scholarly journals Ad Hoc Teamwork With Behavior Switching Agents

2019 ◽  
Author(s):  
Manish Ravula ◽  
Shani Alkoby ◽  
Peter Stone
Keyword(s):  
Neural Network ◽  
Real World ◽  
Change Point ◽  
Ad Hoc ◽  
Change Point Detection ◽  
Planning Problem ◽  
Predator Prey ◽  
Strong Assumption ◽  
New Type ◽  
Point Detection

As autonomous AI agents proliferate in the real world, they will increasingly need to cooperate with each other to achieve complex goals without always being able to coordinate in advance. This kind of cooperation, in which agents have to learn to cooperate on the fly, is called ad hoc teamwork. Many previous works investigating this setting assumed that teammates behave according to one of many predefined types that is fixed throughout the task. This assumption of stationarity in behaviors, is a strong assumption which cannot be guaranteed in many real-world settings. In this work, we relax this assumption and investigate settings in which teammates can change their types during the course of the task. This adds complexity to the planning problem as now an agent needs to recognize that a change has occurred in addition to figuring out what is the new type of the teammate it is interacting with. In this paper, we present a novel Convolutional-Neural-Network-based Change point Detection (CPD) algorithm for ad hoc teamwork. When evaluating our algorithm on the modified predator prey domain, we find that it outperforms existing Bayesian CPD algorithms.

scholarly journals Fast Change Point Detection on Dynamic Social Networks

2017 ◽  
Author(s):  
Yu Wang ◽  
Aniket Chakrabarti ◽  
David Sivakoff ◽  
Srinivasan Parthasarathy
Keyword(s):  
Communication Networks ◽  
Real World ◽  
Change Point ◽  
Dynamic Networks ◽  
Change Point Detection ◽  
Logical Time ◽  
Dynamic Social Networks ◽  
Fast Change ◽  
Time Stamps ◽  
Point Detection

A number of real world problems in many domains (e.g. sociology, biology, political science and communication networks) can be modeled as dynamic networks with nodes representing entities of interest and edges representing interactions among the entities at different points in time. A common representation for such models is the snapshot model - where a network is defined at logical time-stamps. An important problem under this model is change point detection. In this work we devise an effective and efficient three-step-approach for detecting change points in dynamic networks under the snapshot model. Our algorithm achieves up to 9X speedup over the state-of-the-art while improving quality on both synthetic and real world networks.

DEVELOPING TIME-BASED CLUSTERING NEURAL NETWORKS TO USE CHANGE-POINT DETECTION: APPLICATION TO FINANCIAL TIME SERIES

2005 ◽  
Vol 22 (01) ◽  
pp. 51-70 ◽  
Author(s):  
KYONG JOO OH ◽  
TAE HYUP ROH ◽  
MYUNG SANG MOON
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Change Point ◽  
Financial Time Series ◽  
Change Point Detection ◽  
Detection Methods ◽  
Financial Time ◽  
Point Groups ◽  
Point Detection

This study suggests time-based clustering models integrating change-point detection and neural networks, and applies them to financial time series forecasting. The basic concept of the proposed models is to obtain intervals divided by change points, to identify them as change-point groups, and to involve them in the forecasting model. The proposed models consist of two stages. The first stage, the clustering neural network modeling stage, is to detect successive change points in the dataset, and to forecast change-point groups with backpropagation neural networks (BPNs). In this stage, three change-point detection methods are applied and compared. They are: (1) the parametric approach, (2) the nonparametric approach, and (3) the model-based approach. The next stage is to forecast the final output with BPNs. Through the application to financial time series forecasting, we compare the proposed models with a neural network model alone and, in addition, determine which of three change-point detection methods performs better. Furthermore, we evaluate whether the proposed models play a role in clustering to reflect the time. Finally, this study examines the predictability of the integrated neural network models based on change-point detection.

Facilitating Human Activity Data Annotation via Context-Aware Change Detection on Smartwatches

2021 ◽  
Vol 20 (2) ◽  
pp. 1-20
Author(s):  
Ali Akbari ◽  
Jonathan Martinez ◽  
Roozbeh Jafari
Keyword(s):  
Cognitive Load ◽  
Real World ◽  
Change Point ◽  
Detection Algorithm ◽  
Change Point Detection ◽  
Motion Sensors ◽  
Context Aware ◽  
Human Errors ◽  
Data Annotation ◽  
Point Detection

Annotating activities of daily living (ADL) is vital for developing machine learning models for activity recognition. In addition, it is critical for self-reporting purposes such as in assisted living where the users are asked to log their ADLs. However, data annotation becomes extremely challenging in real-world data collection scenarios, where the users have to provide annotations and labels on their own. Methods such as self-reports that rely on users’ memory and compliance are prone to human errors and become burdensome since they increase users’ cognitive load. In this article, we propose a light yet effective context-aware change point detection algorithm that is implemented and run on a smartwatch for facilitating data annotation for high-level ADLs. The proposed system detects the moments of transition from one to another activity and prompts the users to annotate their data. We leverage freely available Bluetooth low energy (BLE) information broadcasted by various devices to detect changes in environmental context. This contextual information is combined with a motion-based change point detection algorithm, which utilizes data from wearable motion sensors, to reduce the false positives and enhance the system's accuracy. Through real-world experiments, we show that the proposed system improves the quality and quantity of labels collected from users by reducing human errors while eliminating users’ cognitive load and facilitating the data annotation process.

Understanding the CoVID-19 pandemic Curve through statistical approach (Preprint)

2020 ◽  
Author(s):  
Ibrar Ul Hassan Akhtar
Keyword(s):  
Probability Density ◽  
Change Point ◽  
Statistical Approach ◽  
Sudden Change ◽  
Global Scale ◽  
Change Point Detection ◽  
Segment Length ◽  
Infected Population ◽  
The Mean ◽  
Point Detection

UNSTRUCTURED Current research is an attempt to understand the CoVID-19 pandemic curve through statistical approach of probability density function with associated skewness and kurtosis measures, change point detection and polynomial fitting to estimate infected population along with 30 days projection. The pandemic curve has been explored for above average affected countries, six regions and global scale during 64 days of 22nd January to 24th March, 2020. The global cases infection as well as recovery rate curves remained in the ranged of 0 ‒ 9.89 and 0 ‒ 8.89%, respectively. The confirmed cases probability density curve is high positive skewed and leptokurtic with mean global infected daily population of 6620. The recovered cases showed bimodal positive skewed curve of leptokurtic type with daily recovery of 1708. The change point detection helped to understand the CoVID-19 curve in term of sudden change in term of mean or mean with variance. This pointed out disease curve is consist of three phases and last segment that varies in term of day lengths. The mean with variance based change detection is better in differentiating phases and associated segment length as compared to mean. Global infected population might rise in the range of 0.750 to 4.680 million by 24th April 2020, depending upon the pandemic curve progress beyond 24th March, 2020. Expected most affected countries will be USA, Italy, China, Spain, Germany, France, Switzerland, Iran and UK with at least infected population of over 0.100 million. Infected population polynomial projection errors remained in the range of -78.8 to 49.0%.

Sign in / Sign up

Export Citation Format

Share Document