DeepClassRooms: a deep learning based digital twin framework for on-campus class rooms

Neural Computing and Applications - A lot of different methods are being opted for improving the educational standards through monitoring of the classrooms. The developed world uses Smart...     

Positive and negative circuits in discrete neural networks

We study the relationships between the positive and negative circuits of the connection graph and the fixed points of discrete neural networks (DNNs). As main results, we give necessary conditions and sufficient conditions for the existence of fixed points in a DNN. Moreover, we exhibit an upper bound for the number of fixed points in terms of the structure and number of positive circuits in the connection graph. This allows the determination of the maximum capacity for storing vectors in DNNs as fixed points, depending on the architecture of the network.     

An autonomous educational mobile robot mediator

So far, most of the applications of robotic technology to education have mainly focused on supporting the teaching of subjects that are closely related to the Robotics field, such as robot programming, robot construction, or mechatronics. Moreover, most of the applications have used the robot as an end or a passive tool of the learning activity, where the robot has been constructed or programmed. In this paper, we present a novel application of robotic technologies to education, where we use the real world situatedness of a robot to teach non-robotic related subjects, such as math and physics. Furthermore, we also provide the robot with a suitable degree of autonomy to actively guide and mediate in the development of the educational activity. We present our approach as an educational framework based on a collaborative and constructivist learning environment, where the robot is able to act as an interaction mediator capable of managing the interactions occurring among the working students. We illustrate the use of this framework by a 4-step methodology that is used to implement two educational activities. These activities were tested at local schools with encouraging results. Accordingly, the main contributions of this work are: i) A novel use of a mobile robot to illustrate and teach relevant concepts and properties of the real world; ii) A novel use of robots as mediators that autonomously guide an educational activity using a collaborative and constructivist learning approach; iii) The implementation and testing of these ideas in a real scenario, working with students at local schools.

Stability analysis of network-based cooperative resource allocation strategies

Resource allocation involves deciding how to divide a resource of limited availability among multiple demands in a way that optimizes current objectives. In this brief paper we focus on one type of distributed resource allocation problem where via an imperfect communication network multiple processors can share the load presented by multiple task types. We introduce asynchronous “cooperative” resource allocation strategies, and show that they lead to a bounded cumulative demand.     

TWC LOGD: A portal for linked open government data ecosystems

International open government initiatives are releasing an increasing volume of raw government datasets directly to citizens via the Web. The transparency resulting from these releases not only creates new application opportunities but also imposes new burdens inherent to large-scale distributed data integration, collaborative data manipulation and transparent data consumption. The Tetherless World Constellation (TWC) at Rensselaer Polytechnic Institute (RPI) has developed the Semantic Web-based TWC LOGD portal to support the deployment of linked open government data (LOGD). The portal is both an open source infrastructure supporting linked open government data production and consumption and a vibrant community portal that educates and serves the growing international open government community of developers, data curators and end users. This paper motivates and introduces the TWC LOGD Portal and highlights innovative aspects and lessons learned.     

Shape-sensitive MLS deformation

This work presents methods for deforming meshes in a shape-sensitive way using Moving Least Squares (MLS) optimization. It extends an approach for deforming space (Cuno et al. in Proceedings of the 27th Computer Graphics International Conference, pp. 115–122, 2007) by showing how custom distance metrics may be used to achieve deformations which preserve the overall mesh shape. Several variant formulations are discussed and demonstrated, including the use of geodesic distances, distances constrained to paths contained in the mesh, the use of skeletons, and a reformulation of the MLS scheme which makes it possible to affect the bending behavior of the deformation. Finally, aspects of the implementation of these techniques in parallel architectures such as GPUs (graphics processing units) are described and compared with CPU-only implementations.     

QoS-aware optimization of sensor network queries

The resource-constrained nature of mote-level wireless sensor networks (WSNs) poses challenges for the design of a general-purpose sensor network query processors (SNQPs). Existing SNQPs tend to generate query execution plans (QEPs) that are selected on the basis of a fixed, implicit expectation, for example, that energy consumption should be kept as small as possible. However, in WSN applications, the same query may be subject to several, possibly conflicting, quality-of-service (QoS) expectations concomitantly (for example maximizing data acquisition rates subject to keeping energy consumption low). It is also not uncommon for the QoS expectations to change over the lifetime of a deployment (for example from low to high data acquisition rates). This paper describes optimization algorithms that respond to stated QoS expectations (about acquisition rate, delivery time, energy consumption and lifetime) when making routing, placement, and timing decisions for in-WSN query processing. The paper shows experimentally that QoS-awareness offers significant benefits in responding to, and reconciling, diverse QoS expectations, thereby enabling QoS-aware SNQPs to generate efficient QEPs for a broader range WSN applications than has hitherto been possible.     

An Algebraic Approach for Compiling Real-Time Programs

Compiler Verification has been identified as a vital process in the implementation of correct safety-critical systems. We extend here Hoare's refinement-algebra approach to compilation in order to include real-time languages in which processes interact asynchronously via communication queues. The existence of unique fixed-points is exploited to verify the implementation of crucial operators such as asynchronous input, delay and timeout.     

Light-weight salient foreground detection for embedded smart cameras

An embedded smart camera is a stand-alone unit that not only captures images, but also includes a processor, memory and communication interface. Battery-powered, embedded smart cameras introduce many additional challenges since they have very limited resources, such as energy, processing power and memory. Computer vision algorithms running on these camera boards should be light-weight and efficient. Considering the memory requirements of an algorithm and its portability to an embedded processor should be an integral part of the algorithm design in addition to the accuracy requirements. This paper presents a light-weight and efficient background modeling and foreground detection algorithm that is highly robust against lighting variations and non-static backgrounds including scenes with swaying trees, water fountains and rain. Compared to many traditional methods, the memory requirement for the data saved for each pixel is very small in the proposed algorithm. Moreover, the number of memory accesses and instructions are adaptive, and are decreased depending on the amount of activity in the scene. Each pixel is treated differently based on its history, and instead of requiring the same number of memory accesses and instructions for every pixel, we require less instructions for stable background pixels. The plot of the number of unstable pixels at each frame also serves as a tool to find the video portions with high activity. The proposed method selectively updates the background model with an automatically adaptive rate, thus can adapt to rapid changes. As opposed to traditional methods, pixels are not always treated individually, and information about neighbors is incorporated into decision making. The results obtained with nine challenging outdoor and indoor sequences are presented, and compared with the results of different state-of-the-art background subtraction methods. The ROC curves and memory comparison of different background subtraction methods are also provided. The experimental results demonstrate the success of the proposed light-weight salient foreground detection method.