In this paper we propose SmartARM-a Smartphone-based group Activity Recognition and Monitoring (ARM) scheme, which is capable of recognizing and centrally monitoring coordinated group and individual group member activities of soldiers in the context of military excercises. In this implementation, we specically consider military operations, where the group members perform similar motions or manoeuvres on a mission. Additionally, remote administrators at the command center receive data from the smartphones on a central server, enabling them to visualize and monitor the overall status of soldiers in situations such as battleelds, urban operations and during soldier's physical training. This work establishes-(a) the optimum position of smartphone placement on a soldier, (b) the optimum classier to use from a given set of options, and (c) the minimum sensors or sensor combinations to use for reliable detection of physical activities, while reducing the data-load on the network. The activity recognition modules using the selected classiers are trained on available data-sets using a testtrain-validation split approach. The trained models are used for recognizing activities from live smartphone data. The proposed activity detection method puts forth an accuracy of 80% for real-time data.

No abstract

No abstract

In India, the population with severe neuro-motor impairments (like people suffering from cerebral palsy) faces an acute problem with electronic-learning because there is a dearth of quality learning aids available for them. By quality learning aids we mean certain softwares that can help this section of special users to learn fast and at the same time with ease. Though similar systems are available in the international market, all of such products have a cost ranging from a few hundred to a few thousand dollars. For an average Indian user, they are too costly to afford. Moreover these products come in foreign languages which cannot facilitate the learning of the Indian languages. Keeping these two problems in focus, we have tried to design and develop a few learning aids which helps these section of users to learn and that too in their own languages. All these tools are indigenous and at the same time available at an affordable price. In this paper we would discuss about a predictive virtual keyboard, which not only helps these users to learn typing but also helps them to write essays, letters, and even compose poetry. All of these they can do in their own language.

Consider K processes, each generating a sequence of identical and independent random variables. The probability measures of these processes have random parameters that must be estimated. Specifically, they share a parameter θ common to all probability measures. Additionally, each process i ∈ {1, . . . , K} has a private parameter αi. The objective is to design an active sampling algorithm for sequentially estimating these parameters in order to form reliable estimates for all shared and private parameters with the fewest number of samples. This sampling algorithm has three key components: (i) data-driven sampling decisions, which dynamically over time specifies which of the K processes should be selected for sampling; (ii) stopping time for the process, which specifies when the accumulated data is sufficient to form reliable estimates and terminate the sampling process; and (iii) estimators for all shared and private parameters. Owing to the sequential estimation being known to be analytically intractable, this paper adopts conditional estimation cost functions, leading to a sequential estimation approach that was recently shown to render tractable analysis. Asymptotically optimal decision rules (sampling, stopping, and estimation) are delineated, and numerical experiments are provided to compare the efficacy and quality of the proposed procedure with those of the relevant approaches.