Search results for "image"
showing 10 items of 6818 documents
Comparison of feature importance measures as explanations for classification models
2021
AbstractExplainable artificial intelligence is an emerging research direction helping the user or developer of machine learning models understand why models behave the way they do. The most popular explanation technique is feature importance. However, there are several different approaches how feature importances are being measured, most notably global and local. In this study we compare different feature importance measures using both linear (logistic regression with L1 penalization) and non-linear (random forest) methods and local interpretable model-agnostic explanations on top of them. These methods are applied to two datasets from the medical domain, the openly available breast cancer …
A Curvature Based Method for Blind Mesh Visual Quality Assessment Using a General Regression Neural Network
2016
International audience; No-reference quality assessment is a challenging issue due to the non-existence of any information related to the reference and the unknown distortion type. The main goal is to design a computational method to objectively predict the human perceived quality of a distorted mesh and deal with the practical situation when the reference is not available. In this work, we design a no reference method that relies on the general regression neural network (GRNN). Our network is trained using the mean curvature which is an important perceptual feature representing the visual aspect of a 3D mesh. Relatively to the human subjective scores, the trained network successfully asses…
Multi-agent control architecture for RFID cyberphysical robotic systems initial validation of tagged objects detection and identification using Playe…
2016
International audience; The objective of this paper is to describe and validate a multi-agent architecture proposed to control RFID Cyber-Physical Robotic Systems. This environment may contain human operators, robots (mobiles, manipulators, mobile manipulators, etc.), places (workrooms, walls, etc.) and other objects (tables, chairs, etc.). The proposed control architecture is composed of two types of agents dispatched on two levels. We find at the Organization level a Supervisory agent to allow operators to configure, manage and interact with the overall control system. At the Control level, we distinguish the Robots agents, to each robot (mobiles, manipulators or mobile manipulators) is a…
El cuerpo materno en la red: entre el orden de lo ?deseable? y el de lo real
2019
El estilo de vida fitness se realiza en, y a través de, un entramado subjetivo y de poder en el que circulan y se ensamblan dispositivos empresariales, terapéuticos, sanitarios y de espectacularización de los cuerpos, tendientes a inscribir la vida de la población en las tramas conflictivas de un capitalismo heterosexista, neoliberal e informacional. En dicho marco, la temporalidad, metamorfosis y plasticidad del cuerpo materno irrumpe como problema y objeto de intervención de tecnologías diversas orientadas a ajustar su tamaño, forma y devenir a los parámetros de la vida activa y saludable. En escenarios digitales, dicha tensión se materializa, por un lado, a través de dispositivos visuale…
Two-step cross correlation-based algorithm for motion estimation applied to fertilizer granules' motion during centrifugal spreading
2011
Imaging systems are progressing in both accuracy and ro- bustness, and their use in precision agriculture is increasing accordingly. One application of imaging systems is to understand and control the cen- trifugal fertilizing spreading process. Predicting the spreading pattern on the ground relies on an estimation of the trajectories and velocities of ejected granules. The algorithms proposed to date have shown low ac- curacy, with an error rate of a few pixels. But a more accurate estimation of the motion of the granules can be achieved. Our new two-step cross- correlation-based algorithm is based on the technique used in particle image velocimetry (PIV), which has yielded highly accurate…
El cineasta como "flâneur". trazado y formalización de la imagen documental en Guest (José Luis Guerin, 2010)
2015
Chronic neural probe for simultaneous recording of single-unit, multi-unit, and local field potential activity from multiple brain sites
2017
Drug resistant focal epilepsy can be treated by resecting the epileptic focus requiring a precise focus localisation using stereoelectroencephalography (SEEG) probes. As commercial SEEG probes offer only a limited spatial resolution, probes of higher channel count and design freedom enabling the incorporation of macro and microelectrodes would help increasing spatial resolution and thus open new perspectives for investigating mechanisms underlying focal epilepsy and its treatment. This work describes a new fabrication process for SEEG probes with materials and dimensions similar to clinical probes enabling recording single neuron activity at high spatial resolution.Polyimide is used as a bi…
A deep learning segmentation approach to calories and weight estimation of food images
2019
Master's thesis Information- and communication technology IKT590 - University of Agder 2019 Today’s generation is very aware of what they are eating and the amountof calories in their food. Eating too many calories can lead to increasedweight, which has become a big health issue. A study from 2016 states thatmore than 1,9 billion adults are overweight where almost one third of theseare obese. Statistics from Norway show that 1 of 4 men and 1 of 5 womenare obese.Artificial Intelligence in general and deep learning in particular can be usedto help understand the content of eaten food. In this master thesis, wepropose a network to estimate the weight of food from a single image. Thisis done in…
Muscular Strength Imbalances Are not Associated with Skin Temperature Asymmetries in Soccer Players
2020
Although strength imbalances using isokinetic dynamometer have been examined for injury risk screening in soccer players, it is very expensive and time-consuming, making the evaluation of new methods appealing. The aim of the study was to analyze the agreement between muscular strength imbalances and skin temperature bilateral asymmetries as well as skin temperature differences in the hamstrings and quadriceps. The skin temperature of the anterior and posterior thigh of 59 healthy male soccer athletes was assessed at baseline using infrared thermography for the identification of hamstrings-quadriceps skin temperature differences and thermal asymmetries (>
Monitoring deforestation and forest degradation linking high-resolution satellite data and field data in the context of REDD+. A case of Tanzania
2017
El principal objetivo de este doctorado es apoyar el desarrollo de un sistema nacional de monitoreo forestal en Tanzania para informar sobre las emisiones actuales e históricas derivadas de la deforestación y la degradación forestal. El marco de la tesis se centra específicamente en el emergente contexto internacional de la iniciativa REDD + (Reducción de Emisiones por Deforestación y Degradación) de las Naciones Unidas, bajo la cual los países pueden obtener subsidios financieros para demostrar que están reduciendo sus emisiones de carbono de tierras forestales con respecto a su práctica histórica reciente. La investigación se centró en cinco áreas de investigación: La parte (1) revisa los…