Due to its low storage cost and fast query speed, hashing has been widely adopted for similarity search in multimedia data. In particular, more and more attentions have been payed to multimodal hashing for search in multimedia data with multiple modalities, such as images with tags. Typically, supervised information of semantic labels is also available for the data points in many real applications. Hence, many supervised multimodal hashing~(SMH) methods have been proposed to utilize such semantic labels to further improve the search accuracy. However, the training time complexity of most existing SMH methods is too high, which makes them unscalable to large-scale datasets. In this paper, a novel SMH method, called semantic correlation maximization~(SCM), is proposed to seamlessly integrate semantic labels into the hashing learning procedure for large-scale data modeling. Experimental results on two real-world datasets show that SCM can significantly outperform the state-of-the-art SMH methods, in terms of both accuracy and scalability.

Multi-label learning concerns learning multiple, overlapping, and correlated classes. In this paper, we adapt a recent structured prediction framework called HC-Search for multi-label prediction problems. One of the main advantages of this framework is that its training is sensitive to the loss function, unlike the other multi-label approaches that either assume a specific loss function or require a manual adaptation to each loss function. We empirically evaluate our instantiation of the HC-Search framework along with many existing multi-label learning algorithms on a variety of benchmarks by employing diverse task loss functions. Our results demonstrate that the performance of existing algorithms tends to be very similar in most cases, and that the HC-Search approach is comparable and often better than all the other algorithms across different loss functions.

Central to robot exploration and mapping is the task of persistent localization in environmental fields characterized by spatially correlated measurements. This paper presents a Gaussian process localization (GP-Localize) algorithm that, in contrast to existing works, can exploit the spatially correlated field measurements taken during a robot's exploration (instead of relying on prior training data) for efficiently and scalably learning the GP observation model online through our proposed novel online sparse GP. As a result, GP-Localize is capable of achieving constant time and memory (i.e., independent of the size of the data) per filtering step, which demonstrates the practical feasibility of using GPs for persistent robot localization and autonomy. Empirical evaluation via simulated experiments with real-world datasets and a real robot experiment shows that GP-Localize outperforms existing GP localization algorithms.

Utilizing multiple queues in Greedy Best-First Search (GBFS) has been proven to be a very effective approach to satisficing planning. Successful techniques include extra queues based on Helpful Actions (or Preferred Operators), as well as using Multiple Heuristics. One weakness of all standard GBFS algorithms is their lack of exploration. All queues used in these methods work as priority queues sorted by heuristic values. Therefore, misleading heuristics, especially early in the search process, can cause the search to become ineffective. Type systems, as introduced for heuristic search by Lelis et al, are a development of ideas for exploration related to the classic stratified sampling approach. The current work introduces a search algorithm that utilizes type systems in a new way – for exploration within a GBFS multiqueue framework in satisficing planning. A careful case study shows the benefits of such exploration for overcoming deficiencies of the heuristic. The proposed new baseline algorithm Type-GBFS solves almost 200 more problems than baseline GBFS over all International Planning Competition problems. Type-LAMA, a new planner which integrates Type-GBFS into LAMA-2011, solves 36.8 more problems than LAMA-2011.

Also, we do many application domains, ranging from search and rescue not assume that all teams are in the same workspace, or all operations to exploration missions, service robotics to cognitive robots are of the same sort. Moreover, our goal is not to find factories. In these domains, the goal is for all teams any coordination of teams that would allow decoupling of to complete their tasks as soon as possible, and should the their local plans, but to find a coordination of teams for an need arise, teams help each other by lending robots.

Scenario-based serious-games have become an important tool for teaching new skills and capabilities. An important factor in the development of such systems is reducing the time and cost overheads in manually creating content for these scenarios. To address this challenge, we present ScenarioGen, an automatic method for generating content about everyday activities through combining computer science techniques with the crowd. ScenarioGen uses the crowd in three different ways: to capture a database of scenarios of everyday activities, to generate a database of likely replacements for specific events within that scenario, and to evaluate the resulting scenarios. We evaluated ScenarioGen in 6 different content domains and found that it was consistently rated as coherent and consistent as the originally captured content. We also compared ScenarioGen's content to that created by traditional planning techniques. We found that both methods were equally effective in generating coherent and consistent scenarios, yet ScenarioGen's content was found to be more varied and easier to create.

Many Artificial Intelligence tasks need large amounts of commonsense knowledge. Because obtaining this knowledge through machine learning would require a huge amount of data, a better alternative is to elicit it from people through human computation. We consider the sentiment classification task, where knowledge about the contexts that impact word polarities is crucial, but hard to acquire from data. We describe a novel task design that allows us to crowdsource this knowledge through Amazon Mechanical Turk with high quality. We show that the commonsense knowledge acquired in this way dramatically improves the performance of established sentiment classification methods.

We propose a combination of AI techniques to improve softwaretesting. When a test fails, a model-based diagnosis(MBD) algorithm is used to propose a set of possible explanations.We call these explanations diagnoses. Then, a planningalgorithm is used to suggest further tests to identify thecorrect diagnosis. A tester preforms these tests and reportstheir outcome back to the MBD algorithm, which uses thisinformation to prune incorrect diagnoses. This iterative processcontinues until the correct diagnosis is returned. We callthis testing paradigm Test, Diagnose and Plan (TDP). Severaltest planning algorithms are proposed to minimize the numberof TDP iterations, and consequently the number of testsrequired until the correct diagnosis is found. Experimentalresults show the benefits of using an MDP-based planning algorithmsover greedy test planning in three benchmarks.

This paper describes how AI is used to plan, schedule, and optimize nightly engineering works for both the commuter and rapid transit lines in Hong Kong. The MTR Corporation Limited operates and manages all the rail lines in Hong Kong. Its “Engineering Works and Traffic Information Management System” (ETMS) is a mission critical system that manages all information related to engineering works and their related track possessions and engineering train movements. The AI Engine described in this paper is a component of this ETMS. In Hong Kong, the maintenance, inspection, repair, or installation works along the rail lines are done during the very short non-traffic hours (NTH) of roughly 4 to 5 hours each night. These engineering works can be along the running tracks, track-side, tunnel, freight yards, sub-depots, depot maintenance tracks, etc. The proper scheduling of necessary engineering works is crucial to maintaining a reliable and safe train service during normal hours. The AI Engine optimizes resource allocation to maximize the number of engineering works that can be performed, while ensuring all safety, environment, and operational rules and constraints are met. The work described is part of a project to redesign and replace the existing ETMS, deployed in 2004, with an updated technology platform and modern IT architecture, to provide a more robust and scalable system that potentially can be deployed to other cities around the world.

Relation inference between concepts in knowledge base has been extensively studied in recent years. Previous methods mostly apply the relations in the knowledge base, without fully utilizing the contents, i.e., the attributes of concepts in knowledge base. In this paper, we propose a content-structural relation inference method (CSRI) which integrates the content and structural information between concepts for relation inference. Experiments on data sets show that CSRI obtains 15% improvement compared with the state-of-the-art methods.