Search published articles


Showing 2 results for Computer Vision
Proposing a conceptual framework for the aesthetics of images on the web: Meta-synthesis and ranking components identified
Maryam Tavosi, Nader Naghshineh, Mohammad Zerehsaz, Siamak Mahboub,
Volume 0, Issue 0 (5-2022)
Abstract
Purpose: Beauty is widely used in the field of art, but when it enters the field of human-computer interaction, it takes the name of "computational aesthetics". Knowing the dimensions of aesthetics can help web designers to design a better user interface for users. The current research aims to identify, rank, and propose a conceptual framework for the aesthetic components of digital images on the web.
Methodology: The present research was carried out with the meta-synthesis method. The documents retrieved from 6 treasure databases, IRANDOC, ISC, SID, Google-Scholar, Emerald, and Web of Science, were retrieved and analyzed with a targeted keyword search and a systematic approach, including 1278 documents. The number of 54 documents were selected and included in the study with the PRISMA approach. The importance coefficient of the identified codes was calculated by Shannon's qualitative content analysis method. EndNote software was used to store and read documents carefully.
Findings: First, the basic conceptual framework was drawn based on the aesthetic theories of Kant, Berlyne, Leibniz, Adorno, Birkhoff, and Husserl, along with 15 documents in English, containing 2 categories, 4 concepts, and 22 aesthetic codes. Then, by performing meta-synthesis, the mentioned framework was upgraded to 2 categories, 4 concepts, and 32 codes. According to Shannon's formula, the two codes "symmetry" and "non-complexity" in the category of objective aesthetics and the two codes "attractive color combination" and "moderate complexity" in the category of subjective aesthetics were identified as having the highest "coefficient of importance".
Conclusion: It is equally important to pay attention to the codes of subjective aesthetics along with objective aesthetics. The current research emphasizes the scientific cooperation of two groups of experts in computer science and humanities to accurately perceive aesthetics and better interaction between humans and computers. The proposed conceptual framework is the first at the national (Iran) and international levels.

Machine Learning and Citizen Science: Opportunities and Challenges of Human-Computer Interaction
Ms. Maryam Abolghasemi, Dr. Fatemeh Fahimnia,
Volume 8, Issue 4 (2-2022)
Abstract
Background and Aim: In processing large data, scientists have to perform the tedious task of analyzing hefty bulk of data. Machine learning techniques are a potential solution to this problem. In citizen science, human and artificial intelligence may be unified to facilitate this effort. Considering the ambiguities in machine performance and management of user-generated data, this paper aims to explain how machine learning can be combined with the active citizenship concept. In addition, it discusses the necessary conditions for advancing the citizen science and beyond.
Method: The review method and comprehensive systematic study was applied to assess the concept of machine learning, citizen science and human-computer interaction.
Results: Many research problems seem to be computationally insolvable and may demand human cognitive skills. Therefore, due to classification activities which are performed in the majority of large-scale citizenship science projects, in addition to participants who may learn lessons about the science, machines also learn lessons about human and imitate him and slowly its learning capacity enhances over time. Artificial intelligence, particularly machine learning is a debatable topic with related ambiguities and biases which should strongly take into consideration.
Conclusion: The application of machine learning techniques carries many advantages including classification time cut and masterful evaluations in the process of making decisions on big data sets. However, algorithms usually act as a black box where data biases are not observable at first glance. Taking this problem into consideration may mitigate serious risks arising from the application of such techniques.
Page 1 from 1     

© 2024 CC BY-NC 4.0 | Human Information Interaction

Designed & Developed by : Yektaweb