Nelson Baloian N. Baloian, J. Frez, C. Fuenzalida, B. Panay, S. Peñafiel, J. A. Pino, and H. Sanson Universudad de Chile, Department of computer sciences Abstract: Retail store managers need to measure the effect of promotions have in terms of the number of people visiting a store and sales in order to make decisions for an efficient use of resources. The state or the art approach to this problem is the authors propose to measure the effects of a promotion is to develop a predictor for the number of people entering the store, in conditions of absence of any promotion campaigns and then compare the output against…
-
-
Explaining and Visualizing Recurrent Neural Network Decisions
Presentation D.Qaramyan and H. Khachatrian Yerevan State University Abstract: Coming Soon Discussion Room: Explaining and Visualizing Recurrent Neural Network Decisions
-
Promotion of Continuous Use of a Self-guided Mental Healthcare System by Using a Chatbot
Boyu Sun T. Kamita, A. Matsumoto, T. Ito, and T. Inoue University of Tsukuba Abstract: Although the stress check registration has been introduced in Japan as a measure to employee mental disorders in companies, there are few employees who wish to have an interview with an industrial physician even if they receive a high stress judgment. Thus, promotion of self-care is required at the same time. The authors developed the digital content from the SAT counseling method, a VR self-guided mental health care system that used the content, and found its stress reduction effect. Then, we developed a chatbot system on a smartphone that used…
-
Online Collaborative Question Refinement Method to Increase Students’ Posed Question Quality
Ari Nugraha A. Nugraha, I. A. Wahono, J. Zhanghe, and T. Inoue University of Tsukuba Abstract: Collaborative learning enables students to develop higher-order thinking skills and achieve richer knowledge generation. In this study we combined online collaborative learning with the student question posing activity to increase students’ posed question quality guided by a question quality level taxonomy. Utilizing off-the-shelf online tools from the Internet, we proposed an online learning method for students to collaboratively pose question and refine their questions based on the learning material they have watched before. Discussion Room: Online Collaborative Question Refinement Method to Increase Students’ Posed Question Quality…
-
Automatic Image Classification Supported by Expert Knowledge
Sergio Peñafiel S.Peñafiel, B. Panay, N. Baloian, J. A. Pino, and W. Luther Universidad de Chile Abstract: In recent years, several algorithms have been proposed to solve image classification problems mainly based on convolutional neural networks which have reached high levels of accuracy. However, new studies state that these models are unstable, very sensitive to noise and requires many data samples to train. We propose a two-phase method to perform expert assisted image classification, in the first steps experts define constraints for the problem to look only at the important aspects of the image, in the second phase we trained a model using the values of the…
-
Protecting Query Privacy Through Semantic Caching in Location-Based Services
Patricio Galdames F. Vera-Catricura, P. Galdames, C. Gutierrez-Soto, and A. Curiel Chile Universidad del Bio-Bio Abstract: We plan to address the problem of processing Location-Based Queries (LBQ) in a MANET for preserving query privacy as much as possible. Our idea is that mobile users will first ask themselves for solving a query before any user decides to submit its query to an untrusted LBS. Our first goal is to define a collaborative caching strategy to be run by the mobile users themselves that exploit the geographic and semantic similarities among the LBQs to perform efficient processing of LCQs. Our second goalto protect a user’s query privacy when any…
-
A Batching Cloaking Scheme for Continuous Location-Based Services
Patricio Galdames C. Faúndez, P. Galdames, C. Gutierrez-Soto and P. Campos-Soto Chile Universidad del Bio-Bio Abstract: Nowadays, the expanded use of LBSs involves opportunities to the adversaries threatening the location privacy of mobile users. Several approaches have been proposed to tackle either location privacy, location safety, and query privacy independently. In this paper, we present a work in progress, which aims to propose a unified framework to protect privacy in all these dimensions simultaneously. The demand for query-privacy protection for many users will be addressed in batch. Discussion Room: A Batching Cloaking Scheme for Continuous Location-Based Services [email protected]
-
Verification and Validation Assessment in Genetic Counseling and Testing
Ekaterina Auer Ekaterina Auer and Wolfram Luther University of Applied Sciences Wismar University of Duisburg-Essen Abstract: In this talk, we apply reliable verification and validation analysis in the context of risk assessment, genetic counseling and testing with the focus on breast cancer. This process is highly affected by uncertainty. However, reliability of test interpretations and counseling conclusions is especially important since they have direct influence on humans and their decisions. Based on multi-criteria binary decision trees and interval analysis, we extend the referral screening tool, designed to facilitate referral of patients at risk of breast cancer for genetic counseling and testing, with three further available risk assessment tools…
-
Inner Bound of E-capacity-Equivocation Region for the Generalized Wiretap Channel
Mariam Haroutunian Institute for Informatics and Automation Problems of NAS of RA Abstract: The problem of information theoretic security recently has attracted great attention. One of the problems concerns secure communication over a wiretap channel. The aim in the general wiretap channel model is to maximize the rate of the reliable communication from the source to the legitimate receiver, while keeping the confidential information as secret as possible from the eavesdroper (wiretapper). We introduce and investigate the E-capacity-equivocation region for the wiretap channel, which is the generalization of the capacity-equivocation region studied by Csisz\’ar and K\”orner. It is the closure of the set of all achievable…
-
Small is Beautiful – Temporal Accelerators for Embedded FPGAs
Christopher Cichiwskyj Christopher Cichiwskyj, Gregor Schiele University of Duisburg-Essen Abstract: When the complexity of a problem rises, its solution needs more hardware resources. A usual way to solve this is to use larger processors and add more memory. When using Field Programmable Gate-Arrays (FPGAs), which can instantiate arbitrary circuit designs, a larger, more costly and power hungry chip is used. In this extended abstract we propose a different approach, namely to split the problem into a graph of interdependent smaller tasks and to reconfigure a small FPGA during runtime to execute each of these tasks efficiently sequentially. This can result in cheaper and more energy efficient systems that…