Search results for "020201 artificial intelligence & image processing"
showing 10 items of 1827 documents
Surrogate-assisted evolutionary multiobjective shape optimization of an air intake ventilation system
2017
We tackle three different challenges in solving a real-world industrial problem: formulating the optimization problem, connecting different simulation tools and dealing with computationally expensive objective functions. The problem to be optimized is an air intake ventilation system of a tractor and consists of three computationally expensive objective functions. We describe the modeling of the system and its numerical evaluation with a commercial software. To obtain solutions in few function evaluations, a recently proposed surrogate-assisted evolutionary algorithm K-RVEA is applied. The diameters of four different outlets of the ventilation system are considered as decision variables. Fr…
Anomaly detection approach to keystroke dynamics based user authentication
2017
Keystroke dynamics is one of the authentication mechanisms which uses natural typing pattern of a user for identification. In this work, we introduced Dependence Clustering based approach to user authentication using keystroke dynamics. In addition, we applied a k-NN-based approach that demonstrated strong results. Most of the existing approaches use only genuine users data for training and validation. We designed a cross validation procedure with artificially generated impostor samples that improves the learning process yet allows fair comparison to previous works. We evaluated the methods using the CMU keystroke dynamics benchmark dataset. Both proposed approaches outperformed the previou…
DOBRO : a prediction error correcting robot under drifts
2016
We propose DOBRO, a light online learning module, which is equipped with a smart correction policy helping making decision to correct or not the given prediction depending on how likely the correction will lead to a better prediction performance. DOBRO is a standalone module requiring nothing more than a time series of prediction errors and it is flexible to be integrated into any black-box model to improve its performance under drifts. We performed evaluation in a real-world application with bus arrival time prediction problem. The obtained results show that DOBRO improved prediction performance significantly meanwhile it did not hurt the accuracy when drift does not happen.
Investigating serendipity in recommender systems based on real user feedback
2018
Over the past several years, research in recommender systems has emphasized the importance of serendipity, but there is still no consensus on the definition of this concept and whether serendipitous items should be recommended is still not a well-addressed question. According to the most common definition, serendipity consists of three components: relevance, novelty and unexpectedness, where each component has multiple variations. In this paper, we looked at eight different definitions of serendipity and asked users how they perceived them in the context of movie recommendations. We surveyed 475 users of the movie recommender system, MovieLens regarding 2146 movies in total and compared tho…
Cross-Domain Recommendations with Overlapping Items
2016
In recent years, there has been an increasing interest in cross-domain recommender systems. However, most existing works focus on the situation when only users or users and items overlap in different domains. In this paper, we investigate whether the source domain can boost the recommendation performance in the target domain when only items overlap. Due to the lack of publicly available datasets, we collect a dataset from two domains related to music, involving both the users’ rating scores and the description of the items. We then conduct experiments using collaborative filtering and content-based filtering approaches for validation purpose. According to our experimental results, the sourc…
User session level diverse reranking of search results
2018
Most Web search diversity approaches can be categorized as Document Level Diversification (DocLD), Topic Level Diversification (TopicLD) or Term Level Diversification (TermLD). DocLD selects the relevant documents with minimal content overlap to each other. It does not take the coverage of query subtopics into account. TopicLD solves this by modeling query subtopics explicitly. However, the automatic mining of query subtopics is difficult. TermLD tries to cover as many query topic terms as possible, which reduces the task of finding a query's subtopics into finding a set of representative topic terms. In this paper, we propose a novel User Session Level Diversification (UserLD) approach bas…
Exploiting ongoing EEG with multilinear partial least squares during free-listening to music
2016
During real-world experiences, determining the stimulus-relevant brain activity is excitingly attractive and is very challenging, particularly in electroencephalography. Here, spectrograms of ongoing electroencephalogram (EEG) of one participant constructed a third-order tensor with three factors of time, frequency and space; and the stimulus data consisting of acoustical features derived from the naturalistic and continuous music formulated a matrix with two factors of time and the number of features. Thus, the multilinear partial least squares (PLS) conforming to the canonical polyadic (CP) model was performed on the tensor and the matrix for decomposing the ongoing EEG. Consequently, we …
A Serendipity-Oriented Greedy Algorithm for Recommendations
2017
Most recommender systems suggest items to a user that are popular among all users and similar to items the user usually consumes. As a result, a user receives recommendations that she/he is already familiar with or would find anyway, leading to low satisfaction. To overcome this problem, a recommender system should suggest novel, relevant and unexpected, i.e. serendipitous items. In this paper, we propose a serendipity-oriented algorithm, which improves serendipity through feature diversification and helps overcome the overspecialization problem. To evaluate our algorithm and compare it with others, we employ a serendipity metric that captures each component of serendipity, unlike the most …
A two-step, user-centered approach to personalized tourist recommendations
2017
Geo-localized, mobile applications can simplify a tourist visit, making the relevant Point of Interests more easily and promptly discernible to users. At the same time, such solutions must avoid creating unfitting or rigid user profiles that impoverish the users' options instead of refining them. Currently, user profiles in recommender systems rely on dimensions whose relevance to the user is more often presumed than empirically defined. To avoid this drawback, we build our recommendation system in a two-step process, where profile parameters are evaluated preliminarily and separately from the recommendations themselves. We describe this two-step evaluation process including an initial surv…
Semi-automatic literature mapping of participatory design studies 2006--2016
2018
The paper presents a process of semi-automatic literature mapping of a comprehensive set of participatory design studies between 2006--2016. The data of 2939 abstracts were collected from 14 academic search engines and databases. With the presented method, we were able to identify six education-related clusters of PD articles. Furthermore, we point out that the identified clusters cover the majority of education-related words in the whole data. This is the first attempt to systematically map the participatory design literature. We argue that by continuing our work, we can help to perceive a coherent structure in the body of PD research.