Unvisited Locations Research Articles

Assessment of the spatial distribution and identification of potential risk areas for the sterility mosaic disease of pigeonpea (Cajanus cajan L. Huth) in Southern India

Sterility mosaic disease (SMD) is an emerging biotic risk to the cultivation of pigeonpea throughout the Indian subcontinent. The prevalence and distribution of SMD documented from diverse agro-climatic zones are still poorly known. In this investigation, we determined the spatial distribution of SMD covering major pigeonpea-growing states of Southern India namely, Karnataka, Telangana, Tamil Nadu, Maharashtra, and Andhra Pradesh by considering 2 years of exploratory survey data. Geospatial approaches were employed to determine the SMD incidence levels at unvisited locations using neighboring observations. The results indicated enormous variability in disease incidence ranging from 0 to 82.64% and 0 to 36.84%, respectively, in Kharif 2021–22 and 2022–23 in pigeonpea-growing states. Spatial autocorrelation analysis and Ripley’s K function established the presence of average clustering over sampling locations. Two main clusters were identified via agglomerative hierarchical cluster analysis. From the Local Moran’s I spatial autocorrelation (LISA) analysis, most of the districts were clustered together at (I<0). From the p-values, Bidar and Krishnagiri districts recorded the highest spatial dependence, while the remaining districts recorded medium spatial dependence (p < 0.05). Based on kriging, the Chittoor district of Andhra Pradesh, Medak and Ranga Reddy districts of Telangana, Bijapur district of Karnataka, and Latur district in Maharashtra states were found to be vulnerable to SMD occurrence in the future. The Matern and Spherical models were shown to be the best of the several semivariogram experimental models tested for spatial patterns of SMD incidence, from which OK and IK maps were created. Based on the interpolation results, the potential SMD hotspots/risk areas were most prominent in Telangana, Andhra Pradesh, Karnataka, and Tamil Nadu states. These identified hotspots for SMD revealed high levels of disease probability rates (>25%) above the threshold level and must be closely monitored to restrict and minimize further disease spread across the studied areas in Southern India. In pigeonpea, this is the first study in India that attempted to understand the spatial pattern of SMD using geostatistical methodologies. The results of the study will aid in the design and dissemination of specific management practices and curb the further spread of SMD.

Large-area soil mapping based on environmental similarity with adaptive consideration of spatial distance to samples

Digital soil mapping (DSM) based on environmental similarity may be used to predict the soil properties at unvisited locations based on the soil–environment relationship at each sample locations, which is more suitable for large-area (or regional scale) predictive mapping with comparatively limited soil samples than (geo-)statistical DSM methods with high requirements for the quantity and spatial distribution of samples. Recently, the DSM method based on environmental similarity but with inadequate consideration of the First Law of Geography was improved by considering the spatial distance to samples by means of the inverse distance weight (IDW), following the assumption that the more similar the environmental conditions and the shorter the spatial distance between the locations of interest and a sample are, the more similar the soil properties of the two locations. However, the current consideration of spatial distance by a constant distance-decay parameter should be improper across a whole large area under mapping due to the spatial variation of both sample distribution and the environmental conditions over a large area. In this paper, we propose a new large-area DSM method based on environmental similarity with adaptive consideration of spatial distance to samples by using adaptive distance-decay parameter values across a large area. An evaluation experiment to predict the soil organic matter at a depth of 0–20 cm at a 90-m resolution with a total of 659 soil samples in Anhui Province (approximately 134000 km2), China, was carried out. Evaluation results show that the proposed method (named iPSM-AdaIDW) achieved higher accuracy (with a root mean square error, or RMSE, of 8.273 g/kg) than two representative environmental-similarity-based DSM methods, i.e., individual Predictive Soil Mapping (iPSM) (without considering the spatial distance to samples) (RMSE = 8.878 g/kg) and iPSM considering spatial distance with a constant distance-decay parameter across the study area (RMSE = 8.310 g/kg), and a representative of large-area DSM not based on environmental similarity, i.e., the random forest kriging method (RMSE = 9.647 g/kg). For large areas with quantitively limited and unevenly distributed samples, the proposed method can achieve more applicable and accurate predictions.

Spatial Distribution Patterns for Identifying Risk Areas Associated with False Smut Disease of Rice in Southern India

False smut disease (FSD) of rice incited by Ustilaginoidea virens is an emerging threat to paddy cultivation worldwide. We investigated the spatial distribution of FSD in different paddy ecosystems of South Indian states, viz., Andhra Pradesh, Karnataka, Tamil Nadu, and Telangana, by considering the exploratory data from 111 sampling sites. Point pattern and surface interpolation analyses were carried out to identify the spatial patterns of FSD across the studied areas. The spatial clusters of FSD were confirmed by employing spatial autocorrelation and Ripley’s K function. Further, ordinary kriging (OK), indicator kriging (IK), and inverse distance weighting (IDW) were used to create spatial maps by predicting the values at unvisited locations. The agglomerative hierarchical cluster analysis using the average linkage method identified four main clusters of FSD. From the Local Moran’s I statistic, most of the areas of Andhra Pradesh and Tamil Nadu were clustered together (at I > 0), except the coastal and interior districts of Karnataka (at I < 0). Spatial patterns of FSD severity were determined by semi-variogram experimental models, and the spherical model was the best fit. Results from the interpolation technique, the potential FSD hot spots/risk areas were majorly identified in Tamil Nadu and a few traditional rice-growing ecosystems of Northern Karnataka. This is the first intensive study that attempted to understand the spatial patterns of FSD using geostatistical approaches in India. The findings from this study would help in setting up ecosystem-specific management strategies to reduce the spread of FSD in India.

Multi-Sensor Optimal Motion Planning for Radiological Contamination Surveys by Using Prediction-Difference Maps

Distributed and networked mobile sensor platforms using unmanned aerial and/or ground vehicles to survey areas of interest offer a safer and more efficient method for radiological contamination mapping; however, most applications rely on uniformly sweeping of the area in a raster-type motion without utilizing the information available in a dynamic sense. We have developed a fully autonomous optimal motion planning procedure for networks with two or more mobile sensors. The procedure utilizes well-established concepts of Gaussian processes in combination with control laws based on centroidal Voronoi tessellations to achieve optimal next-iteration sensor movements. A new method of informing optimal motion planning is proposed, whereby the absolute difference between the prior and current full-map prediction, referred to as the prediction-difference map, is used as the spatial density function within each Voronoi cell, providing immediate and iterative feedback for dynamic use of available information. The Gaussian process regression model used to estimate the contamination in unvisited locations also provides prediction uncertainties, and can be used as a quantitative metric to assess the confidence in the calculated contamination map; these estimates and prediction uncertainties are unavailable for standard uniform survey routines as they can only produce maps in the vicinity of observed locations. We present through simulation the achievable performance gains from using this new method by directly comparing to a uniform survey method. Results show that using the prediction-difference maps to inform motion planning procedures offers a faster rate of producing an accurate and convergent map relative to a uniform survey route.

Spatial distribution and identification of potential risk regions to rice blast disease in different rice ecosystems of Karnataka.

Rice is a globally important crop and highly vulnerable to rice blast disease (RBD). We studied the spatial distribution of RBD by considering the 2-year exploratory data from 120 sampling sites over varied rice ecosystems of Karnataka, India. Point pattern and surface interpolation analyses were performed to identify the spatial distribution of RBD. The spatial clusters of RBD were generated by spatial autocorrelation and Ripley’s K function. Further, inverse distance weighting (IDW), ordinary kriging (OK), and indicator kriging (IK) approaches were utilized to generate spatial maps by predicting the values at unvisited locations using neighboring observations. Hierarchical cluster analysis using the average linkage method identified two main clusters of RBD severity. From the Local Moran’s I, most of the districts were clustered together (at I > 0), except the coastal and interior districts (at I < 0). Positive spatial dependency was observed in the Coastal, Hilly, Bhadra, and Upper Krishna Project ecosystems (p > 0.05), while Tungabhadra and Kaveri ecosystem districts were clustered together at p < 0.05. From the kriging, Hilly ecosystem, middle and southern parts of Karnataka were found vulnerable to RBD. This is the first intensive study in India on understanding the spatial distribution of RBD using geostatistical approaches, and the findings from this study help in setting up ecosystem-specific management strategies against RBD.

Sensor-aware frontier exploration and mapping with application to thermal mapping of building interiors

The combination of simultaneous localization and mapping (SLAM) and frontier exploration enables a robot to traverse and map an unknown area autonomously. Most prior autonomous SLAM solutions utilize information only from depth sensing devices. However, in situations where the main goal is to collect data from auxiliary sensors such as thermal camera, existing approaches require two passes: one pass to create a map of the environment and another to collect the auxiliary data, which is time consuming and energy inefficient. We propose a sensor-aware frontier exploration algorithm that enables the robot to perform map construction and auxiliary data collection in one pass. Specifically, our method uses a real-time ray tracing technique to construct a map that encodes unvisited locations from the perspective of auxiliary sensors rather than depth sensors; this encourages the robot to fully explore those areas to complete the data collection task and map making in one pass. Our proposed exploration framework is deployed on a LoCoBot with the task to collect thermal images from building envelopes. We validate with experiments in both multi-room commercial buildings and cluttered residential buildings. Using a metric that evaluates the coverage of sensor data, our method significantly outperforms the baseline method with a naive SLAM algorithm.

Communication-Aware Robotics: Exploiting Motion for Communication

In this review, we present a comprehensive perspective on communication-aware robotics, an area that considers realistic communication environments and aims to jointly optimize communication and navigation. The main focus of the article is theoretical characterization and understanding of performance guarantees. We begin by summarizing the best prediction an unmanned vehicle can have of the channel quality at unvisited locations. We then consider the case of a single robot, showing how it can mathematically characterize the statistics of its traveled distance until connectivity and further plan its path to reach a connected location with optimality guarantees, in real channel environments and with minimum energy consumption. We then move to the case of multiple robots, showing how they can utilize their motions to enable robust information flow. We consider two specific robotic network configurations—robotic beamformers and robotic routers—and mathematically characterize properties of the co-optimum motion–communication decisions.

A self-training semi-supervised machine learning method for predictive mapping of soil classes with limited sample data

Numerous machine learning models have been developed for constructing the relationship between soil classes or properties and its environmental covariates in digital soil mapping (DSM). Most machine learning models are trained with a supervised learning (SL) method based on training samples. However, the collected sample data is often limited in practice due to that field sampling is expensive and time-consuming. The insufficient samples may limit the learning ability of the model to a large extent. Semi-supervised machine learning, a new machine learning paradigm that makes use of both unsampled data and a small amount of sampled data in the learning process, can be a potential effective method for DSM. In this study, we present a self-training semi-supervised learning (SSL) method for DSM. Different with the SL method for machine learning models, the SSL method not only utilizes the sampled locations but also the abundant environmental covariate information at the unvisited locations. Its basic idea is to iteratively enlarge the training data set by adding the unsampled points with high prediction confidence from the unvisited locations until a stopping criterion reached. The proposed SSL method was applied in machine learning models for predicting soil classes in Heshan Farm of Nenjiang County in Heilongjiang Province, China. Three machine learning models, including multinomial logistic regression (MLR), k-nearest neighbor (KNN) and random forest (RF), were selected to evaluate the efficiency of the SSL method. The entropy threshold was an important parameter in the SSL method, and a sensitivity analysis on this parameter was conducted with using a series of entropy thresholds. The SSL method was compared with the SL method for the three machine learning models for soil prediction. A cross-validation was employed to evaluate the accuracy of the predicted soil class maps generated based on each method. The results showed that the prediction accuracies (the proportion of the correctly predicted samples over the total number of validation samples) of the SSL method were higher than those of the SL method for MLR, KNN, and RF by 5.9%, 12.2%, and 6.0%, respectively. RF-SSL was the most accurate model in the study area, followed by KNN-SSL. Meanwhile, the self-training SSL method for the KNN model had the largest improvement comparing with the other two models. Furthermore, the predicted soil maps using the SSL method showed a more reasonable spatial variation pattern of soil classes. In the study area, a suitable value of the entropy threshold was 0.8 ~ 1.0. We concluded that the SSL method improved the soil prediction accuracy compared with the SL method when applying machine learning models for DSM, and thus is a potential efficient method for DSM with limit sample data.

Solving the clustered traveling salesman problem with ‐relaxed priority rule

AbstractThe clustered traveling salesman problem with a prespecified order on the clusters, a variant of the well‐known traveling salesman problem, is studied in the literature. In this problem, delivery locations are divided into clusters with different urgency levels and more urgent locations must be visited before less urgent ones. However, this could lead to an inefficient route in terms of traveling cost. This priority‐oriented constraint can be relaxed by a rule called ‐relaxed priority that provides a trade‐off between transportation cost and emergency level. Given a positive integer , at any point along the route, the ‐relaxed rule allows the vehicle to visit locations with priority , before visiting all locations in class , where is the highest priority class among all unvisited locations. Our research proposes two approaches to solve the problem with ‐relaxed priority rule. We improve the mathematical formulation proposed in the literature to construct an exact solution method. A metaheuristic method based on the framework of iterated local search with problem‐tailored operators is also introduced to find approximate solutions. Experimental results show the effectiveness of our methods.

A complementing preference based method for location recommendation with cellular data

Location recommendation in a city district plays an essential role for people city experience. Most existing studies consider user mobility data as implicit feedback, and adopt collaborative filtering frameworks to make recommendations. However, most of them treat all unvisited locations as negative examples. This method fails to provide details about users preferences, such as graded ratings in explicit feedback. To cope with this problem, we define geographically similar friends, and propose a Complementing Preference Based Collaborative Filtering method (CPBCF). Specifically, we first build a geosimilarity network for a user and identify the possible locations that he or she could visit. Limiting the study to just these locations alleviates data sparsity caused by a huge number of unrelated locations. Then, we complement the user–location preference matrix using the information from geographically similar friends and adopt a weighted regularized matrix factorization model to make recommendations. We evaluate our method on real-world dataset and the experimental results demonstrate the effectiveness of our methods.

Spatiotemporal geostatistical modeling of groundwater levels under a Bayesian framework using means of physical background

The joint spatiotemporal modeling of aquifer level fluctuations provides a significant tool in the prediction of groundwater levels at unvisited locations. Two types of variogram functions, appropriately modified to incorporate physical information, are presented and compared under Space-time Residual kriging methodology using the Bayesian Bootstrap idea to quantify uncertainty. The spatiotemporal trend is approximated using a component of physical meaning. A recently developed Spartan type non-separable variogram function employs tools of physical meaning to enhance the efficiency and reliability of spatiotemporal geostatistical modeling in groundwater applications. In addition, the product-sum space-time variogram is applied and involves in the separable variogram functions a scale factor of hydraulic conductivity directional ratio. The proposed variogram functions involve a non-Euclidean distance metric and are mathematically valid (i.e., constitutes permissible models). Herein, the efficiency of the proposed tools is tested using groundwater level data from an alluvial unconfined aquifer. Both functions provide improved results compared to those of the Space-time Ordinary kriging. Between the two, the non-separable one has the most efficient performance.

Robotic Active Information Gathering for Spatial Field Reconstruction with Rapidly-Exploring Random Trees and Online Learning of Gaussian Processes.

Information gathering (IG) algorithms aim to intelligently select a mobile sensor actions required to efficiently obtain an accurate reconstruction of a physical process, such as an occupancy map, or a magnetic field. Many recent works have proposed algorithms for IG that employ Gaussian processes (GPs) as underlying model of the process. However, most algorithms discretize the state space, which makes them computationally intractable for robotic systems with complex dynamics. Moreover, they are not suited for online information gathering tasks as they assume prior knowledge about GP parameters. This paper presents a novel approach that tackles the two aforementioned issues. Specifically, our approach includes two intertwined steps: (i) a Rapidly-Exploring Random Tree (RRT) search that allows a robot to identify unvisited locations, and to learn the GP parameters, and (ii) an RRT*-based informative path planning that guides the robot towards those locations by maximizing the information gathered while minimizing path cost. The combination of the two steps allows an online realization of the algorithm, while eliminating the need for discretization. We demonstrate that our proposed algorithm outperforms state-of-the-art both in simulations, and in a lab experiment in which a ground-based robot explores the magnetic field intensity within an indoor environment populated with obstacles.

Energy Optimal Distributed Beamforming Using Unmanned Vehicles

In this paper, we consider a team of unmanned vehicles that are tasked with distributed transmit beamforming (virtual antenna array placement and design), in order to co-operatively transmit information to a remote station in realistic communication environments. We are interested in the energy-aware (both motion and communication energy) co-optimization of robotic paths and transmission powers for cooperative transmit beamforming under a reception quality requirement. We first consider the case where the channel is known. For this case, we propose an efficient approach for getting arbitrarily close to the optimum solution, which involves solving a series of multiple-choice knapsack problems. We then extend our analysis and methodology to the case where the channel is not known. The robots then probabilistically predict the channel at unvisited locations and integrate it with path planning and decision making for energy-aware distributed transmit beamforming. Finally, we extensively confirm our proposed approach with several simulation results with real channel parameters. Our results highlight the underlying trends of the optimum strategy and indicate considerable energy savings.

Integrating geographical and temporal influences into location recommendation: a method based on check-ins

In the online-to-offline (O2O) business model, location recommendation plays an important role and is an essential component of the location-based services. The check-in data, which contains both the geographical and temporal information, has been treated as an important data source for location recommendation. Location-based collaborative filtering is a popular technique for computing location similarities to arrive at the recommendation. In this research we analyze the geographical and temporal characteristics of the user’s check-in activity and incorporate it for deriving recommendations using location-based collaborative filtering. To model the geographical proximity between the recommended location and the visited location, we first get the user’s active regions using the multiple-center discovering algorithm; we then derive the probability of visiting the unvisited locations by using the power-law distribution on the distance. The geographical proximity is derived by multiplying the visiting probability and the check-in ratio of the active region. To consider temporal information, we propose the concept of time-aware location similarity, which splits the user check-ins into twenty-four different time slots in a day. To address the sparsity problem created by splitting check-in data, we propose a mechanism to measure the similarities between time slots and use these similarities to infer the empty ratings. The geographical proximity and time-aware location similarity are integrated to generate the location similarity. We perform the experiments to verify the effectiveness of the proposed algorithm. The experimental results show the superiority of our method compared with the benchmarks.

From known to unknown: moving to unvisited locations in a novel sensorimotor map.

Sensorimotor learning requires knowledge of the relationship between movements and sensory effects: a sensorimotor map. Generally, these mappings are not innate but have to be learned. During learning, the challenge is to build a continuous map from a set of discrete observations, that is, predict locations of novel targets. One hypothesis is that the learner linearly interpolates among discrete observations that are already in the map. Here, this hypothesis is tested by exposing human subjects to a novel mapping between arm movements and sounds. Participants were passively moved to the edges of the workspace receiving the corresponding sounds and then were presented intermediate sounds and asked to make movements to locations they thought corresponded to those sounds. It is observed that average movements roughly match linear interpolation of the space. However, the actual distribution of participants' movements is best described by a bimodal reaching strategy in which they move to one of two locations near the workspace edge where they had prior exposure to the sound-movement pairing. These results suggest that interpolation happens to a limited extent only and that the acquisition of sensorimotor maps may not be driven by interpolation but instead relies on a flexible recombination of instance-based learning.

Time-slot-based point of interest recommendation on location-based social network

Point-of-interest (POI) recommendation on location-based social network (LBSN) is an important service in mobile environment. POI recommendation recommends places that users have not visited before. In this paper, we introduce time slot to describe the feature vector of locations. We consider that the locations that user has visited may reflect user's preference. Hence, we calculate the similarity between the visited locations and the unvisited locations. Meanwhile, we consider the influence of the physical distance and the weight of the visited locations. We conduct an experiment and the experimental results show that our method has better precision and recall than the other two methods.

Next Check-in Location Prediction Combines with Collaborative Filtering

With the thriving of mobile location-based services, location-based social networks (LBSNs) have become a popular form of social media recently. Large numbers of “check-in” records continue to accumulate over time, which contain rich information of social and geographical context and provide a unique opportunity for researchers to study user’s social behavior, which in turn enables a variety of services including place advertisement, intelligent transportation, and Urban Computing. In this paper, we mainly study the problem of user’s location prediction. Firstly we analyzed the regular mobility patterns about the visited locations. However, on account of personality trait of neophilia, people also show propensities of novelty seeking in human mobility, such as exploring unvisited but tailored locations for them to visit. Hence, we not only propose a set of features that aim to describe the regular mobility patterns, but also use the collaborative social knowledge to analysis the users’ mobility patterns on the unvisited locations. Finally, we further extend our study combining all individual features in two supervised learning models, based on linear regression and M5 model trees, to get a higher overall prediction accuracy. And we find that the supervised methodology based on M5 model trees the offers better prediction accuracy.

Similarity-based probabilistic category-based location recommendation utilizing temporal and geographical influence

Location recommendation on location-based social networks, which is a rapidly growing research topic, suggests recommendations for unvisited locations to their users. This recommendation service is based on users’ visit histories and location-related information, such as location categories. Finding similarities in users’ behaviors can help these networks make better recommendations. In this paper, we propose two similarity-based Probabilistic Category-based Location Recommendation (sPCLR) algorithms that recommend locations to users at a given time of the day by utilizing category information: sPCLR-DTW and sPCLR-BCC. Both algorithms utilize temporal and spatial components. The temporal component utilizes the temporal influence of similar users’ check-in behaviors by representing users’ periodic check-in behavior at different location categories as temporal curves. The similarity between users’ periodic check-in behavior is calculated based on the difference between temporal curves. In sPCLR-DTW, the traditional dynamic time warping method (DTW) is used to measure the distance between temporal curves. In order to improve the time efficiency of the recommendation process, a novel sequence-matching technique—best curve coupling (BCC)—is proposed and utilized in sPCLR-BCC. The spatial component utilizes the geographical influence of locations and filters out those locations that are not of interest to the user. The performance of the sPCLR-DTW and sPCLR-BCC algorithms are studied and compared to two existing location recommendation algorithms on a real-world dataset. Experimental results show that the sPCLR-DTW performs better than all other recommendation algorithms, whereas sPCLR-BCC can provide comparable recommendations more quickly, making it ideal for online applications.

MRI: Model-Based Radio Interpolation for Indoor War-Walking

Location estimation methods using radio fingerprint have been studied extensively. The approach constructs a database that associates ambient radio signals with physical locations in training phase, and then estimates the location by finding the most similar signal pattern within the database. To achieve robust and accurate location estimation, the training phase should be conducted across the entire target space. In practice, however, a user may only access limited or authorized places in a building, that causes degradation in accuracy. In this paper, we present a smartphone-based autonomous indoor war-walking scheme, which automatically constructs the location fingerprint database, even covering unvisited locations. While a smartphone user explores the target area, the proposed system tracks the user's trajectory and simultaneously trains the location fingerprint database. Furthermore, our scheme interpolates radio signals in the database with an appropriate radio propagation model, and supplements fingerprints for unvisited places. As a result, although a user may sparsely explore the target site, the scheme returns the complete database. We implemented our solution and demonstrated the feasibility of the solution.

Predictive soil mapping with limited sample data

SummaryExisting predictive soil mapping (PSM) methods often require soil sample data to be sufficient to represent soil–environment relationships throughout the study area. However, in many parts of the world with only a limited quantity of soil sample data to represent the study area, this is still an issue for PSM application. This paper presents a method, named ‘individual predictive soil mapping’ (iPSM), which can make use of limited soil sample data for PSM. With the assumption that similar environmental conditions have similar soils, iPSM uses the soil–environment relationship at each individual soil sample location to predict soil properties at unvisited locations and estimate prediction uncertainty. Specifically, the environmental similarities of an unvisited location to a set of soil sample locations are used in a weighted average method to integrate the soil–environment relationships at sample locations for prediction and uncertainty estimation. As a case study, iPSM was applied to map soil organic matter (SOM) content (%) in the topsoil layer using two sets of soil samples. Compared with multiple linear regression (MLR), iPSM produced a more accurate SOM map (root mean squared error (RMSE) 1.43, mean absolute error (MAE) 1.16) than MLR (RMSE 8.54, MAE 7.34) the ability of the sample set to represent the study area is limited and achieved a comparable accuracy (RMSE 1.10, MAE 0.69) with MLR (RMSE 1.01, MAE 0.73) when the sample set could represent the study area better. In addition, the prediction uncertainty estimated by iPSM was positively related to prediction residuals in both scenarios. This study demonstrates that iPSM is an effective alternative when existing soil samples are limited in their ability to represent the study area and the prediction uncertainty in iPSM can be used as an indicator of its prediction accuracy.