Gesture and Hand Activity Based Emergency Response Communication by Patients, Elderly and Disabled While Using Data Gloves
29 Jan 2013-pp 264-269
TL;DR: The experimental results show that the realization of suggested hand movement activity sets over the coupling of other movements for classes' is always have distinct thresholds which are reliable for error free communication.
Abstract: Monitoring patients on crucial and emergency conditions on clinical basis involve mandatory periodical but lively communication between patient and caretakers. Miscommunication leads to adverse effects and failure in life saving. A simple wearable system can interpret the implicit communication of the users to the caretakers or to an automated life support device. Simple and obvious hand movements or activity may be used for the above purpose. But the challenge is in interpretation of clear and well distinct input classes extracted from the wearable. The proposed system suggests well distinct classes of gestures that are suitable for such system developments. It also gives a clear insight about the combinations that are not very suitable for such implicit communication. The experimental results show that the realization of suggested hand movement activity sets over the coupling of other movements for classes' is always have distinct thresholds which are reliable for error free communication.
Citations
More filters
TL;DR: DMT is presented, a device-free finger gesture tracking system that can track and recognize the finger motion accurately, and a Fourier fitting-based method is proposed in the DMT to accurately detect the Doppler-shift.
Abstract: As a universal interaction method, hand and finger gestures can express people’s intention directly and clearly in daily life, and has been one of the hotspots in human–computer interaction community. In this paper, we present DMT , a device-free finger gesture tracking system that can track and recognize the finger motion accurately. To achieve this, we transform the mobile device, such as a smart phone, into an active sonar system by establishing inaudible audio links between the built-in speakers and microphone. The finger motion will have an effect (e.g., Doppler-shift) on the audio signals, which makes it possible to track the finger motion according to the received signal characteristics at the microphone side. Due to the small reflection energy and slow moving speed of the finger, the existing methods cannot detect the Doppler-shift accurately. To this end, a Fourier fitting-based method is proposed in the DMT to accurately detect the Doppler-shift. With the detected Doppler-shift, the DMT can track the finger motion with high accuracy. The DMT supports all kinds of finger gestures interaction, including characters and shapes. Extensive experiments demonstrate the high accuracy and robustness of the DMT in dynamic environments.
8 citations
Cites methods from "Gesture and Hand Activity Based Eme..."
...These methods are mainly based on various wearable sensors or devices which should be carried by the gesture operator, such as smart headband [17], [18], digital glove [19], smart wrist [20] and smart watch [21]....
[...]
01 Nov 2016
TL;DR: This study proposes a conceptual MyEmergencyAssistant solution, an integrated assistive technology embedded with customized buttons as an emergency device in enhancing the quality of life and safety for the disabled and elderly community.
Abstract: Numerous studies have been conducted in the field of assistive technology for elderly and disabled. However, the overall user needs are rarely considered and understood. There is a dire need for a holistic solution to keep away dangerous happenings especially to the disabled or elderly people, who are physically fragile and feeble. This paper surveys the needs, the pains, the gains, and the challenges faced by the elderly and disabled at home, workplaces and other common vicinities. Assistive technology-based solutions for today tomorrow are to help those vulnerable people to live better and safer are researched in this study. This study proposes a conceptual MyEmergencyAssistant solution, an integrated assistive technology embedded with customized buttons as an emergency device in enhancing the quality of life and safety for the disabled and elderly community. In addition, literature-review unveils user needs based on emergency situations. This conceptual MyEmergencyAssistant solution is developed using the Environmental Map (EM), Business Model Canvas (BMC), and Value Proposition Diagram (VPD) suite of tools.
7 citations
Cites background from "Gesture and Hand Activity Based Eme..."
...Thus, the technology-based gesture communication has the potential of helping those patients in taking the right medicine and also for doctors to inject the patient [8]....
[...]
TL;DR: The main objective of the project is to provide an application that acts as an all-in-one tool for disabled people and the differentiating feature of this application is the ability to perform various functions such as booking an Uber, reserving tables at restaurants, calling ambulances and fire trucks in addition to the detection of diseases.
Abstract: The main objective of the project is to provide an application that acts as an all-in-one tool for disabled people. Most activities are performed digitally, a prime example being online shopping platforms which have replaced the traditional means. In this era of modern technology, people are entirely reliant on electronic gadgets and make use of several features to run their daily lives. To enhance the usability of such features for disabled people, this application has been developed to take care of their basic needs. The dependence of the general public on mobile applications is justified but that is not the case for disabled people. This application has been designed specifically to cater to such people with disabilities. This proposal requires our “Retina App” and breath analyzer module only. The differentiating feature of this appli-cation is the ability to perform various functions such as booking an Uber, reserving tables at restaurants, calling ambulances and fire trucks in addition to the detection of diseases. It can detect the level of alcohol in a person’s breath and when it surpasses a certain level, it displays a notification which can help the user to book a cab directly to take him/her back to his/her residence..
References
More filters
TL;DR: The test results show that the feature vector extraction method and neural networks can be used successfully for isolated word recognition and this system is flexible and open for future extension.
172 citations
"Gesture and Hand Activity Based Eme..." refers background in this paper
...The usage of these motion trackers is expensive and ASL should be taught prior to the elderly and the disabled which is difficult as in [2]....
[...]
TL;DR: With minor modifications, resistive bend sensors are suitable for accurate assessments of human finger movements and the low material costs and easy manufacturing make this solution interesting for widespread use in research, clinical and rehabilitation settings.
144 citations
"Gesture and Hand Activity Based Eme..." refers background in this paper
...It is a new dimension in the field of medicine and health care as in [5]....
[...]
TL;DR: A novel online signature verification system using the singular value decomposition (SVD) numerical tool for signature classification and verification is presented using the data glove as an effective high- bandwidth data entry device for signature verification.
Abstract: Utilizing the multiple degrees of freedom offered by the data glove for each finger and the hand, a novel online signature verification system using the singular value decomposition (SVD) numerical tool for signature classification and verification is presented. The proposed technique is based on the Singular value decomposition in finding r singular vectors sensing the maximal energy of glove data matrix A, called principal subspace, so the effective dimensionality of A can be reduced. Having modeled the data glove signature through its r-principal subspace, signature authentication is performed by finding the angles between the different subspaces. A demonstration of the data glove is presented as an effective high- bandwidth data entry device for signature verification. This SVD-based signature verification technique is tested and its performance is shown to be able to produce equal error rate (EER) of less than 2.37 percent.
76 citations
"Gesture and Hand Activity Based Eme..." refers methods in this paper
...It has been found in many signal processing applications and control systems that the singular value decomposition of matrix formed from observed data can be used to improve methods of signal parameter estimation and system identification as in [4]....
[...]
TL;DR: A real time sign recognition architecture including both gesture and movement recognition is presented, which deals specially with problems like sensor noise and simplification of the training phase.
42 citations
TL;DR: In this article, different classifiers fuzzy k-nearest neighbours FKNN, support vector machine, and linear discriminant analysis were tested in combination with these methods to determine the methodology with the best performance.
Abstract: A brain computer interface BCI enables direct communication between a brain and a computer translating brain activity into computer commands using preprocessing, feature extraction, and classification operations. Feature extraction is crucial, as it has a substantial effect on the classification accuracy and speed. While fractal dimension has been successfully used in various domains to characterize data exhibiting fractal properties, its usage in motor imagery-based BCI has been more recent. In this study, commonly used fractal dimension estimation methods to characterize time series Katz's method, Higuchi's method, rescaled range method, and Renyi's entropy were evaluated for feature extraction in motor imagery-based BCI by conducting offline analyses of a two class motor imagery dataset. Different classifiers fuzzy k-nearest neighbours FKNN, support vector machine, and linear discriminant analysis were tested in combination with these methods to determine the methodology with the best performance. This methodology was then modified by implementing the time-dependent fractal dimension TDFD, differential fractal dimension, and differential signals methods to determine if the results could be further improved. Katz's method with FKNN resulted in the highest classification accuracy of 85%, and further improvements by 3% were achieved by implementing the TDFD method.
38 citations