In interactive data analysis processes, the dialogue between human and computer is enabling mechanism that can lead to actionable observations about phenomena being investigated. It of paramount importance this not interrupted by slow computational mechanisms do consider any known temporal human-computer interaction characteristics prioritize perceptual cognitive capabilities users. cases where involves an integrated method, for instance reduce dimensionality or perform clustering, such...

Customer retention is crucial in a variety of businesses as acquiring new customers often more costly than keeping the current ones. As consequence, churn prediction has attracted great attention from both business and academic worlds. Traditional efforts financial domain mainly focus on specific variables such product ownership or service usage aggregation, however, without considering dynamic behavioral patterns customers' transactions. In this paper, we attempt to fill gap by...

Abstract Much recent work has illuminated the growth, innovation, and prosperity of entire cities, but there is relatively less evidence concerning growth individual neighborhoods. In this paper we show that diversity amenities within a city neighborhood, computed from openly available points interest on digital maps, accurately predicts human mobility (“flows”) between neighborhoods these flows predict neighborhood economic productivity. Additionally, consumption behaviour or together with...

Experiences from various industries show that companies may have problems collecting customer invoice payments. Studies report almost half of the small- and medium-sized enterprise business-to-business invoices in United States Kingdom are paid late. In this study, our aim is to understand behavior regarding payments, propose an analytical approach learning predicting payment behavior. Our logic can then be embedded into a decision support system where makers make predictions future take...

Reading comprehension is difficult to improve for children with dyslexia because of the continuing demands orthographic decoding in combination limited working memory capacity. Children get special education that improves spelling, phonemic and vocabulary awareness, however latest research indicated does not reading comprehension. With aim improving comprehension, speed all other abilities dyslexia, Auto Train Brain a novel mobile app using neurofeedback multi-sensory learning methods was...

Recommending relevant items to users has become an important task in many systems due the increased amount of data produced. For this purpose, transaction datasets such as credit card transactions and e-commerce purchase histories can be used recommendation understand underlying user interests by exploiting user-item interactions, which a powerful signal perform task. This study proposes link prediction-based system combining graph representation learning algorithms gradient boosting...

Multiscale entropy analysis (MSE) is a novel entropy-based approach for measuring dynamical complexity in physiological systems over range of temporal scales. MSE has been successfully applied the literature when autism traits, Alzheimer's, and schizophrenia. However, until now, there no research on to children with dyslexia. In this study, we have EEG data an experimental group consisting dyslexia as well control typically developing compared results. The comprised 16 participants who...

Abstract What predicts a neighborhood’s adaptability to essential public health policies and shelter-in-place regulations that prevent the harmful spread of COVID-19? To answer this question, we present novel application human mobility patterns behavior in network setting. We analyze 2 years data (January 2019 December 2020) from New York City construct weekly networks between census block groups based on aggregated point-of-interest visit patterns. Our results indicate neighborhoods’...

Whenever companies plan to enter new geographical areas, they need disaggregated sales in each location. To make such predictions, time series or final customers' data disaggregation are necessary. However, for most companies, datasets unavailable impractical. The manuscript has two main goals. One focal problem is how disaggregate an aggregate prediction with no historical proportions. other improve spatial models using Point of Interest (POI) data. solve these problems, we combine...

In this paper we present a new framework in Augmented Reality context for rapid evaluation of prototypes before manufacture. The design such is time consuming process, leading t o the need previous realistic interactive environments. We have extended definition modelling object geometry with behaviour being able to evaluate them mixed environment. Such enhancements allow development tools and methods test behaviour, perform interactions between real virtual humans complex objects.We propose...

Crowds must be simulated believable in terms of their appearance and behavior to improve a virtual environment's realism. Due the complex nature human behavior, realistic agents crowd simulations is still challenging problem. In this paper, we propose novel behavioral model which builds analytical maps control agents' adaptively with agent–crowd interaction formulations. We introduce information theoretical concepts construct automatically. Our can integrated into simulators enhance...

This paper introduces a technique to analyze and visualize social networks using Shannon's entropy model. Entropy is exploited measure the information amount in network graphs, conduct sensitivity analyses. Novel measures such as degree, betweenness closeness entropies are evaluated find change graph or actors. In this work we present visualization approach that uses coloring, sizing filtering help users perceive communicated information. The result of analyses integrated into caused by...

The right to protest is perceived as one of the primary civil rights. Citizens participate in mass demonstrations express themselves and exercise their democratic However, because large number participants, protests may lead violence destruction, hence can be costly. Thus, it important predict such advance safeguard against damages. Recent research has shown that about 75 percent are regarded legal, planned advance. Twitter, prominent micro-blogging website, been used a tool by protestors...

Current virtual reality technologies provide many ways to interact with humans. Most of those techniques, however, are limited synthetic elements and require cumbersome sensors. We have combined a real-time simulation rendering platform real-time, non-invasive vision-based recognition system investigate interactions in mixed environment real elements. In this paper, we present the resulting system, example checkers game between person an autonomous human demonstrate its performance.

AutoTrainBrain is a neurofeedback and multi-sensory based mobile phone software application, designed in Sabancı University laboratory with the aim of improving cognitive functions dyslexic children. It reads electroencephalography (EEG) signals from 14 channels eMotiv EPOC+ processes these to provide child for brain visual auditory cues real time. has been applied 14-year old child, 10 minutes per week 9 consecutive weeks. The EEG data analyzed by using following three approaches:...