No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Injecting life into toys
Abstract
This paper envisions a future in which smartphones can be inserted into toys, such as a teddy bear, to make them interactive to children. Our idea is to leverage the smartphones' sensors to sense children's gestures, cues, and reactions, and interact back through acoustics, vibration, and when possible, the smartphone display. This paper is an attempt to explore this vision, ponder on applications, and take the first steps towards addressing some of the challenges. Our limited measurements from actual kids indicate that each child is quite unique in his/her "gesture vocabulary", motivating the need for personalized models. To learn these models, we employ signal processing-based approaches that first identify the presence of a gesture in a phone's sensor stream, and then learn its patterns for reliable classification. Our approach does not require manual supervision (i.e., the child is not asked to make any specific gesture); the phone detects and learns through observation and feedback. Our prototype, while far from a complete system, exhibits promise -- we now believe that an unsupervised sensing approach can enable new kinds of child-toy interactions.
... On the other hand, there still have been various types of AI systems developed specifically for children of different age groups and of different needs. The most represented age groups among the reviewed papers were preschoolers (2)(3)(4)(5) and young children (6)(7)(8)(9)(10)(11)(12), whereas fewer systems have been targeted at infants (0-1) or teens (13)(14)(15)(16)(17)(18). In terms of children with special needs, a considerate number of paper (23 papers) aimed at developing AI systems for children with physical special needs, which includes children with speech/hearing impairment (12 papers), children with visual impairment (1 paper), children with motor disabilities (7 papers), and children with other health issues (3 papers). ...
... Nevertheless, our selected set of AI frameworks represented not only the broadest and the most comprehensive set of policies proposed for AI, but were also the closest (at the time of this writing) to being enacted and having a real influence on AI design in practice. Secondly, those existing regulations not specifically for AI all tend to be developed for a very focused area or domain, e.g., online data protection (GDPR [2]), automatic vehicles [12]. ...
... Our results also showed that thermal dissipation can be sensed from the inside of an object and this could be used as an alternative to identify interactions. For example, an interactive toy could detect when a child plays with it [26]. Another interesting application would be to integrate the sensors as part of medical bottles to support medication management [27]. ...
We contribute MIDAS as a novel sensing solution for characterizing everyday objects using thermal dissipation. MIDAS takes advantage of the fact that anytime a person touches an object it results in heat transfer. By capturing and modeling the dissipation of the transferred heat, e.g., through the decrease in the captured thermal radiation, MIDAS can characterize the object and determine its material. We validate MIDAS through extensive empirical benchmarks and demonstrate that MIDAS offers an innovative sensing modality that can recognize a wide range of materials with up to 83% accuracy and generalize to variations in the people interacting with objects. We also demonstrate that MIDAS can detect thermal dissipation through objects, up to 2 mm thickness, and support analysis of multiple objects that are interacted with
... Our results also showed that thermal dissipation can be sensed from the inside of an object and this could be used as an alternative to identify interactions. For example, an interactive toy could detect when a child plays with it [26]. Another interesting application would be to integrate the sensors as part of medical bottles to support medication management [27]. ...
We contribute MIDAS as a novel sensing solution for characterizing everyday objects using thermal dissipation. MIDAS takes advantage of the fact that anytime a person touches an object it results in heat transfer. By capturing and modeling the dissipation of the transferred heat, e.g., through the decrease in the captured thermal radiation, MIDAS can characterize the object and determine its material. We validate MIDAS through extensive empirical benchmarks and demonstrate that MIDAS offers an innovative sensing modality that can recognize a wide range of materials-with up to 83% accuracy-and generalize to variations in the people interacting with objects. We also demonstrate that MIDAS can detect thermal dissipation through objects, up to 2 mm thickness, and support analysis of multiple objects that are interacted with.
... A study into inserting smartphones into toys reveals a creative approach to utilising device features in an entertaining way (Fan, Shin, & Choudhury, 2014). In a similar way, the speech recognition system from this project can interact with a child to teach them vocabulary and mathematics. ...
This paper presents a prototype for a "robot" device to demonstrate that advanced functionality is achievable by utilising even a low-end smartphone's capabilities. Through a standard client-server architecture implemented using HTML, JavaScript, .Net Core and SQL Server, the robot achieves five innovative functions: remote control, location tracking, video streaming, motion detection, and speech recognition. The robot program integrates commonly available Web APIs and phone functionalities through the browser on the smartphone. This paper also outlines a series of experiments to test whether the robot performed the new tasks to a usable level. The final prototype displayed performance that exceeded expectations for modest low-cost equipment and rivalled or even equalled that of high end devices. The solution's front-end is based entirely on HTML and JavaScript running in-browser, and so it is platform independent and the smartphone stays unaffected. The project's architectural simplicity and modular design is ideal for hobbyists and students to learn technological concepts.
... Current literature regarding children's screen-based Internet use indicates ongoing privacy and security concerns regarding the collection of children's personal information and opinions. However, little research has been published in the area of Internetconnected toys, apart from technical articles outlining software and hardware developments (Corbellini, Aksit, Schmid, Mangold, & Gross, 2014;Fan, Shin, & Choudhury, 2014). There has, however, been an increasing volume of social commentary and news items about these toys, as well as technical commentary about security flaws as these emerge (Adhikari, 2015a;Emm, 2015;Kube, 2015), discussed below. ...
The Internet of Toys refers to a future where toys not only relate one-on-one to children but are wirelessly connected to other toys and/or database data. While existing toy companies and start-ups are eagerly innovating in this area, problems involving data hacking and other privacy issues have already occurred. The Hello Barbie and VTech hacks in late 2015 are recent examples. This article reviews, outlines, and analyses these recent advances in children’s engagement with the Internet. It shows how Internet-connected toys, among other data-inducing practices (such as baby wearables and school analytics), are implicated in big data processes that are datafying a generation of youngsters. Significant issues exist around the data security and safety of The Internet of Toys for child consumers who are usually too young to fully understand and consent to data collection or to understand other security issues.
http://www.tandfonline.com/doi/abs/10.1080/22041451.2016.1266124
Dynamic time warping is a popular technique for comparing time series, providing both a distance measure that is insensitive to local compression and stretches and the warping which optimally deforms one of the two input series onto the other. A variety of algorithms and constraints have been discussed in the literature. The dtw package provides an unification of them; it allows R users to compute time series alignments mixing freely a variety of continuity constraints, restriction windows, endpoints, local distance definitions, and so on. The package also provides functions for visualizing alignments and constraints using several classic diagram types.
The design of an activity recognition and monitoring system based on the eWatch, multi-sensor platform worn on different body positions, is presented in this paper. The system identifies the user's activity in realtime using multiple sensors and records the classification results during a day. We compare multiple time domain feature sets and sampling rates, and analyze the tradeoff between recognition accuracy and computational complexity. The classification accuracy on different body positions used for wearing electronic devices was evaluated.
In this paper we present results related to achieving finegrained activity recognition for context-aware computing applications. We examine the advantages and challenges of reasoning with globally unique object instances detected by an RFID glove. We present a sequence of increasingly powerful probabilistic graphical models for activity recognition. We show the advantages of adding additional complexity and conclude with a model that can reason tractably about aggregated object instances and gracefully generalizes from object instances to their classes by using abstraction smoothing. We apply these models to data collected from a morning household routine.
Notori is a play kit that can revive a worn-out Smartphone. Since Smartphone often upgrade their phones, the number of phones which are serviceable but not used is also increasing. By combining traditional wooden toys with simple apps, Notori revitalizes out-of-date Smartphones and provides an attractive experience for children.
A fundamental difficulty in recognizing human activi- ties is obtaining the labeled data needed to learn mod- els of those activities. Given emerging sensor technol- ogy, however, it is possible to view activity data as a stream of natural language terms. Activity models are then mappings from such terms to activity names, and may be extracted from text corpora such as the web. We show that models so extracted are sufficient to auto- matically producelabeled segmentations ofactivity data with an accuracy of 42% over 26 activities, well above the 3.8% baseline. The segmentation so obtained is suf- ficient to bootstrap learning, with accuracy of learned models increasing to 52%. To our knowledge, this is the first human activity inferencing system shown to learn from sensed activity data with no human intervention per activity learned, even for labeling.
Adequate treatment of cardiac failure should reflect both clinical rules and quantitative evaluation of hemodynamics. For the latter we assumed an extensive model of heart and vessels: For the left and right ventricles the EMAX models were assumed with ...
Physical activity has a positive impact on people's well-being, and it may also decrease the occurrence of chronic diseases. Activity recognition with wearable sensors can provide feedback to the user about his/her lifestyle regarding physical activity and sports, and thus, promote a more active lifestyle. So far, activity recognition has mostly been studied in supervised laboratory settings. The aim of this study was to examine how well the daily activities and sports performed by the subjects in unsupervised settings can be recognized compared to supervised settings. The activities were recognized by using a hybrid classifier combining a tree structure containing a priori knowledge and artificial neural networks, and also by using three reference classifiers. Activity data were collected for 68 h from 12 subjects, out of which the activity was supervised for 21 h and unsupervised for 47 h. Activities were recognized based on signal features from 3-D accelerometers on hip and wrist and GPS information. The activities included lying down, sitting and standing, walking, running, cycling with an exercise bike, rowing with a rowing machine, playing football, Nordic walking, and cycling with a regular bike. The total accuracy of the activity recognition using both supervised and unsupervised data was 89% that was only 1% unit lower than the accuracy of activity recognition using only supervised data. However, the accuracy decreased by 17% unit when only supervised data were used for training and only unsupervised data for validation, which emphasizes the need for out-of-laboratory data in the development of activity-recognition systems. The results support a vision of recognizing a wider spectrum, and more complex activities in real life settings.
birth to 2: muscle memory, 03 2012
- R Lindert
Matthai Philipose, Fine-Grained Activity Recognition by Aggregating Abstract Object Usage
- J Donald
- Dieter Patterson
- Henry Fox
- Kautz
birth to 2: muscle memory 03 2012. Copyright Scholastic Inc. R. Lindert. birth to 2: muscle memory 03 2012
- R Lindert
Copyright Scholastic Inc . R. Lindert. birth to 2: muscle memory
- R Lindert
- Lindert R.