Temporal Weighting Research Articles

Spatiotemporal effects of renewable energy technology innovation on industrial cleaner production: A geographically temporally weighted analysis

Industrial pollution closely related to human health is a growing global problem. Most studies have examined whether technological innovation contributes to increased environmental performance, without detailed investigation of the effects of renewable energy technology innovation (RETI) on industrial pollution. Using the Geographically Temporally Weighted Regression (GTWR), this study explores how RETI affects industrial pollution from a spatial heterogeneity perspective. The results show that, first, industrial pollution in one area was related to the industrial pollution in adjacent areas. Second, RETI would contribute to cleaner industrial production. Third, the influence of RETI on industrial pollutant varied from province to province in China. Based on these results, some suggestions for controlling industrial pollution were put forward.

Multiscale geographically and temporally weighted regression with a unilateral temporal weighting scheme and its application in the analysis of spatiotemporal characteristics of house prices in Beijing

ABSTRACT Geographically and temporally weighted regression (GTWR) has been demonstrated as an effective tool for exploring spatiotemporal data under spatial and temporal heterogeneity. Exploiting the advantages of the two most popular GTWR methods, we propose an alternative GTWR with a good balance between complexity and interpretability via a unilateral temporal weighting scheme called unilateral GTWR (UGTWR). When compared to the other two popular GTWR methods, the simulation experiment shows that UGTWR has comparable estimation accuracy and model fit, but it is more efficient. Furthermore, we propose its multiscale extension, coined multiscale UGTWR (MUGTWR), to characterize the spatiotemporal dynamic regression relationships at multiple scales. The proposed MUGTWR was applied to the analysis of house prices in the period of 2014–2018 in Beijing as a case study. Our analysis reveals that MUGTWR can effectively capture different levels of spatiotemporal heterogeneity in selected factors affecting house prices at different scales. Therefore, this study is useful for the formulation of housing policy in which the spatiotemporal dynamics of house prices with respect to specific factors can be considered.

Identification of coexisting dynamics in boundary layer flows through proper orthogonal decomposition with weighting matrices

A different version of the classic proper orthogonal decomposition (POD) procedure introducing spatial and temporal weighting matrices is proposed. Furthermore, a newly defined non-Euclidean (NE) inner product that retain similarities with the POD is introduced in the paper. The aim is to emphasize fluctuation events localized in spatio-temporal regions with low kinetic energy magnitude, which are not highlighted by the classic POD. The different variants proposed in this work are applied to numerical and experimental data, highlighting analogies and differences with respect to the classic and other normalized variants of POD available in the literature. The numerical test case provides a noise-free environment of the strongly organized vortex shedding behind a cylinder. Conversely, experimental data describing transitional boundary layers are used to test the capability of the procedures in strongly not uniform flows. By-pass and separated flow transition processes developing with high free-stream disturbances have been considered. In both cases streaky structures are expected to interact with other vortical structures (i.e. free-stream vortices in the by-pass case and Kelvin–Helmholtz rolls in the separated type) that carry a significant different amount of energy. Modes obtained by the non-Euclidean POD (NE-POD) procedure (where weighted projections are considered) are shown to better extract low energy events sparse in time and space with respect to modes extracted by other variants. Moreover, NE-POD modes are further decomposed as a combination of Fourier transforms of the related temporal coefficients and the normalized data ensemble to isolate the frequency content of each mode.

Modeling human activity dynamics: an object-class oriented space\u2013time composite model based on social media and urban infrastructure data

Modeling human activity dynamics is important for many application domains. However, there are problems inherent in modeling population information, since the number of people inside a given area can change dynamically over time. Here, a cyberGIS-enabled spatiotemporal population model is developed by combining Twitter data with urban infrastructure registry data to estimate human activity dynamics. This model is an object-class oriented space–time composite model, in which real-world phenomena are modeled as spatiotemporal objects, and people can move from one object to another over time. In this research, all spatiotemporal objects are aggregated into 14 spatiotemporal object classes, and all objects in a given space at different times can be projected down to a spatial plane to generate a common spatiotemporal map. A temporal weight matrix is derived from Twitter activity curves for each spatiotemporal object class and represents population dynamics for each object class at different hours of a day. Finally, model performance is evaluated by using a comparison to registered census data. This spatiotemporal human activity dynamics model was developed in a cyberGIS computing environment, which enables computational and data intensive problem solving. The results of this research can be used to support spatial decision-making in various application areas such as disaster management where population dynamics plays an important role.

Research on the Key Issues of Big Data Quality Management, Evaluation, and Testing for Automotive Application Scenarios

This paper provides an in-depth analysis and discussion of the key issues of quality management, evaluation, and detection contained in big data for automotive application scenarios. A generalized big data quality management model and programming framework are proposed, and a series of data quality detection and repair interfaces are built to express the processing semantics of various data quality issues. Through this data quality management model and detection and repair interfaces, users can quickly build custom data quality detection and repair tasks for different data quality requirements. To improve the operational efficiency of complex data quality management algorithms in large-scale data scenarios, corresponding parallelization algorithms are studied and implemented for detection and repair algorithms with long computation time, including priority-based multiconditional function-dependent detection and repair algorithms, entity detection, and extraction algorithms based on semantic information and chunking techniques, and plain Bayesian-based missing value filling algorithms, and this paper proposes a data validity evaluation algorithm and enhances the validity of the original data in practical applications by adding temporal weights, and finally it passed the experimental validation. Through the comprehensive detection process of data importance, network busyness, duration of transmission process, and failure situation, the efficiency has been increased by 20%, and an adaptive data integrity detection method based on random algorithm and encryption algorithm is designed. After experimental verification, this method can effectively detect the integrity of the data transmission process and improve the application of data value, and the final effect is increased by 30.5%.

Spatial–temporal pooling for action recognition in videos

Recently, deep convolutional neural networks have demonstrated great effectiveness in action recognition with both RGB and optical flow in the past decade. However, existing studies generally treat all frames and pixels equally, potentially leading to poor robustness of models. In this paper, we propose a novel parameter-free spatial–temporal pooling block (referred to as STP) for action recognition in videos to address this challenge. STP is proposed to learn spatial and temporal weights, which are further used to guide information compression. Different from other temporal pooling layers, STP is more efficient as it discards the non-informative frames in a certain clip. In addition, STP applies a novel loss function that forces the model to learn information from sparse and discriminative frames. Moreover, we introduce a dataset for ferry action classification, named Ferryboat-4, which includes four categories: Inshore, Offshore, Traffic, and Negative. This designed dataset can be used for the identification of ferries with abnormal behaviors, providing the essential information to support the supervision, management, and monitoring of ships. All the videos are acquired via real-world cameras. We perform extensive experiments on publicly available datasets as well as Ferryboat-4 and find that the proposed method outperforms several state-of-the-art methods in action classification. Source code and datasets are available at https://github.com/jiaming-wang/STP.

Solvability of the abstract evolution equations in L s -spaces with critical temporal weights

Abstract This paper deals with the abstract evolution equations in L s {L}^{s} -spaces with critical temporal weights. First, embedding and interpolation properties of the critical L s {L}^{s} -spaces with different exponents s s are investigated, then solvability of the linear evolution equation, attached to which the inhomogeneous term f f and its average Φ f \Phi f both lie in an L 1 / s s {L}_{1\hspace{-0.08em}\text{/}\hspace{-0.08em}s}^{s} -space, is established. Based on these results, Cauchy problem of the semi-linear evolution equation is treated, where the nonlinear operator F ( t , u ) F\left(t,u) has a growth number ρ ≥ s + 1 \rho \ge s+1 , and its asymptotic behavior acts like α ( t ) / t \alpha \left(t)\hspace{-0.1em}\text{/}\hspace{-0.1em}t as t → 0 t\to 0 for some bounded function α ( t ) \alpha \left(t) like ( − log t ) − p {\left(-\log t)}^{-p} with 2 ≤ p < ∞ 2\le p\lt \infty .

Kinetic maximal $$L^2$$-regularity for the (fractional) Kolmogorov equation

We introduce the notion of kinetic maximal $$L^2$$ -regularity with temporal weights for the (fractional) Kolmogorov equation. In particular, we determine the function spaces for the inhomogeneity and the initial value which characterize the regularity of solutions to the fractional Kolmogorov equation in terms of fractional anisotropic Sobolev spaces. It is shown that solutions of the homogeneous (fractional) Kolmogorov equation define a semi-flow in a suitable function space and the property of instantaneous regularization is investigated.

Temporal Loudness Weights Are Frequency Specific.

Previous work showed that the beginning of a sound is more important for the perception of loudness than later parts. When a short silent gap of sufficient duration is inserted into a sound, this primacy effect reoccurs in the second sound part after the gap. The present study investigates whether this temporal weighting occurs independently for different frequency bands. Sounds consisting of two bandpass noises were presented in four different conditions: (1) a simultaneous gap in both bands, (2) a gap in only the lower frequency band, (3) a gap in only the higher frequency band, or (4) no gap. In all conditions, the temporal loudness weights showed a primacy effect at sound onset. For the frequency bands without a gap, the temporal weights decreased gradually across time, regardless of whether the other frequency band did or did not contain a gap. When a frequency band contained a gap, the weight at the onset of this band after the gap was increased. This reoccurrence of the primacy effect following the gap was again largely independent of whether or not the other band contained a gap. Thus, the results indicate that the temporal loudness weights are frequency specific.

Choices change the temporal weighting of decision evidence.

Many decisions result from the accumulation of decision-relevant information (evidence) over time. Even when maximizing decision accuracy requires weighting all the evidence equally, decision-makers often give stronger weight to evidence occurring early or late in the evidence stream. Here, we show changes in such temporal biases within participants as a function of intermittent judgments about parts of the evidence stream. Human participants performed a decision task that required a continuous estimation of the mean evidence at the end of the stream. The evidence was either perceptual (noisy random dot motion) or symbolic (variable sequences of numbers). Participants also reported a categorical judgment of the preceding evidence half-way through the stream in one condition or executed an evidence-independent motor response in another condition. The relative impact of early versus late evidence on the final estimation flipped between these two conditions. In particular, participants' sensitivity to late evidence after the intermittent judgment, but not the simple motor response, was decreased. Both the intermittent response as well as the final estimation reports were accompanied by nonluminance-mediated increases of pupil diameter. These pupil dilations were bigger during intermittent judgments than simple motor responses and bigger during estimation when the late evidence was consistent than inconsistent with the initial judgment. In sum, decisions activate pupil-linked arousal systems and alter the temporal weighting of decision evidence. Our results are consistent with the idea that categorical choices in the face of uncertainty induce a change in the state of the neural circuits underlying decision-making.NEW & NOTEWORTHY The psychology and neuroscience of decision-making have extensively studied the accumulation of decision-relevant information toward a categorical choice. Much fewer studies have assessed the impact of a choice on the processing of subsequent information. Here, we show that intermittent choices during a protracted stream of input reduce the sensitivity to subsequent decision information and transiently boost arousal. Choices might trigger a state change in the neural machinery for decision-making.

Decoding and interpreting cortical signals with a compact convolutional neural network

Objective. Brain–computer interfaces (BCIs) decode information from neural activity and send it to external devices. The use of Deep Learning approaches for decoding allows for automatic feature engineering within the specific decoding task. Physiologically plausible interpretation of the network parameters ensures the robustness of the learned decision rules and opens the exciting opportunity for automatic knowledge discovery. Approach. We describe a compact convolutional network-based architecture for adaptive decoding of electrocorticographic (ECoG) data into finger kinematics. We also propose a novel theoretically justified approach to interpreting the spatial and temporal weights in the architectures that combine adaptation in both space and time. The obtained spatial and frequency patterns characterizing the neuronal populations pivotal to the specific decoding task can then be interpreted by fitting appropriate spatial and dynamical models. Main results. We first tested our solution using realistic Monte-Carlo simulations. Then, when applied to the ECoG data from Berlin BCI competition IV dataset, our architecture performed comparably to the competition winners without requiring explicit feature engineering. Using the proposed approach to the network weights interpretation we could unravel the spatial and the spectral patterns of the neuronal processes underlying the successful decoding of finger kinematics from an ECoG dataset. Finally we have also applied the entire pipeline to the analysis of a 32-channel EEG motor-imagery dataset and observed physiologically plausible patterns specific to the task. Significance. We described a compact and interpretable CNN architecture derived from the basic principles and encompassing the knowledge in the field of neural electrophysiology. For the first time in the context of such multibranch architectures with factorized spatial and temporal processing we presented theoretically justified weights interpretation rules. We verified our recipes using simulations and real data and demonstrated that the proposed solution offers a good decoder and a tool for investigating motor control neural mechanisms.

Copernicus Atmosphere Monitoring Service TEMPOral profiles (CAMS-TEMPO): global and European emission temporal profile maps for atmospheric chemistry modelling

Abstract. We present the Copernicus Atmosphere Monitoring Service TEMPOral profiles (CAMS-TEMPO), a dataset of global and European emission temporal profiles that provides gridded monthly, daily, weekly and hourly weight factors for atmospheric chemistry modelling. CAMS-TEMPO includes temporal profiles for the priority air pollutants (NOx; SOx; NMVOC, non-methane volatile organic compound; NH3; CO; PM10; and PM2.5) and the greenhouse gases (CO2 and CH4) for each of the following anthropogenic source categories: energy industry (power plants), residential combustion, manufacturing industry, transport (road traffic and air traffic in airports) and agricultural activities (fertilizer use and livestock). The profiles are computed on a global 0.1 × 0.1∘ and regional European 0.1 × 0.05∘ grid following the domain and sector classification descriptions of the global and regional emission inventories developed under the CAMS programme. The profiles account for the variability of the main emission drivers of each sector. Statistical information linked to emission variability (e.g. electricity production and traffic counts) at national and local levels were collected and combined with existing meteorology-dependent parametrizations to account for the influences of sociodemographic factors and climatological conditions. Depending on the sector and the temporal resolution (i.e. monthly, weekly, daily and hourly) the resulting profiles are pollutant-dependent, year-dependent (i.e. time series from 2010 to 2017) and/or spatially dependent (i.e. the temporal weights vary per country or region). We provide a complete description of the data and methods used to build the CAMS-TEMPO profiles, and whenever possible, we evaluate the representativeness of the proxies used to compute the temporal weights against existing observational data. We find important discrepancies when comparing the obtained temporal weights with other currently used datasets. The CAMS-TEMPO data product including the global (CAMS-GLOB-TEMPOv2.1, https://doi.org/10.24380/ks45-9147, Guevara et al., 2020a) and regional European (CAMS-REG-TEMPOv2.1, https://doi.org/10.24380/1cx4-zy68, Guevara et al., 2020b) temporal profiles are distributed from the Emissions of atmospheric Compounds and Compilation of Ancillary Data (ECCAD) system (https://eccad.aeris-data.fr/, last access: February 2021).

Vehicle Trajectory Prediction Using LSTMs With Spatial–Temporal Attention Mechanisms

Accurate vehicle trajectory prediction can benefit a variety of intelligent transportation system applications ranging from traffic simulations to driver assistance. The need for this ability is pronounced with the emergence of autonomous vehicles as they require the prediction of nearby vehicles&#x2019; trajectories to navigate safely and efficiently. Recent studies based on deep learning have greatly improved prediction accuracy. However, one prominent issue of these models is the lack of model explainability. We alleviate this issue by proposing spatiotemporal attention long short-term memory (STA-LSTM), an LSTM model with spatial-temporal attention mechanisms for explainability in vehicle trajectory prediction. STA-LSTM not only achieves comparable prediction performance against other state-of-the-art models but, more importantly, explains the influence of historical trajectories and neighboring vehicles on the target vehicle. We provide in-depth analyses of the learned spatial&#x2013;temporal attention weights in various highway scenarios based on different vehicle and environment factors, including target vehicle class, target vehicle location, and traffic density. A demonstration illustrating that STA-LSTM can capture and explain fine-grained lane-changing behaviors is also provided. The data and implementation of STA-LSTM can be found at <uri>https://github.com/leilin-research/VTP</uri>.

TSW-FD: A Novel Temporal and Spatial Domain Weight Analysis of Feature Difference for Micro-Expression Spotting

The micro-expression spotting has recently attracted increasing attention from psychology and computer vision community, since embraced in the second facial Micro-Expression Grand Challenge (MEGC 2019). Different from the original feature difference (FD) analysis, in this paper, we proposed a novel temporal and spatial domain weight analysis of feature difference (TSW-FD) to achieve micro-expression spotting. The experimental results showed that TSW-FD improved 17.86% and 24.21% in F1-Score comparing to the FD in CASME II and SMIC-E-HS.

Centrality informed embedding of networks for temporal feature extraction

We propose a two-step methodology for exploring the temporal characteristics of a network. First, we construct a graph time series, where each snapshot is the result of a temporal whole-graph embedding. The embedding is carried out using the degree, Katz and betweenness centralities to characterize first and higher order proximities among vertices. Then a principal component analysis is performed over the collected temporal graph samples, which exhibits eigengraphs, graphs whose temporal weight variations model the sampled graph series. Analysis of the temporal timeline of each of the main eigengraphs reveals moments of importance in terms of structural graph changes. Parameters such as the dimension of the embeddings and the number of temporal samples are explored. Two case studies are presented: a Bitcoin subgraph, where findings are cross-checked by looking at the subgraph behavior itself, and the Enron email network, which allows us to compare our findings with prior studies. In both cases, the proposed methodology successfully identified temporal structural changes in the graph evolution.

Dynamic Point Cloud Inpainting via Spatial-Temporal Graph Learning

The maturity of depth sensors and laser scanning techniques has enabled the convenient acquisition of 3D dynamic point clouds—one natural representation of 3D objects/scenes in motion, leading to a wide range of applications such as immersive tele-presence, autonomous driving, augmented and virtual reality. Nevertheless, dynamic point clouds usually exhibit holes of missing data, thus inpainting is crucial to the subsequent rendering or downstream understanding tasks. Dynamic point cloud inpainting has been largely overlooked so far, which is also quite challenging due to the irregular sampling patterns both in the spatial domain and temporal domain. To this end, we propose an efficient dynamic point cloud inpainting method based on a learnable spatial-temporal graph representation, exploiting both the second-order inter-frame coherence and the intra-frame self-similarity. The key is the second-order inter-frame coherence that enforces the consistent flow in 3D motion over time, for which we search the temporal correspondence in consecutive frames for the same underlying surface by the point-to-plane distance and represent the correlation between them via temporal edge weights in the graph. Based on the second-order inter-frame coherence and intra-frame self-similarity, we formulate dynamic point cloud inpainting as a joint optimization problem of the desired point cloud and underlying spatial-temporal graph, which is regularized by consistency in the temporal edge weights and smoothness in the spatial domain. We analyze and reformulate the optimization, leading to an efficient alternating minimization algorithm. Experimental results show that the proposed approach outperforms several competing methods significantly, both on synthetic holes and real holes.

Learning Dynamic Spatial-Temporal Regularization for UAV Object Tracking

With the wide vision and high flexibility, unmanned aerial vehicle (UAV) has been widely used into object tracking in recent years. However, its limited computing capability poses a great challenges to tracking algorithms. On the other hand, Discriminative Correlation Filter (DCF) based trackers have attracted great attention due to their computational efficiency and superior accuracy. Many studies introduce spatial and temporal regularization into the DCF framework to achieve a more robust appearance model and further enhance the tracking performance. However, such algorithms generally set fixed spatial or temporal regularization parameters, which lack flexibility and adaptability under cluttered and challenging scenarios. To tackle such issue, in this letter, we propose a novel DCF tracking model by introducing dynamic spatial regularization weight, which encourage the filter focuses on more reliable region during training stage. Furthermore, our method could optimize the spatial and temporal regularization weight simultaneously using Alternative Direction Method of Multiplies (ADMM) technique method, where each sub-problem has closed-form solution. Through the joint optimization, our tracker could not only suppress the potential distractors but also construct robust target appearance on the basis of reliable historical information. Experiments on two UAV benchmarks have demonstrated that our tracker performs favorably against other state-of-the-art algorithms.

Attribute Driven Temporal Active Online Community Search

Almost all of the existing approaches to determining online local community are typically deliberated like-minded users who have similar topical interests. However, such methodologies overlook the prospective temporality of users' interests as well as users' degree of topical activeness. As a result, the consequential communities might have extremely lower active users. This research investigates how online social users' behaviors and topical activeness vary over time and how these parameters can be employed in order to improve the quality of the detected local community. For a given input query, consisting a query node (user) and a set of attributes, this research intends to find densely-connected community in which community members are temporally similar in terms of their activities related to the query attributes. To address the proposed problem, we develop a temporal activity biased weight model which gives higher weight to users' recent activities and develop an algorithm to search an effective community. The effectiveness of the proposed methodology is justified using four benchmark datasets and compared with four other baseline methods. Experimental results demonstrate that our proposed framework yields better outcomes than the baseline methods for all four benchmark datasets.

Ensemble Based Temporal Weighting and Pareto Ranking (ETP) Model for Effective Root Cause Analysis

Root-cause identification plays a vital role in business decision making by providing effective future directions for the organizations. Aspect extraction and sentiment extraction plays a vital role in identifying the root-causes. This paper proposes the Ensemble based temporal weighting and pareto ranking (ETP) model for Root-cause identification. Aspect extraction is performed based on rules and is followed by opinion identification using the proposed boosted ensemble model. The obtained aspects are validated and ranked using the proposed aspect weighing scheme. Pareto-rule based aspect selection is performed as the final selection mechanism and the results are presented for business decision making. Experiments were performed with the standard five product benchmark dataset. Performances on all five product reviews indicate the effective performance of the proposed model. Comparisons are performed using three standard state-of-the-art models and effectiveness is measured in terms of F-Measure and Detection rates. The results indicate improved performances exhibited by the proposed model with an increase in F-Measure levels at 1%–15% and detection rates at 4%–24% compared to the state-of-the-art models.

An end-to-end atrial fibrillation detection by a novel residual-based temporal attention convolutional neural network with exponential nonlinearity loss

Atrial fibrillation (AF) is one of the most common abnormal heart rhythms, which is caused by the fast contraction of the two upper atria. Despite of the fact that convolutional neural network (CNN) has been applied to electrocardiogram analysis for AF rhythm, it cannot achieve the expected performance due to the lack of consideration for temporal features and the imbalance problem. In order to make the network concentrate on the learning of AF temporal features, we propose a residual-based temporal attention block (RTA-block). The RTA-block utilizes residual learning to generate temporal attention weights, which enhance informative features related to AF. Powered by the RTA-block, a residual-based temporal attention convolutional neural network (RTA-CNN) is further proposed for AF detection. The network can automatically focus on the parts with more sematic information to achieve better performance. In addition, we propose a novel exponential nonlinearity loss (EN-Loss), which addresses the imbalance problem by changing the nonlinearity of the loss function. We evaluated our framework on the single lead ECG classification dataset of The PhysioNet Computing in Cardiology Challenge 2017. The experimental results show that the proposed RTA-CNN with EN-Loss can obtain competitive results over the state-of-the-arts classification networks, which proves the method’s effectiveness.