Time Warping Research Articles

A data fusion method for maritime traffic surveillance: The fusion of AIS data and VHF speech information

The more comprehensive information supply for Vessel Traffic Service (VTS), the greater capacity for maritime traffic surveillance. To supply ship intention information contained in very high frequency (VHF) speech for VTS, we propose an automatic identification system (AIS) data and VHF speech information fusion method. In the first part of this method, the feature information of VHF speech is extracted by Bert-BiLSTM-CRF-based entity extraction method, likes location, ship name, and ship intention information, etc. In the second part, we design a spatio-temporal range to filter AIS data, the temporal range is determined by receive time of VHF speech, and the spatial range is determined by the location information extracted from VHF speech. In the third part, by measuring the ship name similarity between AIS data and VHF speech, the barriers to fusion are successfully overcome. The similarity is calculated by combining with Chinese pinyin character similarity and Arabic number similarity and Chinese pinyin characters are encoded by pronunciation characters, calculated by the dynamic time warping (DTW) distance. Through experiments, the method can effectively provide comprehensive information for maritime traffic surveillance, and even when crews misreport ship name within a small deviation, our method still possesses a great fusion capability.

River-sea migration patterns of juvenile Japanese seabass influence migrations in subsequent stages

The Japanese seabass Lateolabrax japonicus, an important commercial fishery species, exhibits partial migration, where some individuals migrate upstream into rivers, and others inhabit estuarine and coastal areas within the same population. Although this migratory behavior has been documented in juvenile seabass, the prevalence of river use and the ecological significance of partial migration in subsequent developmental stages remain unclear. To understand the river use of subadult and adult Japanese seabass, we estimated the river use history using otolith Sr/Ca ratios from individuals captured in both marine and riverine environments. Based on hierarchical clustering with Dynamic Time Warping, Sr/Ca ratios at age 0 were clustered into three habitat use patterns: coastal resident, estuarine resident, and river migrant. Groups that used coastal and riverine habitats at age 0 tended to use coastal and riverine habitats, respectively, from spring to fall of age 1 and above, with overlapping distributions during winter. Subadult and adult river use patterns were linked to juvenile river use, indicating a carryover effect. Additionally, seasonal migration between the sea and rivers became less active with age, and the high growth sustained by river use also declined with age, suggesting that the benefits of river use are less for older (subadult and adult) seabass. This study highlights that juvenile habitat use experience drives subadult and adult partial migration of Japanese seabass, with individuals seeking environments adapted from past experiences. Our findings indicate that the seabass population consists of individuals adapted to various environments, from the sea to the rivers, maximizing the use of biological productivity.

PaFESD: Patterns augmented by Features Epileptic Seizure Detection.

The detection of epileptic seizures can have a significant impact on the patients' quality of life and on their caregivers. In this paper we propose a method for detecting such seizures from electroencephalogram (EEG) data named Patterns augmented by Features Epileptic Seizure Detection (PaFESD). The main novelty of our proposal consists in a detection model that combines EEG signal features with pattern matching. After cleaning the signal and removing artifacts (as eye blinking or muscle movement noise), time-domain and frequency-domain features are extracted to filter out non-seizure regions of the EEG. Jointly, pattern matching based on Dynamic Time Warping (DTW) distance is also leveraged to identify the most discriminative patterns of the seizures, even under scarce training data. The proposed model is evaluated on all patients in the CHB-MIT database, and the results show that it is able to detect seizures with an average F1 score of 98.9%. Furthermore, our approach achieves a F1 score of 100% (no false alarms or missed true seizures) for 20 of the patients (out of 24). Additionally, we automatically detect the most seizure/non-seizure discriminative EEG channel so that a wearable with only two electrodes would suffice to warn patients of seizures.

Integrating Dynamic Time Warping and K-means clustering for enhanced cardiovascular fitness assessment

The appropriate measurement of cardiovascular ’Performance Enhancement’ is critical for improving physical fitness and overall health. Traditional methods, effective as they are, often rely on complex, cumbersome equipment, limiting their practical use for real-time, dynamic exercise evaluation. Thus, understanding the intricate relationship between physiological responses and exercise ‘Performance Enhancement’ using wearable technology is essential for tailoring effective fitness regimes. This study involved 52 participants, utilizing Garmin Vivosmart 5 wearables to analyze heart rate time series during the YMCA Three-Minute Step Test, assessing fitness levels and characterizing personalized heartbeat dynamics. The study employed Dynamic Time Warping (DTW) for clustering these time series into high and low VO2max groups. Additionally, heart rate dynamics were examined using K-means clustering to identify distinct patterns during exercise—namely ‘Efficient Adaptation’, ‘Balance Under Pressure’, ‘Active Strain’, and ‘Efficiency Improvement’ clusters. This analysis demonstrated that non-trained individuals showed higher ‘Active Strain’ and ‘Efficiency Improvement’ dynamics and lower ‘Efficient Adaptation’ dynamics, indicating the exercise’s varied effectiveness based on training level. This method provides a novel approach for identifying individual fitness levels and the efficacy of specific exercises, enabling personalized physical activity planning.

BDS time spoofing detection method based on the dynamic time warping

BDS time spoofing detection method based on the dynamic time warping

A Framework for Using Regional Scenarios in Racial Equity Planning

Problem, research strategy, and findings Planning under uncertainty and planning for racial equity both require imagination. In confronting the uncertain future, regional planners often opt for exploratory scenario planning: telling multiple future stories to prepare for any outcome. For equity planning, imagination supports vision beyond the deeply unequal present condition, wherein policy tinkering is insufficient for necessary change. And yet, scenario planning and equity planning are estranged. Although regional planners wish to engage both, they lack guidance on how. I look to close this gap by providing a framework (the Framework) for using scenarios in equity planning. The Framework builds on the five types of racial equity, a six-stage hybrid scenario process, and the three outcomes of public-sector scenarios. Using the Framework, I assessed the inclusion of equity in the Delaware Valley Regional Planning Commission’s Dispatches From Alternative Futures scenario plan. This plan successfully raises racial equity as a concern for the future of the Philadelphia (PA) region. However, the stakeholder group was not sufficiently diverse for deliberative equity and the scenario planners did not use tools that could assess the distributional outcomes. Neither epistemic nor restorative equity were a significant part of the scenario plan, leaving open the possibility for co-designed scenarios for a racial equity future. Takeaway for practice Metropolitan planning organizations (MPOs) can use the Framework to ensure that exploratory scenarios advance equity goals. Although the Framework can supply a starting point for MPOs, the most important voices are those from Black, Indigenous, and people of color (BIPOC) and other marginalized communities. Scenario planners should consider how they can reach out to community members not just as stakeholders but as co-creators of a more epistemically equitable scenario planning process, one that addresses the uncertainties and aspirations that already percolate within these communities.

Touring Absences, Erasures, and Futures in the Unholy Land: A Religiously Literate Diasporic Reading of Palestine/Israel

Abstract This article examines a decolonial approach to teaching a course on Palestine/Israel involving experiential travel to the region. A decolonial syllabus studies absences, erasures, the multiple intersecting mechanisms and matrices of violence, and alternative futures as they inhabit subordinated pasts (histories) and the present in various activist spaces. We expand on other decolonial learning-in-context by underscoring the need for religious literacy. This is especially urgent because the land is a destination for apocalyptic, messianic, and birthright tourism designed to confirm and reinforce people’s redemptive scripts and fantasies about the land. The objective of the decolonial approach is not “metaphorical.” It is to dismantle the oppression of Palestinians, institute mechanisms for restorative justice, and draw ethical political maps. It is also hermeneutical, denoting the urgent need to dezionize Jewish consciousness. This article centers on those dimensions of our work that engage with pathways for decolonial Jewish political ethics in Palestine.

Seeking environmental justice through the state: Insider allies in U.S. state and federal government agencies

Geographers and political ecologists have demonstrated settler-colonial states’ longstanding key roles in producing environmental injustice through colonialism, racial capitalism, neoliberalism, and other mechanisms. Such studies tend to conclude, implicitly or explicitly, that environmental justice (EJ) movements’ pursuits of more sustainable and just futures must therefore antagonistically confront the state or work beyond it entirely to create alternative futures that do not reinforce state hegemony and violence. However, other scholars in recent years have critiqued such characterizations of the state as unilaterally and fundamentally oppressive, arguing instead that states are terrains of struggle whose contradictory programs and practices reflect not only the interests of capital but also actions of movements. They demonstrate that movements pursuing more just and sustainable futures find purchase working both through and beyond the state. Here, we follow these scholars but depart from them in one respect – namely, they frame movements as pressuring the state only from outside of it. We argue that conceptualizing the state and movements as ontologically overlapping and permeable realms in which some actors move back and forth illuminates additional movement influence on state practice and additional factors that mediate their efforts. We make this case by following a group of U.S. EJ activists who pursue EJ movements’ goals by taking formal positions inside the government agencies they seek to change. We show that they accomplish meaningful change in these roles and that their work is mediated not only by industry power over state agencies, as other scholars have rightly identified, but also by elements of regulatory workplace culture, insider allies’ skills honed in external EJ advocacy, and solidarity among EJ advocates within and beyond the state. By more fully identifying such mediating factors and showing how they shape insider allies’ work, we hope to highlight new fronts of struggle as former EJ movement activists use their insider ally positions to wrest more control over the state from capital and for liberatory ends.

Revolutionary Art and the Creation of the Future: The Afrofuturist Texts of José Antonio Aponte and Martin R. Delany

Afrofuturism (an artistic perspective in which Black voices tell alternative narratives of culture, technology, and the future) and the Dark Fantastic (interrupting negative depictions of Black people through emancipatory interpretations of art) are two interrelated concepts used by Black artists in the Atlantic World to counter negative images and emphasize a story from a Black perspective. Likewise, these concepts have been used to recreate and re-narrate history with an eye towards subverting white supremacist historical narratives. By using Afrofuturism and the Dark Fantastic as lenses through which texts by authors from the African Diaspora in the Atlantic World are examined, an alternative narrative of Black histories and futures concerned with revolution, liberation, and justice can be seen. The two texts that are the subject of this research include José Antonio Aponte’s descriptions of his book of paintings under interrogation in 1812–1813, and Martin Delany’s novel Blake; or the Huts of America (1859–1862), providing images of enslavement that run counter to a white supremacist telling of history. They both imagine alternative pasts and futures for Africa and the Afro-Diaspora involving revolution and magic. These works, though produced at different times and locations in the nineteenth century, offer new ways in which to discuss liberation and freedom in the context of the artistic production of the Atlantic World.

Individual differences and motor planning influence self-recognition of actions.

Although humans can recognize their body movements in point-light displays, self-recognition ability varies substantially across action types and participants. Are these variations primarily due to an awareness of visually distinct movement patterns, or to underlying factors related to motoric planning and/or individual differences? To address this question, we conducted a large-scale study in self-action recognition (N = 101). We motion captured whole-body movements of participants who performed 27 different actions across action goals and degree of motor planning. After a long delay period (~ 1 month), participants were tested in a self-recognition task: identifying their point-light action amongst three other point-light actors performing identical actions. We report a self-advantage effect from point-light actions, consistent with prior work in self-action recognition. Further, we found that self-recognition was modulated by the action complexity (associated with the degree of motor planning in performed actions) and individual differences linked to motor imagery and subclinical autism and schizotypy. Using dynamic time warping, we found sparse evidence in support of visual distinctiveness as a primary contributor to self-recognition, though speed distinctiveness negatively influenced self-recognition performance. Together, our results reveal that self-action recognition involves more than an awareness of visually distinct movements, with important implications for how the motor system may be involved.

Semantic Web Techniques for Extracting and Analyzing of Cropland Abandonment in Hilly Areas

Due to rising rural labor costs, farmland abandonment is common in China's hilly areas. Timely, accurate extraction of its spatiotemporal changes is crucial for sustainable farmland use. This study presents a novel approach for extracting abandoned cropland using NDVI time series from Sentinel-2 satellite images, exploiting the difference in vegetation phenology between abandoned and cultivated croplands. Dynamic Time Warping (DTW) algorithm was used to determine the similarity between NDVI time-series curves of different cropland types. The similarity metrics were used to find the optimal NDVI threshold for abandoned cropland through F1-score evaluation. The method's overall accuracy is 92.4%, higher than comparison methods at 84.60% and 75.6%. The approach captures year-round vegetation changes, expands time dimension data, and improves accuracy. Spatiotemporal analysis revealed decreased patch size, increased shape complexity, and more dispersed distribution of abandoned cropland over time. Major factors were proximity to settlements, roads, water bodies.

Research on automatic identification of coal mining subsidence area based on InSAR and time series classification

Large-scale mining of coal resources has caused surface subsidence, threatening the ecological environment and surface safety and hindering the sustainable development of coal resource-based cities seriously. In order to identify coal mining subsidence area more accurately and quickly, a novel method for automatic identification of coal mining subsidence area was proposed in this study, which is based on InSAR technology and time series classification algorithm. The method comprehensively considered the quality of data acquisition and the degree of automation of algorithm implementation, realizing automatic identification of large-space coal mining subsidence area in the case of small samples. Firstly, the unclassified subsidence dataset is constructed by SAR data around time series combined with InSAR technology. Secondly, the degree of change of time series subsidence is used as the basis of classification, and it is divided into two categories: regular type of coal mining subsidence and irregular type of non-coal mining subsidence. Finally, Dynamic Time Warping (DTW) algorithm is used to calculate the similarity distance between the time series curves of each image element of the subsidence dataset to be tested and the standard coal mining subsidence type curves, which aim at identifying the coal mining subsidence area. Through utilizing the multitude filtering algorithm to filter the recognition results, the automatic recognition results of coal mining subsidence area is finally obtained. The results show that this method can still be used to efficiently identify and circle coal mining subsidence area with only 640 samples, and the average Overall Accuracy (OA) and Kappa Coefficient (KC) of coal mining subsidence area are 0.91 and 0.83, respectively. The method can not only identify the existing and potential subsidence area in the mining area, but provide technical support for ecological environment restoration and early warning of subsidence damage.

Accelerating time series similarity search under Move-Split-Merge distance via dissimilarity space embedding

The ubiquity sensory devices across scientific and industrial settings have made time-series data mining an important research topic in the IoT domain. Among all time-series mining techniques, the similarity search is considered the most essential and noteworthy because it is frequently employed as a fundamental subroutine for other procedures. The Dynamic Time Warping (DTW) was once considered the best similarity measure in time-series data mining community; however, two recent studies have demonstrated that the Move-Split-Merge (MSM) performs better than DTW in both supervised and unsupervised settings. Computing MSM between two time-series incurs costly computation because MSM has quadratic time complexity. Regrettably, there is little research on accelerating time-series similarity search under MSM. This paper provides an efficient method named DSEMSM for speeding up this procedure. DSEMSM utilizes dissimilarity space embedding to transform time-series into low-dimensional vectors. The filter-and-verification framework is subsequently employed to reduce the large number of actual MSM computations and to identify the final search results from the candidate set. The furthest prototype selection strategy and lower bound based technique are applied in DSEMSM to improve its retrieval accuracy and efficiency, respectively. We validate the effectiveness of the proposed method on a large number of datasets. The experimental results indicate that, in comparison to its relevant competitors, DSEMSM achieves a more stable speedup rate and higher retrieval accuracy.

Detection of Maize Crop Phenology Using Planet Fusion

Accurate identification of crop phenology timing is crucial for agriculture. While remote sensing tracks vegetation changes, linking these to ground-measured crop growth stages remains challenging. Existing methods offer broad overviews but fail to capture detailed phenological changes, which can be partially related to the temporal resolution of the remote sensing datasets used. The availability of higher-frequency observations, obtained by combining sensors and gap-filling, offers the possibility to capture more subtle changes in crop development, some of which can be relevant for management decisions. One such dataset is Planet Fusion, daily analysis-ready data obtained by integrating PlanetScope imagery with public satellite sensor sources such as Sentinel-2 and Landsat. This study introduces a novel method utilizing Dynamic Time Warping applied to Planet Fusion imagery for maize phenology detection, to evaluate its effectiveness across 70 micro-stages. Unlike singular template approaches, this method preserves critical data patterns, enhancing prediction accuracy and mitigating labeling issues. During the experiments, eight commonly employed spectral indices were investigated as inputs. The method achieves high prediction accuracy, with 90% of predictions falling within a 10-day error margin, evaluated based on over 3200 observations from 208 fields. To understand the potential advantage of Planet Fusion, a comparative analysis was performed using Harmonized Landsat Sentinel-2 data. Planet Fusion outperforms Harmonized Landsat Sentinel-2, with significant improvements observed in key phenological stages such as V4, R1, and late R5. Finally, this study showcases the method’s transferability across continents and years, although additional field data are required for further validation.

An Early Warning Model for Turbine Intermediate-Stage Flux Failure Based on an Improved HEOA Algorithm Optimizing DMSE-GRU Model

As renewable energy sources such as wind and photovoltaics continue to enter the grid, their intermittency and instability leads to an increasing demand for peaking and frequency regulation. An efficient dynamic monitoring method is necessary to improve the safety level of intelligent operation and maintenance of power stations. To overcome the insufficient detection accuracy and poor adaptability of traditional methods, a novel fault early warning method with careful consideration of dynamic characteristics and model optimization is proposed. A combined loss function is proposed based on the dynamic time warping and the mean square error from the perspective of both shape similarity and time similarity. A prediction model of steam turbine intermediate-stage extraction temperature based on the gate recurrent unit is then proposed, and the change in prediction residuals is utilized as a fault warning criterion. In order to further improve the diagnostic accuracy, a human evolutionary optimization algorithm with lens opposition-based learning is proposed for model parameter adaptive optimization. Experiments on real-world normal and faulty operational data demonstrate that the proposed method can improve the detection accuracy by an average of 1.31% and 1.03% compared to the long short-term memory network, convolutional neural network, back propagation network, extreme learning machines, gradient boosting decision tree, and LightGBM models.

Applications of LIF to Document Natural Variability of Chlorophyll Content and Cu Uptake in Moss.

Chlorophyll has long been used as a natural indicator of plant health and photosynthetic efficiency. Laser-induced fluorescence (LIF) is an emerging technique for understanding broad spectrum organic processes and has more recently been used to monitor chlorophyll response in plants. Previous work has focused on developing a LIF technique for imaging moss mats to identify metal contamination with the current focus shifting toward application to moss fronds and aiding sample collection for chemical analysis. Two laser systems (CoCoBi a Nd:YGa pulsed laser system and Chl-SL with two blue continuous semiconductor diodes) were used to collect images of moss fronds exposed to increasing levels of Cu (1, 10, and 100 nmol/cm2) using a CMOS camera. The best methods for the preprocessing of images were conducted before the analysis of fluorescence signatures were compared to a control. The Chl-SL system performed better than the CoCoBi, with dynamic time warping (DTW) proving the most effective for image analysis. Manual thresholding to remove lower decimal code values improved the data distributions and proved whether using one or two fronds in an image was more advantageous. A higher DTW difference from the control correlated to lower chlorophyll a/b ratios and a higher metal content, indicating that LIF, with the aid of image processing, can be an effective technique for identifying Cu contamination shortly after an event.

Similarity measurement of symbolic sequence based on complexity estimate and dynamic time warping

Similarity measurement of symbolic sequence based on complexity estimate and dynamic time warping

What Do Community Doulas Think About the Future of the Doula Workforce?

Expanding access to doula care is a key strategy for improving the perinatal experiences and health outcomes of birthing people of color in the U.S. This study investigates the future of maternal healthcare in the U.S. from the perspective of doulas and highlights emerging technology and other opportunities related to strengthening the doula workforce. The study recruited community doulas from 12 unique U.S. states, ensuring at least half of the doulas predominantly served communities of color. Doulas (N = 26) participated in semi-structured, futures-oriented interviews that explored their experiences providing care during the COVID-19 pandemic and utilization of technology. A subset of doulas (n = 8) were engaged in interactive workshops where they envisioned alternative futures for doula care and childbirth. Interviews and workshops were analyzed using the Framework Method. The COVID-19 pandemic heightened technology use among doulas and increased client accessibility. Social media serves as a unique space for critical community building and client outreach. Doulas reported opportunities to strengthen and mobilize the future workforce: recognizing doula care as a reimbursable service by health insurers, utilizing doula collectives for community practice to decrease burnout, increasing emotional support for doulas, and instilling a chain of learning through mentorship. Futures thinking served as a valuable approach for doulas to illuminate the implications of present-day challenges and empowered doulas to design roadmaps toward better futures for doulas and maternal health. Doulas should be engaged as partners to hold a meaningful decision-making role when discussing policies, employment structures, emerging technology, and other aspects of doulas' positioning within the healthcare system.

Two-stage transfer learning-based nonparametric system identification with Gaussian process regression

Most system identification methods ignore correlations between different identification tasks and do not make full use of historical models when identifying a new process. In this paper, a two-stage transfer learning-based nonparametric system identification method is proposed to improve model accuracy and to reduce identification costs. First, to overcome the transfer capability limitations of the discrete-time model, the target process is modeled as a continuous-time impulse response (IR) function, which consists of a transfer model part and a residual model part, which is regarded as a zero-mean Gaussian process (GP). Then, by utilizing the process geometrical characteristics, the IR functions are classified into three IR domains, and transformation functions within domain or between domains are designed to learn the relationship between the source process model and the target process model. Finally, a two-stage nonparametric identification algorithm based on GP regression is developed: The first stage is performed to select the appropriate type of transformation function through the weighted-derivative dynamical time warping technique, and the second stage is conducted to estimate the transfer model and residual model by using the empirical Bayes approach. Three case studies are conducted to validate the superiority of the proposed identification method.

Bridging the nature–cultural heritage gap: evaluating sustainable entanglements through cemeteries in urban Asia

The expanding footprint of urban Asian settlements and increasing living standards have put pressure on cemetery sites. Public health narratives and the sanctity associated with death matters in Asian urban landscapes have fed into the rhetoric of cemeteries as undesirable heritage spaces. Often lacking protection, many cemeteries have been exhumed, cleared, and relocated to allow room for new developments and infrastructure, risking the survival of this quiet element of the urban cultural patrimony. Within an Asian context, synergies between nature and cultural heritage preservation are not prevalent in major cities like Singapore, Hong Kong, Tokyo, Manila, Kuala Lumpur, and Bangkok. In light of increasing recognition of urban cemeteries as multi-valued sites with both natural and cultural heritage values, this paper turns to deconstructing the nature–cultural binary and the concept of entanglement to frame an investigation of collaborative interactions. A focused study on Asian urban cemeteries follows, examining existing trends and adapted mix uses and highlighting the region’s unique conservation challenges. The analysis reveals three major typologies encapsulating the region’s current nature–cultural heritage entangled preservation approaches: sustainable compromises, memories, and everyday sustainability. To conclude, the paper distils respectful alternative futures for these spaces to be better integrated into the modern textures of the cities, unlocking functional recourses to destruction or oblivion.