Učni načrt predmeta

Predmet:
Ambientalna inteligenca
Course:
Ambient Intelligence
Študijski program in stopnja /
Study programme and level		 Študijska smer /
Study field		 Letnik /
Academic year		 Semester /
Semester
Informacijske in komunikacijske tehnologije, 3. stopnja Inteligentni sistemi in robotika 1 1
Information and Communication Technologies, 3rd cycle Intelligent Systems and Robotics 1 1
Vrsta predmeta / Course type
Izbirni / Elective
Univerzitetna koda predmeta / University course code:
IKT3-626
Predavanja
Lectures		 Seminar
Seminar		 Vaje
Tutorial		 Klinične vaje
work		 Druge oblike
študija		 Samost. delo
Individ. work		 ECTS
15 15 15 105 5

*Navedena porazdelitev ur velja, če je vpisanih vsaj 15 študentov. Drugače se obseg izvedbe kontaktnih ur sorazmerno zmanjša in prenese v samostojno delo. / This distribution of hours is valid if at least 15 students are enrolled. Otherwise the contact hours are linearly reduced and transfered to individual work.

Nosilec predmeta / Course leader:
prof. dr. Mitja Luštrek
Sodelavci / Lecturers:
prof. dr. Matjaž Gams
Jeziki / Languages:
Predavanja / Lectures:
slovenščina, angleščina / Slovenian, English
Vaje / Tutorial:
Pogoji za vključitev v delo oz. za opravljanje študijskih obveznosti:
Prerequisites:

Zaključen študij druge stopnje s področja informacijskih ali komunikacijskih tehnologij ali zaključen študij druge stopnje na drugih področjih z znanjem osnov s področja predmeta. Potrebna so osnovna znanja matematike, računalništva in informatike.

Completed second-cycle studies in information or communication technologies or completed second-cycle studies in other fields with knowledge of fundamentals in the field of this course. Basic knowledge of mathematics, computer science and informatics is required.

Vsebina:
Content (Syllabus outline):

Uvod:
definicija, vizija in izzivi ambientalne inteligence; strojna in programska podlaga – pogoste vrste senzorjev in drugih naprav, vmesna programska oprema, vgrajeni sistemi

Uporaba senzorjev na telesu:
sinhronizacija, filtriranje in združevanje senzorskih podatkov; interpretacija z drsečim oknom in strojnim učenjem ali pravili; upoštevanje konteksta in prilagajanje uporabnikom

Pametni prostori:
računalniški vid in druge metode za brezstično zaznavanje, predstavitev znanja in simbolno sklepanje

Interakcija z uporabniki:
inovativne vhodno-izhodne naprave, uporaba metafor v uporabniških vmesnikih, načela snovanja interakcije z uporabniki v ambientalni inteligenci

Značilne aplikacije ambientalne inteligence:
prepoznavanje aktivnosti, zaznavanje padcev, analiza razpoloženja uporabnikov, zaznavanje nenavadnega obnašanja, spremljanje kroničnih bolnikov, udobje in varčevanje z energijo v pametnih stavbah

Introduction:
definition, vision and challenges of ambient intelligence; hardware and software foundation – common sensors and other devices, middleware and embedded systems

Use of wearable sensors:
synchronisation, filtering and fusion of sensor data; interpretation with a sliding window and machine learning; using context and adapting to individual users

Smart environments:
computer vision and other contact-free sensing methods, knowledge representation and symbolic reasoning

User interaction:
innovative input/output devices, the use of metaphors in user interfaces, the principles of designing user interaction in ambient intelligence

Representative applications of ambient intelligence:
activity recognition, fall detection, mood analysis, detection of unusual behaviour, monitoring of chronic patients, comfort and energy saving in smart buildings

Temeljna literatura in viri / Readings:

- Cvetković et al., Real-time activity monitoring with a wristband and a smartphone, Information Fusion 2018
- Gjoreski et al., Monitoring stress with a wrist device using context, Journal of Biomedical Informatics 2017
- Alirezaie et al., An ontology-based context-aware system for smart homes: E-care@home, Sensors 2017
- Georgiev et al., Low-resource multi-task audio sensing for mobile and embedded devices via shared deep neural network representations, Ubicomp 2017
- Zafari et al., A Survey of indoor localization systems and technologies, 2018
- Al-Fuqaha et al., Internet of Things: A survey on enabling technologies, protocols, and applications, IEEE Communication Surveys & Tutorials 2015
- Hui & Sherratt, Towards disappearing user interfaces for ubiquitous computing: Human enhancement from sixth sense to super senses, Journal of Ambient Intelligence and Humanized Computing 2017

Cilji in kompetence:
Objectives and competences:

Cilj predmeta je seznaniti študenta s področjem ambientalne inteligence in vseprisotnega računalništva. Poudarek bo na inteligentnih algoritmih za interpretacijo podatkov iz senzorjev in ukrepanju na podlagi take interpretacije. Bo pa predmet obravnaval vse glavne vidike ambientalne inteligence, od strojne in nizkonivojske programske opreme do interakcije z uporabniki.

Študenti, ki bodo uspešno končali ta predmet, bodo razumeli smoter ambientalne inteligence in bodo spodobni zasnovati in razviti aplikacije ambientalne inteligence.

The objective of the course is to familiarize the student with the field of ambient intelligence and ubiquitous computing. The focus will be on intelligent algorithms for the interpretation of sensor data and acting upon such interpretation. However, the course will address all the key topics of ambient intelligence, from hardware and low- level software to user interaction.

The students who will successfully complete this course will grasp the purpose of ambient intelligence and will be able to design and develop ambient-intelligence applications.

Predvideni študijski rezultati:
Intendeded learning outcomes:

Študenti bodo z uspešno opravljenimi obveznostmi tega predmeta pridobili:
- razumevanje pojma ambientalne inteligence, njenih zmožnosti in omejitev
- poznavanje temeljnih tehnologij ambientalne inteligence in njihove primernosti za različne aplikacije
- poznavanje širokega nabora algoritmov za interpretacijo senzorskih podatkov in ukrepanje na podlagi take interpretacije ter sposobnost izbire primernih algoritmov za dano aplikacijo
- spodobnost zasnove primernega uporabniškega vmesnika za aplikacije ambientalne inteligence

Students successfully completing this course will acquire:
- Understanding of the concept of ambient intelligence, its capabilities and limitations
- Knowledge of the fundamental technologies of ambient intelligence and their suitability for various applications
- Knowledge of a wide range of intelligent algorithms for the interpretation of sensor data and acting upon such interpretations, and the ability to select algorithms suitable for a given application
- The ability to design an appropriate user interface for an ambient-intelligence application

Metode poučevanja in učenja:
Learning and teaching methods:

Predavanja, seminar, konzultacije, individualno delo

Lectures, seminar, consultations, individual work

Načini ocenjevanja:
Delež v % / Weight in %
Assesment:
Seminarska naloga
50 %
Seminar work
Ustni izpit
50 %
Oral exam
Reference nosilca / Lecturer's references:
1. G. Slapničar, W. Wang, M. Luštrek, “Feasibility of remote blood pressure estimation via narrow-band multi-wavelength pulse transit time”, ACM Transactions on Sensor Networks, in press, 2023.
2. V. Janko, M. Luštrek, “A general framework for making context-recognition systems more energy efficient”, Sensors, vol. 21, no. 3, pp. 766-1-766-31, 2021.
3. M. Gjoreski, V. Janko, G. Slapničar, M. Mlakar, N. Reščič, J. Bizjak, V. Drobnič, M. Marinko, N. Mlakar, M. Luštrek, M. Gams, “Classical and deep learning methods for recognizing human activities and modes of transportation with smartphone sensors”, Information Fusion, vol. 62, pp. 47-62, 2021.
4. J. A. Álvarez-García, B. Cvetković, M. Luštrek, “A survey on energy expenditure estimation using wearable devices”, ACM Computing Surveys, vol. 53, no. 5, pp. 1-35, 2020.
5. V. Pejović, M. Gjoreski, C. Anderson, K. David, M. Luštrek, “Toward cognitive load inference for attention management in ubiquitous systems”, IEEE Pervasive Computing: Mobile and Ubiquitous Systems, vol. 19, no. 2, pp. 35-45, 2020.