Iskanje po katalogu digitalne knjižnice

Opis: The importance and value of real-world data in healthcare cannot be overstated because it offers a valuable source of insights into patient experiences. Traditional patient-reported experience and outcomes measures (PREMs/PROMs) often fall short in addressing the complexities of these experiences due to subjectivity and their inability to precisely target the questions asked. In contrast, diary recordings offer a promising solution. They can provide a comprehensive picture of psychological well-being, encompassing both psychological and physiological symptoms. This study explores how using advanced digital technologies, i.e., automatic speech recognition and natural language processing, can efficiently capture patient insights in oncology settings. We introduce the MRAST framework, a simplified way to collect, structure, and understand patient data using questionnaires and diary recordings. The framework was validated in a prospective study with 81 colorectal and 85 breast cancer survivors, of whom 37 were male and 129 were female. Overall, the patients evaluated the solution as well made; they found it easy to use and integrate into their daily routine. The majority (75.3%) of the cancer survivors participating in the study were willing to engage in health monitoring activities using digital wearable devices daily for an extended period. Throughout the study, there was a noticeable increase in the number of participants who perceived the system as having excellent usability. Despite some negative feedback, 44.44% of patients still rated the app’s usability as above satisfactory (i.e., 7.9 on 1–10 scale) and the experience with diary recording as above satisfactory (i.e., 7.0 on 1–10 scale). Overall, these findings also underscore the significance of user testing and continuous improvement in enhancing the usability and user acceptance of solutions like the MRAST framework. Overall, the automated extraction of information from diaries represents a pivotal step toward a more patient-centered approach, where healthcare decisions are based on real-world experiences and tailored to individual needs. The potential usefulness of such data is enormous, as it enables better measurement of everyday experiences and opens new avenues for patient-centered care.
Ključne besede: multilingual framework, risk assessment, symptom tracking, chronic diseases, patient-centered care, real-world data
Objavljeno v DKUM: 12.08.2024; Ogledov: 74; Prenosov: 8
Celotno besedilo (5,29 MB)

Opis: As the market of electrified vehicles is rapidly growing, the requirements for new products are also increasing, meaning the required development and production times are getting increasingly shorter. Therefore, the major interest in current active research is how to optimize the development process. Within this master’s thesis, we developed the base framework for a digital twin for wiring harness development and cross section optimization. It allows engineering teams to develop a digital replica of the desired physical system, which can be the basis for further review and optimization analyses, already at the development stage.
Ključne besede: digitalni dvojček, kabelski snop, presek, kabel, konektor
Objavljeno v DKUM: 31.01.2024; Ogledov: 382; Prenosov: 0

Opis: Sodobna vozila postajajo vse bolj zmogljivi in zapleteni elektronski sistemi. Dandanes je zato eden od izzivov, s katerimi se moramo soočiti, ob taki kompleksnosti zagotoviti tudi varna, robustna, hitra in visoko zanesljiva vozila. V magistrski nalogi se osredotočamo predvsem na analizo izvajanja storitveno usmerjenih komunikacijskih protokolov v avtomobilski vmesni programski opremi, potrebni za visoko zmogljive računalniške krmilne enote. Naš cilj je med drugim tudi oceniti zmogljivosti dveh storitveno orientiranih komunikacijskih protokolov pod določenimi pogoji. Protokola DDS in SOME/IP se na splošno izvajata na visoko zmogljivem računalniku skupaj s prilagodljivo vmesno programsko opremo Adaptive AUTOSAR Platform Demonstrator.
Ključne besede: AUTOSAR, Yocto, vsomeip, OpenDDS, Cyclone DDS, Linux, kernel, Bash, R, C++
Objavljeno v DKUM: 08.11.2022; Ogledov: 524; Prenosov: 61
Celotno besedilo (13,38 MB)

Opis: Brezžična tehnologija kratkega dosega oz. tehnologija NFC se uporablja že v mnogih dandanašnjih napravah. To tehnologijo je namreč mogoče uporabiti za najrazličnejše namene, kot so: identifikacija osebe, odpiranja vrat, plačevanja s kreditno kartico itd. Tehnologija NFC že leta pridobiva na pomenu. Ustanovil se je tudi forum NFC z namenom razvijati nove specifikacije in prilagajanja arhitekture NFC novim ciljem. V okviru tega je nastala tudi nova tehnologija WLC – specifikacija brezžičnega polnjenja, ki omogoča majhnim elektronskim napravam NFC brezžično polnjenje s prenosi moči do 1 W. V magistrski nalogi smo se osredotočili na antene, ki izhajajo iz standarda NFC Forum WLC. Cilj naloge je bilo določiti vrednosti faktorja sklopitve po celotnem območju delovanja anten iz standarda NFC Forum WLC. Pri raziskovnaju magnetno sklopljenega sistema smo preučevali medsebojno induktivnost, ki je ključni parameter za izračun faktorja sklopitve, ter tudi induktivnosti obeh anten. Vse opravljene meritve smo s pomočjo programskega jezika Python predstavili na grafih, ki prikazujejo vrednosti faktorja sklopitve v vseh izmerjenih točkah specificiranega delovnega volumna. Dodali smo tudi tehnični prikaz uvoza podatkov v programsko opremo PathWave Advanced Design System (ADS), ki jo lahko uporabimo v primeru uporabe izmerjenih podatkov za simuliranje. Odločili smo se za tri načine, kako izmeriti karakteristiko zračno sklopljenega sistema, sestavljenega iz dveh anten s standardom NFC Forum WLC. Tako smo prikazali naslednje tri metode merjenja faktorja sklopitve: – dvo-vhodno meritev z napravo VNA, – eno-vhodno meritev z napravo VNA, z metodo Odprt-Zaprt, – osciloskop in frekvenčni generator. Vse postavitve delovnega prostora smo pomerili s štirimi različnimi pozicijskimi kombinacijami med sprejemnikom in oddajnikom. Ker ima antena sled natisnjeno le na eni površini tiskane plošče, je merilni proces pokazal razliko. Če sta bili anteni obrnjeni ena proti drugi s tiskano stranjo, je bila vrednost faktorja sklopitve visoka. Če pa sta bili anteni obrnjeni s hrbtno stranjo ena proti drugi, je bila vrednost faktorja sklopitve veliko nižja. V primeru, da sta bili anteni obrnjeni v enako smer in je bila spodnja antena sprejemnik, zgornja pa oddajnik ali obratno, je bila vrednost faktorja sklopitve enaka. Vse merilne procese in ugotovitve smo želeli tudi teoretično ovrednotiti. Prikazali smo tri različne načine uvoza podatkov v programsko opremo za razvijanje in simuliranje radio-frekevenčnih sistemov ADS. Glede na rezultate merjenja bi bilo mogoče faktor sklopitve v določenih pozicijah delovnega prostora izboljšati, če bi bila antena koncentrična – s tem bi namreč povečali vrednost faktorja v smereh, kjer je sedaj antena krajša. V primeru simetrije bi v vse smeri definiranega delovnega prostora dobili tako enake vrednosti. Če bi bila antena koncentrične oblike, bi bila posledično večja, s tem pa bi imeli težavo za vgradnjo v manjše električne naprave. Za konec smo v magistrski nalogi podali še meritve z CNC-robotom. V tem primeru smo antene postavili v referenčne pozicije in definirali nov, večji delovni volumen. Iz rezultatov meritve pa smo nato raziskovali spreminjanje faktorja sklopitve izven definiranega delovnega volumna.
Ključne besede: NFC, WLC, oddajnik, sprejemnik, medsebojna induktivnost, faktor sklopitve, iso površina.
Objavljeno v DKUM: 17.10.2022; Ogledov: 380; Prenosov: 0

Opis: This master's thesis presents an advanced video system with human presence detection based on deep learning and an ARM microcontroller. The objective of the thesis is to develop a system that works as a smart video intercom, which could be installed, e.g. on the entrance door, and autonomously alert the owner that a guest is in front of the door. The main goal is to use an AI algorithm, namely the neural network model on a constrained device, such as an ARM microcontroller, as their main advantage is lower power consumption and cost. The thesis also describes commonly used methods to reduce the power and memory footprint and to implement and accelerate the deep learning algorithms more effectively. Further, the most notable deep learning hardware and some general platforms are described in more detail. The thesis also presents the development of a human presence detection system based on an ARM microcontroller, VGA camera, and LCD, where Tensorflow Lite Micro, an open-source C++ framework for deploying deep learning models to embedded platforms and a pre-trained neural network model for person presence detection are used.
Ključne besede: TensorFlow Lite Micro, Video intercom system, ARM Cortex-M microcontroller, Human presence detection, Neural network
Objavljeno v DKUM: 08.07.2022; Ogledov: 783; Prenosov: 57
Celotno besedilo (7,86 MB)