Search results for "artificial intelligence"

An Optimization Package for Electrical Distribution Network Reconfiguration

2008

Realizing airtime allocations in multi-hop Wi-Fi networks: A stability and convergence study with testbed evaluation

2019

Abstract REACT is a distributed resource allocation protocol used to negotiate a max–min allocation of airtime for multi-hop ad hoc wireless networks. Two approaches are proposed for a node to realize its REACT allocation in a contention-based MAC protocol. This is achieved by tuning its contention window to a value that corresponds to its allocation. Only a change in the allocation, due to a change in local traffic requirements or local network views, results in re-tuning. The approaches for tuning are implemented in commercial Wi-Fi devices and their stability and convergence are studied experimentally in the w-iLab.t wireless network testbed. These properties are also studied analyticall…

Coexistence between IEEE802.15.4 and IEEE802.11 through cross-technology signaling

2017

When different technologies use the same frequency bands in close proximity, the resulting interference typically results in performance degradation. Coexistence methods exist, but these are often technology specific and requiring technology specific interference detection methods. To remove the root cause of the performance degradation, devices should be able to negotiate medium access even when using different technologies. To this end, this paper proposes an architecture that allows crosstechnology medium access by means of a Time Division Multiple Access (TDMA) scheme. In order to achieve cross-technology synchronization, which is required for the TDMA solution, an energy pattern beacon…

Random access with repeated contentions for emerging wireless technologies

2017

In this paper we propose ReCo, a robust contention scheme for emerging wireless technologies, whose efficiency is not sensitive to the number of contending stations and to the settings of the contention parameters (such as the contention windows and retry limits). The idea is iterating a basic contention mechanism, devised to select a sub-set of stations among the contending ones, in consecutive elimination rounds, before performing a transmission attempt. Elimination rounds can be performed in the time or frequency domain, with different overheads, according to the physical capabilities of the nodes. Closed analytical formulas are given to dimension the number of contention rounds in order…

Prnu Pattern Alignment for Images and Videos Based on Scene Content

2019

This paper proposes a novel approach for registering the PRNU pattern between different camera acquisition modes by relying on the imaged scene content. First, images are aligned by establishing correspondences between local descriptors: The result can then optionally be refined by maximizing the PRNU correlation. Comparative evaluations show that this approach outperforms those based on brute-force and particle swarm optimization in terms of reliability, accuracy and speed. The proposed scene-based approach for PRNU pattern alignment is suitable for video source identification in multimedia forensics applications.

Twitter Analysis for Real-Time Malware Discovery

2017

In recent years, the increasing number of cyber-attacks has gained the development of innovative tools to quickly detect new threats. A recent approach to this problem is to analyze the content of Social Networks to discover the rising of new malicious software. Twitter is a popular social network which allows millions of users to share their opinions on what happens all over the world. The subscribers can insert messages, called tweet, that are usually related to international news. In this work, we present a system for real-time malware alerting using a set of tweets captured through the Twitter API’s, and analyzed by means of a Bayes naïve classifier. Then, groups of tweets discussing th…

Automatic Generation of Custom Tourist Routes

2019

In this paper we present a new tool for the automatic generation of custom tourist routes. Starting from the user preferences (place to visit, starting and ending points, available time, favourite types of attractions) our system is able to extract information from the Web and to suggest a custom route to the user. Our system is based only onto online information, which is dynamically extracted at the query time, so that it can work for every location in the world, with no restrictions. Furthermore, our method does not require any user intervention, unless the input parameters. Our system is also able to give to the users supplementary information about the route stops, as a photo slideshow…

Deep Motion Model for Pedestrian Tracking in 360 Degrees Videos

2019

This paper proposes a deep convolutional neural network (CNN) for pedestrian tracking in 360◦ videos based on the target’s motion. The tracking algorithm takes advantage of a virtual Pan-Tilt-Zoom (vPTZ) camera simulated by means of the 360◦ video. The CNN takes in input a motion image, i.e. the difference of two images taken by using the vPTZ camera at different times by the same pan, tilt and zoom parameters. The CNN predicts the vPTZ camera parameter adjustments required to keep the target at the center of the vPTZ camera view. Experiments on a publicly available dataset performed in cross-validation demonstrate that the learned motion model generalizes, and that the proposed tracking algo…

Conceptual Commitments of AGI Systems

2013

Standardisation of Artificial Intelligence: Making a “New World” Brave, with Support of Human Requirements in a Machine Intelligence Environment

2022

In line with previous industrial revolutions, standardisation must accompany the deployment of artificial intelligence systems that promise to revolutionise the way we live (home automation, autonomous vehicles, EdTech, etc.) and work (collaborative industrial robots, agricultural robots, inspection and maintenance robots, LegalTech, FinTech, etc.). The standards produced and promoted in Europe will be resolutely geared towards the protection of people and property, thus promoting the acceptability of these intelligent systems and the common interest. They will have to cover the requirements expected of AIs, but also the means and methods for assessing them. The new standards will have to c…