500 research outputs found
Sort by
A Comparative Analysis of Deep Learning Approaches for Network Intrusion Detection Systems (N-IDSs): Deep Learning for N-IDSs
No full textRecently, due to the advance and impressive results of deep learning techniques in the fields of image recognition, natural language processing and speech recognition for various long-standing artificial intelligence (AI) tasks, there has been a great interest in applying towards security tasks too. This article focuses on applying these deep taxonomy techniques to network intrusion detection system (N-IDS) with the aim to enhance the performance in classifying the network connections as either good or bad. To substantiate this to NIDS, this article models network traffic as a time series data, specifically transmission control protocol / internet protocol (TCP/IP) packets in a predefined time-window with a supervised deep learning methods such as recurrent neural network (RNN), identity matrix of initialized values typically termed as identity recurrent neural network (IRNN), long short-term memory (LSTM), clock-work RNN (CWRNN) and gated recurrent unit (GRU), utilizing connection records of KDDCup-99 challenge data set. The main interest is given to evaluate the performance of RNN over newly introduced method such as LSTM and IRNN to alleviate the vanishing and exploding gradient problem in memorizing the long-term dependencies. The efficient network architecture for all deep models is chosen based on comparing the performance of various network topologies and network parameters. The experiments of such chosen efficient configurations of deep models were run up to 1,000 epochs by varying learning-rates between 0.01-05. The observed results of IRNN are relatively close to the performance of LSTM on KDDCup-99 NIDS data set. In addition to KDDCup-99, the effectiveness of deep model architectures are evaluated on refined version of KDDCup-99: NSL-KDD and most recent one, UNSW-NB15 NIDS datasets
An Assembly Line Balancing Application on Oven Production Line with Hyper-Heuristics
No full textIn this study, an oven assembly line that is planning to re-establish manufacturing to increase the efficiency of the assembly process. The importance of the problem emerges from a real-world application consisting of product-oriented restrictions. These multiple restricted problems address the single model assignment restricted ALB problem with positional constraints. A cost-based objective function is used to cope with this problem. The number of platformed and non-platformed stations, the number of direction changes in a station, the number of stations in which both connector and combiner are used are the cost factors of the objective function. Also, the main objective of the problem is to minimize the total number of stations while satisfying the restrictions. A simulated annealing-based hyper-heuristic is adapted and applied to the balancing problem of oven manufacturing process with assignments and operational restrictions with multiple objectives. The results show that better solutions can be found in the current line balance level while satisfying more restrictions. It is also observed that line balance can be improved depending on the relaxation of the restrictions
Conceptual Framework for Enhancing the Implementation of Specific Microfinance Policies in Sub-Sahara Africa
No full textDeficient policy formulation processes and inadequate monitoring and supervision remain factors impeding the growth of microfinance in sub-Saharan Africa. This article explores issues mitigating policy implementation for microfinance institutions to propose a framework that will integrate stakeholders in the microfinance sector for effective financial policy implementation and promotion of microfinance performance and growth. The article proposes financial monitoring policy ownership structure and argues for the creation of an independent national microfinance supervisory authority as an alternative to ensuring effective implementation of microfinance policies in Ghana. This framework, the authors argue, will enhance stakeholder engagement in police formulation and create the necessary implementation environment, with adequate information, in which policy implementation for microfinance will flourish
Information Seeking and Online Deal Seeking Behavior
No full textDeal-seeking behavior is booming over the last decade. This article aims to identify online deal-seeking resources, understand the current status of online deal-seeking and identify key insights and trends for understanding online deal seeker's behaviors. The authors first conducted an in-depth review of the relevant literature including white papers, survey reports, online news articles, as well as, numerous postings on multiple deal-seeking websites. Then, a blog mining approach is used to mine relevant blog posts they found from the Internet. The article identifies different types of online deal-seeking resources and summarizes key insights and trends for understanding online deal seeker's behaviors. Online deal seeking behavior is a subject that is not well explored. The article summarizes key insights and trends for understanding online deal seeker's behaviors. Information-seeking theories are used to help explain shopper's online deal-seeking behaviors
Soybean Price Pattern Discovery Via Toeplitz Inverse Covariance-Based Clustering
No full textThe high volatility of world soybean prices has caused uncertainty and vulnerability particularly in the developing countries. The clustering of time series is a serviceable tool for discovering soybean price patterns in temporal data. However, traditional clustering method cannot represent the continuity of price data very well, nor keep a watchful eye on the correlation between factors. In this work, the authors use the Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data (TICC) to soybean price pattern discovery. This is a new method for multivariate time series clustering, which can simultaneously segment and cluster the time series data. Each pattern in the TICC method is defined by a Markov random field (MRF), characterizing the interdependencies between different factors of that pattern. Based on this representation, the characteristics of each pattern and the importance of each factor can be portrayed. The work provides a new way of thinking about market price prediction for agricultural products
Measuring CRM Effectiveness in Indian Stock Broking Services
No full textThe article tried to develop a multi-item scale for analyzing CRM effectiveness (CRME) from the customer perspective in the Indian stock broking context. The results revealed that customer satisfaction could be improved through to build customer trust and customer involvement substantially by focusing on the CRM system which further influences customer retention and ultimately, customer loyalty within stockbroking services. The findings of the article will help stockbrokers and their managers for a tactical decision making of CRM system implementation and practices for customer perspective. Despite the huge investment in CRM systems by the stockbrokers, critics have remained unconvinced about the effectiveness of CRM for meeting desired business outcomes. The reason being that broking firms often perceive CRM systems as a specific technology solution rather than integrating customer needs with the firm's strategy, people and business process which generates a parallel need to develop a scale to measures CRM effectiveness in Indian stock broking services from the customer perspective
Reversible Watermarking on Stereo Audio Signals by Exploring Inter-Channel Correlation
No full textA new reversible watermarking algorithm on stereo audio signals is proposed in this article. By utilizing correlations between two channels of audio signal, the authors segment one channel based on another one according to the smoothness. For each segmented sub-host sequence, they estimate its capacity and the corresponding embedding distortion firstly, and then select the optimal combinations of sub-host sequences for embedding. Experimental results indicate that the proposed algorithm can improve SNR (signal to noise ratio) for various kinds of capacity
Dynamic Provable Data Possession of Multiple Copies in Cloud Storage Based on Full-Node of AVL Tree
No full textThis article describes how to protect the security of cloud storage, a provable data possession scheme based on full-nodes of an AVL tree for multiple data copies in cloud storage. In the proposed scheme, a Henon chaotic map is first implemented for the node calculation of the AVL tree, and then the location of the data in the cloud is verified by AVL tree. As an AVL tree can keep the balance even with multiple dynamic operations made on the data in the cloud, it can improve the search efficiency of the data block, and reduce the length of the authentication path. Simulation results and analysis confirm that it can achieve good security and high efficiency
Examining Statistical Distributions and Statistical Behavior of Stem Tapers of Fagus Sylvatica in Municipal Forest of Naoussa
No full textThe aim of the present research is the study of the statistical behavior of ninety-three tapers. Tapers are classified into three categories depending on whether they use measured diameters at relative or absolute heights in the tree trunk. In each taper, measures of central tendency, measures of dispersion and a measure of skewness were examined. Each taper was examined if it fits normal distribution or not. It emerged that in the first category all tapers approached the normal distribution. In the second category, eight of the ten tapers are satisfactorily reaching the normal distribution, while in the third category thirty-seven out of seventy-eight are satisfactorily reaching the normal distribution. Data used in the research were collected in the Municipal Forest of Naoussa from 300 trees of Fagus sylvatica using random sampling
The Evolution of Data Science: A New Mode of Knowledge Production
No full textIs data science a new field of study or simply an extension or specialization of a discipline that already exists, such as statistics, computer science, or mathematics? This article explores the evolution of data science as a potentially new academic discipline, which has evolved as a function of new problem sets that established disciplines have been ill-prepared to address. The authors find that this newly-evolved discipline can be viewed through the lens of a new mode of knowledge production and is characterized by transdisciplinarity collaboration with the private sector and increased accountability. Lessons from this evolution can inform knowledge production in other traditional academic disciplines as well as inform established knowledge management practices grappling with the emerging challenges of Big Data