Modeling Behavior as Mutual Dependency between Physiological Signals and Indoor Location in Large-Scale Wearable Sensor Study

2020 ◽  
Author(s):  
Tiantian Feng ◽  
Brandon M. Booth ◽  
Shrikanth S. Narayanan
Keyword(s):  
Large Scale ◽  
Physiological Signals ◽  
Wearable Sensor ◽  
Indoor Location ◽  
Mutual Dependency ◽  
Modeling Behavior

Distributed Optical Sensor Network with Self-Monitoring Mechanism for Accurate Indoor Location and Coordinate Measurement

2012 ◽  
Vol 190-191 ◽  
pp. 972-976 ◽  
Author(s):  
Ling Hui Yang ◽  
Yi Wang ◽  
Ji Gui Zhu ◽  
Xue You Yang
Keyword(s):  
Sensor Network ◽  
Large Scale ◽  
Geometric Model ◽  
Optical Receivers ◽  
Self Monitoring ◽  
Indoor Location ◽  
Coordinate Measurement ◽  
Location Service ◽  
Distributed Framework ◽  
Monitoring Mechanism

In order to provide accurate and robust indoor location service for large-scale mechanical manufacturing, a sensor network consisting of laser transmitters and optical receivers is proposed in a distributed framework. Geometric model described by rotating plane equations is established, re-ceiver’s location algorithm is achieved by utilizing intersection constraint of multiple laser planes form different transmitters. A self-monitoring mechanism for sensor network is also presented by introducing redundant fixed receivers as reference. Experiment has shown that the measuring accu-racy of a minimal sensor network is better than 0.2mm and self-monitoring mechanism can effectively guarantee the accuracy of the measurement results.

scholarly journals Large-Scale Wearable Sensor Deployment in Parkinson’s Patients: The Parkinson@Home Study Protocol

2016 ◽  
Vol 5 (3) ◽  
pp. e172 ◽  
Author(s):  
Ana Lígia Silva de Lima ◽  
Tim Hahn ◽  
Nienke M de Vries ◽  
Eli Cohen ◽  
Lauren Bataille ◽  
...  
Keyword(s):  
Study Protocol ◽  
Large Scale ◽  
Sensor Deployment ◽  
Wearable Sensor ◽  
Home Study

Behavioral Analysis of Decisions in Choice of Commercial Vehicular Mode in Urban Areas

2012 ◽  
Vol 2269 (1) ◽  
pp. 58-64 ◽  
Author(s):  
Qian Wang ◽  
Jinge Hu
Keyword(s):  
Urban Areas ◽  
Large Scale ◽  
Mode Choice ◽  
Data Sets ◽  
Affecting Factors ◽  
Commercial Vehicles ◽  
Home Base ◽  
Business Meetings ◽  
Original Survey ◽  
Modeling Behavior

The decisions of vehicular mode choice by businesses and commercial sectors in urban areas are addressed with attention to the unique trip-chaining behavior of commercial vehicles. Travel diary data from a collection of large-scale commercial vehicles in the Denver, Colorado, metropolitan area were used for analysis. Four types of travel activities were surveyed: business meetings, pickup and drop-off of people, pickup and delivery of cargo, and service calls. The survey results indicated that automobiles, pickup trucks, sport utility vehicles, single-unit trucks, and combination trucks were the main vehicular modes for travel with commercial purposes. The original survey data were sorted into trip-based and tour-based data sets for measuring commercial vehicle travel activities. A “trip” is defined as travel from one stop to another, and a “tour” is an entire travel journey starting from and ending at the home base of a vehicle with visits to various locations of interest. Discrete choice modeling techniques, particularly multinomial logit and nested logit models, were used to quantify the relationship between decisions on the choice of commercial vehicular mode and their affecting factors, and the two data sets were used separately. The modeling results indicate that mode choice by the commercial sector is travel specific, territory dependent, and cargo sensitive and varies by company. As proved by the comparison of trip-based and tour-based models, the tour is an intuitively and quantitatively better unit for measuring the travel activities of commercial vehicles and for modeling behavior of mode choice of the commercial sectors.

scholarly journals Wireless Patrol Sign-In System with Mental Fatigue Detection

2018 ◽  
Vol 2018 ◽  
pp. 1-6
Author(s):  
Kang-Ming Chang ◽  
Hao-Chen Xu ◽  
Congo Tak-Shing Ching ◽  
Shing-Hong Liu
Keyword(s):  
Large Scale ◽  
Case Series ◽  
Mental Fatigue ◽  
Physiological Signals ◽  
Median Frequency ◽  
Image Identification ◽  
Security Guards ◽  
Hand Grip ◽  
Case Series Study ◽  
Hand Dynamometer

Current sign-in methods of patrolling security guards mainly comprise signature, image identification, and fingerprint identification; notably, none of these methods indicate the physical and mental conditions of such guards. In particular, when patrolling security guards perform their duties consecutively for a long period of time, adequate attention should be directed toward their levels of mental fatigue. When a handwriting sign-in system is adopted, security guards may not record their sign-in time accurately, or they may fake signatures during long shifts. In addition, image identification systems cannot comprehensively reflect the physical and mental statuses of on-duty security guards, particularly their levels of fatigue. Monitor fatigue in patrolling security guards is important to avoid burnout and stress in the workplace. Therefore, in this study, a patrolling sign-in system that integrates physiological signals and images was designed. A thermometer, hand dynamometer, and electromyography sensor were combined to measure physiological signals. Results showed that hand grip strength and the median frequency of electromyography signals gradually reduced when muscle fatigue occurred. The system determined whether a security guard had signed in punctually and whether this person should stay on duty. Overall, this system was verified to operate effectively, and it is therefore applicable for monitoring the sign-in of patrolling security guards who work long shifts. This case series study proposed a conceptual prototype of the system; large-scale testing should be performed in subsequent research.

scholarly journals Passive Radio-Frequency Identification Tag-Based Indoor Localization in Multi-Stacking Racks for Warehousing

2020 ◽  
Vol 10 (10) ◽  
pp. 3623 ◽  
Author(s):  
Jaehun Park ◽  
Yong-Jeong Kim ◽  
Byung Kwon Lee
Keyword(s):  
Radio Frequency ◽  
Radio Frequency Identification ◽  
Large Scale ◽  
Indoor Localization ◽  
Electronic Device ◽  
Location Awareness ◽  
Indoor Location ◽  
Significant Difference ◽  
Frequency Identification ◽  
Passive Rfid

Radio-frequency identification (RFID) technology-based real-time indoor location awareness has been widely studied. In this paper, a passive RFID-based indoor inventory localization method for small and medium-sized enterprises (SMEs) is proposed to effectively manage their indoor inventory tracking in terms of the multi-stacking racking (MSR). To achieve this, we introduce a concept of reference tags and a calculation of measurement for the distance between the RFID reader and reference tag to improve the accuracy of the item location recognition. To illustrate the efficacy and applicability of the method, an empirical case study that applies it to an electronic device manufacturing company is conducted. It was noted that there was no significant difference in the location awareness rate of the proposed system compared with the existing active RFID-based methods. Also, it is demonstrated that the construction can be relatively inexpensive in terms of identifying the location of the items loaded in MSR and relatively narrow areas using a passive tag. This advantage makes it suitable for SMEs that have issues with large-scale facility investment, applying the method to compare the location difference between the registered location information in the inventory system and the actual location of the item in the rack.

scholarly journals A 3D MAP AIDED DEEP LEARNING BASED INDOOR LOCALIZATION SYSTEM FOR SMART DEVICES

2020 ◽  
Vol XLIII-B4-2020 ◽  
pp. 391-397
Author(s):  
Y. Yang ◽  
C. Toth ◽  
D. Brzezinska
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Large Scale ◽  
Indoor Localization ◽  
Indoor Positioning ◽  
Location Based Services ◽  
Smart Devices ◽  
Visual Localization ◽  
Indoor Location ◽  
Semantic Labeling

Abstract. Indoor positioning technologies represent a fast developing field of research due to the rapidly increasing need for indoor location-based services (ILBS); in particular, for applications using personal smart devices. Recently, progress in indoor mapping, including 3D modeling and semantic labeling started to offer benefits to indoor positioning algorithms; mainly, in terms of accuracy. This work presents a method for efficient and robust indoor localization, allowing to support applications in large-scale environments. To achieve high performance, the proposed concept integrates two main indoor localization techniques: Wi-Fi fingerprinting and deep learning-based visual localization using 3D map. The robustness and efficiency of technique is demonstrated with real-world experiences.

Sign in / Sign up

Export Citation Format

Share Document