Using Contextual Information for Recognising Human Behaviour

2016 ◽  
Vol 7 (1) ◽  
pp. 27-44 ◽  
Author(s):  
Hans W. Guesgen ◽  
Stephen Marsland
Keyword(s):  
Contextual Information ◽  
Implementation Strategies ◽  
Smart Homes ◽  
Research Problem ◽  
Human Behaviour ◽  
Temporal Data ◽  
Important Research ◽  
Novel Method ◽  
Important Research Problem

Identifying human behaviours in smart homes from sensor observations is an important research problem. The addition of contextual information about environmental circumstances and prior activities, as well as spatial and temporal data, can assist in both recognising particular behaviours and detecting abnormalities in these behaviours. In this paper, the authors describe a novel method of representing this data and discuss a wide variety of possible implementation strategies.

Recognising Human Behaviour in a Spatio-Temporal Context

2011 ◽  
pp. 443-459 ◽  
Author(s):  
Hans W. Guesgen ◽  
Stephen Marsland
Keyword(s):  
Contextual Information ◽  
Implementation Strategies ◽  
Smart Homes ◽  
Research Problem ◽  
Temporal Context ◽  
Temporal Data ◽  
Important Research ◽  
Novel Method ◽  
Spatio Temporal ◽  
Important Research Problem

Identifying human behaviours in smart homes from sensor observations is an important research problem. The addition of contextual information about environmental circumstances and prior activities, as well as spatial and temporal data, can assist in both recognising particular behaviours and detecting abnormalities in these behaviours. In this chapter, we describe a novel method of representing this data and discuss a wide variety of possible implementation strategies.

Invariant Probabilities with Geometric Tail

1996 ◽  
Vol 10 (2) ◽  
pp. 213-221 ◽  
Author(s):  
Jean B. Lasserre ◽  
Henk Tijms
Keyword(s):  
Markov Chain ◽  
Linear Algebra ◽  
Research Problem ◽  
Important Research ◽  
Countable State ◽  
Important Research Problem

We present necessary and suffi2ient Foster-type conditions for a countable state Markov chain to have an invariant probability with at least a geometric tail. These conditions are obtained by using a generalized Farkas Theorem in Linear Algebra. The purpose of this note is also to pose an interesting and important research problem that is still largely open.

scholarly journals A Reinforcement Learning Based Dirt-Exploration for Cleaning-Auditing Robot

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8331
Author(s):  
Thejus Pathmakumar ◽  
Mohan Rajesh Elara ◽  
Braulio Félix Gómez ◽  
Balakrishnan Ramalingam
Keyword(s):  
Reinforcement Learning ◽  
Research Work ◽  
Leading Edge ◽  
Research Problem ◽  
Fundamental Question ◽  
Policy Learning ◽  
Policy Network ◽  
Important Research ◽  
Important Research Problem

Cleaning is one of the fundamental tasks with prime importance given in our day-to-day life. Moreover, the importance of cleaning drives the research efforts towards bringing leading edge technologies, including robotics, into the cleaning domain. However, an effective method to assess the quality of cleaning is an equally important research problem to be addressed. The primary footstep towards addressing the fundamental question of “How clean is clean” is addressed using an autonomous cleaning-auditing robot that audits the cleanliness of a given area. This research work focuses on a novel reinforcement learning-based experience-driven dirt exploration strategy for a cleaning-auditing robot. The proposed approach uses proximal policy approximation (PPO) based on-policy learning method to generate waypoints and sampling decisions to explore the probable dirt accumulation regions in a given area. The policy network is trained in multiple environments with simulated dirt patterns. Experiment trials have been conducted to validate the trained policy in both simulated and real-world environments using an in-house developed cleaning audit robot called BELUGA.

scholarly journals GUILLAIN — BARRÉ SYNDROME AS A RELEVANT ISSUE OF NEUROLOGY (A LITERATURE REVIEW)

2019 ◽  
Vol 26 (2) ◽  
pp. 150-161
Author(s):  
Ivan A. Velichko ◽  
Marina A. Barabanova
Keyword(s):  
Peripheral Nerves ◽  
Research Problem ◽  
Severe Form ◽  
Guillain Barre Syndrome ◽  
Important Research ◽  
Relevant Issue ◽  
Guillain Barré Syndrome ◽  
Acute Polyneuropathy ◽  
Guillain Barré ◽  
Important Research Problem

Acute infl ammatory polyneuropathy is an important research problem of modern neurology. Guillain — Barré syndrome is a severe form of acute polyneuropathy, which is based on autoimmune infl ammation of the myelin sheath of roots and peripheral nerves. Guillain — Barré syndrome is an example of one of the most severe diseases of the nervous system, in which timely diagnosis, proper therapy and qualifi ed care facilitate the achievement of the full recovery of lost functions in most patients. Following an extensive review of Russian and foreign literature, this article discusses modern concepts of Guillain — Barré syndrome, in particular questions related to its epidemiology, etiopathogenesis, classifi cation, clinical features, diagnosis, treatment and prognosis.

scholarly journals Od męki translacji do piekła logosu. O przekładzie w „Przekładzie” Pabla De Santisa

2019 ◽  
pp. 143-166
Author(s):  
Katarzyna Majdzik Papić
Keyword(s):  
Jacques Derrida ◽  
Research Problem ◽  
Julia Kristeva ◽  
The Novel ◽  
Important Research ◽  
Tower Of Babel ◽  
Crime Novel ◽  
The Relationship ◽  
Hans Georg Gadamer ◽  
Important Research Problem

The article presents how the novel The Translation by Pablo De Santis reffers to the most important concepts of theory and philosophy of translation. Among these concepts the most significant are those which consider the boundaries and mechanisms of interpretation in the act of translation. These ideas are metaphorically expressed by the myth of the fall of the Tower of Babel. The interpretative context for the novel by De Santis is determined by the works of Jacques Derrida, Julia Kristeva and Hans-Georg Gadamer. An important research problem is also the relationship between the category of translation and the hybrid genre of the crime novel by De Santis.

scholarly journals Control of separately excited DC motor with series multi-cells chopper using PI - Petri nets controller

2019 ◽  
Vol 8 (1) ◽  
pp. 32-38 ◽  
Author(s):  
Mohamed Lamine Hamida ◽  
Hakim Denoun ◽  
Arezki Fekik ◽  
Sundarapandian Vaidyanathan
Keyword(s):  
Petri Nets ◽  
Research Problem ◽  
Dc Motor ◽  
Pi Controller ◽  
Important Research ◽  
Power Simulation ◽  
Industrial Sectors ◽  
Capacitor Voltage ◽  
Binary Control ◽  
Important Research Problem

Abstract The separately excited Direct Current (DC) motor is widely used in many industrial sectors. During the operation of the DC motor, the load torque and the voltage of the network can cause a destabilization of the actual speed and actual current. Thus, the need to regulate the speed and current of the DC motor is a very important research problem. In this paper, a control strategy of separately excited DC motor using a series multi-cells chopper is described. The proposed control is based on Proportional-Integral (PI) and Petri nets controllers. Specifically, the conventional PI controller is used to control the speed of DC motor. The Petri nets controller ensures the regulation of the armature current and to maintain the capacitor voltage of the multi-cells converter to its reference. The Petri nets controller also generates binary control switches. The proposed control system has been implemented using MATLAB Sim Power. Simulation results demonstrate that a series multi-cells chopper and the proposed control give a good performance and high robustness in load disturbance for the separately excited DC motor.

Research on Location Feedback Based DV-Hop Localization Algorithm

2014 ◽  
Vol 621 ◽  
pp. 699-706
Author(s):  
Fei Liu ◽  
Guang Zeng Feng
Keyword(s):  
Research Problem ◽  
Feedback Mechanism ◽  
Localization Algorithm ◽  
Important Research ◽  
Precise Location ◽  
The Real ◽  
The Difference ◽  
Unknown Node ◽  
Range Free ◽  
Important Research Problem

In wireless sensor networks (WSNs), estimation of the location of the unknown node based on the average hop distance is an important research problem for range free localization algorithm. As one of the range free algorithm, DV-Hop chooses the average hop distance comes from the nearest beacon, can't reflect the real status of WSNs. We observe that the unknown node can achieve the precise location when one feedback channels are built between the unknown node and the beacons which embedded accurate location. Based on this observation, we propose one improved DV-Hop localization algorithm based on feedback mechanism (FDV-Hop). Using DV-Hop, the unknown node achieves the estimated location, and broadcasts its average hop distance to the beacons. The beacons also use DV-Hop to calculate their location based on the average hop distance from the unknown node. Then the beacons calculate the difference between the estimated location and the real location, and send the difference between them to unknown node with weights setting. The unknown node recalculates its location which involving the difference of location and the weights. The simulation shows that FDV-Hop can reduce the average localization error effectively and keep the localization stable.

scholarly journals Augmented Context-Based Conceptual User Modeling for Personalized Recommendation System in Online Social Networks

2020 ◽  
Vol 14 (3) ◽  
pp. 1-19
Author(s):  
Ammar Alnahhas ◽  
Bassel Alkhatib
Keyword(s):  
Social Networks ◽  
Online Social Networks ◽  
Recommendation System ◽  
Contextual Information ◽  
Detailed Comparison ◽  
Personalized Recommendation ◽  
User Models ◽  
Proposed Model ◽  
Recommendation Algorithms ◽  
Novel Method

As the data on the online social networks is getting larger, it is important to build personalized recommendation systems that recommend suitable content to users, there has been much research in this field that uses conceptual representations of text to match user models with best content. This article presents a novel method to build a user model that depends on conceptual representation of text by using ConceptNet concepts that exceed the named entities to include the common-sense meaning of words and phrases. The model includes the contextual information of concepts as well, the authors also show a novel method to exploit the semantic relations of the knowledge base to extend user models, the experiment shows that the proposed model and associated recommendation algorithms outperform all previous methods as a detailed comparison shows in this article.

Sign in / Sign up

Export Citation Format

Share Document