Indian Institute of Science, Bangalore.
Data Driven Crop Portfolio Recommendation for Agricultural Farmers
Agriculture has a significant role to play in any emerging economy and provides the source of income and employment for a significant fraction of the population. A key challenge faced by small and marginal farmers is to determine which crops to grow to maximize their utililties. With a wrong choice of crops, farmers could end up with sub-optimal yields and possibly significant loss of revenue. In this talk, we describe a data driven system - ACRE (Agricultural Crop Recommendation Engine) - a novel tool designed by us, that provides a scientific method to choose a crop or a portfolio of crops, to maximize the utility to the farmer. ACRE uses available data such as soil characteristics, weather conditions, and historical yield data, and uses state-of-the-art machine learning/deep learning models to compute an estimated utility to the farmer. A technical novelty in ACRE is to harness the use of Sharpe Ratio, a popular risk metric in financial investments. Using the Sharpe ratio, we generate a ranking on candidate recommendations of portfolios of crops. We use publicly available data from the agmarknet portal in India to present several promising data driven thought experiments with ACRE.
Narahari got his B.E. from Department of Electrical Communication Engineering in 1982, M.E. and Phd from Department of Computer Science and Automation in 1984 and 1987 respectively. In February 1988, he joined as the faculty of the Department of Computer Science and Automation and was Chair of the department during January 2010 – July 2014. He was the Dean of the Division of EECS (Electrical, Electronics, and Computer Sciences) from August 2014 to July 2021. He was also chairing the Office of DIGITS (Digital Campus and Informational Technology Services) from January 2016 to August 2020. During 1992, he was a Post-Doctoral Researcher at the Laboratory for Information and Decision Systems (LIDS), Massachusetts Institute of Technology, Cambridge, USA and during 1997, he was a Visiting Scientist on sabbatical at the National Institute of Standards and Technology, Gaithersberg, Maryland, USA.
The focus of Narahari’s current research is to apply game theory, mechanism design, and machine learning to research problems at the interface of computer science and economics. In particular, he is interested in algorithmic game theory, design of auctions and electronic markets, dynamic mechanisms with learning, crowdsourcing , online education, social network analysis, and blockchains.
University at Buffalo.
Data Challenges and Societal Impacts – the case in favor of the Blueprint for an AI Bill of Rights
Artificial Intelligence (AI) technologies contribute tremendously to various areas of life and society. Therefore, we are witnessing massive investments in this area. Grand-view Research has calibrated the global AI market at 93.5 billion dollars as of 2021. Further, according to their report, it is expected to grow at a compound annual growth rate (CAGR) of 38.1% from 2022 to 2030. It is believed that nations that adopt and use AI will have a competitive edge. AI, in some form, will be part of most products and services we use. I will talk about some of the challenges, tradeoffs, and remedies concerning BIG DATA in the age of Artificial Intelligence. I will also provide a brief overview of the maladies that plague the landscape of BIG DATA and some academic literature that provides solutions to the problems in the context of AI. The driving motivation for writing this article is to highlight our responsibility to create algorithms and automated systems that do not harm and are equitable and just. I also hope to create awareness that leads to businesses and Software laboratories that focus on testing software and data that alleviates our fear - modeling the work of the US Food and Drug Administration. The tenets echoed in this concord with the Blueprint for an AI Bill of Rights released by the United States (US) White House Office of Science and Technology Policy (OSTP) on October 4, 2022, and the AI Risk Management Framework by the US National Institute of Standards and Technology.
Sharman's research is focused on extreme events from a decision-support system perspective and on health information technology-related issues. This includes factors influencing online health information search, meaningful use of ambulatory EMR, resilience in hospital information systems, health information exchanges, health care social networks as well as a simulation based study for managing the hospital's emergency room capacity in extreme events, active shooter incidents and mass casualty event management.
His expertise also includes information systems infrastructure management as it relates to information assurance, internet performance and distributed computing. Sharman's papers have been published in a number of national and international journals, and he is the recipient of several grants from the university as well as external agencies, including the National Science Foundation.
He serves as an associate editor for the following journals: Journal of Information Systems Security, Journal of Information Privacy and Security, and Springer Security Informatics Journal.
Shenzhen University, China.
Advances and challenges for the discovery of interesting patterns in data
Intelligent systems and tools play an important role in various domains such as for factory automation, e-business, and software engineering. To build intelligent systems and tools, high-quality data is generally required. Moreover, these systems need to process complex data and can yield large amounts of temporal data such usage logs, and data collected from sensors. Managing the data to gain insights and improve these systems is thus a key challenge. It is also desirable to be able to extract information or models from data that are easily understandable by humans. Based on these objectives, this talk will discuss the use of data mining algorithms for discovering interesting and useful patterns in temporal data generated from intelligent systems or from other applications.
The talk will first briefly review early study on designing algorithms for identifying frequent temporal patterns in discrete sequences and time-interval data. Then, an overview of recent challenges and advances will be presented to identify other types of interesting patterns in complex data. Topics that will be discussed include high utility patterns, locally interesting patterns, trending patterns, time-interval patterns and periodic patterns. Lastly, the SPMF open-source software will be mentioned and opportunities related to the combination of pattern mining algorithms with traditional artificial intelligence techniques for intelligent systems will be discussed.
Philippe Fournier-Viger is distinguished professor at the Shenzhen University (China). He obtained his Ph.D at University of Quebec in Montreal (Canada) in 2010. After working as post-doctoral researcher at National Cheng Kung University, and being a faculty member at University of Moncton, he came to China in 2015 and became full professor at the Harbin Institute of Technology (Shenzhen). There, he received a title of national talent from the National Science Foundation of China. His interests are data mining, algorithm design, pattern mining, sequence mining, big data, and applications. He has published more than 340 research papers related to data mining, intelligent systems and applications, which have received more than 8500 citations (H-Index 46). He is associate editor-in-chief of the Applied Intelligence journal (SCI, Q1) and editor-in-chief of Data Science and Pattern Recognition. He is the founder of the popular SPMF data mining library, offering more than 200 algorithms for analyzing data, cited in more than 1,000 research papers. He is a co-founder of the UDML, MLiSE and PMDB series of workshops held at the ICDM, PKDD, KDD and DASFAA conferences.
Missouri University of Science and Technology, USA.
EMOCOV: Machine Learning for Emotion Detection, Analysis and Visualization using COVID-19 Tweets
The adversarial impact of the Covid-19 pandemic has created a health crisis globally all over the world. This unprecedented crisis forced people to lockdown and changed almost every aspect of the regular activities of the people. Thus, the pandemic is also impacting everyone physically, mentally, and economically, and it, therefore, is paramount to analyze and understand emotional responses during the crisis affecting mental health. Negative emotional responses at fine-grained labels like anger and fear during the crisis might also lead to irreversible socio-economic damages. In this talk, I will discuss a neural network model trained using manually labeled data to detect various emotions at fine-grained labels in the Covid-19 tweets automatically. I will discuss about a manually labeled tweets dataset on COVID-19 emotional responses along with regular tweets data. A custom Q&A roBERTa model to extract phrases from the tweets that are primarily responsible for the corresponding emotions has been designed. None of the existing datasets and work currently provide the selected words or phrases denoting the reason for the corresponding emotions. The classification model outperforms other systems and achieves a Jaccard score of 0.6475 with an accuracy of 0.8951. The custom RoBERTa Q&A model outperforms other models by achieving a Jaccard score of 0.7865. Further, I will present a historical emotion analysis using COVID-19 tweets over the USA including each state level analysis.
Sanjay K Madria is a Curators’ Distinguished Professor in the Department of Computer Science at the Missouri University of Science and Technology (formerly, University of Missouri-Rolla, USA). He has published over 290 Journal and conference papers in the areas of mobile and sensor computing, Big data and cloud computing, data analytics and cyber security. He won five IEEE best papers awards in conferences such as IEEE MDM and IEEE SRDS. He is a co-author of a book (published with his two PhD graduates) on Secure Sensor Cloud published by Morgan and Claypool in Dec. 2018. He has graduated 20 PhDs and 33 MS thesis students, with 9 PhDs currently progressing. NSF, NIST, ARL, ARO, AFRL, DOE, Boeing, CDC-NIOSH, ORNL, Honeywell, etc. have funded his research projects of over $18M. He has been awarded JSPS (Japanese Society for Promotion of Science) invitational visiting scientist fellowship, and ASEE (American Society of Engineering Education) fellowship. In 2012 and in 2019, he was awarded NRC Fellowship by National Academies, US. He is ACM Distinguished Scientist, and served/serving as an ACM and IEEE Distinguished Speaker, and is an IEEE Senior Member as well as IEEE Golden Core Awardee.