An interpretability security framework for intelligent decision support systems based on saliency map

International Journal of Information Security - Benefiting from the high-speed transmission and super-low latency, the Fifth Generation (5G) networks are playing an important role in contemporary...     

Observer-based leader-following consensus of one-sided Lipschitz multi-agent systems over input saturation and directed graphs

This paper investigates a local observer-based leader-following consensus control of one-sided Lipschitz (OSL) multi-agent systems (MASs) under input saturation. The proposed consensus control scheme has been formulated by using the OSL property, input saturation, directed graphs, estimated states, and quadratic inner-boundedness condition by attaining the regional stability. It is assumed that the graph always includes a (directed) spanning tree with respect to the leader root to develop matrix inequalities for investigating parameters of the proposed observer and consensus protocols. Further, a new observer-based consensus tracking method for MASs with saturation, concerning independent topologies for communicating outputs and estimates over the network, is explored to deal with a more perplexing and realistic situation. In contrast to the traditional methods, the proposed consensus approach considers output feedback and deals with the input saturation for a generalized class of nonlinear systems. The efficiency of the obtained results is illustrated via application to a group of five moving agents in the Cartesian coordinates.     

Scientific Workflow Makespan Minimization in Edge Multiple Service Providers Environment

The edge computing model offers an ultimate platform to support scientific and real-time workflow-based applications over the edge of the network. However, scientific workflow scheduling and execution still facing challenges such as response time management and latency time. This leads to deal with the acquisition delay of servers, deployed at the edge of a network and reduces the overall completion time of workflow. Previous studies show that existing scheduling methods consider the static performance of the server and ignore the impact of resource acquisition delay when scheduling workflow tasks. Our proposed method presented a meta-heuristic algorithm to schedule the scientific workflow and minimize the overall completion time by properly managing the acquisition and transmission delays. We carry out extensive experiments and evaluations based on commercial clouds and various scientific workflow templates. The proposed method has approximately 7.7% better performance than the baseline algorithms, particularly in overall deadline constraint that gives a success rate.

     

Semi-Supervised Deep Learning for Multi-Tissue Segmentation from Multi-Contrast MRI

Journal of Signal Processing Systems - Segmentation of thigh tissues (muscle, fat, inter-muscular adipose tissue (IMAT), bone, and bone marrow) from magnetic resonance imaging (MRI) scans is useful...     

Investigating the effect of varying block size on power and energy consumption of GPU kernels

The Journal of Supercomputing - Power consumption is likely to remain a significant concern for exascale performance in the foreseeable future. In addition, graphics processing units (GPUs) have...     

Design of backpropagated neurocomputing paradigm for Stuxnet virus dynamics in control infrastructure

Neural Computing and Applications - In the present study, a novel application of backpropagated neurocomputing heuristics (BNCH) is presented for epidemic virus model that portrays the Stuxnet...     

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.     

Amended hybrid multi-verse optimizer with genetic algorithm for solving task scheduling problem in cloud computing

The Journal of Supercomputing - The central cloud facilities based on virtual machines offer many benefits to reduce the scheduling costs and improve service availability and accessibility. The...     

High-feed turning of AISI D2 tool steel using multi-radii tool inserts: Tool life,material removed,and workpiece surface integrity evaluation

Multi-radii tool inserts offer novel configuration that comprises of multiple radii at tool nose. A review of the available literature indicates that there exists a need for experimental investigation on certain key machining characteristics of such tools. This paper reports on tool wear/life, material removed, and workpiece surface roughness when multi-radii mixed alumina TiN coated tool inserts are employed for turning D2 steel. Inserts of three different nose radii (0.40, 0.80, 1.20?mm) at six levels of feed rates (ranging from 0.157 to 0.562?mm/rev) are used. Results show that flank wear is the dominant wear mode with catastrophic tool failure occurring at highest nose radius (1.20?mm) and feed rate (0.562?mm/rev) combination. Also, there is ～59% reduction in tool life accompanied by ～62% increase in quantity of material removed as the feed rate increases from 0.157 to 0.562?mm/rev at maximum nose radius (1.20?mm). Feed rate is found to be statistically significant factor for all three responses considered herein at 95% confidence level. Surface integrity assessment at maximum feed rate reveals presence of a strain hardened layer extending to the depth of 150?µm below the machined surface without any observance of white layer for all the tool conditions and nose radius.