In machine learning, one often assumes the data are independent when evaluating model performance. However, this rarely holds in practice. Geographic information datasets are an example where the data points have stronger dependencies among each other the closer they are geographically. This phenomenon known as spatial autocorrelation (SAC) causes the standard cross validation (CV) methods to produce optimistically biased prediction performance estimates for spatial models, which can result in increased costs and accidents in practical applications. To overcome this problem, we propose a modified version of the CV method called spatial k-fold cross validation (SKCV), which provides a useful estimate for model prediction performance without optimistic bias due to SAC. We test SKCV with three real-world cases involving open natural data showing that the estimates produced by the ordinary CV are up to 40% more optimistic than those of SKCV. Both regression and classification cases are considered in our experiments. In addition, we will show how the SKCV method can be applied as a criterion for selecting data sampling density for new research area.

In recent years, Artificial Intelligence (AI) has been widely deployed in a variety of business sectors and industries, yielding numbers of revolutionary applications and services that are primarily driven by high-performance computation and storage facilities in the cloud. On the other hand, embedding intelligence into edge devices is highly demanded by emerging applications such as autonomous systems, human-machine interactions, and the Internet of Things (IoT). In these applications, it is advantageous to process data near or at the source of data to improve energy & spectrum efficiency and security, and decrease latency. Although the computation capability of edge devices has increased tremendously during the past decade, it is still challenging to perform sophisticated AI algorithms in these resource-constrained edge devices, which calls for not only low-power chips for energy efficient processing at the edge but also a system-level framework to distribute resources and tasks along the edge-cloud continuum. In this overview, we summarize dedicated edge hardware for machine learning from embedded applications to sub-mW “always-on” IoT nodes. Recent advances of circuits and systems incorporating joint design of architectures and algorithms will be reviewed. Fog computing paradigm that enables processing at the edge while still offering the possibility to interact with the cloud will be covered, with focus on opportunities and challenges of exploiting fog computing in AI as a bridge between the edge device and the cloud.

Autonomous harvesting and transportation is a long-term goal of the forest industry. One of the main challenges is the accurate localization of both vehicles and trees in a forest. Forests are unstructured environments where it is difficult to find a group of significant landmarks for current fast feature-based place recognition algorithms. This paper proposes a novel approach where local point clouds are matched to a global tree map using the Delaunay triangularization as the representation format. Instead of point cloud based matching methods, we utilize a topology-based method. First, tree trunk positions are registered at a prior run done by a forest harvester. Second, the resulting map is Delaunay triangularized. Third, a local submap of the autonomous robot is registered, triangularized and matched using triangular similarity maximization to estimate the position of the robot. We test our method on a dataset accumulated from a forestry site at Lieksa, Finland. A total length of 200 m of harvester path was recorded by an industrial harvester with a 3D laser scanner and a geolocation unit fixed to the frame. Our experiments show a 12 cm s.t.d. in the location accuracy and with real-time data processing for speeds not exceeding 0.5 m/s. The accuracy and speed limit are realistic during forest operations.

Abnormal behavior detection is currently receiving much attention because of the availability of marine equipment and data allowing maritime agents to track vessels. One of the most popular tools for developing an efficient anomaly detection system is the Automatic Identification System (AIS). The aim of this paper is to explore the performance of existing well-known clustering methods for detecting the two most dangerous abnormal behaviors based on the AIS. The methods include K-means, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Affinity Propagation (AP), and the Gaussian Mixtures Model (GMM). In order to evaluate the performance of the clustering methods, we also used the AIS data of vessels, which were collected through the Finnish transport agency from the whole Baltic Sea for three months. Although most existing studies focus on ocean route recognition, deviations from regulated ocean routes, or irregular speed, we focused on dark ships or those sets of vessels that turn off the AIS to perform illegal activities and spiral vessel movements. The experimental results demonstrate that the K-means clustering method can effectively detect dark ships and spiral vessel movements, which are the most threatening events for maritime safety.

Forest harvesting operations with heavy machinery can lead to significant soil rutting. Risks of rutting depend on the soil bearing capacity which has considerable spatial and temporal variability. Trafficability prediction is required in the selection of suitable operation sites for a given time window and conditions, and for on-site route optimization during the operation. Integrative tools are necessary to plan and carry out forest operations with minimal negative ecological and economic impacts. This study demonstrates a trafficability prediction framework that utilizes a spatial hydrological model and a wide range of spatial data. Trafficability was approached by producing a rut depth prediction map at a 16 × 16 m grid resolution, based on the outputs of a general linear mixed model developed using field data from Southern Finland, modelled daily soil moisture, spatial forest inventory and topography data, along with field measured rolling resistance and information on the mass transported through the grid cells. Dynamic rut depth prediction maps were produced by accounting for changing weather conditions through hydrological modelling. We also demonstrated a generalization of the rolling resistance coefficient, measured with harvester CAN-bus channel data. Future steps towards a nationwide prediction framework based on continuous data flow, process-based modelling and machine learning are discussed.

Robust real-time object detection and tracking are challenging problems in autonomous transportation systems due to operation of algorithms in inherently uncertain and dynamic environments and rapid movement of objects. Therefore, tracking and detection algorithms must cooperate with each other to achieve smooth tracking of detected objects that later can be used by the navigation system. In this paper, we first present an efficient multi-sensor fusion approach based on the probabilistic data association method in order to achieve accurate object detection and tracking results. The proposed approach fuses the detection results obtained independently from four main sensors: radar, LiDAR, RGB camera and infrared camera. It generates object region proposals based on the fused detection result. Then, a Convolutional Neural Network (CNN) approach is used to identify the object categories within these regions. The CNN is trained on a real dataset from different ferry driving scenarios. The experimental results of tracking and classification on real datasets show that the proposed approach provides reliable object detection and classification results in maritime environments.