Search results

1 – 10 of 697
Click here to view access options
Article
Publication date: 16 January 2017

Ye Chen and Zhelong Wang

Existing studies on human activity recognition using inertial sensors mainly discuss single activities. However, human activities are rather concurrent. A person could be…

Abstract

Purpose

Existing studies on human activity recognition using inertial sensors mainly discuss single activities. However, human activities are rather concurrent. A person could be walking while brushing their teeth or lying while making a call. The purpose of this paper is to explore an effective way to recognize concurrent activities.

Design/methodology/approach

Concurrent activities usually involve behaviors from different parts of the body, which are mainly dominated by the lower limbs and upper body. For this reason, a hierarchical method based on artificial neural networks (ANNs) is proposed to classify them. At the lower level, the state of the lower limbs to which a concurrent activity belongs is firstly recognized by means of one ANN using simple features. Then, the upper-level systems further distinguish between the upper limb movements and infer specific concurrent activity using features processed by the principle component analysis.

Findings

An experiment is conducted to collect realistic data from five sensor nodes placed on subjects’ wrist, arm, thigh, ankle and chest. Experimental results indicate that the proposed hierarchical method can distinguish between 14 concurrent activities with a high classification rate of 92.6 per cent, which significantly outperforms the single-level recognition method.

Practical implications

In the future, the research may play an important role in many ways such as daily behavior monitoring, smart assisted living, postoperative rehabilitation and eldercare support.

Originality/value

To provide more accurate information on people’s behaviors, human concurrent activities are discussed and effectively recognized by using a hierarchical method.

Click here to view access options
Article
Publication date: 19 June 2017

Zhelong Wang and Ye Chen

In sensor-based activity recognition, most of the previous studies focused on single activities such as body posture, ambulation and simple daily activities. Few works…

Abstract

Purpose

In sensor-based activity recognition, most of the previous studies focused on single activities such as body posture, ambulation and simple daily activities. Few works have been done to analyze complex concurrent activities. The purpose of this paper is to use a statistical modeling approach to classify them.

Design/methodology/approach

In this study, the recognition problem of concurrent activities is explored with the framework of parallel hidden Markov model (PHMM), where two basic HMMs are used to model the upper limb movements and lower limb states, respectively. Statistical time-domain and frequency-domain features are extracted, and then processed by the principal component analysis method for classification. To recognize specific concurrent activities, PHMM merges the information (by combining probabilities) from both channels to make the final decision.

Findings

Four studies are investigated to validate the effectiveness of the proposed method. The results show that PHMM can classify 12 daily concurrent activities with an average recognition rate of 93.2 per cent, which is superior to regular HMM and several single-frame classification approaches.

Originality/value

A statistical modeling approach based on PHMM is investigated, and it proved to be effective in concurrent activity recognition. This might provide more accurate feedback on people’s behaviors.

Practical implications

The research may be significant in the field of pervasive healthcare, supporting a variety of practical applications such as elderly care, ambient assisted living and remote monitoring.

Click here to view access options
Article
Publication date: 13 March 2020

Zhiqiang Xie, Lei Wang, Zhengyang Zhu, Zhi Fu and Xingdong Lv

The purpose of this paper is to introduce an interval finite element method (IFEM) to simulate the temperature field of mass concrete under multiple influence…

Abstract

Purpose

The purpose of this paper is to introduce an interval finite element method (IFEM) to simulate the temperature field of mass concrete under multiple influence uncertainties e.g. environmental temperature, material properties, pouring construction and pipe cooling.

Design/methodology/approach

Uncertainties of the significant factors such as the ambient temperature, the adiabatic temperature rise, the placing temperature and the pipe cooling are comprehensively studied and represented as the interval numbers. Then, an IFEM equation is derived and a method for obtaining interval results based on monotonicity is also presented. To verify the proposed method, a non-adiabatic temperature rise test was carried out and subsequently simulated with the method. An excellent agreement is achieved between the simulation results and the monitoring data.

Findings

An IFEM method is proposed and a non-adiabatic temperature rise test is simulated to verify the method. The interval results are discussed and compared with monitoring data. The proposed method is found to be feasible and effective.

Originality/value

Compared with the traditional finite element methods, the proposed method taking the uncertainty of various factors into account and it will be helpful for engineers to gain a better understanding of the real condition.

Details

Engineering Computations, vol. 37 no. 7
Type: Research Article
ISSN: 0264-4401

Keywords

Click here to view access options
Article
Publication date: 12 August 2014

Shunchong Li, Xinjun Sheng, Honghai Liu and Xiangyang Zhu

This paper aims to describe the design of a multi-degree of freedom (DOF) prosthetic hand prototype implementing postural synergy mechanically, which is actuated by two…

Abstract

Purpose

This paper aims to describe the design of a multi-degree of freedom (DOF) prosthetic hand prototype implementing postural synergy mechanically, which is actuated by two motors via a transmission unit, and is controlled using surface electromyography (sEMG) signal.

Design/methodology/approach

First, an anthropomorphic robotic hand is designed to imitate the human hand. The robotic hand has 18 DOF, 12 of which are actively driven by Bowden cables. Next, a set of different grasp modes are performed on a “full actuation” robotic hand, and principal component analysis (PCA) method is used to extract the first two postural synergies. Then, they are used to design a differential pulley-based transmission unit using two independent inputs to drive 12 output tendons. Finally, two control signals extracted from six channels of sEMG signals are used to proportionally control the two motors for achieving hand posture synthesis.

Findings

Using a differential pulley-based mechanical transmission unit to implement the synthesis of the first two postural synergies can make the prosthetic hand achieve different grasps by two motors, such as power, precision and lateral grasps. It is also feasible to control this “two actuation” prosthetic hand by relating the two-dimensional sEMG inputs with the first two postural synergies.

Originality/value

Mechanical implantation of postural synergies reduces the number of independent actuators without sacrificing the prosthetic hand’s versatility and simplifies its controller. Two-dimensional control extracted from sEMG is mapped into the combination coefficients of postural synergy synthesis. It shows potential application in the practical prosthetic hand.

Details

Industrial Robot: An International Journal, vol. 41 no. 5
Type: Research Article
ISSN: 0143-991X

Keywords

Click here to view access options
Article
Publication date: 26 February 2010

Sheng Zhu and Yongjiang Shi

The purpose of this paper is to explore an indigenous innovation phenomenon – entitled the Shanzhai phenomenon – which has emerged in the Chinese mobile phone industry…

Downloads
5478

Abstract

Purpose

The purpose of this paper is to explore an indigenous innovation phenomenon – entitled the Shanzhai phenomenon – which has emerged in the Chinese mobile phone industry, and to understand its value creation network and operational mechanism, as well as to recognize its policy implications in regional and industrial developments.

Design/methodology/approach

Although the Shanzhai phenomenon emerged from the end of 2008, detailed understanding of its systems and operational mechanism is still very limited, partly because of its secrecy and dynamics in the value chain operations. Based on characteristics of the Shaizhai phenomenon, the paper focuses on three levels of the phenomenon – regional historical, regional industrial specific, and typical Shanzhai mobile phone project levels – to pursue a comprehensive understanding of the Shanzhai system and its emerging environments. At the regional and industrial level, the combined approaches of interview and secondary data collection is adopted. At the Shanzhai project level, a case study approach is conducted by focusing on the project and its whole value chain, from the idea creation towards detailed product design, production and integration, as well as its distribution.

Findings

Chinese government has called for indigenous innovation to upgrade Chinese manufacturing capability and value creation as well as appropriation. Based on the fast growth of the Chinese indigenous mobile phone industry in the last two years, the Shanzhai manufacturing system is recognized as a new positive alternative way for Chinese manufacturing companies to achieve this aim. Behind the Shanzhai phenomenon, there is a strong globally specialized and collaborated network enabling the down‐stream Chinese small‐ and medium‐sized mobile phone companies to very quickly respond to customers' demands or lead the demands. This new type of alternative innovation system is transforming unaffordable luxury goods into affordable for normal consumers. Because of its mass volume and involvement, however, government policies to harness the energy and development direction become essential.

Research limitations/implications

This research is just a very early stage of preliminary observation. From the methodology perspective, it provides background information about Shanzhai phenomenon and an in‐depth case study about a Shanzhai project. Comprehensive understandings of the Shanzhai phenomenon in terms of its behaviours, systems constructs and patterns, trajectories in the future and implications for policies will be achieved only at a much later date.

Practical implications

ShanZhai manufacturing might be one possible alternative innovative paradigm in some sectors of China.

Originality/value

This is the first academic research paper to offer relatively comprehensive and systematic observations about the emerging ShanZhai manufacturing system in the largest developing country.

Details

Journal of Science and Technology Policy in China, vol. 1 no. 1
Type: Research Article
ISSN: 1758-552X

Keywords

Content available
Article
Publication date: 24 February 2012

Downloads
350

Abstract

Details

Journal of Science and Technology Policy in China, vol. 3 no. 1
Type: Research Article
ISSN: 1758-552X

Keywords

Content available
Article
Publication date: 26 February 2010

Jiang Yu and John Adams

Downloads
438

Abstract

Details

Journal of Science and Technology Policy in China, vol. 1 no. 1
Type: Research Article
ISSN: 1758-552X

Click here to view access options
Article
Publication date: 23 August 2019

Yiqun Kuang, Hong Cheng, Yali Zheng, Fang Cui and Rui Huang

This paper aims to present a one-shot gesture recognition approach which can be a high-efficient communication channel in human–robot collaboration systems.

Abstract

Purpose

This paper aims to present a one-shot gesture recognition approach which can be a high-efficient communication channel in human–robot collaboration systems.

Design/methodology/approach

This paper applies dynamic time warping (DTW) to align two gesture sequences in temporal domain with a novel frame-wise distance measure which matches local features in spatial domain. Furthermore, a novel and robust bidirectional attention region extraction method is proposed to retain information in both movement and hold phase of a gesture.

Findings

The proposed approach is capable of providing efficient one-shot gesture recognition without elaborately designed features. The experiments on a social robot (JiaJia) demonstrate that the proposed approach can be used in a human–robot collaboration system flexibly.

Originality/value

According to previous literature, there are no similar solutions that can achieve an efficient gesture recognition with simple local feature descriptor and combine the advantages of local features with DTW.

Details

Assembly Automation, vol. 40 no. 1
Type: Research Article
ISSN: 0144-5154

Keywords

Click here to view access options
Article
Publication date: 8 March 2018

Prathiba Udupa and Siva S. Yellampalli

The purpose of this paper is to explain, in brief, about smart, intelligent system which actively monitors the wellness of the elderly and will also send necessary alarms…

Abstract

Purpose

The purpose of this paper is to explain, in brief, about smart, intelligent system which actively monitors the wellness of the elderly and will also send necessary alarms to the caretakers or doctors during an emergency because nowadays most of elderly people wish to stay alone independently. It is necessary to monitor their health conditions and activities continuously to prevent occurrence of health problems and also be able to provide medical assistance to them during emergencies.

Design/methodology/approach

The review paper describes the development of a methodology to monitor elderly continuously with a combination of advanced intelligent sensors, networking technologies and data processing system.

Findings

This paper identified various sensors used in smart home such as a pressure sensor, temperature sensor, etc., for monitoring elders health and their characteristics and also the cost, model number, etc., of various sensors available in the market.

Originality/value

This paper contains the comparison of various sensors available in the market that can be used in the smart home and also where we can use those sensors in smart home based on their characteristics.

Details

Circuit World, vol. 44 no. 2
Type: Research Article
ISSN: 0305-6120

Keywords

Click here to view access options
Article
Publication date: 1 September 2004

Jian Liu and De‐jie Yu

Precise and logical plant maintenance evaluation, which enables enterprise to distinguish its most suitable maintenance pattern for application, is the base of improvement…

Downloads
2507

Abstract

Precise and logical plant maintenance evaluation, which enables enterprise to distinguish its most suitable maintenance pattern for application, is the base of improvement in plant maintenance. In this paper a new method based on data envelopment analysis (DEA) is proposed to evaluate the relative efficiency of plant maintenance. In this method, a systematic functional model is built to analyze the input/output of plant maintenance, which is processed as a service system, and DEA is applied as a calculate model for plant maintenance evaluation. Practical implications. The aim of this work is to provide management with a method to evaluate and quantify the relative efficiency of plant maintenance among a group of units. The maintenance pattern, scheme and experience of the relatively effective unit are guidance to others in improving themselves in plant maintenance and the quantified evaluation result points out the detailed maintenance limitation of relatively less efficient units so that the management can make corresponding improvement scheme.

Details

Journal of Quality in Maintenance Engineering, vol. 10 no. 3
Type: Research Article
ISSN: 1355-2511

Keywords

1 – 10 of 697