No description available.

Machine Learning (ML) and Artificial Intelligence (AI) impact many aspects of human life, from recommending a significant other to assist the search for extraterrestrial life. The area develops rapidly and exiting unexplored design spaces are constantly laid bare. The focus in this work is one of these areas; ML systems where decisions concerning ML model training, usage and selection of target domain lay in the hands of domain experts.  This work is then on ML systems that function as a tool that augments and/or enhance human capabilities. The approach presented is denoted Human In Command ML (HIC-ML) systems. To enquire into this research domain design experiments of varying fidelity were used. Two of these experiments focus on augmenting human capabilities and targets the domains commuting and sorting batteries. One experiment focuses on enhancing human capabilities by identifying similar hand-painted plates. The experiments are used as illustrative examples to explore settings where domain experts potentially can: independently train an ML model and in an iterative fashion, interact with it and interpret and understand its decisions.  HIC-ML should be seen as a governance principle that focuses on adding value and meaning to users. In this work, concrete application areas are presented and discussed. To open up for designing ML-based products for the area an abstract model for HIC-ML is constructed and design guidelines are proposed. In addition, terminology and abstractions useful when designing for explicability are presented by imposing structure and rigidity derived from scientific explanations. Together, this opens up for a contextual shift in ML and makes new application areas probable, areas that naturally couples the usage of AI technology to human virtues and potentially, as a consequence, can result in a democratisation of the usage and knowledge concerning this powerful technology.

Adaptive Large Neighborhood Search (ALNS) is a fairly recent yet popular single-solution heuristic for solving discrete optimization problems. Even though the heuristic has been a popular choice for researchers in recent times, the parallelization of this algorithm is not widely studied in the literature compared to the other classical metaheuristics. To extend the existing literature, this study proposes several different parallel schemes to parallelize the basic/sequential ALNS algorithm. More specifically, seven different parallel schemes are employed to target different characteristics of the ALNS algorithm and the capability of the local computers. The schemes of this study are implemented in a master-slave architecture to manage and assign loads in processors of the local computers. The overall goal is to simultaneously explore different areas of the search space in an attempt to escape the local minima, taking effective steps toward the optimal solution and, to the end, accelerating the convergence of the ALNS algorithm. The performance of the schemes is tested by solving a capacitated vehicle routing problem (CVRP) with available wellknown test instances. Our computational results indicate that all the parallel schemes are capable of providing a competitive optimality gap in solving CVRP within our investigated test instances. However, the parallel scheme (scheme 1), which runs the ALNS algorithm independently within different slave processors (e.g., without sharing any information with other slave processors) until the synchronization occurs only when one of the processors meets its predefined termination criteria and reports the solution to the master processor, provides the best running time with solving the instances approximately 10.5 times faster than the basic/sequential ALNS algorithm. These findings are applied in a real-life fulfillment process using mixed-mode delivery with trucks and drones. Complex but optimized routes are generated in a short time that is applicable to perform last-mile delivery to customers.

This work shows the application of artificial intelligence (AI) on invasion game tracking data to realize a fast (sub-second) and adaptable search engine for sports scenes, scene ratings based on machine learning (ML) and computer-generated solutions using reinforcement learning (RL). We provide research results for all three areas. Benefits are expected for accelerated video analysis at professional sports clubs. / Diese Arbeit zeigt die Anwendung von künstlicher Intelligenz (KI) auf Invasionsspielverfolgungsdaten, um eine schnelle (unter einer Sekunde) und anpassungsfähige Suchmaschine für Sportszenen zu realisieren, Szenenbewertungen auf der Grundlage von maschinellem Lernen (ML) und computergenerierte Lösungen unter Verwendung von Verstärkungslernen (RL). Wir stellen Forschungsergebnisse für alle drei Bereiche vor. Es werden Vorteile für eine beschleunigte Videoanalyse in Profisportvereinen erwartet.