Time Window Length Research Articles

A cooperative team orienteering optimisation model and a customised resolution metaheuristic

Workforce routing optimisation is an essential management task to achieve customer satisfaction and minimise costs in service-providing companies. A typical problem for an energy-saving company (ESCo) is to optimise the provisioning of maintenance services for the contracted buildings through a fleet of heterogeneous maintenance staff. This problem is modelled as a cooperative orienteering problem with time windows, operator qualification, and synchronisation constraints. A novel insertion heuristic is proposed and embedded in an adaptive large neighbourhood search algorithm and it is tested against a state-of-the-art algorithm using real-world data. The comparative study demonstrates the potential of the heuristic and a sensitivity analysis shows its robustness, focusing on time window length variation, and the number of synchronisation requirements. We consider managerial insights supported by results and concerns, e.g., the employment of further technicians to increase the number of served facilities. The proposed model and algorithm apply to similar problems as well.

Measurement of distortion-product otoacoustic emissions at low frequency and effect of contralateral acoustic stimulation on its level

Measurement of distortion-product otoacoustic emissions (DPOAEs) is one of the functional tests for the outer hear cells in the cochlea. Since the sound levels of the DPOAEs are quite low, it is easy to be buried in noise especially in the low frequency range, and frequency analysis and time averaging are required to detect them. In this study, focusing on the frequency stability of two stimulus sounds and a most prominent DPOAE-component, we tried to reduce noise floor and shorten the measurement time by choosing an adequate time window length for averaging the sound pressure waveform in the ear canal and the number of the averaging. As a result, it has become possible to measure DPOAEs at the low frequencies around 300 Hz in a relatively short time. Using this method, the changes in the DPOAE level induced by contralateral acoustic stimulation, which are caused by medial olivocochlear reflex, were measured. Although some exceptions were observed, the DPOAE was suppressed with increasing the sound pressure of the contralateral stimulus, and the degree of suppression was greater for the lower-frequency DPOAEs.

μ-STAR: A novel framework for spatio-temporal M/EEG source imaging optimized by microstates

Source imaging of Electroencephalography (EEG) and Magnetoencephalography (MEG) provides a noninvasive way of monitoring brain activities with high spatial and temporal resolution. In order to address this highly ill-posed problem, conventional source imaging models adopted spatio-temporal constraints that assume spatial stability of the source activities, neglecting the transient characteristics of M/EEG. In this work, a novel source imaging method μ-STAR that includes a microstate analysis and a spatio-temporal Bayesian model was introduced to address this problem. Specifically, the microstate analysis was applied to achieve automatic determination of time window length with quasi-stable source activity pattern for optimal reconstruction of source dynamics. Then a user-specific spatial prior and data-driven temporal basis functions were utilized to characterize the spatio-temporal information of sources within each state. The solution of the source reconstruction was obtained through a computationally efficient algorithm based upon variational Bayesian and convex analysis. The performance of the μ-STAR was first assessed through numerical simulations, where we found that the determination and inclusion of optimal temporal length in the spatio-temporal prior significantly improved the performance of source reconstruction. More importantly, the μ-STAR model achieved robust performance under various settings (i.e., source numbers/areas, SNR levels, and source depth) with fast convergence speed compared with five widely-used benchmark models (including wMNE, STV, SBL, BESTIES, & SI-STBF). Additional validations on real data were then performed on two publicly-available datasets (including block-design face-processing ERP and continuous resting-state EEG). The reconstructed source activities exhibited spatial and temporal neurophysiologically plausible results consistent with previously-revealed neural substrates, thereby further proving the feasibility of the μ-STAR model for source imaging in various applications.

Real-Time EEG-Based Emotion Recognition.

Most studies have demonstrated that EEG can be applied to emotion recognition. In the process of EEG-based emotion recognition, real-time is an important feature. In this paper, the real-time problem of emotion recognition based on EEG is explained and analyzed. Secondly, the short time window length and attention mechanisms are designed on EEG signals to follow emotion change over time. Then, long short-term memory with the additive attention mechanism is used for emotion recognition, due to timely emotion updates, and the model is applied to the SEED and SEED-IV datasets to verify the feasibility of real-time emotion recognition. The results show that the model performs relatively well in terms of real-time performance, with accuracy rates of 85.40% and 74.26% on SEED and SEED-IV, but the accuracy rate has not reached the ideal state due to data labeling and other losses in the pursuit of real-time performance.

Bispectral Index Changes Following Boluses of Commonly Used Intravenous Medications During Volatile Anesthesia Identified From Retrospective Data.

Although patients are commonly monitored for depth of anesthesia, it is unclear to what extent administration of intravenous anesthetic medications may affect calculated bispectral (BIS) index values under general anesthesia. In a retrospective analysis of electronic anesthesia records from an academic medical center, we examined BIS index changes associated with 14 different intravenous medications, as administered in routine practice, during volatile-based anesthesia using a novel screening approach. Discrete-time windows were identified in which only a single drug bolus was administered, and subsequent changes in the BIS index, concentration of volatile anesthetic, and arterial pressure were analyzed. Our primary outcome was change in BIS index, following drug administration. Adjusted 95% confidence intervals were compared to predetermined thresholds for clinical significance. Secondary sensitivity analyses examined the same outcomes, with available data separated according to differences in baseline volatile anesthetic concentrations, doses of the administered medications, and length of time window. The study cohort was comprised of data from 20,170 distinct cases, 54.7% of patients were men, with a median age of 55. In the primary analysis, ketamine at a median dose of 20 mg was associated with a median (confidence limits) increase in BIS index of 3.8 (2.5-5.0). Midazolam (median dose 2 mg) was associated with a median decrease in BIS index of 3.0 (1.5-4.5). Neither of these drug administrations occurred during time periods associated with changes in volatile anesthetic concentration. Analysis for dexmedetomidine was confounded by concomitant decreases in volatile anesthetic concentration. No other medication analyzed, including propofol and common opioids, was associated with a significant change in BIS index. Secondary analyses revealed that similar BIS index changes occurred when midazolam and ketamine were administered at different volatile anesthetic concentrations and different doses, and these changes persisted 11 to 20 minutes postadministration. Modest, but persistent changes in BIS index occurred following doses of ketamine (increase) and midazolam (decrease) during periods of stable volatile anesthetic administration.

Route planning for last-mile deliveries using mobile parcel lockers: A hybrid q-learning network approach

Mobile parcel lockers (MPLs) have been recently proposed by logistics operators as a technology that could help reduce traffic congestion and operational costs in urban freight distribution. Given their ability to relocate throughout their area of deployment, they hold the potential to improve customer accessibility and convenience. In this study, we formulate the Mobile Parcel Locker Problem (MPLP), a special case of the Location-Routing Problem (LRP) which determines the optimal stopover location for MPLs throughout the day and plans corresponding delivery routes. A Hybrid Q-Learning-Network-based Method (HQM) is developed to resolve the computational complexity of the resulting large problem instances while escaping local optima. In addition, the HQM is integrated with global and local search mechanisms to resolve the dilemma of exploration and exploitation faced by classic reinforcement learning (RL) methods. We examine the performance of HQM under different problem sizes (up to 200 nodes) and benchmarked it against the exact approach and Genetic Algorithm (GA). Our results indicate that HQM achieves better optimisation performance with shorter computation time than the exact approach solved by the Gurobi solver in large problem instances. Additionally, the average reward obtained by HQM is 1.96 times greater than GA’s, which demonstrates that HQM has a better optimisation ability. Further, we identify critical factors that contribute to fleet size requirements, travel distances, and service delays. Our findings outline that the efficiency of MPLs is mainly contingent on the length of time windows and the deployment of MPL stopovers. Finally, we highlight managerial implications based on parametric analysis to provide guidance for logistics operators in the context of efficient last-mile distribution operations.

A Multiscale Four-Dimensional Variational Data Assimilation Scheme: A Squall-Line Case Study

Abstract This study presents a multiscale four-dimensional variational data assimilation (MS-4DVar) scheme that aims to assimilate multiscale information from conventional and radar observations. The MS-4DVar scheme separately assimilates conventional and radar data in different outer loop iterations of an incremental 4DVar with varied resolutions in the tangent linear and adjoint models (TLM/ADM) and time window lengths in the 4DVar. The MS-4DVar scheme was evaluated through a series of single observation tests and several cycled assimilation and forecasting experiments for a real squall-line case. Our results indicated that different TLM/ADM resolutions and time window lengths applied to the conventional and radar observations improved the multiscale analysis. In addition, the MS-4DVar scheme was more efficient than the common 4DVar because of the low-resolution TLM/ADM used for conventional data and the shortened time window length for radar data. Verification of the squall-line forecasts suggested that the MS-4DVar scheme improved the hourly accumulated precipitation and radar reflectivity forecast skills and reduced the forecast errors of both large-scale environmental and convective-scale states. Further diagnosis revealed that the improvement of precipitation forecast skill was attributable to the stronger cold pool, deeper saturated water vapor layer, and stronger updraft of the simulated squall-line system, as well as a more favorable convective environment.

Automatic Seizure Detection and Prediction Based on Brain Connectivity Features and a CNNs Meet Transformers Classifier.

(1) Background: Epilepsy is a neurological disorder that causes repeated seizures. Since electroencephalogram (EEG) patterns differ in different states (inter-ictal, pre-ictal, and ictal), a seizure can be detected and predicted by extracting various features. However, the brain connectivity network, a two-dimensional feature, is rarely studied. We aim to investigate its effectiveness for seizure detection and prediction. (2) Methods: Two time-window lengths, five frequency bands, and five connectivity measures were used to extract image-like features, which were fed into a support vector machine for the subject-specific model (SSM) and a convolutional neural networks meet transformers (CMT) classifier for the subject-independent model (SIM) and cross-subject model (CSM). Finally, feature selection and efficiency analyses were conducted. (3) Results: The classification results on the CHB-MIT dataset showed that a long window indicated better performance. The best detection accuracies of SSM, SIM, and CSM were 100.00, 99.98, and 99.27%, respectively. The highest prediction accuracies were 99.72, 99.38, and 86.17%, respectively. In addition, Pearson Correlation Coefficient and Phase Lock Value connectivity in the β and γ bands showed good performance and high efficiency. (4) Conclusions: The proposed brain connectivity features showed good reliability and practical value for automatic seizure detection and prediction, which expects to develop portable real-time monitoring equipment.

A Novel Polarization Estimation Method for Seismic Recordings

Abstract The polarization attributes of seismic recordings are usually used to determine the seismic phase and to design a filter. However, different time window lengths lead to different time-domain polarization estimation results; the time window length is difficult to determine and has no uniform criterion. We propose a time-domain polarization estimation method employing an optimal time window based on the instantaneous frequency of the seismic signals. First, the time–frequency spectrum of the seismic signal is obtained using the continuous wavelet transform, and an optimal time window is constructed using the corresponding instantaneous dominant frequency. Then, a complex polarization analysis algorithm is used to estimate the polarization parameters. Compared with the conventional constant and center frequency time window, the polarization properties estimated using an optimal time window can achieve more accurate seismic phase identification. The picked arrival time error decreases from 82.4 to 32.0 s, about 60%. Furthermore, the corresponding polarization filter can effectively denoise noisy seismic recordings and increase the signal-to-noise ratio (SNR) increased by 0.49–2.65 times for original signals with different SNRs. The cross-correlation coefficient is increased by 0.26 on average, further preservation of signal information.

A dynamically optimized time-window length for SSVEP based hybrid BCI-VR system

Identification accuracy and information transfer rate are two critical performance indicators of the brain-computer interfaces and virtual reality (BCI_VR) hybrid system. A parameter closely related to these two indicators is the time-window length of the data. When the time-window value is too large, it is not conducive to the information transmission rate. Similarly, it affects recognition accuracy when the value is too small. How to set the time-window value reasonably to achieve a balance between recognition accuracy and information transfer rate to ensure the high-performance of the hybrid system is very important. In this paper, a dynamic time-window length optimized mechanism is proposed, which decides whether to change the time-window value of different subjects or trials according to the online performance of the hybrid system. Ten participants took part in the online experiment with an average accuracy of 92.07% and an average information transfer rate of 34.367 bits/min. Compared with the time-window adjustment method based on fixed-step in the existing study, the proposed method has achieved a 10.51% increase in information transfer rate and a 5.66% reduction in average detection time under the same experimental flow.

Mathematical Modeling and Validation of Saturating and Clampable Cascaded Magnetics for Magnetic Energy Harvesting

Electromagnetic energy harvesting extracts energy from magnetic fields and can provide power to sensors, monitoring nodes, cyber-physical systems and control elements without additional battery and external power source and wiring. This article presents a novel ac-driven electromagnetic energy harvester based on periodically saturating, cascaded magnetics, consisting of a clampable magnetic core and an ungapped high permeability core. The high permeability core guarantees the maximum energy extraction, whereas the clampable core enables the nonintrusive installation of the energy harvester for more pervasive applications. This article first builds a comprehensive mathematical model based on this saturating cascaded magnetic structure, considering the reachability of an individual saturation flux density of the two magnetic cores. This model resolves the new challenges introduced by the cascaded magnetics with respect to a traditional single-core case, providing the accurate calculation of the lengths of the relevant time windows for harvesting and the amount of the harvested power. Our mathematical model is verified against simulation and experiment, showing excellent agreement among them with the maximum discrepancy of less than 6%. This article also reveals that the maximum power extraction occurs when the ungapped core operates in its slightly saturated state and that the harvested power increases with a higher primary current as well as a higher line frequency.

A deep learning method for classification of steady-state visual evoked potentials in a brain-computer interface speller

ABSTRACT The main drawback of SSVEP-based BCIs is the lack of a classifier that categorizes SSVEPs with high accuracy and Information Transfer Rate (ITR). Addressing this, we proposed a deep convolutional neural network (CNN) for classifying a 40-class SSVEP. Time windows of length 2 and 3.5 seconds were used for training and testing the model by leave-one-subject-out cross-validation, using nine, three, and single-channel EEG. The proposed model reached 88.5% average accuracy for the nine-channel EEG with the mean and max ITR of 72 and 91.23 bpm, respectively. It outperformed the previous deep learning methods for SSVEP-based BCIs, in terms of accuracy and ITR. In the three-channel experiment the mean accuracy and ITR were 76.02% and 40.1 bpm. In single-channel implementation, O1 channel achieved 77.38 % average accuracy (highest) and the mean ITR was 57.51 bpm. The model showed promising performance to put this technology forward and make it more practical.

Energy consumption prediction using the GRU-MMattention-LightGBM model with features of Prophet decomposition.

The prediction of energy consumption is of great significance to the stability of the regional energy supply. In previous research on energy consumption forecasting, researchers have constantly proposed improved neural network prediction models or improved machine learning models to predict time series data. Combining the well-performing machine learning model and neural network model in energy consumption prediction, we propose a hybrid model architecture of GRU-MMattention-LightGBM with feature selection based on Prophet decomposition. During the prediction process, first, the prophet features are extracted from the original time series. We select the best LightGBM model in the training set and save the best parameters. Then, the Prophet feature is input to GRU-MMattention for training. Finally, MLP is used to learn the final prediction weight between LightGBM and GRU-MMattention. After the prediction weights are learned, the final prediction result is determined. The innovation of this paper lies in that we propose a structure to learn the internal correlation between features based on Prophet feature extraction combined with the gating and attention mechanism. The structure also has the characteristics of a strong anti-noise ability of the LightGBM method, which can reduce the impact of the energy consumption mutation point on the overall prediction effect of the model. In addition, we propose a simple method to select the hyperparameters of the time window length using ACF and PACF diagrams. The MAPE of the GRU-MMattention-LightGBM model is 1.69%, and the relative error is 8.66% less than that of the GRU structure and 2.02% less than that of the LightGBM prediction. Compared with a single method, the prediction accuracy and stability of this hybrid architecture are significantly improved.

A migration method for service function chain based on failure prediction

With the deep application of network technologies in different industries, the demand for network services is becoming more and more diversified. Network operation and maintenance are facing severe challenges, which can be solved by network function virtualization (NFV). NFV technology provides services for users through deploying service function chain (SFC) on servers and substrate links. However, once a server fails, the services it hosts will be affected or even interrupted. Therefore, it is very important to predict failures and migrate SFCs in advance according to predicted results. In this paper, we propose a failure prediction method based on the improved long short-term memory neural network (PMILSTM), which employs LSTM to predict failures. To further improve prediction accuracy, the simulated annealing particle swarm optimization algorithm is adopted to optimize the number of neurons in each long short-term memory layer and the time window length. A server may host multiple SFCs. When a server fails, in order to reduce the impact on users, it is necessary to simultaneously migrate all the SFCs hosted by the server. We propose an improved sparrow search algorithm (ISSA) and a service function chain migration method based on the ISSA (MMISSA). The ISSA introduces tent chaos, opposition-based learning, dynamic weight factor, and mutation operation into SSA to achieve the better global optimization ability. The MMISSA method adopts the ISSA to migrate SFCs so that it can simultaneously search for migration servers for all the virtual network functions deployed on a soon-to-fail server. The better global optimization ability of the ISSA enables better migration results. Therefore, the migration success ratio is improved. Moreover, the fitness function simultaneously considers the average migration cost and migration time. As a result, the MMISSA method effectively reduces the migration cost and migration time.

An Improved Method to Enhance SNR of Non-Stationary Signal Based on Nonuniform Windows Adaptive Modulation for Measurement

It is very important for non-stationary signal processing, signal measurement, and signal enhancement to improve signal-to-noise ratio (SNR) and suppress noise. For complex non-stationary signals measurement, there is still a lack of effective methods to improve the signal-to-noise ratio without damaging original signal. Therefore, it is vital to develop signal processing method to improve SNR of non-stationary signal in many actual industrial measurement. This paper proposes a new method to enhance the SNR for non-stationary signal processing. First, a self-adapting mathematic model is presented to describe the short-time impulse with board spectrum, judge the non-stationary part of the signal, and determine the length of time window based on itself. Then, for the non-stationary signals in this short time window, the improved self-adaptive modulation is used to remove the non-stationary components and retain the stationary components. Third, the stationary component of the short-time window and the normal part of the original signal are connected via cubic spline interpolation algorithm. Finally, this paper analyzes the range of SNR improvement and measurement accuracy of the new method. Based on the results of experiment, the proposed method can effectively improve the signal-to-noise ratio of non-stationary signals and suppress noise, which is of great significance for measurement.

Data-Driven Surface Classification for Differential Drive Autonomous Guided Vehicles

As a result of the digital transformation, the degree of automation in production environments is constantly increasing. The automation of logistics processes offers great potential for optimizing material flows within production. However, there are strong requirements regarding the reliability of automated guided vehicles (AGVs). This paper investigates if it is possible to identify the surface of an AGV based on control and measurement parameters compared to target parameters. The vehicle concept is based on differential drive and is used for the autonomous transport of goods within and between production halls. The information about the surface can be used to ensure a better and safer interaction with the environment. The creation of a dataset consisting of a low and a high friction surface is described. Furthermore, the pre-processing of the data which covers the time window length, resampling and data scaling is described. Finally, different algorithms for multivariable time series classification are benchmarked on the created dataset. Experiments show that the state of the art algorithm HIVE-COTE 2.0 provides the highest accuracy on the test dataset with 97.5%. Finally, a validation is performed by reviewing sequences with low confidence levels.

Weighted Score Fusion Based LSTM Model for High-Speed Railway Propagation Scenario Identification

Propagation scenario identification is of vital significance for boosting the performance of future smart high-speed railway (HSR) communication networks. This paper investigates the HSR propagation scenario identification model, based on deep learning networks and feature fusion methods. With the assistance of railway long-term evolution (LTE) networks, we collected the channel impulse responses in four typical HSR scenarios including unobstructed viaduct, obstructed viaduct, station and suburban. Four channel characteristics involving power delay profile, root mean square (RMS) delay spread, RMS angular spread and Ricean K-factor form the datasets used for model training and testing. Then, a novel propagation scenario identification model is proposed by merging a weighted score based feature fusion method into the long short-term memory (LSTM) neural network. The hyper-parameters of the proposed model such as time window length and numbers of hidden units and layers are determined by autocorrelation analysis and cross-validation. Finally, the model performance is evaluated by focusing on the impact of feature selection, comparison of different feature fusion methods, and computational complexity. The evaluation results show that the proposed model has high identification accuracy but acceptable computational complexity.

Generalisable machine learning models trained on heart rate variability data to predict mental fatigue

A prolonged period of cognitive performance often leads to mental fatigue, a psychobiological state that increases the risk of injury and accidents. Previous studies have trained machine learning algorithms on Heart Rate Variability (HRV) data to detect fatigue in order to prevent its consequences. However, the results of these studies cannot be generalised because of various methodological issues including the use of only one type of cognitive task to induce fatigue which makes any predictions task-specific. In this study, we combined the datasets of three experiments each of which applied different cognitive tasks for fatigue induction and trained algorithms that detect fatigue and predict its severity. We also tested different time window lengths and compared algorithms trained on resting and task related data. We found that classification performance was best when the support vector classifier was trained on task related HRV calculated for a 5-min time window (AUC = 0.843, accuracy = 0.761). For the prediction of fatigue severity, CatBoost regression showed the best performance when trained on 3-min HRV data and self-reported measures (R2 = 0.248, RMSE = 17.058). These results indicate that both the detection and prediction of fatigue based on HRV are effective when machine learning models are trained on heterogeneous, multi-task datasets.

A Novel Deep Learning Method Based on an Overlapping Time Window Strategy for Brain-Computer Interface-Based Stroke Rehabilitation.

Globally, stroke is a leading cause of death and disability. The classification of motor intentions using brain activity is an important task in the rehabilitation of stroke patients using brain-computer interfaces (BCIs). This paper presents a new method for model training in EEG-based BCI rehabilitation by using overlapping time windows. For this aim, three different models, a convolutional neural network (CNN), graph isomorphism network (GIN), and long short-term memory (LSTM), are used for performing the classification task of motor attempt (MA). We conducted several experiments with different time window lengths, and the results showed that the deep learning approach based on overlapping time windows achieved improvements in classification accuracy, with the LSTM combined vote-counting strategy (VS) having achieved the highest average classification accuracy of 90.3% when the window size was 70. The results verified that the overlapping time window strategy is useful for increasing the efficiency of BCI rehabilitation.

Drayage routing with heterogeneous fleet, compatibility constraints, and truck load configurations

This paper addresses drayage routing problems with heterogeneous fleets, compatibility constraints, and truck load configurations. In these problems, containers can be of any size and cargo category. In addition, compatibility and load configuration constraints define which and how many containers can be transported by each truck. We propose a state transition logic to model these constraints. Based on this logic, we develop two mixed-integer programming models for this family of problems. The first model is a compact formulation that can be input into a black-box solver. The second model combines partial routes in a space–time network and is solved with a tailored branch-and-cut approach. To analyze the efficiency of the proposed models, we conduct extensive computational tests on instances with different numbers of requests, geographical distributions of locations, time-window lengths, and fleet compositions. Moreover, we discuss how our modeling approach can assist decision-making in three different drayage routing applications.