Home » Events » ICADS 2022: International Conference on Applied Data Science
Loading Events

« All Events

  • This event has passed.

ICADS 2022: International Conference on Applied Data Science

July 12 @ 8:00 am - 12:00 pm

Please register (free) to attend: https://r6.ieee.org/scv-cs/?p=2073 Fuzzy Loss Functions for Generative Adversarial Neural Network Generative Adversarial neural Networks (GAN) are very popular for medical image analysis. The paper presents an innovative fuzzy loss function for the GAN in the domain of image analysis. The GAN architecture presented here uses two convolutional neural networks, one of which is a generator and the other is a discriminator. Besides the loss function, the training algorithm is also presented in the paper. The proposed approach is generic and can be used for many domains pertaining to medical image analysis and diagnosing. The proposed work with the modified loss function is experimented on the Covid-19 image set. The results achieved are discussed in brief. In the end, the paper presents limitations and future enhancements possible based on the work. Applied Data Science in Education Learning analytics (LA) is a growing research area, which aims at selecting, analyzing and reporting student data (in their interaction with the online learning environment), finding patterns in student behavior, displaying relevant information in suggestive formats; the end goal is the prediction of student performance, the optimization of the educational platform and the implementation of personalized interventions. The topic is highly interdisciplinary, including machine learning techniques, educational data mining, statistical analysis, social network analysis, natural language processing, but also knowledge from learning sciences, pedagogy and sociology. Despite its increasing popularity, LA has been applied less in the context of social media-based environments; hence in this talk we focus especially on research in social learning analytics area. In particular, we explore academic performance predictors and the relationships between students’ learning styles and their social media use; we also investigate students’ collaboration patterns and the community of inquiry supported by social media tools. Four research directions are tackled: analytics dashboards, predictive analytics, social network analytics and discourse analytics. As far as analysis techniques are concerned, we apply various approaches, such as: classification, regression, clustering and PCA algorithms, textual complexity analysis, social network analysis techniques, content analysis based on Community of Inquiry. We thus address the “trinity” of methodological approaches: i) network analysis (representing actor-actor / social relations); ii) process-oriented analysis (based on action logs and pattern detection); iii) content-oriented analysis (based on learner created artefacts); hence a more comprehensive learning analytics perspective is provided. Next Generation Artificial Intelligence and Energy Sustainability The industry is on a mission to capture the business value that comes with the Next Generation Artificial Intelligence in the context of Industry 5.0 and Energy 5.0 as regarding the provision of renewable energy production facilities. This has greatly increased the need to address the cyber risk landscape with a secure, vigilant, and resilient response and system in place. This marriage of algorithms, processes, and ingenuity will enable humans and machines work hand-in-hand utilising human-centric design solutions in collaboration with human resources to enable sustainable, personalized and autonomous manufacturing through enterprise social networks. This talk will analyse how AI could engender better and more informed decision-making during crisis management scenarios. Furthermore, we shall elaborate how Industry 5.0 actively encourages and enhances the relationship between humans and robots in a cyber-physical domain and in the field of energy consumption, while also relying on advanced five-sense and hologram-based communications. Deep Learning for Melodic Frameworks Audio signals that appeal to the ear and create melody usually confirm to a structural framework. Audio is one of the four datatypes that deep learning works best on, the other three being image, video, and text. This talk will give insights into our deep learning experiments on audio signals particularly with respect to latent melodic frameworks within them. Speaker(s): Dr Pendyala, Vishnu S. Pendyala Agenda: 8:00 am “Fuzzy Loss Functions for Generative Adversarial Neural Network” Prof. Priti Sajja, India (8:30 pm India time) 9:00 am “Applied Data Science for Education” Prof. Elvira Popescu, Romania (7 pm Romania time) 10:00 am “Next Generation Artificial Intelligence and Energy Sustainability” Dr. Celestine Iwendi, Bolton, UK (6 pm UK time) 11:00 am “Deep Learning for Melodic Frameworks” Dr. Vishnu S. Pendyala Virtual: https://events.vtools.ieee.org/m/317245

Details

Date:
July 12
Time:
8:00 am - 12:00 pm
Event Category:
Website:
https://events.vtools.ieee.org/m/317245

Follow Us

Find Announcements

Past Announcements

Upcoming Local Meetings

Mon 08
Tue 09

IEEE Seattle Section Excom Meeting August 2022

August 9 @ 7:00 pm - 9:00 pm
Thu 11
Thu 11
Thu 11

Is Now a Good Time to Buy a Home?

August 11 @ 6:00 pm - 7:00 pm

Upcoming Region & Volunteer Meetings

Mon 08
Tue 09

IEEE Seattle Section Excom Meeting August 2022

August 9 @ 7:00 pm - 9:00 pm
Thu 11
Thu 11
Thu 11

Is Now a Good Time to Buy a Home?

August 11 @ 6:00 pm - 7:00 pm