Search results for "kommunikasjon"
showing 10 items of 768 documents
Environment Sound Classification using Multiple Feature Channels and Attention based Deep Convolutional Neural Network
2020
In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism. The novelty of the paper lies in using multiple feature channels consisting of Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Frequency Cepstral Coefficients (GFCC), the Constant Q-transform (CQT) and Chromagram. Such multiple features have never been used before for signal or audio processing. And, we employ a deeper CNN (DCNN) compared to previous models, consisting of spatially separable convolutions working on time and feature domain separately. Alongside, we use atten…
Biometric Fish Classification of Temperate Species Using Convolutional Neural Network with Squeeze-and-Excitation
2019
Our understanding and ability to effectively monitor and manage coastal ecosystems are severely limited by observation methods. Automatic recognition of species in natural environment is a promising tool which would revolutionize video and image analysis for a wide range of applications in marine ecology. However, classifying fish from images captured by underwater cameras is in general very challenging due to noise and illumination variations in water. Previous classification methods in the literature relies on filtering the images to separate the fish from the background or sharpening the images by removing background noise. This pre-filtering process may negatively impact the classificat…
Word-level human interpretable scoring mechanism for novel text detection using Tsetlin Machines
2021
Recent research in novelty detection focuses mainly on document-level classification, employing deep neural networks (DNN). However, the black-box nature of DNNs makes it difficult to extract an exact explanation of why a document is considered novel. In addition, dealing with novelty at the word-level is crucial to provide a more fine-grained analysis than what is available at the document level. In this work, we propose a Tsetlin machine (TM)-based architecture for scoring individual words according to their contribution to novelty. Our approach encodes a description of the novel documents using the linguistic patterns captured by TM clauses. We then adopt this description to measure how …
Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples
2022
In this article, we propose a novel algorithm for deep reinforcement learning named Expert Q-learning. Expert Q-learning is inspired by Dueling Q-learning and aims at incorporating semi-supervised learning into reinforcement learning through splitting Q-values into state values and action advantages. We require that an offline expert assesses the value of a state in a coarse manner using three discrete values. An expert network is designed in addition to the Q-network, which updates each time following the regular offline minibatch update whenever the expert example buffer is not empty. Using the board game Othello, we compare our algorithm with the baseline Q-learning algorithm, which is a…
Dynamics of inertial pair coupled via frictional interface
2022
Understanding the dynamics of two inertial bodies coupled via a friction interface is essential for a wide range of systems and motion control applications. Coupling terms within the dynamics of an inertial pair connected via a passive frictional contact are non-trivial and have long remained understudied in system communities. This problem is particularly challenging from a point of view of modeling the interaction forces and motion state variables. This paper deals with a generalized motion problem in systems with a free (of additional constraints) friction interface, assuming the classical Coulomb friction with discontinuity at the velocity zero crossing. We formulate the dynamics of mot…
Innføring av CRM i offentlig sektor
2007
Masteroppgave i informasjonssystemer 2007 - Høgskolen i Agder, Kristiansand Modernisering av offentlig sektor basert på informasjons- og kommunikasjonsteknologi (IKT) er i økende grad et fokusområde under begrepet e-forvaltning. Dette har ført til nye teknologiske muligheter og arbeidsmåter internt og eksternt mellom offentlige organisasjoner, næringslivet og innbyggere. Integrering av isolerte systemer til standardiserte og virksomhetsomfattende informasjonssystemer har potensiale til å samle informasjonsflyten i en organisasjon. Dette kan skape radikale endringer både fra et organisatorisk og et teknologisk perspektiv. Customer Relationship Management (CRM) er et konsept fra privat sektor…
Scenario-based Serious Game to Teach about Healthcare
2019
Author's accepted manuscript (postprint). © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Available from 29/10/2021. In this paper, we explore the concept of a scenario-based serious game for healthcare solutions. The complexity of the interactions and the multitude of actors is captured in a scenario, which is then played with the help of an additional game pl…
Deep Learning for Classifying Physical Activities from Accelerometer Data
2021
Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify the physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the proposed models on two phy…
Secure and scalable dataprocessing and communications for an Animal Tracking System
2003
Masteroppgave i informasjons- og kommunikasjonsteknologi 2003 - Høgskolen i Agder, Grimstad Modern technology is constantly being employed in new fields, by new industries and people. The cost of advanced technological equipment decreases continously, and equipment that was reserved for people and corporations with a lot of money has now become household products. This enables many interesting ideas and projects, Kitron Development’s radiocollar project being one of them. Kitron Development is involved in a project to track the position of animals by substituting the traditional bell collar with a collar that contains a GPS receiver. The collar transmits its position to a base station using…
A Trajectory-Driven 3D Non-Stationary mm-Wave MIMO Channel Model for a Single Moving Point Scatterer
2021
This paper proposes a new non-stationary three-dimensional (3D) channel model for a physical millimeter wave (mm-Wave) multiple-input multiple-output (MIMO) channel. This MIMO channel model is driven by the trajectory of a moving point scatterer, which allows us to investigate the impact of a single moving point scatterer on the propagation characteristics in an indoor environment. Starting from the time-variant (TV) channel transfer function, the temporal behavior of the proposed non-stationary channel model has been analyzed by studying the TV micro-Doppler characteristics and the TV mean Doppler shift. The proposed channel model has been validated by measurements performed in an indoor e…