Information Security Assurance implies ensuring the integrity, confidentiality and availability of critical assets for an organization. The large amount of events to monitor in a fluid system in terms of topology and ...
详细信息
ISBN:
(纸本)9781467367974
Information Security Assurance implies ensuring the integrity, confidentiality and availability of critical assets for an organization. The large amount of events to monitor in a fluid system in terms of topology and variety of new hardware or software, overwhelms monitoring controls. Furthermore, the multi-facets of cyber threats today makes it difficult even for security experts to handle and keep up-to-date. Hence, automatic "intelligent" tools are needed to address these issues. In this paper, we describe a 'work in progress' contribution on intelligent based approach to mitigating security threats. The main contribution of this work is an anomaly based IDS model with active response that combines artificial immune systems and swarm intelligence with the SVM classifier. Test results for the NSL-KDD dataset prove the proposed approach can outperform the standard classifier in terms of attack detection rate and false alarm rate, while reducing the number of features in the dataset.
Proper location management of the mobile users in the mobile cellular networks is of great importance in this era of wireless communications. This paper has solved the location management issue based on the reporting ...
详细信息
ISBN:
(纸本)9781538629895
Proper location management of the mobile users in the mobile cellular networks is of great importance in this era of wireless communications. This paper has solved the location management issue based on the reporting cell planning approach. The mobile location management comprises of two perspectives: location update and paging and it is developed as a cost optimization problem. In this paper, we propose a new metaheuristic popular, nature-inspired batalgorithm with the objective of minimizing the involved location management cost. We have compared the proposed approach with the state-of-the-art approaches available M the literature. Here the applicability of the batalgorithm to the location management problem has been addressed using the reference networks as well the realistic networks of Odisha state. The computational results clearly show that the proposed approach performs as good as other approaches in terms of solution quality and has an added advantage of faster convergence.
1Classification is a central problem in the fields of data mining and machine learning. Using a training set of labeled instances, the task is to build a model (classifier) that can be used to predict the class of new...
详细信息
ISBN:
(纸本)9781509056866
1Classification is a central problem in the fields of data mining and machine learning. Using a training set of labeled instances, the task is to build a model (classifier) that can be used to predict the class of new unlabelled instances. Data preparation is crucial to the data mining process, and its focus is to improve the fitness of the training data for the learning algorithms to produce more effective classifiers. Searching for the frequent pattern within a specific sequence has become a much needed task in various sectors. Feature selection is selecting a subset of optimal features. Feature selection is being used in high dimensional data reduction and it is being used in several applications like medical, image processing, text mining, etc. In the existing work, unsupervised feature selection methods using Artificial Bee Colony Optimization algorithm, batalgorithm and Ant Colony Optimization have been introduced. We have compared these three algorithms and concluded that batalgorithm proves to be better in performance than the rest. The proposed system will use a novel method to select subset of features from unlabelled data using batalgorithm with one of the clustering algorithm and develop an expert information retrieval system.
The development of methods based on demonstrating portions of the power system network at the detailed level has brought about new perceptions for topology error identification in modeling power system in real-time. T...
详细信息
ISBN:
(纸本)9781538651865
The development of methods based on demonstrating portions of the power system network at the detailed level has brought about new perceptions for topology error identification in modeling power system in real-time. This paper reports the issue of defining the noteworthy portions of the network to be represented in details so as to guarantee satisfactory topological conditions for determination of topology inaccuracies. Beginning with the reduced network model, the suggested methodology executes error investigation and states l inkage indices used for suspicious branches determination. binary bat algorithm is then used to enlarge the suspicious branches into a significant subnetwork to be represented at the detailed level. This subnetwork contains all uncertain substations and shows the essential properties for determination topology inaccuracies. Simulation results for the proposed methodology using IEEE 14-bus and 30-bus test systems proved its effectiveness.
With the recent advancements in the fields of machine learning and artificial intelligence, spoken language identification-based applications have been increasing in terms of the impact they have on the day-to-day liv...
详细信息
With the recent advancements in the fields of machine learning and artificial intelligence, spoken language identification-based applications have been increasing in terms of the impact they have on the day-to-day lives of common people. Western countries have been enjoying the privilege of spoken language recognition-based applications for a while now, however, they have not gained much popularity in multi-lingual countries like India owing to various complexities. In this paper, we have addressed this issue by attempting to identify different Indian languages based on various well-known features like Mel-Frequency Cepstral Coefficient (MFCC), Linear Prediction Coefficient (LPC), Discrete Wavelet Transform (DWT), Gammatone Frequency Cepstral Coefficient (GFCC) as well as a few deep learning architecture based features like i-vector and x-vector extracted from the audio signals. After comparing the initial results, it is observed that the combination of MFCC and LPC produces the best results. Then we have developed a new nature-inspired feature selection (FS) algorithm by hybridizing binary bat algorithm (BBA) with Late Acceptance Hill-Climbing (LAHC) to select the optimal subset from the said feature vectors in order to reduce the model complexity and help it train faster. Using Random Forest (RF) classifier, we have achieved an accuracy of 92.35% on Indic TTS database developed by IIT-Madras, and an accuracy of 100% on the Indic Speech database developed by the Speech and Vision Laboratory (SVL) IIIT-Hyderabad. The proposed algorithm is also found to outperform many standard meta-heuristic FS algorithms. The source code of this work is available at: https://***/CodeChef97dotcom/Feature-Selection
One of the least expensive and safest diagnostic modalities routinely used is ultrasound imaging. An attractive development in this field is a two-dimensional (21)) matrix probe with three-dimensional (3D) imaging. Th...
详细信息
One of the least expensive and safest diagnostic modalities routinely used is ultrasound imaging. An attractive development in this field is a two-dimensional (21)) matrix probe with three-dimensional (3D) imaging. The main problems to implement this probe come from a large number of elements they need to use. When the number of elements is reduced the side lobes arising from the transducer change along with the grating lobes that are linked to the periodic disposition of the elements. The grating lobes are reduced by placing the elements without any consideration of the grid. In this study, the binary bat algorithm (BBA) is used to optimize the number of active elements in order to lower the side lobe level. The results are compared to other optimization methods to validate the proposed algorithm.
This paper presents a new approach to determine the optimal number and arrangement of power quality monitors (PQMs) for voltage sag detection. It is necessary to determine the optimal number and arrangement of PQMs si...
详细信息
ISBN:
(纸本)9781728138169
This paper presents a new approach to determine the optimal number and arrangement of power quality monitors (PQMs) for voltage sag detection. It is necessary to determine the optimal number and arrangement of PQMs since their installation at all buses in a network is an uneconomical option due to relatively high price of PQMs. The appropriate mathematical model, that describes the considered optimization problem, is created by using the concept of topological monitor reach area. A new definition of the cost function is presented in the paper in order to simultaneously determine the required number of PQMs and their best arrangement. Also, the effect of setting different values of monitor's coverage control parameter on the obtained results is analyzed. Four optimization methods are implemented to solve the considered problem: binary bat algorithm, binary Dragonfly algorithm, binary Particle Swarm Optimization and Genetic algorithm. The presented approach is tested on the IEEE 34-node test system. Simulations proved that the binary bat algorithm has the best performance in terms of computational time, convergence and the probability rate of finding the global optimum.
暂无评论