation. Four-dimensional track prediction and two-dimensional prediction of each feature of Height, Speed, Speed, Longitude, and Latitude are carried out for the standard data. Performance is judged by Root Mean Squared Error (RMSE) and the average prediction error of each feature. Through comparison, the track prediction effect of the LSTM neural network is better than the existing BP neural network prediction method.

Motor delay image recognition based on deep learning and human skeleton model

Children with developmental delays often exhibit gross motor delay during their early childhood. Identifying such delay typically requires standardized assessments, but these assessments are susceptible to subjective interpretation. To enhance objectivity and reliability in these assessments, this study proposes a novel method utilizing an AI model for identifying gross motor delay in children. The proposed method divides the assessment of gross motor skills into two components: static balance and dynamic balance. First, the Yolo target detection model and the Mediapipe human posture detection model are employed for preprocessing to determine skeletal joints and body positioning information. Subsequently, dimensionality reduction techniques are applied to extract key features. A sliding window method is then used to extract action features identifying static balance features of the human body (e.g., standing on one foot, standing on the left foot) and dynamic balance features (e.g., lifting the heels while walking, jumping on a mat). The machine learning classifier and LSTM-CNN are then used to categorize the static and dynamic balance feature data. Experimental results demonstrate that the proposed method achieved accuracy scores of 80 % and 87 % for static and dynamic balancing skills, respectively.

Development of a locating method for optical windows in shock tube

A method was proposed in the present study for locating single and/or multiple optical windows in shock tubes. It involved establishing a diagnostic time calculation model by transforming challenging conventional conditions into equivalent special scenarios. The method strategically balanced experimental pressure and optical window locations. Pressure-time history experiments were conducted in a shock tube to verify the reliability of the proposed locating method. An example showcased the versatility of the locating method for determining the positions of single or multiple optical windows. Lastly, the proposed locating method provided evaluation for optimizing several existing shock tube setups.

Improving the estimation of the Boyce index using statistical smoothing methods for evaluating species distribution models with presence‐only data

Species distribution models (SDMs) underpin a wide range of decisions concerning biodiversity. Although SDMs can be built using presence‐only data, rigorous evaluation of these models remains challenging. One evaluation method is the Boyce index (BI), which uses the relative frequencies between presence sites and background sites within a series of bins or moving windows spanning the entire range of predicted values from the SDM. Obtaining accurate estimates of the BI using these methods relies upon having a large number of presences, which is often not feasible, particularly for rare or restricted species that are often the focus of modelling. Wider application of the BI requires a method that can accurately and reliably estimate the BI using small numbers of presence records. In this study, we investigated the effectiveness of five statistical smoothing methods (i.e. thin plate regression splines, cubic regression splines, B‐splines, P‐splines and adaptive smoothers) and the mean of these five methods (denoted as ‘mean') to estimate the BI. We simulated 600 species with varying prevalence and built distribution models using random forest and Maxent methods. For training data, we used two levels for the number of presences (NPtrain: 20 and 500), along with 2 × NPtrain and 10000 random points (i.e. random background sites) for each modelling method. We used the number of presences at four levels (NPbi: 1000, 200, 50 and 10) to investigate its effect, together with 5000 random points to calculate the BI. Our results indicate that the BI estimates from the binning and moving window methods are severely affected by the decrease of NPbi, but all the estimates of the BI from smoothing‐based methods were almost always unbiased for realistic situations. Hence, we recommend these methods for estimating the BI for evaluating SDMs when verified absence data are unavailable.

Identifying crucial financial markets in the flows of cross-border capital – evidence from China's financial risk network

With the increasing openness of China's financial markets, it is important to address cross-border capital risks. This paper first calculates the stress indicators of financial markets by 24 variables, and then utilizes the Diebold-Yilmaz connectedness approach to examine the spillover effects among the volatility of cross-border capital and the stress indicators of various financial markets. We show both the real estate and stock market are crucial for cross-border capital flow. Using the rolling window method, we find significant time-varying spillovers between cross-border capital and financial markets, which peak during the periods with significant events such as the global financial crisis, the COVID-19 epidemic, and the shift in currency regime. This paper further applies the Markov-switching autoregressive model to identify three different states for the synthetic financial stress. After re-analyzing the subsample data, we observe that stock and real estate markets play significant roles in the low-stress state, foreign exchange and real estate markets in the medium-stress state, and stock and money markets in the high-stress state.

Simple and efficient step detection algorithm for foot-mounted IMU

Abstract This paper presents a concise, efficient, and adaptive step detection algorithm based on foot-mounted inertial measurement unit sensors. The proposed method maps the temporal values of pedestrian motion and gait diversity into two variables: the distance between peaks and valleys, and the slope. Compared to traditional sliding window methods, this approach amplifies the differences between normal and abnormal steps, allowing it to adapt to various indoor activities such as fast walking, slow walking, running, jogging, standing still, and turning. By incorporating adaptive factors, it addresses the challenge of detecting steps while going up and down stairs. The proposed algorithm overcomes the limitations of traditional adaptive threshold methods that require different temporal and peak thresholds for various gait conditions. By utilizing the significant differences in distance and slope, it effectively resolves the issue of detecting steps during stationary periods. Unlike neural network-based gait classifiers, this algorithm does not need to account for multiple gait conditions, thereby simplifying the training process. Experimental results demonstrate that the algorithm achieves an average accuracy of over 99% under mixed indoor walking conditions and over 98% accuracy in long-term outdoor walking conditions.

An accurate state-of-charge estimation of lithium-ion batteries based on improved particle swarm optimization-adaptive square root cubature kalman filter

The state of charge (SOC) of lithium-ion batteries (LIBs) is regarded as the fundamental parameter of the battery management system (BMS). In this paper, a parameter optimization method for mobile estimation windows based on particle swarm optimization-adaptive square root cubature Kalman filter (PSO-ASRCKF) is established to improve the SOC estimation ability and accuracy of LIBs. The filtering algorithm parameters are optimized to achieve high-precision SOC estimation. An improved ASRCKF with the PSO algorithm to optimize the moving estimation window is constructed to obtain the best adaptive window value. Different temperatures and initial SOC values are used to verify the proposed method under dynamic stress test (DST) and other conditions. The results show that the relative error is mainly distributed within 0.5 % when the SOC is stable. In addition, robustness and adaptability are verified with the root mean square error (RMSE) and the mean absolute error (MAE) values of 0.0019 and 0.0017, respectively, under the DST working condition. The experimental results show that the proposed method can achieve accurate SOC estimation under different temperatures, operating conditions, and initial SOC values.

On the use of Change History Data to Enhance Class Change-Proneness Prediction Models

As software evolves, new artifacts are created, modified, or removed. One of these main artifacts generated in the development of object-oriented software is the class. Classes have a very dynamic life cycle that can result in additional costs to the project. One way to mitigate this is to detect, in the early stages of the development, classes that are prone to change. Some approaches in the literature adopt Machine Learning (ML) algorithms to predict the change-proneness of a class. However, most of these approaches do not consider the temporal dependency between training instances, i.e., they consider that the instances are independent. To overcome such a limitation, this study presents an approach for predicting change-proneness based on the class change history. The approach adopts the sliding window method and is evaluated to obtain six kinds of models, which are derived by using, as predictors, different sets of metrics: structural, evolutionary, and smell-based. The evaluation uses five systems, four ML algorithms, and also explores some resample techniques to deal with imbalanced data. Regardless of the kind of model analyzed and the algorithm used, our approach overcomes the traditional one in 378 (~80) cases, out of 420, considering all systems, kinds of models, indicators, and algorithms. Moreover, the results show that our approach presents the best performance when the set of evolutionary metrics is used as predictors. There is no improvement when smell-based metrics are added. The Random Forest algorithm with the resampling technique ADA reaches the best performance among the ML algorithms evaluated.