Generation of Movement Explanations for Testing Gesture Based Co-Operative Learning Applications

Banerjee, Ayan; Lamrani, Imane; Paudyal, Pradip; Gupta, Sandeep

doi:10.1109/aitest.2019.00-15

Cited by 6 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The overall signatures of these activities were found to be clustered in the feature space even if there existed individual variations for each activity type. However, more complex gestures related to activities such as eating or using gestural languages are poly-componential in nature, where multiple gestures are combined in definite sequences [2,3,31] which makes recognition more challenging. Thus, in this article, we focus on detecting eating actions from eating episodes in a User-Independent manner, which is a much more difficult problem than determining the presence of an eating episode.…”

Section: Methodsmentioning

confidence: 99%

“…The most significant sensor-set is the EMG set, because the combination involving EMG sensors had a better performance compared to other combinations. 3 However, usage of devices with only EMG sensors would not be feasible due to the poor segmentation performance of the EMG sensors, as seen in Table 3. Although most of the commercially available smartwatches or wristbands do not yet include the EMG sensors, they do include accelerometer, gyroscope, or orientation sensors.…”

Section: Sensor Selectionmentioning

confidence: 99%

See 1 more Smart Citation

A User-adaptive Modeling for Eating Action Identification from Wristband Time Series

Lee

Paudyal

Banerjee

et al. 2019

ACM Trans. Interact. Intell. Syst.

Self Cite

View full text Add to dashboard Cite

Eating activity monitoring using wearable sensors can potentially enable interventions based on eating speed to mitigate the risks of critical healthcare problems such as obesity or diabetes. Eating actions are polycomponential gestures composed of sequential arrangements of three distinct components interspersed with gestures that may be unrelated to eating. This makes it extremely challenging to accurately identify eating actions. The primary reasons for the lack of acceptance of state-of-the-art eating action monitoring techniques include the following: (i) the need to install wearable sensors that are cumbersome to wear or limit the mobility of the user, (ii) the need for manual input from the user, and (iii) poor accuracy in the absence of manual inputs. In this work, we propose a novel methodology, IDEA, that performs accurate eating action identification within eating episodes with an average F1 score of 0.92. This is an improvement of 0.11 for precision and 0.15 for recall for the worst-case users as compared to the state of the art. IDEA uses only a single wristband and provides feedback on eating speed every 2 min without obtaining any manual input from the user. CCS Concepts: • Human-centered computing → Ubiquitous and mobile computing;

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Sensor Selectionmentioning

confidence: 99%

A User-adaptive Modeling for Eating Action Identification from Wristband Time Series

Lee

Paudyal

Banerjee

et al. 2019

ACM Trans. Interact. Intell. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In such a case, we consider utilizing the reach set analysis technique to derive the reach set and compare with the safety thresholds to re-evaluate the system safety in the near future (Alur et al 1995). We have used the proposed approach in providing movement explanations for testing gesture based co-operative learning applications (Banerjee et al 2019).…”

Section: Safety Verification Ha-miningmentioning

confidence: 99%

Toward Operational Safety Verification of AI-Enabled CPS (Student Abstract)

Lamrani

Banerjee

Gupta

2020

AAAI

Self Cite

View full text Add to dashboard Cite

AI-enabled Cyber-physical systems (CPS) such as artificial pancreas (AP) or autonomous cars are using machine learning to make several critical decisions. The system is subject to inputs and scenarios which are not observed during training and the expected outputs are not known. Hence, popular model based verification techniques that characterize behavior of a control system before deployment using predictive models may be inaccurate and often result in incorrect safety analysis results. In addition, regulatory agencies are required to regulate safety-critical AI enabled CPS to ensure their operational safety. However, high complexity of the system result in myriad of safety concerns all of which may not only be comprehensively tested before deployment but also may not even be detected during design and testing phase. In this work, we propose a tool to help regulatory agencies compare the operation of the CPS with the specifications given by the manufacturer to ensure that the operation results conform with the safety assured design of a CPS.

show abstract

“…Automatic sign recognition is a well established problem and exist different approaches in literature. First of all, it is necessary to consider the gesture components such as hand shape, location and movement [2].…”

Section: Introductionmentioning

confidence: 99%

“…Many artificial vision systems have been developed in [2,[9][10][11], nevertheless they are based on a camera using and lighting dependency. In other words, their performance is affected on situation where there is high or a low illumination.…”

Section: Introductionmentioning

confidence: 99%

American Sign Language Electromiographic Alphabet Sign Translator

Catalan-Salgado

Lopez-Ramirez

Zagal-Flores

2019

Communications in Computer and Information Science

View full text Add to dashboard Cite

Communication between people is complicated, thus is due to correct idea and thought expression. But for the deaf or mute people this is even worse due to that our main communication channel is sound. They can use their own language using sign and ideograms made with hands, called American Sign Language. But as every language it is needed to learn and the population that dominate this language is small. In this work we propose an American Sign Language translator for 24 alphabet signs, using a wearable that give us eight electromiographic signals and KNN classifier for signs processing with 80% of accuracy.

show abstract

Generation of Movement Explanations for Testing Gesture Based Co-Operative Learning Applications

Cited by 6 publications

References 38 publications

A User-adaptive Modeling for Eating Action Identification from Wristband Time Series

A User-adaptive Modeling for Eating Action Identification from Wristband Time Series

Toward Operational Safety Verification of AI-Enabled CPS (Student Abstract)

American Sign Language Electromiographic Alphabet Sign Translator

Contact Info

Product

Resources

About