Search results for "artificial intelligence"

Service level guarantee framework for IoT environments

2017

Nowadays, providing IoT environments with service level guarantee is a challenging task. We propose a framework for IoT service level guarantee thanks to several specific Service Level Agreements (SLAs) for IoT environments. We specify different SLAs for each entity contributing in our IoT architecture in order to conclude a global SLA called IoT-SLA (iSLA). These different SLAs enable IoT service provision with Quality of Service (QoS) guarantee. Achieving this guarantee requires several communications and interactions between the components of the proposed IoT architecture. These interactions allow an IoT Service Provider (IoT-SP) to conclude the iSLA with an IoT Client (IoT-C). We specif…

A Hybrid Algorithm Based on WiFi for Robust and Effective Indoor Positioning

2019

Indoor positioning based on the Wireless Fidelity (WiFi) protocol and the Pedestrian Dead Reckoning (PDR) approach is widely exploited because of the existing WiFi infrastructure in buildings and the advancement of built-in smartphone sensors. In this work, a hybrid algorithm that combines WiFi fingerprinting and PDR to both exploit their advantages as well as limiting the impact of their disadvantages is proposed. Specifically, to build a probability map from noisy Received Signal Strength (RSS), a Gaussian Process (GP) regression is deployed to estimate and construct the RSS fingerprints with incomplete data. Mean and variance of generated points are used to estimate WiFi fingerprinting p…

Fast algorithm for detection of reference spheres in digital panoramic radiography.

2009

In this paper, an algorithm for detection of reference spheres from digital panoramic radiographic images is presented. The proposed algorithm was tested on a database of 107 digital panoramic radiographic images which were used for dental diagnostics. Results show that the proposed method exhibits for detection of reference spheres, a sensitivity of 97.33% and specificity of 93.85%. Performance time differed between 0.55 and 2.36s depending on image size. The aim of this work was to provide a fast ellipse detection algorithm to reduce measuring time on preoperative implant planning by lowering the computational cost.

Emulating Human Supervision in an Intelligent Tutoring System for Arithmetical Problem Solving

2014

This paper presents an intelligent tutoring system (ITS) for the learning of arithmetical problem solving. This is based on an analysis of a) the cognitive processes that take place during problem solving; and b) the usual tasks performed by a human when supervising a student in a one-to-one tutoring situation. The ITS is able to identify the solving strategy that the student is following and offer adaptive feedback that takes into account both the problem's constraints and the decisions previously made by the user. An observational study shows the ITS's accuracy at emulating expert human supervision, and a randomized experiment reveals that the ITS significantly improves students' learning…

Chapter 3. Prosodic versatility, hierarchical rank and pragmatic function in conversational markers

2019

Experimental Characterization of Mobile Fading Channels Aiming the Design of Non-Wearable Fall Detection Radio Systems at 5.9 GHz

2016

One of the major concerns for the independent living of elderlies is a fall incident. To decrease human interaction errors and user privacy concerns of existing fall detection systems, a new generation of fall detection systems is emerging. The new trend is to design non-wearable devices that can monitor the physical activities of the home user using radio waves reflected off the body. This paper reports an in-home radio measurement campaign at 5.9 GHz, which has been conducted to study the impacts of different physical activities of the user, including fall incidents, on the channel transfer function (CTF) and the power delay profile (PDP) of indoor mobile radio channels. The home is equip…

A Sentiment Enhanced Deep Collaborative Filtering Recommender System

2021

Recommender systems use advanced analytic and learning techniques to select relevant information from massive data and inform users’ smart decision-making on their daily needs. Numerous works exploiting user’s sentiments on products to enhance recommendations have been introduced. However, there has been relatively less work exploring higher-order user-item features interactions for sentiment enhanced recommender system. In this paper, a novel Sentiment Enhanced Deep Collaborative Filtering Recommender System (SE-DCF) is developed. The architecture is based on a Neural Attention network component aggregated with the output predictions of a Convolution Neural Network (CNN) recommender. Speci…

Reconstruction Improvement in Integral Fourier Holography by Micro-Scanning Method

2015

Although integral holography has many promising advantages in the field of 3D imaging, the resolution of reconstructed holographic image is still limited by the insufficient information captured. To improve the reconstruction quality, an integral Fourier holographic imaging method based on micro-scanning of the micro-lens array is proposed in this paper. The micro-scanning of the micro-lens array can increase the sampling rate in spatial frequency domain and the information of the generated Fourier hologram, which will eventually eliminate the overlapping effect in the reconstructed 3D image. Experiments for different micro-scanning modes are carried out to verify the feasibility of the pro…

Polarization-based Robot Orientation and Navigation

2015

From insects in your garden to creatures in the sea, inspiration can be drawn from nature to design a whole new class of smart robotic devices. These smart machines may move like living creatures. They can be launched toward a specific target for a pre-defined task. Bio-inspiration is developing to meet the needs of many challenges particularly in machine vision. Some species in the animal kingdom like cephalopods, crustaceans and insects are distinguished with their visual capabilities which are strongly improved by means of polarization. This work surveys the most recent research in the area of bio-inspired polarization based robot orientation and navigation. Firstly, the authors will bri…

Locality-sensitive hashing enables signal classification in high-throughput mass spectrometry raw data at scale

2021

Mass spectrometry is an important experimental technique in the field of proteomics. However, analysis of certain mass spectrometry data faces a combination of two challenges: First, even a single experiment produces a large amount of multi-dimensional raw data and, second, signals of interest are not single peaks but patterns of peaks that span along the different dimensions. The rapidly growing amount of mass spectrometry data increases the demand for scalable solutions. Existing approaches for signal detection are usually not well suited for processing large amounts of data in parallel or rely on strong assumptions concerning the signals properties. In this study, it is shown that locali…