No abstract

Recent research has shown that reliable recognition of sign language words and phrases using user-friendly and noninvasive armbands is feasible and desirable. This work provides an analysis and implementation of including fingerspelling recognition (FR) in such systems, which is a much harder problem due to lack of distinctive hand movements. A novel algorithm called DyFAV (Dynamic Feature Selection and Voting) is proposed for this purpose that exploits the fact that fingerspelling has a finite corpus (26 alphabets for the American Sign Language (ASL)). Detailed analysis of the algorithm used as well as comparisons with other traditional machine-learning algorithms is provided. The system uses an independent multiple-agent voting approach to identify letters with high accuracy. The independent voting of the agents ensures that the algorithm is highly parallelizable and thus recognition times can be kept low to suit real-time mobile applications. A thorough explanation and analysis is presented on results obtained on the ASL alphabet corpus for nine people with limited training. An average recognition accuracy of 95.36% is reported and compared with recognition results from other machine-learning techniques. This result is extended by including six additional validation users with data collected under similar settings as the previous dataset. Furthermore, a feature selection schema using a subset of the sensors is proposed and the results are evaluated. The mobile, noninvasive, and real-time nature of the technology is demonstrated by evaluating performance on various types of Android phones and remote server configurations. A brief discussion of the user interface is provided along with guidelines for best practices.

A regional decline in the Korean fir (Abies koreana) has been observed since the 1980s in the subalpine region. To explain this decline, it is important to investigate the degree to which environmental factors have contributed to plant distributions on diverse spatial scales. We applied a hierarchical regression model to determine quantitatively the relationship between the abundance of Korean fir (seedlings) and diverse environmental factors across two different ecological scales. We measured Korean fir density and the occurrence of its seedlings in 102 (84) plots nested at five sites and collected a range of environmental factors at the same plots. Our model included hierarchical explanatory variables at both site-level (weather conditions) and plot-level (micro-topographic factors, soil properties, and competing species). The occurrence of Korean fir seedlings was positively associated with moss cover and rock cover but negatively related to dwarf bamboo cover. At the site level, winter precipitation was significantly and positively related to the occurrence of seedlings. A hierarchical Poisson regression model revealed that Korean fir density was negatively associated with slope aspect, topographic position index, Quercus mongolica cover, and mean summer temperature. Our results suggest that rising temperature, drought, and competition with other species are factors that impede the survival of the Korean fir. We can predict that the population of Korean fir will continue to decline in the subalpine, and only a few Korean fir will survive on northern slopes or valleys due to climate change.

No abstract

No abstract

In this paper, we present and evaluate the outcomes of a measurement study amongst Android mobile device users, who volunteered their device-level network activity data through a newly developed mobile application in January 2013. We evaluate the submitted data in two hour time intervals with respect to device-level network traffic amounts, application network activity times, and data distribution (as measure of connectivity) between mobile (cellular) and wireless LAN networks.We find fairly homogeneous values with low levels of autocorrelation or long range dependence for the device-level amounts of data, but an indication for self-similarity for the summed application network usage times, which are positively correlated. In addition, we observe that the average distribution for cellular interface usage exhibits clear patterns for the day of the week as well as the time of the day. The combination of these findings can find direct utilization in future mobile device utilization modeling efforts.

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;

No abstract