Current work presents a case study that simultaneously addresses the classical problem of job sequencing and batch sizing in a manufacturing firm. The firm produces engines and transmission sets for automotive industries and is characterized by multi-stage processing of several sub-products followed by the final assembly. The firm processes 11 components using 23 machines to cater customer demand of transmission sets under constraints like machine capacity and delivery schedule. To propose an improvised schedule and batch sizes, a planning model is developed which also aims to improvise specific performance measurement criteria i.e. makespan. The problem is complex due to exceedingly large solution space, which precludes the use of any exact algorithm. A simulation based Genetic Algorithm (GA) approach is thus used to solve this optimization problem. Authors report successful implementation of the approach and demonstrate improvised results over the existing approach of the firm. The work assists operations manager for efficient planning, and constitutes a practical application of simulation-based optimization involving effective monitoring and control of production.

Submitted on June 18, 2017; Revised on July 14, 2017; Accepted on August 2, 2017
References: 27

Opting right alternative between numerous alternatives is really complicated decision, which becomes more complex when alternatives are conflicting in nature and there is minor difference among alternatives. Complexity in decision making can be minimized if analytical methods are used for selection of alternatives. In everyday life, we often have to make decisions and several times we come across circumstances where the decision to make is selection of best alternative among various alternatives. This paper demonstrates application of Fuzzy Analytical Hierarchical Process approach integrated with Grey Relation Analysis to select the best car among various cars available in the market taking into consideration all the required qualitative and quantitative decision aspects.
Submitted on May 8, 2017; Revised on June 28, 2017; Accepted on August 13, 2017
References: 15

A humidity sensor detects, measures and reports the content of moisture in the air. Using low cost composite materials, a humidity sensor has been fabricated. The characterization has been done using various techniques to prove its surface morphology and working. The fabricated sensor detects relative humidity in the range of 15% to 65%. The life of the sensor has been calculated using different experimental and statistical methods. An expert system has been modeled using different artificial intelligence techniques which predicts failure of the sensor. The Failure prediction of fabricated sensor using Fuzzy Logic, ANN and ANFIS are 81.4%, 97.4% and 98.2% accurate respectively. ANFIS technique proves to be the most accurate technique for prediction of reliability.

Submitted on June 10, 2017; Revised on August 12, 2017; Accepted on August 16, 2017
References: 24

For the rolling bearing with expensive test cost or of inconvenient test, in order to efficiently and accurately analyze its contact fatigue reliability under elliptical contact elastohydrodynamic lubrication (EHL), an intelligent reliability assessment method is proposed. Contact stress under EHL is obtained by the mapping of oil film pressure, gotten by finite difference method (FDM), in the Hertz contact zone of the finite element model of rolling bearing. Considering the randomness of the EHL, material and fatigue strength correction factors, the limit state function is established by using artificial neural network (ANN). For finding the optimal reliability index and the design point, genetic algorithm (GA) based on normalized real number encoding is employed and the two adjusting factors are introduced into fitness function to resolve convergence and stability problem. Reliability sensitivity analysis is achieved by the advanced first-order second-moment (AFOSM) method. Compared with the traditional Monte Carlo method (MCM), the proposed intelligent assessment method could embody the influence of EHL on contact fatigue reliability and has higher calculation efficiency and a wonderful global search capability in the whole optimization room.

Submitted on June 18, 2017; Revised on July 14, 2017; Accepted on August 2, 2017
References: 20

Port hopping is an effective solution for Moving Target Defense (MTD), which randomly changes the server’s service port number to provide a robust communication against malicious Denial of Service (DoS) and Distributed DoS (DDoS) attack. Although a series of novel and feasible port hopping mechanisms have been proposed and implemented, most of them cannot prevent the messages transmitted in the network from being intercepted by an attacker. This paper addresses the problem of defending the eavesdropping attack with the port hopping process. We propose a new module that combines the properties of port hopping and the encryption of DNA microdots to resist the eavesdropping attacks in the network. The proposed port hopping process is compatible with the UDP and TCP protocols, in which the four IP addresses equipped in the server stand for the different nucleotides of DNA strands. We implement the proposed scheme and conduct the theoretical analysis on it. The theoretical analysis and experimental results illustrate that the proposed scheme can effectively defend against the DoS/DDoS and eavesdropping attacks.

Submitted on March 16, 2017; Revised on June 2, 2017; Accepted on August 15, 2017
References: 24

With the rapid development of big data and cloud computing, recommender systems (RSs) have gained significant attention in recent decades. However, there are still many challenges and drawbacks existed in RSs, such as complex and high-dimensional data, low recommendation accuracy, time-consuming and low-efficiency, which to a large extent restrict its applications. Non-negative Matrix Factorization algorithm (NMF) is a matrix factorization algorithm which finds the positive factorization of a given positive matrix. It can eliminate invalid and redundant features in user-rating matrix (URM), reduce URM’s dimension. Exact Euclidean Locality Sensitive Hashing (E2LSH) is an advanced algorithm for solving the approximate or exact Near Neighbor Search in high dimensional spaces. It can cluster similar-interest users (SIUs) of URM efficiently. Therefore, the authors propose an improved recommender system model named NE-UserCF (NMF-E2LSH-UserCF) based on NMF and E2LSH to improve the quality and performance of recommendation. The authors first utilize the NMF to process original URM, get a new-URM without invalid and redundant features. Then use E2LSH to cluster users in new-URM based on their interests and produce the similar-interest-user matrix (SIUM). The authors further process the Top-10 recommendations by adopting the user-based collaborative filtering algorithm (UserCF). Finally evaluate experimental results by analyzing metrics Precision, Recall, Coverage and Popularity. Experiments indicate that NE-UserCF proposed in this paper improves the quality of recommendation and has a good performance.

Submitted on April 8, 2017; Revised on July 10, 2017; Accepted on August 23, 2017
References: 29

XML is the de facto standard for data representation and exchanging on web. The query processing technique of XML streaming data is a hotspot in current research. Focused on the characteristics of processing semi-structure XML streaming data such as the stream arriving continuously, requiring to be read sequentially and only once into memory, the querying must be processed on the fly, a method of processing XPath query based on forest transducer is proposed. Firstly, conversion rules of forest transducer are defined for XPath query. And then the transducer is driven by input streaming data nodes. Stack and abstract syntax tree are applied to implement match and state transformation in running procedure. The relationships between state functions and intermediate results are kept by the abstract syntax tree, and the query results are output in reducing process. Finally, the experimental results show that our approach is effective and efficient on this problem, and outperforms about 30 percent of the state-of-the-art algorithms especially for large processed data. At the same time, memory usage is nearly constant. This method resolves the balance between time and space complexity, and it is a useful reference for other methods.

Submitted on March 28, 2017; Revised on July 2, 2017; Accepted on August 10, 2017
References: 29

The lightweight of artificial bone models is one of the most important and challenging topics in the precision medicine (individualized medicine), and porous structures are the first choice to achieve the lightweight. This paper presents a porous structure based lightweight framework of artificial bones, and it consists of porous analysis, modeling and optimization of lightweight, and practical validation. Specially, firstly, the triply periodic minimal surface (TPMS) is exploited to design the porous structures of lightweight. Secondly, a modeling of lightweight is constructed according to the stress condition and the geometric analysis, then, an optimal solution of the lightweight model can be obtained using the finite element analysis. Finally, the 3D printing is utilized to manufacture the lightweight models, which will be further used for practical verification and feedback correction. The experiments show that the lightweight bone models not only meet the specified requirements, such as fully-connected porous structures and conditions of external force, but also have obvious advantages in terms of structure stability, lightweight controllability and individual compatibility, which are ideal for the personalized precision medicine.

Submitted on May 1, 2017; Revised on July 8, 2017; Accepted on August 27, 2017
References: 37

In this paper, we focus on nuclear norm regularized matrix completion model in large matrices, and propose a new model named stochastic sub-gradient method for low rank matrix completion (SS-LRMC). To the problem of traditional SVT algorithm that would use one fixed threshold to shrink all the singular values during iterations, and the enormous computation burden when faced with large matrices, we define an adaptive singular value thresholding operator, and put forward a kind of matrix completion model applicable for user-item rating matrix of collaborative filtering. During iterations, we combine stochastic sub-gradient descent techniques with the adaptive singular value thresholding operator to obtain low rank intermediate solutions. Empirical results confirm that our proposed model and algorithm outperform several state-of-the-art matrix completion algorithms and the application to collaborative filtering recommendation can effectively solve the sparse problem of the user-item rating matrix and can significantly improve recommendation accuracy.

Submitted on April 14, 2017; Revised on June 28, 2017; Accepted on August 12, 2017
References: 21

This paper addresses the problem of approximate nearest neighbors (ANN) search in large-scale image collections. Inspired by the idea of multi-view observation in daily life, we propose a novel unsupervised hashing method to solve large-scale image retrieval on the scenarios of single information source, dubbed Multi-view Ensemble Hashing (MEH). MEH is realized by ensemble learning and a parallel architecture. In our approach, MEH learns a set of convolution filters from abundant images by principal component analysis (PCA) off-line at first. Next, MEH filters the original image collection of single information source respectively via these convolution filters, to generate the multi-view data itself. Then, MEH uses a traditional hashing method to learn hash function and hash code respectively in each generated view. Finally, MEH merges the results of multi-view together to achieve a final retrieval result by voting. Extensive experiments on dataset CIFAR-10 and LabelMe show the superiority of our proposed approach over several state-of-the-art hashing methods. Compared to the original hashing methods that used as the operator in MEH, our proposed approach improves the retrieval precision over 100% at code size of 16-bit, and 10% at code size of 256-bit. Furthermore, the cost of MEH maintains an approximate level for its parallelizable structure.

Submitted on May 5, 2017; Revised on July 15, 2017; Accepted on August 22, 2017
References: 30

Loopholes exist in nearly every regime, which leads to invalidity and instability in the running process of a regime. In this paper, we propose a new framework based on agent method and game theory to find loopholes in a regime, which contains two players with their clear payoffs. Following the principle of “winners stay, losers change”, agents make their own choices among strategies, and their choices can affect the payoffs of other players, resulting in a dynamic equilibrium that has obvious features in decision path, which can be easily found in the final figures after simulation. We further exploit typical cases, such as prisoner's dilemma, anti-coordination game, coordination game and harmony, of which the results have been mathematical proved, to illustrate the validity of our method. Finally, we make some regimes in this paper based on the classical case, “Boxed Pigs”, and find the loopholes in these regimes. By utilizing the framework proposed in this paper, managers are able to detect possible problems in advance at the time when they make regimes, which helps reduce the loss of costs caused by management and improve team relations.

Submitted on April 11, 2017; Revised on June 13, 2017; Accepted on August 21, 2017
References: 15

Three-dimensional reconstruction can reflect the dynamic relationship between lung lesions and surrounding tissues. It is easy to obtain an intuitive understanding of the shape, size, appearance and surroundings of pulmonary nodules, such as pleura or blood vessels. Three-dimensional reconstruction greatly improves the quality of surgery and reduces risk. This technique can help doctors to understand disease better and can guide operations in complex anatomical areas; therefore, it is worth recommending its clinical use. Therefore, our paper proposes a 3D segmentation method for use with pulmonary nodule image sequences based on supervoxels and multimodal data. First, we segment the lung parenchyma into superpixels. Then, we register PET/CT images using mutual information to roughly locate pulmonary nodule areas, matching the accurate pulmonary nodule areas using a multi-scale circular template matching algorithm. Finally, an improved three-dimensional supervoxel region-growing algorithm is proposed to reconstruct three-dimensional pulmonary nodules. The experimental results show that compared with the 3D region-growing algorithm, our algorithm can reconstruct complex pulmonary nodules more accurately and reduce time complexity.

Submitted on April 20, 2017; Revised on June 13, 2017; Accepted on August 20, 2017
References: 35

The tailings reservoir is a major hazard source with high potential energy, which may cause an artificial debris flow. The stability of the tailings reservoir is extremely important to the normal operation of the mining enterprises and the safety of people's lives and property. In order to settle the problem that traditional manual monitoring is scattered, not timely, and difficult to manage, this article takes Huangmailing tailings as an example, and establishes the CMST model to optimize the network topology connection of the tailings monitoring points. BP neural network algorithm is used to discuss the intelligent discovery and early warning of the faults on-line monitoring system of tailings. In this way, the fault-points and the causes can be perceived quickly and accurately, and the risk of the tailings’ safety accident can be reduced. It can be proved by the experimental results and two years stable operation of the system that BP neural network algorithm can accurately predict the value of safety monitoring data.

Submitted on April 20, 2017; Revised on June 30, 2017; Accepted on August 15, 2017
References: 19

Sensitive data is a very important to information safety. The real-world sensitive data is often illegally altered because database administrators (DBAs) have special identity and permissions in database system. However, the traditional secure measures, such as user authentication and access control, do not work well for them. For this case, it is necessary to identify effectively whether the sensitive data in database in enterprise trusted domain is illegally altered or not. Therefore, combining active detection at the security server with passive detection at the security client, a detection approach of the tampered sensitive data based on negotiable hash algorithm is proposed in this paper. Experiments show our algorithm can performs well for sensitive data tamper detection, and it is adapt to protect sensitive data in medical database.

Submitted on March 24, 2017; Revised on June 29, 2017; Accepted on August 21, 2017
References: 23

The social networks with the complex user relations and huge amount of data and hidden information, bring new opportunities and challenges for the study of information diffusion and influence maximization. In recent years, there are more and more researches on the influence maximization of topic preference. However, most of the existing researches only take the topic as an attribute of the users, and the importance of the topic in network structure is not considered. In view of this situation, firstly, this paper constructed a new topic attention network model fusing the social relation and the topic preference. Secondly, based on connected degree of set pair and Markov random walk model, we propose the calculated method of the topic preference for users, and then mining the seed set with influence by the greedy strategy. Thirdly, we propose the calculated method of the activation probability of the user based on the user relation and the topic preference, and propose the influence maximization algorithm TAN_CELF in topic attention networks. Finally, on Dou-ban network dataset, from three metrics ISST, ISRT and ISRNT, compare with algorithm L_GAUP and CELF, the experimental results show that algorithm TAN_CELF that is proposed by this paper has a higher performance on influence scope.

Submitted on March 26, 2017; Revised on June 16, 2017; Accepted on August 13, 2017
References: 17

Underwater Acoustic Networks (UANs) adopt acoustic communication. The opening and sharing features of underwater acoustic channel make communication in UANs vulnerable to eavesdropping and interfering, and UANs appeal for higher security. This paper presents a secure and depth-based anonymous routing (SDBR) protocol tailored for UANs. Based on bilinear pairings and hash function, by involving limited computation and communication resources, SDBR protocol achieves the backward and forward secrecy for underwater depth-based routing protocol. Theoretical analysis shows that SDBR protocol can provide identity confidentiality, location privacy and routing anonymity as well as decrease computation and communication costs.

Submitted on April 5, 2017; Revised on June 21, 2017; Accepted on August 20, 2017
References: 31

Ensemble feature selection is one of the ensemble learning methods, where each classifier is trained or built by feature selection result. Ensemble feature selection is an effective way for dealing with high dimension and small sample data, such as microarray data. However, ensemble feature selection should achieve more accurate and stable classification performance. In this paper, we present a novel diversity measure based on information theory called Sum of Minimal Information Distance (SMID), which maximizes the relevance between feature subsets and class label as well as the diversity between feature subsets. Moreover, a novel ensemble feature selection framework satisfying this criterion is proposed. In this framework, features that have more mutual information with class label and more diversity between each other are retained. Different feature subsets are used to train base classifiers after being obtained by incremental search method, and then these classifiers are aggregated into a consensus classifier by majority voting. Comparing with three representative feature selection methods and five ensemble learning methods on ten microarray datasets, the experiment results show that the proposed method achieves better performance than the other methods in terms of the classification accuracy.

Submitted on March 8, 2017; Revised on July 1, 2017; Accepted on August 27, 2017
References: 30

With the rise of Bitcoin, cryptographic currencies have attracted more and more attention. Subsequently, other cryptographic currencies were gradually created, such as Zcash, Moreno, Dash and so on. In cryptographic currency, privacy preserving and expansion are two key technical points. In terms of privacy preserving, more effective solutions were proposed in Zcach, Moreno, Dash and other cryptographic currencies systems, in which ring signature, zero knowledge proof and other cryptographic techniques played important roles. But these schemes mainly considered protecting the addresses of both sides of the transaction. In terms of expansion, lightning network and other projects also give solutions. But most of these projects will bring other problems. In this paper, a signature scheme based on the aggregate signature and the elliptic curve algorithm is proposed to hide the transaction value of a single sender and receiver in the transactions which contain multiple inputs and outputs. This signature scheme achieves the purpose of privacy preserving from the transaction value. Further, the correctness proof and security analysis are given in this paper. In addition to that, another signature scheme that combines aggregation signature with bilinear ring signature is proposed. This aggregate ring signature scheme gives another attempt to solve the problem of expansion in the cryptographic currency system only using cryptographic technologies. At the same time, the sender's addresses can be hidden. Similarly, we also confirmed the correctness of this signature scheme.

Submitted on March 24, 2017; Revised on June 17, 2017; Accepted on August 20, 2017
References: 23

Because of the randomness of attacker and defender’s strategy selection, the state variation during the network attack process must be a random process. So, the network attack and defense process can be abstracted a confrontation of multi-state based on different gains matrix. This paper describes the random of attack and defense strategy selection with Markov decision, and extends the Markov game model from single-state to multi-state and multi-agent. After that, it proves the existence of equilibrium strategy and gives the solving method of nonlinear programming. Finally, deduction and simulation analysis of the practical example indicate that this model's method is correspond to the actual application and the evaluation result is accurate, so it can be used to have a more detailed simulation to network attack and defense process in reality.

Submitted on January 29, 2017; Revised on April 12, 2017; Accepted on July 23, 2017
References: 32

Generative Summarization is of great importance in understanding large-scale textual data. In this work, we propose an attention-based Tree-LSTM model for sentence summarization, which utilizes an attention-based syntactic structure as auxiliary information. Thereinto, block-alignment is used to align the input and output syntax blocks, while inter-alignment is used for alignment of words within that of block pairs. To some extent, block-alignment can prevent structural deviations on the long sentences and inter-alignment is capable of increasing the flexibility of the generation in the blocks. This model can be easily trained to end-to-end mode and deal with any length of the input sentences. Compared with several relatively strong baselines, our model has achieved the state-of-art on DUC-2004 shared task.

Submitted on January 29, 2017; Revised on April 12, 2017; Accepted on June 23, 20177
References: 21