In the past few years, the popularity of AI applications has taken off.
This past December, The Conference on Neural Information Processing Systems – one of the most popular AI conferences – was sold out within 11 minutes.
Quite a difference from two years prior when the conference sold out after 2 weeks.
This points to a general trend of the field growing in the number of researchers.
Moreover, it points to many industry practitioners and the public interested in the development of intelligence applications and machine learning.
As another point of reference, the AAAI Conference (Association for the Advancement of Artificial Intelligence), one of the oldest and most influential AI conferences, received a record number of submissions this year.
With 7095 submissions, the numbers nearly doubled from last year.
Overall, 1150 papers were accepted, which is not a significant increase from previous years. As a result, only about 16% of the submissions were accepted.
Certainly at AI applications conference
Certainly is a Danish-Spanish AI Chatbot Building Platform for Business and Enterprise with a focus on Retail, Apparel, Fashion and E-commerce.
We had a great discussion with other researchers about how to tackle problems that are of scientific interest to many researchers but also great interest to industry practitioners.
AAAI – collocated with IAAI (Innovative AI Applications) and EAAI (Educational Advances in AI) was a great place to exchange ideas and learn about innovative research on dialogue and AI apps.
Many AI apps deal with robotics, dialogue systems, and assistive technologies. However, there was a great deal of research using machine learning for social sciences, medical purposes, etc.
Below, we describe 9 revolutionary AI applications that stood out for us!
As a disclaimer, we must say that within 1095 papers, there were many interesting topics and we had a hard time picking just a few!
PhoneMD: Learning to Diagnose Parkinson’s Disease from Smartphone Data
Parkinson’s disease is the second most common age-related neurodegenerative disease, following Alzheimer’s disease.
According to the Parkinson’s Foundation, in the United States, healthcare costs related to this disease total about 25 billion dollars per year alone.
Quality of life for Parkinson’s patients relies heavily on how early treatment starts, therefore requiring a correct diagnosis.
It motivates the authors of this paper and presents an intelligence applications and machine learning approach to tackling the misdiagnosis of Parkinson’s disease.
They collect smartphone data on 1853 participants with and without Parkinson’s disease.
Specifically, they collect signals from walking, voice, tapping, and memory tests using smartphone AI applications.
As previously mentioned, Parkinson’s is a progressive neurodegenerative disease. Therefore, they use the temporal nature of the data to detect the disease.
Also, once someone is diagnosed using this method, the authors use a hierarchical neural attention model to identify which of the 4 tests was more significant in the prediction, to help clinicians assess whether this was a valid assessment.
Ensemble Machine Learning for Estimating Fetal Weight at Varying Gestational Age
Intrauterine growth restriction, which means that an unborn baby is not growing at normal rates, can put the babies at risk throughout pregnancy, delivery, and after birth.
Not growing at a normal rate can lead to low resistance to infections, troubles maintaining body temperature, or even death during delivery.
The authors based the research on the impact that machine learning from AI applications can have on helping obstetricians estimate the weight of a fetus better.
It is not meant to replace traditional clinical practices, but to work in collaboration for an improved prediction, which can reduce prenatal morbidity and mortality.
The approach used here uses data from intrapartum recordings and uses simple machine learning algorithms combined in an ensemble model.
Overall, they show an improvement in the accuracy of their predictions by a significant 12%.
Feature Isolation for Hypothesis Testing in Retinal Imaging: An Ischemic Stroke Prediction Case Study
An ischemic stroke happens when there is a blockage in the arteries that pumps blood to the brain.
It can occur by the formation of a blood clot within the brain, commonly known as a thrombotic stroke.
According to the Stroke Center organization, about 88 percent of all strokes are Ischemic strokes. It is also a disease that affects more women than men.
However, it doesn’t discriminate according to age. The research presented here aims to exploit the knowledge in the medical community for predicting the risk of ischemic stroke in individuals.
They focus on retinal blood vessels and the features that correlate with cerebral blood circulation.
Their AI applications explore ways of isolating important features from retinal images and attempt to use deep neural networks to predict ischemic strokes.
This proved to be a difficult task, as it became very difficult to generalize to new images.
However, this gives light to a task worth exploring further.
Crash to Not Crash: Learn to Identify Dangerous Vehicles Using a Simulator
The Insurance Institute for Highway Safety reports a cost of about 36,096 lives due to car crashes in the U.S. in 2019. This number reaches millions when looking at global statistics.
One way of preventing many of these cases is through warning systems that allow telling the driver whether there is a danger of a collision.
However, to develop AI applications that can do this, the researchers would need to collect a great amount of data.
In the real world, this is very difficult, and annotating the data accurately is also a challenge in itself.
The authors point to this fact as motivation and take on the challenge of collecting a large amount of collision data. This is done by developing a synthetic data generator on top of a driving simulator.
Specifically, they manipulate internal functions of a game called Grand Theft Auto (which many of us have played!) to create accident versus non-accident scenes.
They generally find that labels created through simulation are very noisy.
However, they are still able to reduce missed detection by 18% than those trained with real-world data.
Cooperative Multimodal Approach to Depression Detection on Twitter
Although detection of depression through deep learning and Twitter data is not a new idea, it remains a complex task that still needs solving.
According to the World Health Organization, about 20% of children and teenagers experience mental illnesses.
In addition, statistics reported by the American Academy of child and adolescent psychiatry, show that suicide is the second leading cause of death for individuals aged 5-24 in the United States.
With the rise of social media, we often hear that there is a causal link between social media use and depression and loneliness.
These feelings of depression can be expressed in complex ways through posts, images, comments, etc.
The authors of these AI applications point to the fact that sometimes words can be deceiving.
Moreover, they suggest that using a combination of text and visual cues might be the best way to understand what someone is really saying.
In this study, they use text and images from users’ posts on Twitter to detect depression.
More specifically, they employ a reinforcement learning method. The system learns to select text and images as indicator posts, leading to greater rewards or greater accuracy of detection.
This model, of course, assumes that the diagnosis of the user is already known, which is not typically the case.
However, through their method, they find that they are able to detect important features that are most indicative of depression. The results can be useful for future research in this direction.
Predicting Hurricane Trajectories using a Recurrent Neural Network
According to the National Hurrican Center in The United States, Hurrican Katrina, which occurred in 2005, has been the costliest in history.
The estimated economic damage by Katrina was at about 125,000,000,000 USD.
However, it also showed to be a very deadly natural disaster, totaling close to 2000 deaths.
Fresher in our minds is Hurricane Maria, which hit Puerto Rico and the U.S. Virgin Islands in September 2017 and cost nearly 5,000 lives.
Ways of estimating the trajectory of hurricanes and cyclones exist and are commonly employed to prevent these situations from happening. Still, the methods researchers used have much room for improvement.
The motivation for this study lies in the disastrous impact that hurricanes can have on human lives and the economic stability of the region affected.
It also includes the study on how the rise of deep learning can have a tremendous positive impact.
Although weather forecasting using deep neural networks is not new, the methods proposed here are novel. The new methods teach a model to learn the trajectory of hurricanes from one grid to the next.
Thanks to the ai apps, the authors are able to predict the next location of a hurricane 6 hours prior.
What’s more, their proposed model is able to predict hurricanes of any type. Other methods, on the other hand, tend to only work with the assumption that storms cannot turn back on themselves.
Overall, this investigation introduces an interesting approach to a problem. Hence, resolving the problem can effectively save many lives and reduce economic damage.
Multi-GCN: Graph Convolutional Networks for Multi-View Networks, with AI Applications to Global Poverty
According to Our World in Data, which bases their estimates on household surveys, in 1981, 44% of the world lived in extreme poverty. These numbers dropped below 10% by 2015.
Although global poverty rates have decreased and are at an all-time low, extreme poverty is still a problem worth tackling. Extreme poverty leaves the ones affected at an incredible disadvantage.
In this study, the authors aim to explore the complicated nature of human behavior. Specifically, they explore the extensive use of mobile phones to better pinpoint extreme poverty in developing countries.
The authors focus on three tasks:
- Predicting poverty,
- Forecasting product adoption (the rate at which individuals in developing countries adopt different mobile financial services), and
- Predicting gender from mobile phone data, as an indicator of inequality
The method proposed uses multi-view graph convolutional neural networks. These networks exploit the fact that individuals can connect in more than one way.
Overall, they find that considering the multi-view nature of social networks and interactions, the prediction of poverty can be improved.
Allocating Interventions Based on Predicted Outcomes: A Case Study on Homelessness Services
The National Alliance to End Homelessness in the United States, identified that in January 2017, 553742 people were homeless.
Across the U.S., there are community programs that try to tackle homelessness. These communities provide emergency shelters, transitional housing, food services, and permanent housing solutions.
These depend on the number of resources available or collected.
This investigation is motivated by the lack of resources available for social services in many of these communities.
Specifically, this paper focuses on the optimal ways of allocating different types of social services in the context of homelessness.
The type of services considered range from time-limited, non–residential support, to rental assistance, among others.
The authors of these AI applications use existing records across homeless services in the U.S. which include:
- Different service allocation mechanisms
- Information about families who have requested assistance
- Building a counterfactual model to predict whether a household would re-enter homelessness when receiving different services.
This aims at finding the best way to allocate services to reduce the rate of homelessness in the long run.
Generating Live Soccer-Match Commentary from Play Data
The authors propose an AI applications method for generating live football-match commentaries.
The authors generate templates using placeholders instead of player names and team names and implement a gate mechanism in order to select the important plays.
This investigation, however, assumes that play data is always available, an assumption that the authors clearly state.
It also assumes that the players that will be mentioned throughout the commentary are given beforehand.
Given the unrealistic assumptions, this paper proposes incorporating visual cues as part of future work.
However, it is still a fun and entertaining experiment showcasing the use of natural language processing techniques and neural networks for more creative purposes.
Final thoughts on intelligence applications
Overall, this year’s AAAI saw a great variety of research topics.
As one can see from the collection of topics presented here, there are many ai apps of machine learning that we often neglect to consider on a day-to-day basis.
However, it has become clear that despite the common debate of how Artificial Intelligence will negatively affect our lives, intelligence applications actually have the potential of having a tremendously positive impact.
These are just some examples of AI applications; however, if you would like to explore other research topics presented, go check out the AAAI 2022 website!
If you want to learn more about how to create your own AI-driven Virtual Assitant, start your journey here.
Author: Ana Gonzalez