Search

Given the common problem of missing data in real-world applications from various fields, such as remote sensing, ecology and meteorology, the interpolation of missing spatial and spatio-temporal data can be of tremendous value. Existing methods for spatial interpolation, most notably Gaussian processes and spatial autoregressive models, tend to suffer from (a) a trade-off between modelling local or global spatial interaction, (b) the assumption there is only one possible path between two points, and (c) the assumption of homogeneity of intermediate locations between points. Addressing these issues, we propose a value propagation-based spatial interpolation method called VPint, inspired by Markov reward processes (MRPs), and introduce two variants thereof: (i) a static discount (SD-MRP) and (ii) a data-driven weight prediction (WP-MRP) variant. Both these interpolation variants operate locally, while implicitly accounting for global spatial relationships in the entire system through recursion. We evaluated our proposed methods by comparing the mean absolute error, root mean squared error, peak signal-to-noise ratio and structural similarity of interpolated grid cells to those of 8 common baselines. Our analysis involved detailed experiments on a synthetic and two real-world datasets, as well as experiments on convergence and scalability. Empirical results demonstrate the competitive advantage of VPint on randomly missing data, where it performed better than baselines in terms of mean absolute error and structural similarity, as well as spatially clustered missing data, where it performed best on 2 out of 3 datasets.

As the popularity of Location-based Social Networks (LBSNs) increases, designing accurate models for Point-of-Interest (POI) recommendation receives more attention. POI recommendation is often performed by incorporating contextual information into previously designed recommendation algorithms. Some of the major contextual information that has been considered in POI recommendation are the location attributes (i.e., exact coordinates of a location, category, and check-in time), the user attributes (i.e., comments, reviews, tips, and check-in made to the locations), and other information, such as the distance of the POI from user's main activity location, and the social tie between users. The right selection of such factors can significantly impact the performance of the POI recommendation. However, previous research does not consider the impact of the combination of these different factors. In this paper, we propose different contextual models and analyze the fusion of different major contextual information in POI recommendation. The major contributions of this paper are: (i) providing an extensive survey of context-aware location recommendation (ii) quantifying and analyzing the impact of different contextual information (e.g., social, temporal, spatial, and categorical) in the POI recommendation on available baselines and two new linear and non-linear models, that can incorporate all the major contextual information into a single recommendation model, and (iii) evaluating the considered models using two well-known real-world datasets. Our results indicate that while modeling geographical and temporal influences can improve recommendation quality, fusing all other contextual information into a recommendation model is not always the best strategy., Comment: To appear in ACM TOIS

Remaining useful life (RUL) of an asset or system is defined as the length from the current time and operating state to the end of the useful life. It is of paramount importance for safety-critical industries such as aviation and lies in the heart of prognostics and health management (PHM). This paper investigates the usage of automated machine learning (AutoML) for RUL estimation, based on using classical machine learning algorithms for regression. The data is pre-processed by extracting statistical features from expanding windows of the signal in order to uncover the degradation that has been accumulating from the early life of the system or after an overhaul. We evaluate our methodology on the widely-used C-MAPSS dataset and compare our approach to the state-of-the-art deep neural networks (DNNs) and classical machine learning algorithms. The experimental results show that AutoML outperforms or is comparable to traditional machine learning techniques and standard neural networks, while being outperformed by specifically designed neural networks on datasets with multiple fault mode and operating conditions. These results show that with the correct pre-processing automated machine learning is able to accurately estimate the RUL, which implies that such approaches can be industrially deployed.

A Public Domain Dataset to SimulateChildren’s Free Play

Geocast is the concept of sending data packets to nodes in a specified geographical area instead of nodes with a specific address. This forwarding method is valuable in situations where any number of nodes inside a geographic area need to be reached, such as vehicular networking scenarios. To facilitate large scale geocast, a wired network geographic routing algorithm is needed that can route packets efficiently towards a destination area. Our goal is to design an algorithm that can deliver shortest path tree like geographic forwarding while relying purely on distributed data without central knowledge. In this paper we present and implement two algorithms for geographic routing. One algorithm is based purely on distance-vector data. Another, more complicated algorithm is based on path data. We show that our purely distance-vector-based algorithm can come close to the number of links used by a shortest path tree when a small number of routers are present in the destination area. We also show that our path-based algorithm can come close to the link usage of a shortest path tree in almost all geocast situations. We also show that the algorithms converge relatively quickly following link drops.

Early time series classification (EarlyTSC) involves the prediction of a class label based on partial observation of a given time series. Most EarlyTSC algorithms consider the trade-off between accuracy and earliness as two competing objectives, using a single dedicated hyperparameter. To obtain insights into this trade-off requires finding a set of non-dominated (Pareto efficient) classifiers. So far, this has been approached through manual hyperparameter tuning. Since the trade-off hyperparameters only provide indirect control over the earliness-accuracy trade-off, manual tuning is tedious and tends to result in many sub-optimal hyperparameter settings. This complicates the search for optimal hyperparameter settings and forms a hurdle for the application of EarlyTSC to real-world problems. To address these issues, we propose an automated approach to hyperparameter tuning and algorithm selection for EarlyTSC, building on developments in the fast-moving research area known as automated machine learning (AutoML). To deal with the challenging task of optimising two conflicting objectives in early time series classification, we propose MultiETSC, a system for multi-objective algorithm selection and hyperparameter optimisation (MO-CASH) for EarlyTSC. MultiETSC can potentially leverage any existing or future EarlyTSC algorithm and produces a set of Pareto optimal algorithm configurations from which a user can choose a posteriori. As an additional benefit, our proposed framework can incorporate and leverage time-series classification algorithms not originally designed for EarlyTSC for improving performance on EarlyTSC; we demonstrate this property using a newly defined, “naïve” fixed-time algorithm. In an extensive empirical evaluation of our new approach on a benchmark of 115 data sets, we show that MultiETSC performs substantially better than baseline methods, ranking highest (avg. rank 1.98) compared to conceptually simpler single-algorithm (2.98) and single-objective alternatives (4.36).

Current AutoML systems have been benchmarked with traditional natural image datasets. Differences between satellite images and natural images (e.g., bit-wise resolution, the number, and type of spectral bands) and lack of labeled satellite images for training models, pose open questions about the applicability of current AutoML systems on satellite data. In this paper, we demonstrate how AutoML can be leveraged for classification tasks on satellite data. Specifically, we deploy the Auto-Keras system for image classification tasks and create two new variants, IMG-AK and RS-AK, for satellite image classification that respectively incorporate transfer learning using models pre-trained with (i) natural images (using ImageNet) and (ii) remote sensing datasets. For evaluation, we compared the performance of these variants against manually designed architectures on a benchmark set of 7 satellite datasets. Our results show that in 71% of the cases the AutoML systems outperformed the best previously proposed model, highlighting the usefulness of a customized satellite data search space in AutoML systems. Our RS-AK variant performed better than IMG-AK for small datasets with a limited amount of training data. Furthermore, it found the best automated model for the datasets composed of near-infrared, green, and red bands.

This book contains a selection of the best papers of the 32nd Benelux Conference on Artificial Intelligence, BNAIC/Benelearn 2020, held in Leiden, The Netherlands, in November 2020. Due to the COVID-19 pandemic the conference was held online. The 12 papers presented in this volume were carefully reviewed and selected from 41 regular submissions. They address various aspects of artificial intelligence such as natural language processing, agent technology, game theory, problem solving, machine learning, human-agent interaction, AI and education, and data analysis.

How do we make sure that all citizens in a city have access to enough green space? An increasing part of the world’s population lives in urban areas, where contact with nature is largely reduced to street trees and parks. As optional tree planting sites and financial resources are limited, determining the best planting site can be formulated as an optimization problem with constraints. Can we locate these sites based on the popularity of nearby venues? How can we ensure that we include groups of people who tend to spend time in tree deprived areas?

Urban movement data as collected by location-based social networks provides valuable information about routes and specific roads that people are likely to drive on. This allows us to pinpoint roads that occur in many routes and are thus sensitive to congestion. Redistributing some of the traffic to avoid unnecessary use of these roads could be a key factor in improving traffic flow. Many of the previously proposed approaches to combat congestion are either static (e.g. a city tax) or do not incorporate any movement data and hence ignore how citizens use the infrastructure. In this work, we present a method to redistribute traffic through the introduction of externally imposed variable costs to each road segment, assuming that all drivers seek to drive the cheapest route. We propose using a metaheuristic optimisation approach to minimise total travel times by optimising a set of road-specific variable cost parameters, which are used as input for an objective function based on Greenshields traffic flow theory. We evaluate the performance of this approach within the context of a case study on the city centre of Tokyo. An optimisation scenario was defined for this city using public spatial road network data, and movement data acquired from Foursquare. Experimental results on this case study show that, depending on the amount of cars on the road network, our proposed method has the potential to achieve an improvement between 1.35% (437 hours for 112,985 drivers) and 13.15% (925 hours for 31,584 drivers) of total travel time, compared to that of a currently operational road network configuration with no imposed variable costs.

In different application areas, the prediction of values that are hierarchically related is required. As an example, consider predicting the revenue per month and per year of a company where the prediction of the year should be equal to the sum of the predictions of the months of that year. The idea of reconciliation of prediction on grouped time-series has been previously proposed to provide optimal forecasts based on such data. This method in effect, models the time-series collectively rather than providing a separate model for time-series at each level. While originally, the idea of reconciliation is applicable on data of time-series nature, it is not clear if such an approach can also be applicable to regression settings where multi-attribute data is available. In this paper, we address such a problem by proposing Reconciliation for Regression (R4R), a two-step approach for prediction and reconciliation. In order to evaluate this method, we test its applicability in the context of Travel Time Prediction (TTP) of bus trips where two levels of values need to be calculated: (i) travel times of the links between consecutive bus-stops; and (ii) total trip travel time. The results show that R4R can improve the overall results in terms of both link TTP performance and reconciliation between the sum of the link TTPs and the total trip travel time. We compare the results acquired when using group-based reconciliation methods and show that the proposed reconciliation approach in a regression setting can provide better results in some cases. This method can be generalized to other domains as well.

Unsupervised discretization is a crucial step in many knowledge discovery tasks. The state-of-the-art method for one-dimensional data infers locally adaptive histograms using the minimum description length (MDL) principle, but the multi-dimensional case is far less studied: current methods consider the dimensions one at a time (if not independently), which result in discretizations based on rectangular cells of adaptive size. Unfortunately, this approach is unable to adequately characterize dependencies among dimensions and/or results in discretizations consisting of more cells (or bins) than is desirable. To address this problem, we propose an expressive model class that allows for far more flexible partitions of two-dimensional data. We extend the state of the art for the one-dimensional case to obtain a model selection problem based on the normalized maximum likelihood, a form of refined MDL. As the flexibility of our model class comes at the cost of a vast search space, we introduce a heuristic algorithm, named PALM, which Partitions each dimension ALternately and then Merges neighboring regions, all using the MDL principle. Experiments on synthetic data show that PALM 1) accurately reveals ground truth partitions that are within the model class (i.e., the search space), given a large enough sample size; 2) approximates well a wide range of partitions outside the model class; 3) converges, in contrast to the state-of-the-art multivariate discretization method IPD. Finally, we apply our algorithm to three spatial datasets, and we demonstrate that, compared to kernel density estimation (KDE), our algorithm not only reveals more detailed density changes, but also fits unseen data better, as measured by the log-likelihood., Comment: Accepted version at Machine Learning

With the rapid growth of Location-Based Social Networks, personalized Points of Interest (POIs) recommendation has become a critical task to help users explore their surroundings. Due to the scarcity of check-in data, the availability of geographical information offers an opportunity to improve the accuracy of POI recommendation. Moreover, matrix factorization methods provide effective models which can be used in POI recommendation. However, there are two main challenges which should be addressed to improve the performance of POI recommendation methods. First, leveraging geographical information to capture both the user’s personal, geographic profile and a location’s geographic popularity. Second, incorporating the geographical model into the matrix factorization approaches. To address these problems, a POI recommendation method is proposed in this paper based on a Local Geographical Model, which considers both users’ and locations’ points of view. To this end, an effective geographical model is proposed by considering the user’s main region of activity and the relevance of each location within that region. Then, the proposed local geographical model is fused into the Logistic Matrix Factorization to improve the accuracy of POI recommendation. Experimental results on two well-known datasets demonstrate that the proposed approach outperforms other state-of-the-art POI recommendation methods.

From detecting skin cancer to translating languages and to forecasting electricity consumption, machine learning is enabling advanced capabilities of computer systems across a broad range of important real-world applications. In this work, we present machine learning models for forecasting the consumption of electricity. Short-term electric load forecasting has been a fundamental concern in power operation systems for over a century. Energy load forecasting is of even greater importance, due to applications in the planning of demand side management, smart electric vehicles and other smart grid technologies. We use two state-of-the-art automated machine learning systems (auto-sklearn and TPOT), which automate model selection and hyperparameter optimization, to achieve maximum prediction accuracy, and compare their performance for the task of load prediction using two benchmark problems. These benchmarks are derived from real world load consumption tasks, namely household consumption from the UCI data repository and consumption data from an industrial office building. Our experimental results indicate great potential for improving the accuracy of energy consumption prediction by using automated machine learning approaches.

Recently, Point of interest (POI) recommendation has gained ever-increasing importance in various Location-Based Social Networks (LBSNs). With the recent advances of neural models, much work has sought to leverage neural networks to learn neural embeddings in a pre-training phase that achieve an improved representation of POIs and consequently a better recommendation. However, previous studies fail to capture crucial information about POIs such as categorical information. In this paper, we propose a novel neural model that generates a POI embedding incorporating sequential and categorical information from POIs. Our model consists of a check-in module and a category module. The check-in module captures the geographical influence of POIs derived from the sequence of users' check-ins, while the category module captures the characteristics of POIs derived from the category information. To validate the efficacy of the model, we experimented with two large-scale LBSN datasets. Our experimental results demonstrate that our approach significantly outperforms state-of-the-art POI recommendation methods., Comment: 4 pages, 1 figures