We conduct an examination of the preferences of drivers and passengers alike for in-vehicle interactions with a multistudy approach consisting of (1) a targeted literature survey of applications and user interfaces designed to support interactions with in-vehicle controls and systems based on gesture and voice input; (2) a large-scale survey (N = 160 participants) to understand drivers and passengers’ preferences for driving and traveling by car; and (3) an end-user elicitation study (N = 40 drivers and passengers) to collect preferences for gesture and voice input commands for in-vehicle interaction. We analyze and discuss the gesture and voice commands proposed by our participants and describe their characteristics, such as production times for gesture input and the vocabulary size of voice commands.
Despite an exciting area with many promises for innovations in wearable interactive systems, research on interaction techniques for smart rings lacks structured knowledge and readily-available resources for designers to systematically attain such innovations. In this work, we conduct a systematic literature review of ring-based gesture input, from which we extract key results and a large set of gesture commands for ring, ring-like, and ring-ready devices. We use these findings to deliver GestuRING, our web-based tool to support design of ring-based gesture input. GestuRING features a searchable gesture-to-function dictionary of 579 records with downloadable numerical data files and an associated YouTube video library. These resources are meant to assist the community in attaining further innovations in ring-based gesture input for interactive systems.
We present empirical results from a gesture elicitation study conducted with eleven wheelchair users that proposed on-body, in-air, and on-wheelchair gestures to effect twenty-one referents representing common actions, types of digital content, and navigation commands for interactive systems. We report a large preference for on-body (47.6%) and in-air (40.7%) compared to on-wheelchair (11.7%) gestures, mostly represented by touch input on different parts of the body and hand poses performed in mid-air with one hand. Following an agreement analysis that revealed low consensus (≤ 5.5%) between users, although high perceived gesture ease, goodness, and social acceptability within users, we examine our participants’ gesture characteristics in relation to their self-reported motor impairments, e.g., low strength, rapid fatigue, etc. We highlight the need for personalized gesture sets, tailored to and reflective of both users’ preferences and specific motor abilities, an implication that we examine through the lenses of ability-based design.
We explore the chair as a referential frame for facilitating hand gesture input to control interactive systems. First, we conduct a Systematic Literature Review on the topic of interactions supported by chairs, and uncover little research on harnessing everyday chairs for input, limited to chair rotation and tilting movements. Subsequently, to understand end users’ preferences for gestures performed on the chair’s surface (i.e., on-chair gestures) and in the space around the chair (i.e., from-chair gestures), we conduct an elicitation study involving 54 participants, 3 widespread chair variations—armchair, office-chair, and stool,—and 15 referents encompassing common actions, digital content types, and navigation commands for interactive systems. Our findings reveal a preference for unimanual gestures implemented with strokes, hand poses, and touch input, with specific nuances and kinematic profiles according to the chair type. Based on our findings, we propose a range of implications for interactive systems leveraging on-chair and from-chair gestures.
Hyperspectral images are becoming a valuable tool much used in agriculture, mineralogy, and so on. The challenge is to successfully classify the materials founded in the field relevant for different applications. Due to a large amount of data corresponding to a big number of spectral bands, the classification programs require a long time to analyze and classify the data. The purpose is to find a better method for reducing the classification time. We exploit various algorithms on real hyperspectral data sets to find out which algorithm is more effective. This paper presents a comparison of unsupervised hyperspectral image classification such as K-means, Hierarchical clustering, and Parafac decomposition, which allows the performance of the model reduction and feature extraction. The results showed that the method useful for big data is the classification of data after Parafac Decomposition.