Given that dilution is a problem that reduces the profit of many underground operations, the dilution monitoring, prediction, and reduction convey the capability to increase operational efficiency. The proposed research aims to develop an unplanned dilution monitoring, prediction, and reduction tool. The research methodology will be based on artificial intelligence (AI)-based models. More specifically, the research will focus on the applicability of ensemble classifiers, naive Bayes classifiers, logistic regression, and neural networks.
Over the last 20 years, online shopping has been steadily increasing, and recently doubled since the start of the coronavirus pandemic. Shoppers have also become more ethically conscious and interested in fair trade, sustainability, the source of goods, and company working conditions and taxes. However, for the average online shopper, the ability to make ethical choices is limited as the necessary information can be difficult to find.
Internet of things (IoT) systems require significant management related to external intrusions, internal threats, device failures, access management, and performance monitoring. In addition to network management issues, quality of service (QoS) must be maintained to predict changes and determine device and network performance. A good IoT system should be able to identify, track, and mitigate problems while dynamically adjusting its operation.
In the Arctic, climate change is leading to declines in seasonal sea-ice cover. Polar bears are increasingly at-risk from sea-ice loss because they use the ice as a platform to hunt seals, their preferred food source. When the ice retreats seasonally, bears rely on their stored energy reserves as fuel, but climate-driven changes in sea-ice melt and refreezing have forced bears to go for longer periods without access to seals. With temperatures expected to increase, it is important to know how polar bear populations will respond to never-before-seen declines in sea ice.
The Firefighter Problem is a deterministic, discrete-time model of the spread of a fire on the nodes of a graph. If a graph is a network where bank accounts are nodes, then an edge between two accounts is a transaction between one bank account and another. Imagine we have a suspicious bank account with suspicious transactions possibly tied to money laundering. We view this suspicious bank account as a place a fire breaks out. Then, those accounts that receive money from the suspicious bank account are considered suspect.
Modern video games are composed of different types of artifacts, such as images, sounds, and software code. All these artifacts are developed at the same time by different teams. While the independent creation and modification of each artifact allows different teams to make changes without blocking each other from making progress, how artifacts are combined into the final game must be carefully coordinated. If two or more artifacts are dependent on each other, and a change occurs to one artifact, all other artifacts must be updated and (re-) evaluated.
Nowadays, mental health issues have become a major public health challenge. Moodie app allows patients to track their emotions, moods, routines, sleep, diet, physical activity, and associated context via journal logs. This provides the therapist with a rich pool of data for accurate diagnosis and assists with the treatment. This project aims to (1) Develop machine learning models and evaluate their ability to predict individual’s emotional state using over one year journaling log and associated emotion from Moodie app.
Scientific research papers are complex, dense, and filled with jargon, so traditionally the valuable knowledge they contain has been accessible to only a handful of experts. SAGE publishing, one of the world’s largest academic publishers, and Dr. Adam Frost, a cognitive neuroscientist, independently created video formats that help scientists directly communicate their discoveries and practices in approachable ways so that that knowledge can reach a much wider audience. Both SAGE and Dr.
Pipeline alerts are beneficial to analysts to determine where their attention is needed. However, a high false positive rate leads to a noisy stream and wastes analysts’ time. The first sub-project will aim to classify the alerts as either low or high likelihood of a false positive, allowing analysts to spend their time where it is most effective.Living-off-the-Land binaries (Lolbins) is an increasingly common technique among attackers, yet there is currently little detection for such an attack.
