Spatiotemporal Data Clustering: A Survey of Methods

3D clustering of gene expression data from systemic autoinflammatory diseases using self-organizing maps (Clust3D)

Background and objective

Systemic autoinflammatory diseases (SAIDs) are characterized by widespread inflammation, but for most of them there is a lack of specific biomarkers for accurate diagnosis. Although a number of machine learning algorithms have been used to analyze SAID datasets, aiding in the discovery of novel biomarkers, there is a growing recognition of the importance of SAID timeseries clustering, as it can capture the temporal dynamics of gene expression patterns.

Methodology

This paper proposes a novel clustering methodology to efficiently associate three-dimensional data. The algorithm utilizes competitive learning to create a self-organizing neural network and adjust neuron positions in time-dependent and high dimensional feature space in order to assign them as clustering centers. The quantitative evaluation of the clustering was based on well-known clustering indices. Furthermore, a differential expression analysis and classification pipeline was employed to assess the capability of the proposed methodology to extract more accurate pathway-specific genes from its clusters. For that, a comparative analysis was also conducted against a heuristic timeseries clustering method.

Results

The proposed methodology achieved better overall clustering indices scores and classification metrics using genes derived from its clusters. Notable cases include a threefold increase in the Calinski-Harabasz clustering index, a twofold improvement in the Davies-Bouldin clustering index and a ∼ 60 % increase in the classification specificity score.

Conclusion

A novel clustering methodology was developed and applied on several gene expression timeseries datasets from systemic autoinflammatory diseases, and its ability to efficiently produce well separated clusters compared to existing heuristic methods was demonstrated.

Particle filtering supported probability density estimation of mobility patterns

This paper presents a methodology that aims to enhance the accuracy of probability density estimation in mobility pattern analysis by integrating prior knowledge of system dynamics and contextual information into the particle filter algorithm. The quality of the data used for density estimation is often inadequate due to measurement noise, which significantly influences the distribution of the measurement data. Thus, it is crucial to augment the information content of the input data by incorporating additional sources of information beyond the measured position data. These other sources can include the dynamic model of movement and the spatial model of the environment, which influences motion patterns. To effectively combine the information provided by positional measurements with system and environment models, the particle filter algorithm is employed, which generates discrete probability distributions. By subjecting these discrete distributions to exploratory techniques, it becomes possible to extract more certain information compared to using raw measurement data alone. Consequently, this study proposes a methodology in which probability density estimation is not solely based on raw positional data but rather on probability-weighted samples generated through the particle filter. This approach yields more compact and precise modeling distributions. Specifically, the method is applied to process position measurement data using a nonparametric density estimator known as kernel density estimation. The proposed methodology is thoroughly tested and validated using information-theoretic and probability metrics. The applicability of the methodology is demonstrated through a practical example of mobility pattern analysis based on forklift data in a warehouse environment.

A Two-Layer Self-Organizing Map with Vector Symbolic Architecture for Spatiotemporal Sequence Learning and Prediction

We propose a new nature- and neuro-science-inspired algorithm for spatiotemporal learning and prediction based on sequential recall and vector symbolic architecture. A key novelty is the learning of spatial and temporal patterns as decoupled concepts where the temporal pattern sequences are constructed using the learned spatial patterns as an alphabet of elements. The decoupling, motivated by cognitive neuroscience research, provides the flexibility for fast and adaptive learning with dynamic changes to data and concept drift and as such is better suited for real-time learning and prediction. The algorithm further addresses several key computational requirements for predicting the next occurrences based on real-life spatiotemporal data, which have been found to be challenging with current state-of-the-art algorithms. Firstly, spatial and temporal patterns are detected using unsupervised learning from unlabeled data streams in changing environments; secondly, vector symbolic architecture (VSA) is used to manage variable-length sequences; and thirdly, hyper dimensional (HD) computing-based associative memory is used to facilitate the continuous prediction of the next occurrences in sequential patterns. The algorithm has been empirically evaluated using two benchmark and three time-series datasets to demonstrate its advantages compared to the state-of-the-art in spatiotemporal unsupervised sequence learning where the proposed ST-SOM algorithm is able to achieve 45% error reduction compared to HTM algorithm.

Identifying the patterns and sizes of the first lumpy skin disease outbreak clusters in Northern Thailand with a high degree of dairy farm aggregation using spatio-temporal models

Lumpy skin disease (LSD) is one of the most important notifiable transboundary diseases affecting cattle in many parts of the world. In Thailand, LSD outbreaks in cattle farming areas have been reported in 69 out of 77 provinces, indicating a serious nationwide situation. Understanding the dynamics of spatial and temporal LSD epidemic patterns can provide important information on disease transmission and control. This study aims to identify spatial and temporal clusters in the first LSD outbreaks in dairy farming areas with a high degree of aggregation in Northern Thailand using spatio-temporal models. The data were obtained from an official LSD outbreak investigation conducted between June and August 2021 on dairy farms (n = 202). The outbreak of LSD was confirmed by employing clinical observations and laboratory analysis. The spatio-temporal models including space-time permutation (STP), Poisson, and Bernoulli were applied to the outbreak data with the settings of 10%, 25%, and 50%, respectively, for the maximum reported cluster size (MRCS). Overall, the number of most likely and secondary clusters varied depending on the model and MRCS settings. All MRCS settings in the STP model detected the most likely clusters in the same area and the Poisson models in different areas, with the largest being defined by a 50% MRCS. Although the sizes of the most likely clusters identified by the Bernoulli models were different, they all had the same cluster period. Based on the sizes of the detected clusters, strict LSD insect-vector control should be undertaken within one kilometer of the outbreak farm in areas where no LSD vaccination has been administered. This study determines the sizes and patterns of LSD outbreak clusters in the dairy farming area with a high degree of farm aggregation. The spatio-temporal study models used in this study, along with multiple adjusted MRCS, provide critical epidemiological information. These models also expand the options for assisting livestock authorities in facilitating effective LSD prevention and control programs. By prioritizing areas for resource allocation, these models can help improve the efficiency of such programs.

Spatio-temporal patterns of the mortality of diseases associated with malnutrition and their relationship with food establishments in Mexico

This study explores the spatio-temporal behavior of mortality due to multiple causes associated with several diseases and their relationship with the physical availability of food. We analyze data for the 2010-2020 period at the municipality level in Mexico. After collecting and standardizing national databases for each disease, we perform SATSCAN temporal and FleXScan spatial cluster analyses. We use the he Kruskal-Wallis test to analyze the differences between municipalities with high relative risk of mortality and their relationship with food retail units and food establishments. We found statistically significant relationships between clusters by disease and the physical availability of food per hundred thousand inhabitants. The main pattern is a higher average density of convenience stores, supermarkets, fast food chains and franchises, and Mexican snack restaurants in high-risk municipalities, while a higher density of grocery stores and inns, cheap kitchens, and menu restaurants exists in the municipalities with low risk. The density of convenience stores, fast food chains and franchises, and Mexican snack restaurants plays a very important role in mortality behavior, so measures must exist to regulate them and encourage and protect convenience stores, grocery stores, and local food preparation units.

Spatiotemporal clustering of suicide attempt in Kermanshah, West-Iran

Background

A suicide attempt is a major societal problem because it imposes high costs on societies worldwide. This paper analyses the spatiotemporal clustering of suicide attempt in Kermanshah, Iran from 2006-14.

Methods

This study draws on 18,333 individuals (7,234 males and 11,097 females) who attempted suicide across the Kermanshah province. Data was collected from the records of individuals registered in hospitals across the Kermanshah province between 2006 and 2014. Mean Center, Standard Deviational Ellipse (SDE), Moran's I and Kernel Density Estimation (KDE) in Arc/GIS10.6 software were used for the analysis of the spatial distribution of suicide attempt, while the chi-squared test in SPSS was used to examine the different demographic variables between groups within/outside spatial clusters of suicide.

Results

The results show that a total of 18,331 suicide attempts (39.46% male and 60.53% female) were reported between 2006 and 2014 in the Kermanshah province. The spatial pattern of suicide attempts was clustered in 16 clusters (6 high clusters and 10 low clusters) and statistically significant differences were found within and outside the hotspots of suicide attempts. Most hot spots were formed in and around cities. Younger people were at a greater risk. The rate of suicide attempts reduced in illiterate people and increased in people with university degrees. Unmarried people were associated with a higher risk of suicide attempt than was married status for both males and females.

Conclusion

The results of this study could help public health practitioners and policymakers in Iran prioritize resources and target efforts for suicide attempt prevention.

Trajectory Clustering-Based Anomaly Detection in Indoor Human Movement

Human movement anomalies in indoor spaces commonly involve urgent situations, such as security threats, accidents, and fires. This paper proposes a two-phase framework for detecting indoor human trajectory anomalies based on density-based spatial clustering of applications with noise (DBSCAN). The first phase of the framework groups datasets into clusters. In the second phase, the abnormality of a new trajectory is checked. A new metric called the longest common sub-sequence using indoor walking distance and semantic label (LCSS_IS) is proposed to calculate the similarity between trajectories, extending from the longest common sub-sequence (LCSS). Moreover, a DBSCAN cluster validity index (DCVI) is proposed to improve the trajectory clustering performance. The DCVI is used to choose the epsilon parameter for DBSCAN. The proposed method is evaluated using two real trajectory datasets: MIT Badge and sCREEN. The experimental results show that the proposed method effectively detects human trajectory anomalies in indoor spaces. With the MIT Badge dataset, the proposed method achieves 89.03% in terms of F1-score for hypothesized anomalies and above 93% for all synthesized anomalies. In the sCREEN dataset, the proposed method also achieves impressive results in F1-score on synthesized anomalies: 89.92% for rare location visit anomalies (τ = 0.5) and 93.63% for other anomalies.

EDPNet: An Encoding-Decoding Network with Pyramidal Representation for Semantic Image Segmentation

This paper proposes an encoding-decoding network with a pyramidal representation module, which will be referred to as EDPNet, and is designed for efficient semantic image segmentation. On the one hand, during the encoding process of the proposed EDPNet, the enhancement of the Xception network, i.e., Xception+ is employed as a backbone to learn the discriminative feature maps. The obtained discriminative features are then fed into the pyramidal representation module, from which the context-augmented features are learned and optimized by leveraging a multi-level feature representation and aggregation process. On the other hand, during the image restoration decoding process, the encoded semantic-rich features are progressively recovered with the assistance of a simplified skip connection mechanism, which performs channel concatenation between high-level encoded features with rich semantic information and low-level features with spatial detail information. The proposed hybrid representation employing the proposed encoding-decoding and pyramidal structures has a global-aware perception and captures fine-grained contours of various geographical objects very well with high computational efficiency. The performance of the proposed EDPNet has been compared against PSPNet, DeepLabv3, and U-Net, employing four benchmark datasets, namely eTRIMS, Cityscapes, PASCAL VOC2012, and CamVid. EDPNet acquired the highest accuracy of 83.6% and 73.8% mIoUs on eTRIMS and PASCAL VOC2012 datasets, while its accuracy on the other two datasets was comparable to that of PSPNet, DeepLabv3, and U-Net models. EDPNet achieved the highest efficiency among the compared models on all datasets.

Applying OHSA to Detect Road Accident Blackspots

With increasing numbers of crashes and injuries, understanding traffic accident spatial patterns and identifying blackspots is critical to improve overall road safety. This study aims at detecting blackspots using optimized hot spot analysis (OHSA). Traffic accidents were classified by their participants and severity to explore the relationship between blackspots and different types of accidents. Based on the outputs of incremental spatial autocorrelation, OHSA was then implemented on different types of accidents. Finally, the performance of OHSA in evaluating the road safety level of the proposed RBT index are examined using a binary correlation analysis (i.e., R² = 0.89). The results show that: (1) The optimal scale distance varies from 0.6 km to 2.8 km and is influenced by the distance of the travel mode. (2) Central cities, with 54.6% of the total accidents, experiences more rigorous challenges regarding traffic safety than satellite cities. (3) There are many types of black spots in vulnerable communities, but in some specific areas, there are only black spots of non-motor vehicle accidents. Considering the practical significance of the above results, policy makers and traffic engineers are expected to give higher attention to central cities and vulnerable communities or prioritize the implementation of relevant optimization measures.

Big Data Clustering Using Chemical Reaction Optimization Technique: A Computational Symmetry Paradigm for Location-Aware Decision Support in Geospatial Query Processing

The emergence of geospatial big data has opened up new avenues for identifying urban environments. Although both geographic information systems (GIS) and expert systems (ES) have been useful in resolving geographical decision issues, they are not without their own shortcomings. The combination of GIS and ES has gained popularity due to the necessity of boosting the effectiveness of these tools in resolving very difficult spatial decision-making problems. The clustering method generates the functional effects necessary to apply spatial analysis techniques. In a symmetric clustering system, two or more nodes run applications and monitor each other simultaneously. This system is more efficient than an asymmetric system since it utilizes all available hardware and does not maintain a node in a hot standby state. However, it is still a major issue to figure out how to expand and speed up clustering algorithms without sacrificing efficiency. The work presented in this paper introduces an optimized hierarchical distributed k-medoid symmetric clustering algorithm for big data spatial query processing. To increase the k-medoid method’s efficiency and create more precise clusters, a hybrid approach combining the k-medoid and Chemical Reaction Optimization (CRO) techniques is presented. CRO is used in this approach to broaden the scope of the optimal medoid and improve clustering by obtaining more accurate data. The suggested paradigm solves the current technique’s issue of predicting the accurate clusters’ number. The suggested approach includes two phases: in the first phase, the local clusters are built using Apache Spark’s parallelism paradigm based on their portion of the whole dataset. In the second phase, the local clusters are merged to create condensed and reliable final clusters. The suggested approach condenses the data provided during aggregation and creates the ideal clusters’ number automatically based on the dataset’s structures. The suggested approach is robust and delivers high-quality results for spatial query analysis, as shown by experimental results. The proposed model reduces average query latency by 23%.

Measuring Social Modulation of Gaze in Autism Spectrum Condition With Virtual Reality Interviews

Gaze behavior in dyadic conversations can indicate active listening and attention. However, gaze behavior that is different from the engagement expected during neurotypical social interaction cues may be interpreted as uninterested or inattentive, which can be problematic in both personal and professional situations. Neurodivergent individuals, such as those with autism spectrum conditions, often exhibit social communication differences broadly including via gaze behavior. This project aims to support situational social gaze practice through a virtual reality (VR) mock job interview practice using the HTC Vive Pro Eye VR headset. We show how gaze behavior varies in the mock job interview between neurodivergent and neurotypical participants. We also investigate the social modulation of gaze behavior based on conversational role (speaking and listening). Our three main contributions are: (i) a system for fully-automatic analysis of social modulation of gaze behavior using a portable VR headset with a novel realistic mock job interview, (ii) a signal processing pipeline, which employs Kalman filtering and spatial-temporal density-based clustering techniques, that can improve the accuracy of the headset's built-in eye-tracker, and (iii) being the first to investigate social modulation of gaze behavior among neurotypical/divergent individuals in the realm of immersive VR.

Rapid surveillance of COVID-19 by timely detection of geographically robust, alive and emerging hotspots using Particle Swarm Optimizer

A novel virus, called severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has rapidly become a pandemic called Coronavirus disease 2019 (COVID-19). According to the World Health Organization, COVID-19 was first detected in Wuhan city in December 2019 and has affected 216 countries with 9473214 confirmed cases and 484249 deaths globally as on June 26th, 2020. Also, this outbreak continues to grow in many countries like the United States of America (U.S.), Brazil, India, and Russia. To ensure rapid surveillance and better decision-making by government authorities in different countries, it is vital to identify alive and emerging hotspots within a country promptly. State-of-the-art methods based on space-time scan statistics (like SaTScan) are not geographically robust. Also, due to the enumeration of many Spatio-temporal cylinders, the computation cost of Spatio-temporal SaTScan (ST-SaTScan) is very high. In the applications like COVID-19 where we need to detect the emerging hotspots daily as soon as the new count of cases gets updated, ST-SaTScan seems inefficient. Therefore, this paper proposes a Particle Swarm Optimizer-based scheme to timely detect geographically robust, alive, and emerging COVID-19 hotspots in a country. Timely detection can help government officials design better control strategies like increasing testing in hotspots, imposing stricter containment rules, or setting up temporary hospital beds. Performance of ST-SaTScan and proposed scheme have been analyzed for four worst-hit U.S. states for the incubation period of 14 days between June 11th, 2020, and June 24th, 2020. Results indicate that the proposed scheme detects hotspots of a higher likelihood ratio (a measure to indicate the significance of hotspot) than ST-SaTScan in significantly less time. We also applied the proposed scheme to detect the emerging COVID-19 hotspots in all states of the U.S. During the study period, the proposed scheme has detected 104 emerging COVID-19 hotspots.

A GIS-Based Spatiotemporal Modelling of Urban Traffic Accidents in Tabriz City during the COVID-19 Pandemic

The main aim of the present study was to investigate the spatiotemporal trends of urban traffic accident hotspots during the COVID-19 pandemic. The severity index was used to determine high-risk areas, and the kernel density estimation method was used to identify risk of traffic accident hotspots. Accident data for the time period of April 2018 to November 2020 were obtained from the traffic police of Tabriz (Iran) and analyzed using GIS spatial and network analysis procedures. To evaluate the impacts of COVID-19, we used the seasonal variation in car accidents to analyze the change in the total number or urban traffic accidents. Eventually, the sustainability of urban transport was analyzed based on the demographic and land use data to identify the areas with a high number of accidents and its respective impacts for the local residences. Based on the results, the lockdown measures in response to the pandemic have led to significant reductions in road traffic accidents. From the perspective of urban planning, the spatiotemporal urban traffic accident analysis indicated that areas with high numbers of elderly people and children were most affected by car accidents. As we identified the hotspots of urban traffic accidents and evaluated their spatiotemporal correlation with land use and demography characteristics, we conclude that the results of this study can be used by urban managers and support decision making to improve the situation, so that fewer accidents will happen in the future.

Spatiotemporal patterns of mortality associated with chronic non-communicable diseases and child malnutrition at the municipal level in Mexico

Malnutrition is one of the main risk factors related to chronic non-communicable diseases and child undernourishment on a planetary scale. Mexico is one of the countries with the highest levels of malnutrition, but there is also an accelerated increase in overweight or obesity. This study explored the spatiotemporal behaviour of mortality associated with chronic non-communicable diseases such as type II diabetes mellitus, hypertension, ischemic heart disease and cerebrovascular disease. The analysis was carried out at the municipality level for the 2000-2020 period targeting two age groups: ≥60-year olds and 20-59-year olds. In addition, 0-4-year olds were investigated with respect to undernourishment. National databases were gathered and standardized for each disease and SaTScan spatiotemporal cluster analyses were performed. We found that mortality associated with most of the diseases evaluated has increased since 2016 except for mortality caused by child undernourishment, which showed a downward trend during the study period. To focus on active conglomerates of diseases is important as they currently represent a threat to public health. Our results contribute to the potential spatial prioritization of the allocation of resources and campaigns for prevention and treatment of chronic non-communicable diseases and child undernourishment. Generally, geographical studies are fundamental for the discovery of disease aetiology and they provide valuable and timely information to multiple stakeholders.

ST-DEVS: A Methodology Using Time-Dependent-Variable-Based Spatiotemporal Computation

Various real systems are being replicated in cyberspace to solve complex and difficult problems, as exemplified by the digital twin. Once such a software system is implemented, an effective computational method should be applied to the system so that the corresponding real system, connected by networks or sensors, can be indirectly controlled. Considering that all behaviors in real systems occur in space−time, the behavior-related computation in the corresponding software system should adopt both time and space as essential elements to ensure a valid representation of the real system and to effectively perform subsequent computations. Therefore, applying a spatiotemporal computation consisting of time-dependent variables and temporal statements that use such variables is a natural approach to solving problems encountered in the target real system. In this study, the ST-DEVS (spatiotemporal computation DEVS) formalism is proposed to define time-dependent variables and an execution algorithm on temporal logic statements whose arguments are the time-dependent variables; the ST-DEVS is an extension of the discrete event system specification (DEVS). To control real systems with a certain level of autonomy, at least two basic capabilities must be ensured: monitoring and action execution. In this study, action-type temporal logic with time-dependent variables and an action execution algorithm are proposed to illustrate the effectiveness of the spatiotemporal computation process. The previously defined monitoring capability is integrated into ST-DEVS so that monitoring and action execution can be processed uniformly. The proposed approach is designed considering the symmetry between the real world and the cyber world, in that both worlds are influenced by time and space.

Measuring the spatiotemporal evolution of accident hot spots

One reality of transportation systems is that vehicular accidents can happen practically anywhere and at any time. An increasing body of research suggests though that spatial and/or temporal dependencies (i.e., clusters or hot spots) among accidents likely exist. Along with understanding where and when such spatiotemporal dependencies may occur, another important facet to consider is the geographic extent or area associated with the hot spots. For example, an accident hot spot may involve a small, isolated portion of the transportation system or a much more expansive geographic area. Better delineation and quantification of the morphological characteristics of accident hotspots can provide valuable decision support for planning for accident hot spot mitigation and prevention. As the size and shape of accident hot spots may evolve over time, the capability to track such dynamics is vital, especially with respect to the identification of processes effecting hot spot occurrence as well as assessments of the efficacy of efforts to mitigate factors underlying hot spot development. To this end, a Geographical Information Systems (GIS) based framework is outlined to facilitate the analysis of the morphological characteristics of hot spots over time. The analysis framework is applied to a case study of vehicular accidents reported over a two-year period to demonstrate its practical utility. The application results indicate that patterns of change in hot spot morphology can be effectively quantified and a variety of informative spatial and temporal patterns can be detected.

A Spatio-temporal distribution analysis of vesicular stomatitis outbreak in Ecuador, 2018

Vesicular stomatitis (VS) is a viral disease primarily affecting cattle, swine, and equine causing economic losses. It is of particular interest because its outward signs are similar to those of foot-and-mouth disease. Outbreaks of VS occurred in several herds in Ecuador in 2018, affecting principally bovines. In this sense, the present study was conducted to characterize the temporal and spatial dynamics of Vesicular stomatitis occurrence between January and December 2018. During the study period, 583 animals with symptoms of VS were reported. In this way, tissue samples were collected, VS was diagnosed, and outbreaks were defined as herds with a confirmed positive test for the disease. Outbreaks were georeferenced, and Space-time clusters were used to determine zones where the number of reported outbreaks was more significant than expected. A space-time permutation scan statistic (STPSS) was used to identify hot spots of space-time interaction within patterns of the cases reported. Standard Monte Carlo Critical Value was used to test for the cluster's significance. A total of 399 outbreaks were presented in 18 provinces. Spatial scan statistics allowed the detection of four significant space-time clusters of VS outbreaks. The highest incidence was reported around week 35 and week 44, which were observed outbreaks increase in the country's north region. In this sense, clusters coincided with the areas with the highest incidence of outbreaks. Besides, maps showed places where the disease is not shared. The information showed in the present study may contribute to prevents VS spread into regions of Ecuador that is only sporadically affected by the disease. Monitoring in affected zones may lead to quick responses to possible outbreaks issuing alerts when there is a greater than typical risk of spreading the disease

Spatiotemporal clustering and Random Forest models to identify risk factors of African swine fever outbreak in Romania in 2018-2019

African swine fever (ASF) has affected Romania since July 2017, with considerable economic and social consequences, despite the implementation of control measures mainly based on stamping out of infected pig populations. On the basis of the 2973 cumulative recorded cases up to September 2019 among wild boars and domestic pigs, analysis of the epidemiological characteristics could help to identify the factors favoring the persistence and spread of ASF. A statistical framework, based on a random forest methodology, was therefore developed to assess the spatiotemporal features of the epidemics and their relationships with environmental, human, and agricultural factors. The landscape of Romania was associated with the infection dynamics, particularly concerning forested and wetland areas. Waterways were also identified as a pivotal factor, raising questions about possible waterborne transmission since these waterways are often used as a water supply for backyard holdings. However, human activity was clearly identified as the main risk factor for the spread of ASF. Although the situation in Romania cannot be directly transposed to intensive pig farming countries, the findings of this study highlight the need for strict biosecurity measures on farms, and during transportation, to avoid ASF transmission at large geographic and temporal scales.

Toward Detecting Infection Incidence in People With Type 1 Diabetes Using Self-Recorded Data (Part 1): A Novel Framework for a Personalized Digital Infectious Disease Detection System

BACKGROUND

Type 1 diabetes is a chronic condition of blood glucose metabolic disorder caused by a lack of insulin secretion from pancreas cells. In people with type 1 diabetes, hyperglycemia often occurs upon infection incidences. Despite the fact that patients increasingly gather data about themselves, there are no solid findings that uncover the effect of infection incidences on key parameters of blood glucose dynamics to support the effort toward developing a digital infectious disease detection system.

OBJECTIVE

The study aims to retrospectively analyze the effect of infection incidence and pinpoint optimal parameters that can effectively be used as input variables for developing an infection detection algorithm and to provide a general framework regarding how a digital infectious disease detection system can be designed and developed using self-recorded data from people with type 1 diabetes as a secondary source of information.

METHODS

We retrospectively analyzed high precision self-recorded data of 10 patient-years captured within the longitudinal records of three people with type 1 diabetes. Obtaining such a rich and large data set from a large number of participants is extremely expensive and difficult to acquire, if not impossible. The data set incorporates blood glucose, insulin, carbohydrate, and self-reported events of infections. We investigated the temporal evolution and probability distribution of the key blood glucose parameters within a specified timeframe (weekly, daily, and hourly).

RESULTS

Our analysis demonstrated that upon infection incidence, there is a dramatic shift in the operating point of the individual blood glucose dynamics in all the timeframes (weekly, daily, and hourly), which clearly violates the usual norm of blood glucose dynamics. During regular or normal situations, higher insulin and reduced carbohydrate intake usually results in lower blood glucose levels. However, in all infection cases as opposed to the regular or normal days, blood glucose levels were elevated for a prolonged period despite higher insulin and reduced carbohydrates intake. For instance, compared with the preinfection and postinfection weeks, on average, blood glucose levels were elevated by 6.1% and 16%, insulin (bolus) was increased by 42% and 39.3%, and carbohydrate consumption was reduced by 19% and 28.1%, respectively.

CONCLUSIONS

We presented the effect of infection incidence on key parameters of blood glucose dynamics along with the necessary framework to exploit the information for realizing a digital infectious disease detection system. The results demonstrated that compared with regular or normal days, infection incidence substantially alters the norm of blood glucose dynamics, which are quite significant changes that could possibly be detected through personalized modeling, for example, prediction models and anomaly detection algorithms. Generally, we foresee that these findings can benefit the efforts toward building next generation digital infectious disease detection systems and provoke further thoughts in this challenging field.

Analyzing traffic violation behavior at urban intersections: A spatio-temporal kernel density estimation approach using automated enforcement system data

The Automated Enforcement System (AES) has become the most important traffic enforcement system in China. In this study, a spatio-temporal kernel density estimation (STKDE) model, integrating spatio-temporal statistics and three-dimensional visualization techniques, was applied to reveal the spatial and temporal patterns of traffic violation behavior at urban intersections. The multivariate Gaussian kernel function was selected for space and time density estimation, as it has been shown to be a good arbitrary probability density function for continuous multivariate data. Because the STKDE model builds a space-time cube that adopts different colors of voxels to visualize the density of traffic violations, an optimal bandwidth selector that combines unconstrained pilot bandwidth matrices with a data-driven method was selected for achieving the best visualization result. The raw AES traffic violation data over 200 weekdays from 69 intersections in the city of Wujiang were empirically analyzed. The results show that the STKDE space-time cube made it easier to detect the spatio-temporal patterns of traffic violations than did the traditional hotspots map. An interesting finding was that traffic sign violations and traffic marking violations were primarily concentrated not in regular peak hours, but during the time period of 14:00-16:00, which indicates that these intersections were the most congested during this period. Primarily, the STKDE model identified seven patterns of spatio-temporal traffic violation hotspots and coldspots. These results are important because their prediction of temporal trends of traffic violations may help contribute toward the understanding and improvement of intersection safety problems.

An Integrated Approach for Spatio-Temporal Cholera Disease Hotspot Relation Mining for Public Health Management in Punjab, Pakistan

Public health management can generate actionable results when diseases are studied in context with other candidate factors contributing to disease dynamics. In order to fully understand the interdependent relationships of multiple geospatial features involved in disease dynamics, it is important to construct an effective representation model that is able to reveal the relationship patterns and trends. The purpose of this work is to combine disease incidence spatio-temporal data with other features of interest in a mutlivariate spatio-temporal model for investigating characteristic disease and feature patterns over identified hotspots. We present an integrated approach in the form of a disease management model for analyzing spatio-temporal dynamics of disease in connection with other determinants. Our approach aligns spatio-temporal profiles of disease with other driving factors in public health context to identify hotspots and patterns of disease and features of interest in the identified locations. We evaluate our model against cholera disease outbreaks from 2015–2019 in Punjab province of Pakistan. The experimental results showed that the presented model effectively address the complex dynamics of disease incidences in the presence of other features of interest over a geographic area representing populations and sub populations during a given time. The presented methodology provides an effective mechanism for identifying disease hotspots in multiple dimensions and relation between the hotspots for cost-effective and optimal resource allocation as well as a sound reference for further predictive and forecasting analysis.

Storage Efficient Trajectory Clustering and k-NN for Robust Privacy Preserving Spatio-Temporal Databases

The need to store massive volumes of spatio-temporal data has become a difficult task as GPS capabilities and wireless communication technologies have become prevalent to modern mobile devices. As a result, massive trajectory data are produced, incurring expensive costs for storage, transmission, as well as query processing. A number of algorithms for compressing trajectory data have been proposed in order to overcome these difficulties. These algorithms try to reduce the size of trajectory data, while preserving the quality of the information. In the context of this research work, we focus on both the privacy preservation and storage problem of spatio-temporal databases. To alleviate this issue, we propose an efficient framework for trajectories representation, entitled DUST (DUal-based Spatio-temporal Trajectory), by which a raw trajectory is split into a number of linear sub-trajectories which are subjected to dual transformation that formulates the representatives of each linear component of initial trajectory; thus, the compressed trajectory achieves compression ratio equal to M : 1 . To our knowledge, we are the first to study and address k-NN queries on nonlinear moving object trajectories that are represented in dual dimensional space. Additionally, the proposed approach is expected to reinforce the privacy protection of such data. Specifically, even in case that an intruder has access to the dual points of trajectory data and try to reproduce the native points that fit a specific component of the initial trajectory, the identity of the mobile object will remain secure with high probability. In this way, the privacy of the k-anonymity method is reinforced. Through experiments on real spatial datasets, we evaluate the robustness of the new approach and compare it with the one studied in our previous work.