Shakra: Tracking and Sharing Daily Activity Levels with Unaugmented Mobile Phones

Anderson, Ian B.; Maitland, Julie; Sherwood, Scott; Barkhuus, Louise; Chalmers, Matthew; Hall, Malcolm; Brown, Barry; Muller, Henk

doi:10.1007/s11036-007-0011-7

Cited by 191 publications

(149 citation statements)

References 18 publications

Supporting

Mentioning

145

Contrasting

Unclassified

Order By: Relevance

“…can be used for learning and feature extraction for identifying the activities. Artificial intelligence, machine learning and recently deep learning approaches have been used in studies showing effective results in identifying different activities from body-fixed sensor data [4], [9], [18]- [20]. A wide variety of approaches has been used to extract the features form the accelerometer data directly using time-varying acceleration signal [4] and frequency analysis [15], [21], [22].…”

Section: Related Workmentioning

confidence: 99%

“…A wide variety of approaches has been used to extract the features form the accelerometer data directly using time-varying acceleration signal [4] and frequency analysis [15], [21], [22]. Wavelet analysis is also used to derive the features [18]. Recently Mohammad Abu Alsheikh [23] have analyzed the activity recognition in some datasets and have implemented deep learning paradigms and have shown recognition improvement than other state-of-the art methods in human activity recognition.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Smartphone Sensor-Based Activity Recognition by Using Machine Learning and Deep Learning Algorithms

Liu¹,

Zhou²,

Shakya³

et al. 2018

IJMLC

View full text Add to dashboard Cite

Abstract-Smartphones are widely used today, and it becomes possible to detect the user's environmental changes by using the smartphone sensors, as demonstrated in this paper where we propose a method to identify human activities with reasonably high accuracy by using smartphone sensor data. First, the raw smartphone sensor data are collected from two categories of human activity: motion-based, e.g., walking and running; and phone movement-based, e.g., left-right, up-down, clockwise and counterclockwise movement. Firstly, two types of features extraction are designed from the raw sensor data, and activity recognition is analyzed using machine learning classification models based on these features. Secondly, the activity recognition performance is analyzed through the Convolutional Neural Network (CNN) model using only the raw data. Our experiments show substantial improvement in the result with the addition of features and the use of CNN model based on smartphone sensor data with judicious learning techniques and good feature designs.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Smartphone Sensor-Based Activity Recognition by Using Machine Learning and Deep Learning Algorithms

Liu¹,

Zhou²,

Shakya³

et al. 2018

IJMLC

View full text Add to dashboard Cite

show abstract

“…(PmEB) [2], hosted on a mobile device, monitors caloric consumption and expenditure; however, details must be manually entered to enable the calculation of an updated caloric balance. SHAKRA [3] detects patterns in GSM signal strength fluctuation to infer the physical activities of the carrier. HealthGear [4] harnesses a suite of body sensor technologies to detect incidences of Sleep Apnea.…”

Section: Related Researchmentioning

confidence: 99%

Implicit Interaction: A Modality for Ambient Exercise Monitoring

Wan

O’Grady

O’Hare

2009

Human-Computer Interaction – INTERACT 2009

View full text Add to dashboard Cite

Abstract. Ambient Exercise refers to the implicit exercise that people undertake in the course of their everyday duties -a simple example being climbing stairs. Increasing awareness of the potential health benefits of such activities may well contribute to an increase in a person's well-being. Initially, it is necessary to monitor and quantify such exercise so that personalized fitness plans may be constructed. In this paper, the implicit interaction modality is harnessed to enable the capturing of ambient exercise activity thereby facilitating its subsequent quantification and interpretation. The novelty of the solution proposed lies in its ubiquity and transparency.

show abstract

“…the works of Kramer (1999), Marsh (1994) and Goldbeck (2005Goldbeck ( , 2006. Although certainly not complete the following properties are the most noted ones: Social uncertainty 1 , Commitment (Dellarocas, 2003) 1 , Goodwill/Benign intent 1,2 , Reputation 1 , Consistency 1 (Past experience/interaction), Delegation 2 (Castelfranchi and Falcone, 1998), Attitude/Mood/Optimism 2 (Jones, 1996) and Confidence (Golembiewski and McConkie 1975).…”

Section: Introductionmentioning

confidence: 99%

“…Which kinds of features are appropriate to help realizing one or more of the above mentioned properties of trust? It is a well accepted fact that games can be used to motivate people to take part in various kinds of activities they otherwise would be more reluctant to do -for example to do sport activities (Mueller et al 2007), to look after one's health (Anderson et al 2007), learning (Johnson 2010) or even to work for free (like labeling photos on the web or map the world, Ahn and Dabbish 2008). The first two practices are used in the research of serious gaming while the later one is featured in the human computation (Ahn and Dabbish 2008) and volunteered geographic information (VGI) (Goodchild 2007) field.…”

Section: Introductionmentioning

confidence: 99%

Game-Based Trust

Matyas

Kato

Shime

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Trust stands at the beginning of every meaningful interaction between members of any kind of community -be it in the real world or in a virtual one. But how could an application look like that helps to create or even foster the interpersonal trust of its users? We developed a game -Kokochiwith the goal to positively affect the interpersonal trust level of its players. We evaluated Kokochi in two case studies and compared the results with a control group that didn´t play the game. We could show that playing the game -featuring three unique game elements to enhance trust: disclosure of personal information (emotional statements), collaborations (face-to-face) and showing goodwill towards other players (virtual hugging) -resulted in an (significant) higher interpersonal trust level of the subjects after the game than they had before.

show abstract

Shakra: Tracking and Sharing Daily Activity Levels with Unaugmented Mobile Phones

Cited by 191 publications

References 18 publications

Smartphone Sensor-Based Activity Recognition by Using Machine Learning and Deep Learning Algorithms

Smartphone Sensor-Based Activity Recognition by Using Machine Learning and Deep Learning Algorithms

Implicit Interaction: A Modality for Ambient Exercise Monitoring

Game-Based Trust

Contact Info

Product

Resources

About