The amount of sequencing data for SARS-CoV-2 is several orders of magnitude larger than any virus. This will continue to grow geometrically for SARS-CoV-2, and other viruses, as many countries heavily finance genomic surveillance efforts. Hence, we need methods for processing large amounts of sequence data to allow for effective yet timely decision-making. Such data will come from heterogeneous sources: aligned, unaligned, or even unassembled raw nucleotide or amino acid sequencing reads pertaining to the whole genome or regions (e.g., spike) of interest. In this work, we propose \emph{ViralVectors}, a compact feature vector generation from virome sequencing data that allows effective downstream analysis. Such generation is based on \emph{minimizers}, a type of lightweight "signature" of a sequence, used traditionally in assembly and read mapping -- to our knowledge, the first use minimizers in this way. We validate our approach on different types of sequencing data: (a) 2.5M SARS-CoV-2 spike sequences (to show scalability); (b) 3K Coronaviridae spike sequences (to show robustness to more genomic variability); and (c) 4K raw WGS reads sets taken from nasal-swab PCR tests (to show the ability to process unassembled reads). Our results show that ViralVectors outperforms current benchmarks in most classification and clustering tasks.

In order to better prevent and cure debilitating ailments including Alzheimer's disease, schizophrenia, and autism, new research at Georgia State University's TReNDS Center may result in early detection. For a recent study published in Nature Scientific Reports, a team of seven scientists from Georgia State University created a sophisticated computer program to sift through enormous amounts of brain imaging data and discover unexpected patterns related to mental health disorders. The brain imaging data were generated using functional magnetic resonance imaging (fMRI) scans, which measure dynamic brain activity by detecting minute fluctuations in the flow of blood. Although exceedingly complicated, brain dynamics are the key to understanding how the brain functions and malfunctions. Functional magnetic resonance imaging resting-state dynamics are noisy, high-dimensional, and difficult to understand.

A new study at Georgia State University's TReNDS Center may result in the early detection of debilitating diseases such as Alzheimer's, schizophrenia, and autism. The findings of this study were published in the Journal of Scientific Reports. A team of seven Georgia State scientists created a sophisticated computer program that could sift through massive amounts of brain imaging data and uncover unexpected patterns related to mental health disorders. The brain imaging data is produced by functional magnetic resonance imaging (fMRI) scans, which evaluate dynamic brain activity by detecting minute variations in blood flow. "We constructed artificial intelligence models to analyze the substantial volumes of information from fMRI," said Sergey Plis, the study's lead author and an associate professor of computer science and neuroscience at Georgia State University.

Advances in AI, especially based on machine learning, have provided a powerful way to extract useful patterns from large, heterogeneous data sources. The rise in massive amounts of data, coupled with powerful computing capabilities, makes it possible to tackle previously intractable real-world problems. Medicine, business, government, and science are rapidly automating decisions and processes using machine learning. Unlike traditional AI approaches based on explicit rules expressing domain knowledge, machine learning often lacks explicit human-understandable specification of the rules producing model outputs. With growing reliance on automated decisions, an overriding concern is understanding the process by which "black box" AI techniques make decisions.

Non-IID dataset and heterogeneous environment of the local clients are regarded as a major issue in Federated Learning (FL), causing a downturn in the convergence without achieving satisfactory performance. In this paper, we propose a novel Label-wise clustering algorithm that guarantees the trainability among geographically dispersed heterogeneous local clients, by selecting only the local models trained with a dataset that approximates into uniformly distributed class labels, which is likely to obtain faster minimization of the loss and increment the accuracy among the FL network. Through conducting experiments on the suggested six common non-IID scenarios, we empirically show that the vanilla FL aggregation model is incapable of gaining robust convergence generating biased pre-trained local models and drifting the local weights to mislead the trainability in the worst case. Moreover, we quantitatively estimate the expected performance of the local models before training, which offers a global server to select the optimal clients, saving additional computational costs. Ultimately, in order to gain resolution of the non-convergence in such non-IID situations, we design clustering algorithms based on local input class labels, accommodating the diversity and assorting clients that could lead the overall system to attain the swift convergence as global training continues. Our paper shows that proposed Label-wise clustering demonstrates prompt and robust convergence compared to other FL algorithms when local training datasets are non-IID or coexist with IID through multiple experiments.

Technology has kept life going during the pandemic but it's also changed life at home and at work. The pandemic accelerated the use of AI in the workforce. Liz Owens found it's transforming the future of jobs everywhere. A report by World Economic Forum predicts half of all employees will need reskilling or upskilling in just four years because of recent advances in technology. A tap and a swipe and your order is now being prepared.

Many people hate to walk away from a situation they've invested significant time, money or resources on, even if it's hopeless. Those wasted efforts are called'sunk costs' and the more you spend, the more you're likely to keep at it. It turns out our primate cousins act the same way, according to a new study from Georgia State University. Researchers taught dozens of monkeys to play a video game and, rather than starting over on a new level, the animals kept trying to win the same one round. In fact, they spent up to seven times as long as they should have on one round when they would have had a better chance of getting a treat just skipping ahead to the next one.

A program at Georgia State University is widening the scope of digital literacy to include problem-solving and leadership strategies. Most every college or university recognizes the importance of digital literacy to future graduates, and increasingly, you'll find technology competencies and digital skill development experiences included widely in general education programs. But at Georgia State University, leaders within the Center for Excellence in Teaching and Learning are making certain that GSU's digital literacy offerings will spawn not only technically competent individuals, but also a diverse range of professional leaders who know how to use their technology skills in context for better problem solving. Digital Learners to Leaders is an experiential learning program aimed at developing the next generation of digital problem solvers through industry/higher-education partnerships and exposure to digital technologies and the Internet of Things. DLL began as a co-curricular program, seeing its first cohort of 45 students in Spring 2018.

From faculty who deliver classroom lectures to copywriters who create recruitment brochures, colleges employ plenty of professional communicators. These roles often shift as institutions adopt new technologies to better convey information to students. Accordingly, the spread of communication tools powered by artificial intelligence has created a new kind of higher ed job: college chatbot writer. These are the wordsmiths who craft dialogue for chatbot "scripts," the curated conversations that unfold when algorithms correspond with humans. In selecting words, images and emojis, writers not only deliver information, but also establish the voice, identity and character of a college chatbot.

New research shows that monkeys outperform humans in a test meant to measure cognitive flexibility. The experiment, conducted by a team of psychology researchers at George State University, pitted humans against capuchin and rhesus macaque monkeys. Both groups were asked to interact with a touchscreen computer that featured four squares with different patterns in them. When subjects pressed on the squares in the right sequence, a triangle would appear in place of one of the squares, and when pressed the triangle would produce a reward. For the monkeys, the reward was a banana pellet, and for humans it was either a short audio jingle or a sign of points being tallied up.