No abstract

We investigate the problem of scheduling a set of tasks with individual deadlines and conditional precedence constraints on a heterogeneous Network on Chip (NoC)-based Multi-Processor System-on-Chip (MPSoC) such that the total expected energy consumption of all the tasks is minimized, and propose a novel approach. Our approach consists of a scheduling heuristic for constructing a single unified schedule for all the tasks and assigning a frequency to each task and each communication assuming continuous frequencies, an Integer Linear Programming (ILP)-based algorithm and a polynomial time heuristic for assigning discrete frequencies and voltages to tasks and communications. We have performed experiments on 16 synthetic and 4 real-world benchmarks. The experimental results show that compared to the state-of-theart approach, our approach using the ILP-based algorithm and our approach using the polynomial-time heuristic achieve average improvements of 31% and 20%, respectively, in terms of energy reduction. compared to v j and traverse the same links that v j traverses. 4) If v j is a task node, compute its finish time ζ j = r j + t k,j , and insert unconditional directed edges from v j to unscheduled nodes concurrent to v j and mapped on the same processor where v j is mapped. 5) Delete v j from ReadySet and insert all ready nodes in G to ReadySet. Consider the CTG in Figure 1(b) and the MPSoC in Figure 2(a) where all the processors are identical. The execution times of tasks at the maximum processor frequency are t 1,1

Sentiment classification is an important but challenging task in natural language processing (NLP) and has been widely used for determining the sentiment polarity from user opinions. And word embedding technique learned from a various contexts to produce same vector representations for words with same contexts and also has been extensively used for NLP tasks. Recurrent neural networks (RNNs) are common deep learning architecture that are extensively used mechanism to address the classification issue of variable-length sentences. In this paper, we analyze to investigate variant-Gated Recurrent Unit (GRU) that includes encoder method to preprocess data and improve the impact of word embedding for sentiment classification. The real contributions of this paper contain the proposal of a novel Two-State GRU, and encoder method to develop an efficient architecture namely (E-TGRU) for sentiment classification. The empirical results demonstrated that GRU model can efficiently acquire the words employment in contexts of user's opinions provided large training data. We evaluated the performance with traditional recurrent models, GRU, LSTM and Bi-LSTM two benchmark datasets, IMDB and Amazon Products Reviews respectively. Results present that: 1) proposed approach (E-TGRU) obtained higher accuracy than three stateof-the-art recurrent approaches; 2) Word2Vec is more effective in handling as word vector in sentiment classification; 3) implementing the network, an imitation strategy shows that our proposed approach is strong for text classification.

<span>Developments in computer networking have raised concerns of the associated Botnets threat to the Internet security. Botnet is an inter-connected computers or nodes that infected with malicious software and being controlled as a group without any permission of the computer’s owner. <br /> This paper explores how network traffic characterising can be used for identification of botnet at local networks. To analyse the characteristic, behaviour or pattern of the botnet in the network traffic, a proper network analysing tools is needed. Several network analysis tools available today are used for the analysis process of the network traffic. In the analysis phase, <br /> the botnet detection strategy based on the signature and DNS anomaly approach are selected to identify the behaviour and the characteristic of the botnet. In anomaly approach most of the behavioural and characteristic identification of the botnet is done by comparing between the normal and anomalous traffic. The main focus of the network analysis is studied on UDP protocol network traffic. Based on the analysis of the network traffic, <br /> the following anomalies are identified, anomalous DNS packet request, <br /> the NetBIOS attack, anomalous DNS MX query, DNS amplification attack and UDP flood attack. This study, identify significant Botnet characteristic in local network traffic for UDP network as additional approach for Botnet detection mechanism.</span>