Lung nodules detection using semantic segmentation and classification with optimal features

Neural Computing and Applications - Lung cancer is a deadly disease if not diagnosed in its early stages. However, early detection of lung cancer is a challenging task due to the shape and size of...     

Single mask fabrication process for movable MEMS devices

The current work reports on the realization of movable micromachining devices using self-aligned single-mask fabrication process. Only dry etching process utilizing inductively coupled plasma reactive ion etching was used to release 3D micro structures from single crystal silicon substrate. No wet etching process is required to release the structures as is the case with silicon on insulator (SOI) wafers. Also the developed process does not require an SOI substrate and accordingly dispensing with the application of a wet etching step, thus yielding uniform structures without stiction. The optimized process was applied to realize thermally actuated microgrippers. The article presents the development of the fabrication process and demonstrates the operation of the fabricated device. The optimized process provides an avenue for low cost fabrication of movable micromachining devices without the use of complicated wet etching steps typically associated with SOI substrates.     

Silhouette-based human action recognition using SAX-Shapes

Human action recognition is an important problem in Computer Vision. Although most of the existing solutions provide good accuracy results, the methods are often overly complex and computationally expensive, hindering practical applications. In this regard, we introduce the combination of time-series representation for the silhouette and Symbolic Aggregate approXimation (SAX), which we refer to as SAX-Shapes, to address the problem of human action recognition. Given an action sequence, the extracted silhouettes of an actor from every frame are transformed into time series. Each of these time series is then efficiently converted into the symbolic vector: SAX. The set of all these SAX vectors (SAX-Shape) represents the action. We propose a rotation invariant distance function to be used by a random forest algorithm to perform the human action recognition. Requiring only silhouettes of actors, the proposed method is validated on two public datasets. It has an accuracy comparable to the related works and it performs well even in varying rotation.     

Growth and formation mechanism of sea urchin-like ZnO nanostructures on Si

Sea urchin-like nanostructures of ZnO consisting of ZnO nanowires with blunt faceted ends were grown on Si (100) substrates by oxidation of metallic Zn at 600 °C. ZnO nanowires having a diameter of 30–60 nm and length of 2–4 Μm were in similar shape with uniform diameter along its entire length with well faceted blunt ends. X-ray diffraction and transmission electron microscope analysis showed that the as-grown nanostructures were highly crystalline with wurtzite hexagonal structure having lattice constants of a=b=3.25 å and c=5.21 å. Room temperature photoluminescence (PL) measurements showed a weak near band-edge emission at 380 nm, but a strong green emission at 500–530 nm. A model for vapor-solid (VS) growth mechanism of ZnO nanowires was presented, in which nucleation of ZnO is crucial for the growth of the nanostructures.     

A cross-layer approach for partition detection at overlay layer for structured P2P in MANETs

Due to limited radio range and mobility of nodes in mobile ad hoc networks (MANETs), the network partitioning and merging could occur frequently. When structured peer-to-peer (P2P) overlays are running over MANETs, then network partition in the physical network can also cause network partition at the overlay layer. Existing approaches for structured P2P overlay over MANETs do not detect network partition at the overlay layer. This paper proposes a cross-layer approach to detect network partition at the overlay layer for structured P2P overlay over MANETs. Simulation results show that the proposed approach is highly effective and efficient in terms of routing overhead, success ratio and false-negative ratio.     

Architectural Design,Improvement, and Challenges of Distributed Software-Defined Wireless Sensor Networks

Wireless Personal Communications - Software-defined networking (SDN) is widely perceived to simplify network management and monitoring. The introduction of the SDN model into wireless sensor...     

The Double Edge Sword Based Distributed Executor Service

Scalability is one of the most important quality attribute of software-intensive systems, because it maintains an effective performance parallel to the large fluctuating and sometimes unpredictable workload. In order to achieve scalability, thread pool system (TPS) (which is also known as executor service) has been used extensively as a middleware service in software-intensive systems. TPS optimization is a challenging problem that determines the optimal size of thread pool dynamically on runtime. In case of distributed-TPS (DTPS), another issue is the load balancing b/w available set of TPSs running at backend servers. Existing DTPSs are overloaded either due to an inappropriate TPS optimization strategy at backend servers or improper load balancing scheme that cannot quickly recover an overload. Consequently, the performance of software-intensive system is suffered. Thus, in this paper, we propose a new DTPS that follows the collaborative round robin load balancing that has the effect of a double-edge sword. On the one hand, it effectively performs the load balancing (in case of overload situation) among available TPSs by a fast overload recovery procedure that decelerates the load on the overloaded TPSs up to their capacities and shifts the remaining load towards other gracefully running TPSs. And on the other hand, its robust load deceleration technique which is applied to an overloaded TPS sets an appropriate upper bound of thread pool size, because the pool size in each TPS is kept equal to the request rate on it, hence dynamically optimizes TPS. We evaluated the results of the proposed system against state of the art DTPSs by a client-server based simulator and found that our system outperformed by sustaining smaller response times.     

Low-Dimensional Halide Perovskites and Their Advanced Optoelectronic Applications

Nano-Micro Letters - A NiFe2O4/expanded graphite (NiFe2O4/EG) nanocomposite was prepared via a simple and inexpensive synthesis method. Its lithium storage properties were studied with the goal of...     

Learning from demonstration in robots: Experimental comparison of neural architectures

Robots have played an important role in the automation of computer aided manufacturing. The classical robot control implementation involves an expensive key step of model-based programming. An intuitive way to reduce this expensive exercise is to replace programming with machine learning of robot actions from demonstration where a (learner) robot learns an action by observing a demonstrator robot performing the same. To achieve this learning from demonstration (LFD) different machine learning techniques such as Artificial Neural Networks (ANN), Genetic Algorithms, Hidden Markov Models, Support Vector Machines, etc. can be used. This piece of work focuses exclusively on ANNs. Since ANNs have many standard architectural variations divided into two basic computational categories namely the recurrent networks and feed-forward networks, representative networks from each have been selected for study, i.e. Feed Forward Multilayer Perceptron (FF) network for feed-forward networks category and Elman (EL), and Nonlinear Autoregressive Exogenous Model (NARX) networks for the recurrent networks category. The main objective of this work is to identify the most suitable neural architecture for application of LFD in learning different robot actions. The sensor and actuator streams of demonstrated action are used as training data for ANN learning. Consequently, the learning capability is measured by comparing the error between demonstrator and corresponding learner streams. To achieve fairness in comparison three steps have been taken. First, Dynamic Time Warping is used to measure the error between demonstrator and learner streams, which gives resilience against translation in time. Second, comparison statistics are drawn between the best, instead of weight-equal, configurations of competing architectures so that learning capability of any architecture is not forced handicap. Third, each configuration's error is calculated as the average of ten trials of all possible learning sequences with random weight initialization so that the error value is independent of a particular sequence of learning or a particular set of initial weights. Six experiments are conducted to get a performance pattern of each architecture. In each experiment, a total of nine different robot actions were tested. Error statistics thus obtained have shown that NARX architecture is most suitable for this learning problem whereas Elman architecture has shown the worst suitability. Interestingly the computationally lesser MLP gives much lower and slightly higher error statistics compared to the computationally superior Elman and NARX neural architectures, respectively.     

A new region aware invisible robust blind watermarking approach

Multimedia Tools and Applications - The multimedia revolution has made a strong impact on our society. The explosive growth of Internet access to this digital information has generated new...