Search

In Bangladesh, groundwater is the main source of both drinking water and irrigation. Suction lift pumps and force mode of operation are the predominant technologies for groundwater abstraction in Bangladesh. For a sustainable usage policy, it is thus important to identify which technology would be more appropriate for which area in Bangladesh. With that aim in mind, this paper proposes a methodology that leverages the power of machine learning that can potentially learn intricate relationships between the (annual maximum) groundwater level (GWL) and the relevant hydrogeological factors (HGFs). A number of machine learning algorithms—both classification and regression models—was trained. Our classification models were trained as a binary classifier to predict the abstraction technology of a particular point. Notably, our best classification model was based on the Random Forest algorithm, which achieved an accuracy of 91% and an excellent value of 96% for the area under receiver operating characteristics curve, indicating its strong discriminant capability. We also identified (elevation derived from) digital elevation model, specific yield and lithology as the three most important HGFs for GWL in Bangladesh. On the other hand, to predict the actual (annual maximum) GWL, we employed a two-stage approach, where we first employed the above-mentioned classification model to identify the suitable abstraction technology for the point of interest and subsequently predict the actual GWL using the appropriate Random Forest regressor. This also had a reasonable accuracy (minimum absolute error was less than 1 for suction mode and less than 5 for the force mode). Finally, using our prediction models, we prepared groundwater (technology) maps for the whole Bangladesh.

Background Limited timely, cost-effective, and regional availability of healthcare data is considered one of the limiting factors for timely analyses in the field of health services research and thus for healthcare delivery to the general population. Thus, Internet search engine analyses are coming into focus in this context. Objectives What contribution can data on the volume of Internet searches for various diseases make to the health care of the German population? Where is the potential and where are the limitations? Methods A review of the current literature and a selective overview of Internet search engine analyses of dermatological, allergological, and infectious diseases published in the last 4 years in Germany were performed. Results By analyzing web search data, temporal developments such as seasonality, months with the highest interest, and geographical differences can be mapped at the national, state (Bundeslander), and city level and major points of interest (e.g., skin cancer of the eye or anal itching) regarding a certain health topic can be identified. In addition, some studies were able to show correlations between search volume and external factors (e.g., temperature, care structure) and to registered cases (e.g., skin cancer, Lyme disease). Conclusion Web search data, given the limitations noted, are able to directly provide spatiotemporal mapping regarding the needs of the Internet-using population. They are particularly useful in situations where traditional health data are limited or unavailable.

With the continuous development of urbanization in China, the country’s growing population brings great challenges to urban development. By mastering the refined population spatial distribution in administrative units, the quantity and agglomeration of population distribution can be estimated and visualized. It will provide a basis for a more rational urban planning. This paper takes Beijing as the research area and uses a new Luojia1–01 nighttime light image with high resolution, land use type data, Points of Interest (POI) data, and other data to construct the population spatial index system, establishing the index weight based on the principal component analysis. The comprehensive weight value of population distribution in the study area was then used to calculate the street population distribution of Beijing in 2018. Then the population spatial distribution was visualize using GIS technology. After accuracy assessments by comparing the result with the WorldPop data, the accuracy has reached 0.74. The proposed method was validated as a qualified method to generate population spatial maps. By contrast of local areas, Luojia 1–01 data is more suitable for population distribution estimation than the NPP/VIIRS (Net Primary Productivity/Visible infrared Imaging Radiometer) nighttime light data. More geospatial big data and mathematical models can be combined to create more accurate population maps in the future.

Gaussian process regression is a flexible regression scheme but suffers from its high computational complexity regarding the inversion of a matrix with the same size as the training dataset. Aggregation method is one of the approximation techniques for reducing the complexity. In this paper, we propose a novel aggregation method, Nested Aggregation of Experts using Inducing Points (NAE-IP), which is an extension of a conventional method and enables dimensionality reduction by making use of the idea of linear sketching. There are some options for selecting inducing points in the proposed method. The options can introduce test points of interest as inducing points, albeit at the cost of slightly higher computational complexity. The other options exploiting less informative inducing points can yield a significant reduction of the computational complexity. The proposed NAE-IP is theoretically guaranteed to have consistency under certain conditions. Results of our computational experiments using synthetic and real data show that the proposed method achieves lower prediction error and even lower computing time than conventional methods.

Recommender Systems (RSs) are often assessed in off-line settings by measuring the system precision in predicting the observed user’s ratings or choices. But, when a precise RS is on-line, the generated recommendations can be perceived as marginally useful because lacking novelty. The underlying problem is that it is hard to build an RS that can correctly generalise, from the analysis of user’s observed behaviour, and can identify the essential characteristics of novel and yet relevant recommendations. In this paper we address the above mentioned issue by considering four RSs that try to excel on different target criteria: precision, relevance and novelty. Two state of the art RSs called SKNN and s-SKNN follow a classical Nearest Neighbour approach, while the other two, Q-BASE and Q-POP PUSH are based on Inverse Reinforcement Learning. SKNN and s-SKNN optimise precision, Q-BASE tries to identify the characteristics of POIs that make them relevant, and Q-POP PUSH, a novel RS here introduced, is similar to Q-BASE but it also tries to recommend popular POIs. In an off-line experiment we discover that the recommendations produced by SKNN and s-SKNN optimise precision essentially by recommending quite popular POIs. Q-POP PUSH can be tuned to achieve a desired level of precision at the cost of losing part of the best capability of Q-BASE to generate novel and yet relevant recommendations. In the on-line study we discover that the recommendations of SKNN and Q-POP PUSH are liked more than those produced by Q-BASE. The rationale of that was found in the large percentage of novel recommendations produced by Q-BASE, which are difficult to appreciate. However, Q-BASE excels in recommending items that are both novel and liked by the users.

With the rapid development of Information Technology, there exist massive amounts of data available on the Internet, which result in a severe information overload problem. Especially, it becomes more and more challenging but necessary to help users find the contents or services that they really need. To address the problem mentioned above, recommender systems have been developed to exploit user’s historical behavior data and provide personalized services for promoting customer experiences in many fields, such as Point of Interest (POI) applications, multimedia services, and e-commerce websites. Specifically, in POI recommendation, user’s next check-in behaviors depend on both long- and short-term preferences. However, traditional recommendation methods often ignore the dynamic changes of user’s short-term preferences over time, which limits their performance. Besides, many existing methods cannot fully exploit the complex correlations and transitions between POI in check-ins sequences. In this paper, we propose an A ttentive S equential model based on G raph N eural N etwork (ASGNN) for accurate next POI recommendation. Specifically, ASGNN firstly models user’s check-in sequences as graphs and then use Graph Neural Networks (GNN) to learn the informative low-dimension latent feature vectors (embeddings) of POIs. Secondly, a personalized hierarchical attention network is adopted to exploit complex correlations between users and POIs in check-in sequences and capture user’s long- and short-term preferences. Finally, we perform the next POI recommendation via leveraging user’s long- and short-term preferences obtained from their behavior sequences with ASGNN. Extensive experiments are conducted on three real-world check-in datasets, and the results demonstrate that the proposed model ASGNN outperforms baselines, including some state-of-the-art methods.

The learning similarity between users and points of interests (POIs) is an important function in location-based social networks (LBSN), which could primarily benefit multiple location-based services, especially in terms of POI recommendation. As one of the well-known recommender technologies, Collaborative Filtering (CF) has been employed to a great extent in literature, due to its simplicity and interpretability. However, it is facing a great challenge in generating accurate similarities between users or items, because of data sparsity. Traditional similarity measures which rely on explicit user feedback (e.g., rating) are not applicable for implicit feedback (e.g., check-ins). In this study, we propose multi-criteria user–user and POI–POI similarity measures, based on the dominance concept. In this regard, we incorporate geographical, temporal, social, preferential and textual criteria into the similarity measures of CF. We are interested in measuring POI similarity from a location perspective, by taking into account the influence of the dominance concept on multiple dimensions of POIs. To evaluate the effectiveness of our method, a series of experiments are conducted with a large-scale real dataset, collected from the Foursquare of two cities in terms of POI recommendation. Experimental results revealed that the proposed method significantly outperforms the existing state-of-the-art alternatives. A further experiment demonstrates the superiority of the proposed method in alleviating sparsity and handling the cold-start problem affecting POI recommendation.

Real estate contributes significantly to all major economies around the world. In particular, house prices have a direct impact on stakeholders, ranging from house buyers to financing companies. Thus, a plethora of techniques have been developed for real estate price prediction. Most of the existing techniques rely on different house features to build a variety of prediction models to predict house prices. Perceiving the effect of spatial dependence on house prices, some later works focused on introducing spatial regression models for improving prediction performance. However, they fail to take into account the geo-spatial context of the neighborhood amenities such as how close a house is to a train station, or a highly-ranked school, or a shopping center. Such contextual information may play a vital role in users’ interests in a house and thereby has a direct influence on its price. In this paper, we propose to leverage the concept of graph neural networks to capture the geo-spatial context of the neighborhood of a house. In particular, we present a novel method, the geo-spatial network embedding (GSNE), that learns the embeddings of houses and various types of points of interest (POIs) in the form of multipartite networks, where the houses and the POIs are represented as attributed nodes and the relationships between them as edges. Extensive experiments with a large number of regression techniques show that the embeddings produced by our proposed GSNE technique consistently and significantly improve the performance of the house price prediction task regardless of the downstream regression model. Relevant source code for GSNE is available at: https://github.com/sarathismg/gsne .

Point of interest (POI) recommendation problem in location based social network (LBSN) is of great importance and the challenge lies in the data sparsity, implicit user feedback and personalized preference. To improve the precision of recommendation, a tensor decomposition based collaborative filtering (TDCF) algorithm is proposed for POI recommendation. Tensor decomposition algorithm is utilized to fill the missing values in tensor (user-category-time). Specifically, locations are replaced by location categories to reduce dimension in the first phase, which effectively solves the problem of data sparsity. In the second phase, we get the preference rating of users to POIs based on time and user similarity computation and hypertext induced topic search (HITS) algorithm with spatial constraints, respectively. Finally the user’s preference score of locations are determined by two items with different weights, and the Top-N locations are the recommendation results for a user to visit at a given time. Experimental results on two LBSN datasets demonstrate that the proposed model gets much higher precision and recall value than the other three recommendation methods.

Point of interest (POI) recommendation is a fundamental task in location-based social networks (LBSN). The increasing proliferation of LBSNs brings about considerable amounts of user-generated check-in data. Such data can significantly contribute to understanding user behaviors, based on which personalized recommendations can be efficiently derived. Spatial and temporal effects are crucial factors in the user’s decision-making for choosing a POI to visit. Most existing methods treat them as two independent features and cannot accurately capture users’ interests. We argue that spatial and temporal effects should be analyzed simultaneously in POI recommendations. To this end, we propose a S patioT emporal heterogeneous information Network (HIN)-based PO I RE commendation model (STORE) to model various heterogeneous context features, e.g., the joint spatiotemporal effects, types of POI, and social relations. Specifically, we defined the spatiotemporal effects entity (St) in HIN to model the joint spatiotemporal effects. Instead of modeling the traditional two-way interaction , we further design a four-way neural interaction model . In this way, our model can effectively mine and extract useful information from the meta-path-based context and spatiotemporal effects, thereby improving recommendation performance. We conduct extensive experiments on two real-world datasets, and the results demonstrate that the STORE model outperforms the best baseline by about 12% in NDCG@5 and 11% in Rec@5.

This paper investigates the impact of street pattern, metro stations, and density of urban functions on pedestrian distribution in Tianjin, China. Thirteen neighborhoods are selected from the city center and suburbs. Pedestrian and vehicle volumes are observed through detailed gate count from 703 street segments in these neighborhoods. Regression models are constructed to analyze the impact of the street pattern, points of interest (POIs), and vehicle and metro accessibility on pedestrian volumes in each neighborhood and across the city. The results show that when analyzing all neighborhoods together, local street connectivity and POIs had a strong influence on pedestrian distribution. Proximity to metro stations and vehicle accessibility had a minor impact. When analyzing each neighborhood separately, both local- and city-scale street patterns affect pedestrian distributions. These findings suggest that the street pattern provides a base layer for metro stations to attract both the emergence of active urban functions and pedestrian movement.

With the rapid development of global positioning systems, cellular networks, and relative technologies, people can request location-based services (LBSs) from the service provider using a handheld device quickly and easily. In recent years, privacy issues related to LBS services have attracted a lot of attention. In this paper, we focus on the difficult problem of k-nearest neighbor query based on cryptography. Instead of using the traditional Hilbert curve to store the information of the points of interest in the target map, we use the Z-order curve and quad-tree to store location information. In this way, it improves the efficiency of localization and is able to support distributed storage. Meanwhile, the algorithm uses the homomorphic encryption algorithm ASM-PH that supports additive and multiplicative homomorphism to keep the query secret, which can save the user’s cost by calculating the encrypted content with the LBS server or the storage devices when only the user knows the encrypted content. Experimental results show that the algorithm has high query accuracy and low user encryption and decryption cost. At the same time, we propose a privacy query scheme on distributed storage that supports the scheme. Based on distributed storage and quadratic residual theorem, this scheme is a secure and efficient LBS user privacy protection scheme.

This paper presents a framework for the use of unmanned aerial vehicles (UAVs) equipped with cameras and wireless sensors to search an area after the occurrence of a tornado. This paper attempts to demonstrate how tornado weather data can be incorporated into search and rescue procedures to allocate and route the UAVs. Traditionally, the time to assess and search an area after a tornado strikes is on the order of several days. Incorporating UAVs into a search and rescue team’s available tools can reduce this time span to the order of hours. These methods are applied and model in this project to three real-world cases. Several methods for creating ”waypoints,” points of interest for the UAVs to inspect, to route the UAVs were tested. An analysis was performed to compare the time it took to generate the waypoints and the resulting objective function value. It is observed that while there is an opportunity to use exact methods to generate waypoints, our proposed heuristic is sufficient for the rapid response needed in post-disaster relief.

It has been gradually recognized that mobile phones can be used as a practical and promising way to identify individual travel trajectories. Researchers have developed various approaches to detecting human mobility and trip characteristics including trip origin–destination, travel modes, trip purposes based on mobile phone data. Among these researches, trip purpose detection has drawn less attention from researchers. This paper presents our work to investigate a set of machine learning approaches to identifying the trip purposes for tourists based on mobile signaling data combined with sampling surveys and point of interest (POI) data. Five machine learning algorithms, including support vector machine, decision tree, random forest, artificial neural network, and deep stacked auto-encoded (DSAE), have been employed to infer trip purposes under multiple scenarios. Four scenarios have been designed by considering the POI information around trip end [a 500 m buffer or Thiessen polygon (the coverage of the base station theoretically)] and training dataset selection (equal probabilities selection or equal proportion selection). The accuracy of trip purpose classification with machine learning algorithms has compared under different scenarios. The highest accuracy of 93.47% for the test dataset is achieved based on DSAE model under the scenario of a trip end 500 m buffer and equal probabilities selection. The experimental results indicate that the methodology developed with machine learning algorithms based on mobile signaling data combined with sample travel survey is expected as an alternative way to traditional travel surveys for trip purposes.

With the popularization of smart devices and the rapid development of Internet of Things (IoT), location-based social networks (LBSNs) are growing rapidly. As a crucial personalized location service of LBSNs, point-of-interest (POI) recommendation has become a research hotspot. However, due to the use of personal information, POI recommendation system brings serious risks of privacy disclosure. Existing studies mainly focused on improving recommendation performance while ignoring privacy issues. To cope with the challenges, we propose a POI recommendation framework with users’ privacy preserving in an IoT environment based on local differential privacy (LDP). We first design an LDP-friendly POI recommendation method based on improved Hawkes process (HawkesRec) to integrate users’ long-term static and time-varying preferences. Then we put forward a privacy preserving recommendation framework based on HawkesRec and local differential privacy to protect the visited POIs and recommendation results of users. Experimental results over three real-world datasets demonstrate that the proposed solution achieves better performance than other baselines and has a good capability of privacy preserving.

Bicycling is an increasingly popular mode of travel in Canadian urban areas, like the Greater Toronto and Hamilton Area (GTHA). While trip origins and destinations can be inferred from travel surveys, data on route choice is often not collected which makes it challenging to capture the attributes of routes travelled by people who cycle. With new algorithms for cycle routing it is now possible to infer routes. Using bicycle trip records from the most recent regional travel survey, a spatial interaction model is developed to investigate the built environment correlates of bicycling flows in Hamilton, Ontario, a mid-sized city part of the GTHA. A feature of the analysis is the use of CycleStreets to compare the distance and time according to different routes inferred between trip zones of origin and destination. In addition, network autocorrelation is accounted for in the estimated models. The most parsimonious model suggests that shortest-path quietest routes that minimize traffic best explain the pattern of bicycle trip flows in Hamilton. Commercial and office locations and points of interest at the zone of origin negatively correlate with the production of trips, while different land uses and the availability of jobs at the zone of destination are trip attractors. The use of a route planner offers a novel approach to modelling and understanding bicycling flows within a city. This may be useful for transportation planners to infer different types of routes that bicyclists may seek out and consider these in travel demand models.

Recent years have witnessed the rapid prevalence of big data and it is necessary for mobile application to filter out information for users. As a significant means of information retrieval, recommendation system that recommends a ranked list of items to users according to their preferences has become a key functionality in Location-Based Social Networks (LBSNs). Point of interest (POI) recommendation that aims to recommend satisfactory locations that users may be interested in plays an important role in LBSNs. However, the traditional POI recommendation uses the original user-POI matrix, which faces a huge challenge of data sparsity because most users just check in a few POIs in their phones. Moreover, it is hard for POI recommendation to give reasonable explanations on why user will visit these locations that we recommend. Therefore, in terms of the challenges mentioned above, we propose a new POI recommendation model called PR-RCUC that uses region-based collaborative filtering and user-based mobile context. Firstly, we cluster locations into different regions and enhance the traditional collaborative filtering with region factor. Secondly, we capture the preferences of users on mobile context such as geographical distance and location category. Thirdly, by combing the two parts we present, we finish the final computation of prediction score and recommend Top-K locations to users. The results of experiments on two real-world datasets collected from Foursquare demonstrate the PR-RCUC model outperforms some popular recommendation algorithms and achieves our expected goal.

Point of interest (POI) recommendation can help people explore new regions. Existing methods tend to exploit different information to improve recommendation performance. However, there are still challenges in how to integrate different information flexibly and effectively. Therefore, we propose a multi-task embedding based personalized POI recommendation method (MTEPR). On one hand, multi-information (sequential, social, temporal, geographical, semantic, gender, and preference information) are exploited to embed users and POIs. On the other hand, MTEPR incorporates sequence and graph embedding methods to model user location history, as well as to preserve the relationships between users, POIs, and different information. Specifically, sequential information is captured by applying a sequence embedding method on users’ check-in sequences, and other information are captured by applying graph embedding methods on User–User, User-Time Slot, POI-Time Slot, POI-Region Hierarchy, POI-Category Hierarchy, User-Gender, and User-POI graphs. The scores of candidate POIs are calculated based on the embeddings to make recommendations. We conduct extensive experiments to evaluate the performance of MTEPR on two real-world datasets, and the results show its superiority over baselines. We also study the impact of different information, and the results reveal that temporal and semantic information contribute most to improving recommendation performance.

Tourism is one of the largest service industries and a popular leisure activity participated by people with friends or family. A significant problem faced by the tourists is how to plan sequences of points of interest (POIs) that maintain a balance between the group preferences and the given temporal and spatial constraints. Most traditional group itinerary recommendation methods adopt predefined preference aggregate strategies without considering the group members’ distinctive characteristics and inner relations. Besides, POI textual information is beneficial to capture overall group preferences but is rarely considered. With these concerns in mind, this paper proposes an AMT-IRE (short for Attentive Multi-Task learning-based group Itinerary REcommendation) framework, which can dynamically learn the inner relations between group members and obtain consensus group preferences via the attention mechanism. Meanwhile, AMT-IRE integrates POI categories and POI textual information via another attention network. Finally, the group preferences are used in a variant of the orienteering problem to recommend group itineraries. Extensive experiments on six datasets validate the effectiveness of AMT-IRE.

The success of new scientific areas can be assessed by their potential for contributing to new theoretical approaches aligned with real-world applications. The Euclidean distance transform (EDT) has fared well in both cases, providing a sound theoretical basis for a number of applications, such as median axis transform, fractal analysis, skeletonization, and Voronoi diagrams. Despite its wide applicability, the discrete form of the EDT includes interesting properties that have not yet been fully exploited in the literature. In this paper, we are particularly interested in the properties of 1) working with multiple objects/labels; and 2) identifying and counting equidistant pixels/voxels from certain points of interest. In some domains (such as dataset classification, texture, and complexity analysis), the result of applying the EDT transform with different objects, and their respective tied distances, may compromise the performance. In this sense, we propose an efficient modification in the method presented in [1], which leads to a novel approach for computing the distance transform in a space with multiple objects, and for counting equidistant pixels/voxels.

Ultra-wideband (UWB) bio-radar is a promising technology for the contactless detection and wireless monitoring of stationary living persons remotely. However the optional detection approach is fewer and the accuracy is less. Thus some other alternative methods for the detection of living persons are urgently required. Here, we investigated the detection of living persons by extracting human respiratory signals based on the machine learning under non-line of sight (NLOS) multipath environments. Extreme learning machine (ELM) was utilized to determine if one person is present in the detection environment or not based on the distributions of vital signs acquired from the statistics fingerprint analysis (SFA). Then, the life sign points of interest (LSPOI) can be defined to measure the frequency of human cardiopulmonary movement when the living persons in present in the environments. Meanwhile the amount of data can be reduced and the system efficiency can be enhanced which plays a key role in human detection. The detection results indicate the developed algorithm outperform the known references.

Motivated by location-based social networks which allow people to access location-based services as a group, we study a novel variant of optimal sequenced route (OSR) queries, optimal sequenced route for group meetup (OSR-G) queries. OSR-G query aims to find the optimal meeting POI (point of interest) such that the maximum users’ route distance to the meeting POI is minimized after each user visits a number of POIs of specific categories (e.g., gas stations, restaurants, and shopping malls) in a particular order. To process OSR-G queries, we first propose an OSR-Based (OSRB) algorithm as our baseline, which examines every POI in the meeting category and utilizes existing OSR (called E-OSR) algorithm to compute the optimal route for each user to the meeting POI. To address the shortcomings (i.e., requiring to examine every POI in the meeting category) of OSRB, we propose an upper bound based filtering algorithm, called circle filtering (CF) algorithm, which exploits the circle property to filter the unpromising meeting POIs. In addition, we propose a lower bound based pruning (LBP) algorithm, namely LBP-SP which exploits a shortest path lower bound to prune the unqualified meeting POIs to reduce the search space. Furthermore, we develop an approximate algorithm, namely APS, to accelerate OSR-G queries with a good approximation ratio. Finally the experimental results show that both CF and LBP-SP outperform the OSRB algorithm and have high pruning rates. Moreover, the proposed approximate algorithm runs faster than the exact OSR-G algorithms and has a good approximation ratio.

Modeling point-of-Interest (POI) for recommendations is vital in location-based social networks, yet it is a challenging task due to data sparsity and cold-start problems. Most existing approaches incorporate content features into a probabilistic matrix factorization model using unsupervised learning, which results in inaccuracy and weak robustness of recommendations when data is sparse, and the cold-start problems remain unsolved. In this paper, we propose a deep multimodal rank learning (DMRL) model that improves both the accuracy and robustness of POI recommendations. DMRL exploits temporal dynamics by allowing each user to have time-dependent preferences and captures geographical influences by introducing spatial regularization to the model. DMRL jointly learns ranking for personal preferences and supervised deep learning models to create a semantic representation of POIs from multimodal content. To make model optimization converge more rapidly while preserving high effectiveness, we develop a ranking-based dynamic sampling strategy to sample adverse or negative POIs for model training. We conduct experiments to compare our DMRL model with existing models that use different approaches using two large-scale datasets obtained from Foursquare and Yelp. The experimental results demonstrate the superiority of DMRL over the other models in creating cold-start POI recommendations and achieving excellent and highly robust results for different degrees of data sparsity.

The aim of our study was to recommend a novel method for measuring the distance from the umbilicus to intra-abdominal organs, as well as recommend an instrument length that would accommodate transumbilical laparoendoscopic single-site (U-LESS) surgeries to these areas. From CT scans of 50 men and 50 women, we calculated the distance from the umbilicus to 11 intra-abdominal points of interest using two triangles oriented perpendicular to each other. Using known lengths of the triangles, we used the Pythagorean theorem to calculate distances with and without insufflation. Distances were measured from the umbilicus to the xyphoid process, superior most aspect of the spleen, neck of the gallbladder, bifurcation of the descending aorta, adrenal glands, superior pole(s) of the kidneys, inferior most aspect of the inguinal canal, suprapubic margin, and the apex of the prostate (or female bladder neck). We found that an instrument working length of 43 cm would be sufficient to facilitate U-LESS surgery for all of our patients to each of the measured points of interest. The technique described in this paper serves as a useful method by which to measure the distance from the umbilicus to any intra-abdominal point of interest. These measurements would allow surgeons to correctly select instruments with adequate length when planning to perform U-LESS surgery.

More lightweight structure and higher control bandwidth are highly desirable in next-generation motion stages, satisfying the continuously increasing requirements in throughput and accuracy. However, these lead to more severe flexible deformation, causing that the estimation accuracy of the generalized displacements of a point of interest (POI) cannot be guaranteed under the rigid-body assumption. In this paper, a method for estimating the generalized displacement of the POI using critical modes is proposed. This method can realize a more accurate estimation under the limited measurement points. In this method, since the number of measurement points is limited, the selection criterion of the critical modes is firstly proposed for the over-actuator system; then, with regard to the estimation accuracy, the influences of the measurement layout and the residual modes on the estimation matrix are analyzed mathematically, and a performance measure is proposed for evaluating this method from the perspective of system control. In the verification section, the validity of the estimation method is demonstrated through numerical simulation and an experiment on a representative but straightforward case using a plate structure.

A city contains a variety of different urban functions with referring to the purpose of land use to support the diverse needs of urban residents, such as residence, working and recreation. Exploring urban functional zones is a critical task, which provides valuable applications for business site selection, transportation management and urban planning. It is well known that location information and human mobility semantics both are significant factors for identifying urban functional zones, just considering one factor is not effective. However, most of existing techniques capture the transformation of functional zones and interpret the results based solely on location or mobility semantics, and lack the capacity to deal with the multifaceted features of urban data. To tackle these problems, in this paper, we propose an interactive visual analytics system for effectively exploring urban functional zones based on spatio-temporal OD data and Points of Interest data. We first adaptively partition the territory into region units based on adaptive blue noise sampling method, extract POI feature matrix (location information) as a prior knowledge, model multidimensional spatio-temporal OD data as a tensor for addressing multifaceted features and propose an augment tensor-based algorithm that enables users to simultaneously combine mobility semantics and inherent location information for identifying functional zones. In addition, we design a set of visual encodings to better understand and interpret the results in a visual and intuitive manner. This system has been demonstrated using two case studies with a real-world dataset of HangZhou city and domain-expert interviews.

In order to calculate the spatial distribution of high-resolution air-pollutant levels, the land use regression (LUR) model can be an effective method due to the comprehensive consideration of various factors. Traditional LUR models mostly use predefined buffers, which have the disadvantage of not matching high-resolution data well. In order to get a better-fitting model, a few researches have proposed new buffer selection methods. To solve this problem, we propose a new optimal buffer selection method based on the dichotomy to improve the correlation between predicted variables and pollutant concentration. For some socioeconomic data with high spatial resolution that cannot be obtained, for example, building data is used instead of population density data. Compared with the model with the predefined buffers, the model with our buffer selection strategy explained additional 5% variability in measured concentrations, in terms of the R2 of the final model. Our model explained 98% of the samples, and the deviation (1.78%) and root mean square error (5.17 μg/m) were small. It means that the LUR model with our buffer selection strategy can be used as a fit method to better describe spatial variability in atmospheric pollutant levels, which will be conducive to epidemiological research and urban environmental planning.

The various performances of buses at stations bring lots of difficulties for operators to manage them to improve the service quality. This paper proposes a data-driven framework to analyze the patterns of stations with network structure data, points of interest (POI) data and vehicle global positioning system (GPS) trajectory data. First, we build six indicators based on these data to measure the performance from station perspective. The results show that the number of POI around stations within 1 kilometer follows an exponential distribution. Moreover, the average headway and headway deviation of stations follow lognormal distributions. Second, we use agglomerative hierarchical clustering method to divided bus stations into different groups. Results indicate that the bus stations of Jinan could be divided into four groups with obvious characteristics. The findings could help operators to make exclusive strategies to manage bus systems.

The coronavirus disease 2019 (COVID-19) pandemic markedly changed human mobility patterns, necessitating epidemiological models that can capture the effects of these changes in mobility on the spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)1. Here we introduce a metapopulation susceptible-exposed-infectious-removed (SEIR) model that integrates fine-grained, dynamic mobility networks to simulate the spread of SARS-CoV-2 in ten of the largest US metropolitan areas. Our mobility networks are derived from mobile phone data and map the hourly movements of 98 million people from neighbourhoods (or census block groups) to points of interest such as restaurants and religious establishments, connecting 56,945 census block groups to 552,758 points of interest with 5.4 billion hourly edges. We show that by integrating these networks, a relatively simple SEIR model can accurately fit the real case trajectory, despite substantial changes in the behaviour of the population over time. Our model predicts that a small minority of 'superspreader' points of interest account for a large majority of the infections, and that restricting the maximum occupancy at each point of interest is more effective than uniformly reducing mobility. Our model also correctly predicts higher infection rates among disadvantaged racial and socioeconomic groups2-8 solely as the result of differences in mobility: we find that disadvantaged groups have not been able to reduce their mobility as sharply, and that the points of interest that they visit are more crowded and are therefore associated with higher risk. By capturing who is infected at which locations, our model supports detailed analyses that can inform more-effective and equitable policy responses to COVID-19.

Point-of-Interest (POI) recommendation has become an important service on Location-Based Social Networks (LBSNs). In order to improve the performance of recommendation, besides the check-in data generated in LBSNs, researchers are striving to exploit various auxiliary information such as social relation among users and geographical influence among neighbourhood POIs. However, existing works cannot effectively study the diverse degrees of influence from user’s friends, neither are they able to capture the feature impacts of POIs in the preference modelling process. To overcome these challenges, by making use of a M ulti-A ttention N etwork to learn the C ontextual influence of both users and POIs, this paper presents a model named MANC for POI recommendation. The MANC model consists of two parts: a user-friend module and a POI neighbourhood module. Unlike existing works which treat the influences from different friends of a user equally, the user-friend module in MANC applies an attention-based memory component to generate specific relation vectors which can differentiate the influence from the aspect of interest, and applies a friend-level attention network to adaptively capture the preferences of users. For the POI contextual information, the POI neighbourhood module in MANC applies a feature-level attention network to capture the latent features of neighbourhood POIs, and applies a POI-level attention network to capture the geographical influence among POIs. Extensive experiments are carried out, and it is shown that the MANC model achieves better performance than other state-of-the-art methods.

The effective Point-of-Interest (POI) recommendation can significantly assist users to find their preferred POIs and help POI owners to attract more customers. As a result, a variety of methods have been proposed to tackle the issue of POI recommendation recently. However, it is still very difficult to precisely model the strong correlations between the POIs visited by the user and the POIs to be visited next, which leads to the poor performance of POI recommendation. In this paper, we propose a context- and preference- aware model (CPAM) to incorporate both contextual influence and user preferences into POI recommendation. Firstly, we design a Skip-Gram based POI Embedding Model (SG-PEM) to capture the contextual influence of POIs and learn the vector representation (embedding) of POIs from visiting sequences. The users’ preferences for the target POIs are obtained from the learned embeddings via similarity metric. Secondly, for the implicit feedback information contained in the check-in data, we use the Logistic Matrix Factorization (LMF) algorithm to model the users’ personalized preferences for POI. Finally, we unify SG-PEM and LMF as the CPAM model to perform personalized recommendation by leveraging contextual influence and user preferences. The experimental results on two real-world datasets of Foursquare and Gowalla show that the proposed model outperforms the state-of-the-art baselines.

In this research, a fractional-order method for distinctive keypoints detection and to the image matching based on the Caputo-Fabrizio derivative and in the Speeded-Up Robust Feature (SURF) algorithm is presented and experimentally tested. The main advantage of introducing the fractional-order derivative is the improvement of the texture details detection, by combining this derivative with the SURF algorithm, the images feature extraction is improved to reach accurate images matching. The proposed method is compared experimentally with conventional SURF and SIFT algorithms. The experimental results showed that the proposed method has a high capacity for detecting points of interest in a region of the image with low contrast and weak texture.

Online taxi-hailing has become people’s most popular trip mode due to its convenience and low cost. However, it also poses a privacy threat to passengers and drivers, since the online taxi-hailing service providers are able to track their precise mobility trajectories. In addition, there is a certain time delay between the time of a passenger makes a request and the time of the driver arrives the passenger’s boarding position in current online taxi-hailing system. To solve these two problems, we present a new and efficient location privacy protection scheme based on the MinHash algorithm (LPPM). With the LPPM, the exact positions of passengers and drivers are generalized into a set of points of interest around them, and the distance between them is transformed into the similarity between the two sets. Thus a service provider can efficiently match passengers and drivers by using MinHash algorithm without revealing their specific location information. In this paper, we use mobile edge computing technology in the online taxi-hailing system to address the second challenge. It can speed up data processing, drivers can make decisions in advance and reduce the possibility of road congestion. Security analysis shows that LPPM has high security, and the final experimental results confirmed that LPPM is effective.

The advances of mobile equipment and localization techniques put forward the accuracy of the location-based service (LBS) in mobile networks. One core issue for the industry to exploit the economic interest of the LBSs is to make appropriate point-of-interest (POI) recommendation based on users’ interests. Today, the LBS applications expect the recommender systems to recommend the accurate next POI in an anonymous manner, without inquiring users’ attributes or knowing the detailed features of the vast number of POIs. To cope with the challenge, we propose a novel attentive model to recommend appropriate new POIs for users, namely Geographical Attentive Recommendation via Graph (GARG), which takes full advantage of the collaborative, sequential and content-aware information. Unlike previous strategies that equally treat POIs in the sequence or manually define the relationships between POIs, GARG adaptively differentiates the relevance of POIs in the sequence to the prediction, and automatically identifies the POI-wise correlation. Extensive experiments on three real-world datasets demonstrate the effectiveness of GARG and reveal a significant improvement by GARG on the precision, recall and mAP metrics, compared to several state-of-the-art baseline methods.

Traditional collaborative filtering methods perform poorly in providing location recommendations due to the high sparsity of users’ check-in data, prompting the development of new location recommendation approaches that can integrate situational factors such as time and location. Using long short-term memory (LSTM) neural networks and kernel density estimation (KDE), this paper integrates the impact of point-of-interest (POI) location and category on users’ check-in behavior according to check-in sequence data. First, LSTM neural networks are used to model users’ periodic and repetitive daily activities for a sequence-based prediction of the probability of whether the user will visit a candidate POI. Second, the user’s geographical preference in the two-dimensional space is represented by KDE and used to make a location-based check-in probability prediction. Next, the user’s category preference is used to predict the check-in probability of a candidate POI. Finally, a user preference model is constructed from three perspectives of time, location, and category, and the comprehensive check-in probability is used for Top-N recommendation. The validation experiments on Foursquare dataset verifies that, in terms of recommendation precision and recall, the proposed recommendation method is superior to both the basic LSTM approach and the method that uses only location information. In addition, it is experimentally confirmed that the geographical preference, which is reflected by “clustering” of a user’s check-in locations, is stable, but the user’s category preference is prone to drift.

Point of interest (POI) recommendation is of great value for both service providers and users. However, it is hard due to data scarcity. To this end, in this paper, we propose a transfer learning based deep neural model, which fuses valueable cross-domain knowledge to achieve more accurate POI recommendation. We first learn the user’s spatial and non-spatial preferences based on their historical POI interactions. The model further captures user interactions in other domains and introduces useful preferences into POI recommendations, which can address data sparsity problems. Compared to the matrix factorization based cross-domain techniques, our method utilizes deep transfer learning, which can learn complex user-item interaction relationships and accurately capture user general preferences to transfer. Finally, we evaluate the proposed model using three real-world datasets. The experimental results show that our model significantly outperforms the state-of-the-art approaches for POI recommendation.

POI group recommendation is one of the hottest research topics in location-based social networks, which recommends the most agreeable places for a group of users. However, traditional POI group recommendation methods only generate a consensus function to aggregate individual preference into group preference and they do not consider all the factors that can determine the results of POI group recommendation, which leads to a low recommendation accuracy. What’s more, these methods have a long running time. Therefore, in this paper, we propose a new POI group recommendation method with an extreme learning machine (ELM) called PGR-ELM. The PGR-ELM method regards POI group recommendation as a binary classification problem. First, three features are extracted from three factors: POI popularity, group members’ distance to POI, members’ interest preferences combined affinity between group members. These features simultaneously consider all the factors that can determine the results of recommendation and guarantee the effectiveness of POI group recommendation. Then, the extracted features are input to train an ELM classifier because of its fast learning speed, which guarantees the efficiency of POI group recommendation. Finally, extensive experiments verify the accuracy and efficiency of PGR-ELM method.

PurposeSustained delivery of regenerative retinal therapies by robotic systems requires intra-operative tracking of the retinal fundus. We propose a supervised deep convolutional neural network to densely predict semantic segmentation and optical flow of the retina as mutually supportive tasks, implicitly inpainting retinal flow information missing due to occlusion by surgical tools.MethodsAs manual annotation of optical flow is infeasible, we propose a flexible algorithm for generation of large synthetic training datasets on the basis of given intra-operative retinal images. We evaluate optical flow estimation by tracking a grid and sparsely annotated ground truth points on a benchmark of challenging real intra-operative clips obtained from an extensive internally acquired dataset encompassing representative vitreoretinal surgical cases.ResultsThe U-Net-based network trained on the synthetic dataset is shown to generalise well to the benchmark of real surgical videos. When used to track retinal points of interest, our flow estimation outperforms variational baseline methods on clips containing tool motions which occlude the points of interest, as is routinely observed in intra-operatively recorded surgery videos.ConclusionsThe results indicate that complex synthetic training datasets can be used to specifically guide optical flow estimation. Our proposed algorithm therefore lays the foundation for a robust system which can assist with intra-operative tracking of moving surgical targets even when occluded.

In this study, a novel transfer path analysis formulation using an emerging deep neural network model is presented and numerically validated for a multi-structural system. In the proposed formulation, only the operational responses of structures are utilized to identify the contributions of all paths to vibration responses at a point of interest in the frequency domain. To this end, the model parameters of a dense neural network model are initially determined using a training dataset to predict the responses precisely. Next, the contribution of each path is identified from the responses predicted by using the trained network model with the input associated with the selected path eliminated. To establish the correct model, the original operational datasets are augmented using the phase shift and the cross-spectrum. The path contributions estimated using the proposed formulation with another numerically generated operational dataset are compared with the known path contributions. The comparison results show that the proposed method based on a deep neural network model can successfully predict the path contributions using only operational responses.

Transportation network companies (TNC) provide mobility services that are influencing travel behavior in unknown ways due to limited TNC trip-level data. How they interact with other modes of transportation can have direct societal impacts, prompting appropriate policy intervention. This paper outlines a method to inform such policies through a data-driven approach that specifically analyzes the interaction between TNCs and bus services in Pittsburgh, PA. Uber surge multiplier data is used over a 6-month time period to approximate TNC usage (i.e., demand over supply ratio) for ten predefined points of interest throughout the city. Bus boarding data near each point of interest is used to relate TNC usage. Data from multiple sources (weather, traffic speed data, bus levels of service) are used to control for conditions that influence bus ridership. We find significant changes in bus boardings during periods of unusually high TNC usage at four locations during the evening hours. The remaining six locations observe no significant change in bus boardings. We find that the presence of a dedicated bus way transit station or a nearby university (or dense commercial zones in general) both influence ad-hoc substitutional behavior between TNCs and public transit. We also find that this behavior varies by location and time of day. This finding is significant and important for targeted policies that improve transportation network efficiency.

Attended collection and delivery points are vital components of ‘last-mile logistics’. Based on point of interest (POI) data for Cainiao Stations and China Post stations in Changsha City, China, this paper provides a detailed exploration of the basic features, spatial distribution, and location influencing factors of attended collection and delivery points. Specifically, analyses of the types, service objects and location distributions of the attended collection and delivery points alongside a discussion of their spatial pattern and influencing factors provides a reference for their general geographic layout and characteristics. The findings of this study indicate that: 1) The main mode of operation of attended collection and delivery points is franchises, with other modes of operation rely on supermarkets and other individual shop types. 2) The main service targets of attended collection and delivery points are communities, schools, and businesses, followed by townships, enterprises, scenic spots, and administrative units. 3) Approximately 77.44% of the attended collection and delivery points are located near the exits of service areas; others are situated in the centre of the service areas. For the Cainiao Stations, 80% are located within 125 m of the exit; for the China Post stations, 80% are located within 175 m of the exit. 4) The spatial distribution of the attended collection and delivery points in Changsha is unbalanced, with ‘more centre and fewer surrounding’. The centre is an ‘inverted triangle’, and the edge is an ‘orphan’, showing a northwest-southeast orientation and symmetrical along the axis. The layout of the attended collection and delivery points forms three core areas, and the number of sites decreases with the distance from the core. 5) The number and distribution of the attended collection and delivery points are strongly consistent with the regional economic development level, population, and roadway system traffic convenience. Most attended collection and delivery points are on residential, scientific and educational, and commercial and financial land.

The realization of pervasive computing massively piqued the productivity of the ways by which users perceive information from their environment. The amalgam of augmented reality and device ubiquity can assist users in mapping new Points Of Interest (POI) in their vicinity. This paper discusses a prototype developed for mobile devices with the objective of designing simpler user experiences for amateur users for contributing to OpenStreetMap (OSM). The application has exploited the inertial sensors and camera of the mobile devices, hence capacitating it to function as a mobile augmented reality tool. Often it is perplexing for novice users to add data conforming to the data standards. A feature to fetch the related tags used in OSM for the node data elements is an integral part of this work. The tool also fetches the existing POIs, displays them using color-coding and allows addition of missing data and correct the incorrect tag values. The overall aim is to reduce the coverage of unmapped areas and improve the completeness feature of OSM data. Thereby the tool extends the availability and opportunities of mapping OSM and enhances its degree of disposability for various geographic information system domains.

Similarity coefficients between artifact samples can be used for constructing larger groupings or for seriating the artifact samples. Indeed, these two approaches work well together, because the construction of groupings assists the seriation of the samples within and across groups. Sequentially grouping the samples into a single total sample, through hierarchical analysis of their coefficients, enables the use of these coefficients to seriate the artifact samples in the reverse order of their grouping. If the main point of interest is the composition of the groupings (for instance, as a summary of attribute similarities between artifact samples), seriation is still valuable in providing the hierarchical structure with an overall orientation that would otherwise be lacking. Alternatively, if the main point of interest is the seriated order (for instance, based on patterns of co-occurrences between the artifact samples), grouping analysis provides a structure to the seriation that would otherwise be lacking. Moreover, because we are dealing with samples, these can be subjected to stepwise agglomeration (rather than hierarchical clustering as commonly understood) during the grouping process, and then subjected to reverse-order sequential partitioning during the seriation process. The advantage of using agglomerated samples is that the coefficients between them can be calculated directly rather than derived indirectly from the constituent sample coefficients. How this approach can be applied to the seriation of artifact types is illustrated through a revisited analysis of high-fired ceramics imported to Sulawesi, Indonesia.

RF-EMF exposure assessment carried out in an observatory open for general public visits, where there are multiple RF sources in the surrounding area. Fields at some points of interest have exceeded the ICNIRP exposure limits for the general public and, to comply with normative limits, relevant stations reduced their radiated power. Nevertheless, the total electric field strength in the vicinity of the observatory’s metallic parapet still exceeds exposure limits due to re-radiation. Thus, the main broadcast stations reduced even more their transmitted power to comply with the regulatory limits throughout the observatory area. A detailed evaluation is carried out close to metallic objects to assess the re-radiation phenomenon. Additionally, laboratory experiments were carried out to confirm the influence of re-radiation from the metallic parapet.

Land use data is limited by timeliness. Therefore, based on the features of urban spatial pattern elements of construction land use and Point of Interest (POI) data, this paper applied the improved extraction method of urban commercial center to solve the access problem to land use data, and assist the extraction of urban land spatial pattern, improve the accuracy of extraction results. Since the traditional plane kernel density estimation method uses Euclidean distance calculation, it cannot take into account the important influence of road in urban development, so the road intersection point should be taken as an important influence parameter. Based on Baidu POI data of Nanjing in 2020 as the basic experimental data, the commercial centers of Nanjing are extracted by the kernel density estimation method of commercial-road intersection points. Based on the latest spatial distribution of commercial centers, this paper puts forward the strategic suggestions for future urban planning.

Aiming at the problems of traditional point of interest (POI), such as sparse data, lack of negative feedback, and dynamic and periodic changes of user preferences, a POI recommendation method using deep learning in location-based social networks (LBSN) considering privacy protection is proposed. First, the idea of Embedding is used to quantify the user information, friend relationship, POI information, and so on, so as to obtain the internal relationship of the location. Then, based on the user's history and current POI check-in sequence set, the long- and short-term attention mechanism (LSA) is constructed, and the quantified information is used as the input of LSA to better capture the user's long-term and short-term preferences. Finally, the social network information and semantic information are fitted in different input layers, and the time and geographical location information of user's historical behavior are used to recommend the next POI for users. Gowalla and Brightkite datasets are used to demonstrate the proposed method. The results show that the performance of the proposed method is better than other comparison methods under different sparsity, location sequence length, and embedding length. When the number of iterations is 500, the recommended method tends to be stable, and the accuracy is 0.27. Moreover, the recommendation time of the proposed method is less than 130 ms, which is better than other comparative deep learning methods.

Many location-based social networks (LBSNs) applications such as customized Point-Of-Interest (POI) recommendation, preference-based trip planning, travel time estimation, etc., involve an important task of understanding human trajectory patterns. In particular, identifying and linking trajectories to users who generate them – a problem called Trajectory-User Linking (TUL) – has become a focus of many recent works. TUL is usually studied as a multi-class classification problem and has gained recent attention because: (1) the number of labels/classes (i.e., users) is way larger than the number of motion patterns among various trajectories; and (2) the location-based trajectory data, especially the check-ins – i.e., events of reporting a location at particular Point of Interest (POI) with known semantics – are often extremely sparse. Towards addressing these challenges, we introduce a Trajectory Generative Adversarial Network (TGAN) as an approach to enable learning users motion patterns and location distribution, and to eventually identify human mobility. TGAN consists of two jointly trained neural networks, playing a Minimax game to (iteratively) optimize both components. The first one is the generator, learning trajectory representation by a Recurrent Neural Network (RNN) based model, aiming at fitting the underlying trajectory distribution of a particular individual and generate synthetic trajectories with intrinsic invariance and global coherence. The second one is the discriminator – a Convolutional Neural Network (CNN) based model that discriminates the generated trajectory from the real ones and provides guidance to train the generator model. We demonstrate that the above two models can be well tuned together to improve the TUL performance, while achieving superior accuracy when compared to existing approaches.

This paper presents a new immunity-based approach to measure the displacement of nodes (or points of interest) in successive-yetsparse images, in order to measure the settlement of deep-foundations under heavy loads. It is developed as a close-range photogrammetric technique to search the nodes, similar to immune-cells searching bacteria in their vicinity. The immunological concepts of chemotaxis, biased random walk, diffusion and inflammation are implemented herein to accomplish the task. The technique greatly reduces the errors and is also validated on site of a mega project to record the settlements in deep foundations. The accuracy levels are found to be conforming to ASTM’s standards for static load testing, including both compression and lateral-load tests. Unlike other techniques, such as particle image velocimetry, this approach is able to handle successive-images with varying ΔT between them. Furthermore, the technique is completely autonomous and does not require any embedded instrumentation.

The automatic detection of a great number of points of interest provides to photogrammetry essential capabilities for the automation of the procedure as well as for achieving optimum target position determination. The article deals with the use of image processing techniques in 2D images, which contribute to the detection of the targets, the ellipse fitting based on the least squares adjustment for the position determination of the targets, the decoding of encoded targets, and the usage of collinearity equations combined with least squares in order to find the homologous points among several images for the uncoded targets.

The daily trajectories of individual movements convey a concise overview of their behaviors, with different social roles having different trajectory patterns. Therefore, we can identify users or groups based on the similar of their trajectory patterns. However, most existing trajectory analysis focuses only on the spatial and temporal analyses of the raw trajectory data and misses essential semantic information concerning behaviors. In this paper, we propose a new trajectory semantics calculation method to identify groups with similar behaviors. We first propose a fast and efficient two-phase method for identifying stay regions within daily trajectories and enriching the stay regions with semantic labels based on points of interest to generate semantic trajectories. Furthermore, we design a semantic similarity measure model using geographic and semantic similarity factors to measure the similarity between semantic trajectories. We also propose a pruning strategy using time entropy to decrease the number of complex calculations and comparisons to improve performance. The results of our extensive experiments on the real trajectory dataset of the Geolife project show that our proposed method is both effective and efficient.