scholarly journals Wildcard Fields-Based Partitioning for Fast and Scalable Packet Classification in Vehicle-to-Everything

Sensors ◽  
2019 ◽  
Vol 19 (11) ◽  
pp. 2563 ◽  
Author(s):  
Jaehyung Wee ◽  
Jin-Ghoo Choi ◽  
Wooguil Pak
Keyword(s):  
Decision Tree ◽  
Communication Networks ◽  
High Speed ◽  
Classification Performance ◽  
Packet Classification ◽  
Classification Algorithms ◽  
Packet Processing ◽  
Security Issues ◽  
Security Of Network ◽  
High Level

Vehicle-to-Everything (V2X) requires high-speed communication and high-level security. However, as the number of connected devices increases exponentially, communication networks are suffering from huge traffic and various security issues. It is well known that performance and security of network equipment significantly depends on the packet classification algorithm because it is one of the most fundamental packet processing functions. Thus, the algorithm should run fast even with the huge set of packet processing rules. Unfortunately, previous packet classification algorithms have focused on the processing speed only, failing to be scalable with the rule-set size. In this paper, we propose a new packet classification approach balancing classification speed and scalability. It can be applied to most decision tree-based packet classification algorithms such as HyperCuts and EffiCuts. It determines partitioning fields considering the rule duplication explicitly, which makes the algorithm memory-effective. In addition, the proposed approach reduces the decision tree size substantially with the minimal sacrifice of classification performance. As a result, we can attain high-speed packet classification and scalability simultaneously, which is very essential for latest services such as V2X and Internet-of-Things (IoT).

Extensions to decision-tree based packet classification algorithms to address new classification paradigms

2017 ◽  
Vol 122 ◽  
pp. 83-95 ◽  
Author(s):  
Thibaut Stimpfling ◽  
Normand Bélanger ◽  
Omar Cherkaoui ◽  
André Béliveau ◽  
Ludovic Béliveau ◽  
...  
Keyword(s):  
Decision Tree ◽  
Packet Classification ◽  
Classification Algorithms ◽  
New Classification

scholarly journals Genetic Programming With a New Representation to Automatically Learn Features and Evolve Ensembles for Image Classification

2020 ◽  
Author(s):  
Ying Bi ◽  
Bing Xue ◽  
Mengjie Zhang
Keyword(s):  
Genetic Programming ◽  
Image Classification ◽  
Domain Knowledge ◽  
Ensemble Methods ◽  
Classification Performance ◽  
Classification Algorithms ◽  
New Approach ◽  
Terminal Set ◽  
Class Labels ◽  
High Level

Image classification is a popular task in machine learning and computer vision, but it is very challenging due to high variation crossing images. Using ensemble methods for solving image classification can achieve higher classification performance than using a single classification algorithm. However, to obtain a good ensemble, the component (base) classifiers in an ensemble should be accurate and diverse. To solve image classification effectively, feature extraction is necessary to transform raw pixels into high-level informative features. However, this process often requires domain knowledge. This article proposes an evolutionary approach based on genetic programming to automatically and simultaneously learn informative features and evolve effective ensembles for image classification. The new approach takes raw images as inputs and returns predictions of class labels based on the evolved classifiers. To achieve this, a new individual representation, a new function set, and a new terminal set are developed to allow the new approach to effectively find the best solution. More important, the solutions of the new approach can extract informative features from raw images and can automatically address the diversity issue of the ensembles. In addition, the new approach can automatically select and optimize the parameters for the classification algorithms in the ensemble. The performance of the new approach is examined on 13 different image classification datasets of varying difficulty and compared with a large number of effective methods. The results show that the new approach achieves better classification accuracy on most datasets than the competitive methods. Further analysis demonstrates that the new approach can evolve solutions with high accuracy and diversity.

scholarly journals Genetic Programming With a New Representation to Automatically Learn Features and Evolve Ensembles for Image Classification

2020 ◽  
Author(s):  
Ying Bi ◽  
Bing Xue ◽  
Mengjie Zhang
Keyword(s):  
Genetic Programming ◽  
Image Classification ◽  
Domain Knowledge ◽  
Ensemble Methods ◽  
Classification Performance ◽  
Classification Algorithms ◽  
New Approach ◽  
Terminal Set ◽  
Class Labels ◽  
High Level

Image classification is a popular task in machine learning and computer vision, but it is very challenging due to high variation crossing images. Using ensemble methods for solving image classification can achieve higher classification performance than using a single classification algorithm. However, to obtain a good ensemble, the component (base) classifiers in an ensemble should be accurate and diverse. To solve image classification effectively, feature extraction is necessary to transform raw pixels into high-level informative features. However, this process often requires domain knowledge. This article proposes an evolutionary approach based on genetic programming to automatically and simultaneously learn informative features and evolve effective ensembles for image classification. The new approach takes raw images as inputs and returns predictions of class labels based on the evolved classifiers. To achieve this, a new individual representation, a new function set, and a new terminal set are developed to allow the new approach to effectively find the best solution. More important, the solutions of the new approach can extract informative features from raw images and can automatically address the diversity issue of the ensembles. In addition, the new approach can automatically select and optimize the parameters for the classification algorithms in the ensemble. The performance of the new approach is examined on 13 different image classification datasets of varying difficulty and compared with a large number of effective methods. The results show that the new approach achieves better classification accuracy on most datasets than the competitive methods. Further analysis demonstrates that the new approach can evolve solutions with high accuracy and diversity.

A Novel Image Encryption Algorithm Using Multiple Encryption Techniques for Mobile Devices

2020 ◽  
Vol 10 (2) ◽  
pp. 123-142
Author(s):  
Showkat Ahmad Bhat ◽  
Amandeep Singh
Keyword(s):  
Wireless Communication ◽  
Communication Networks ◽  
Image Encryption ◽  
High Speed ◽  
Security Analysis ◽  
Encryption Algorithm ◽  
Multiple Encryption ◽  
Communication Devices ◽  
Cryptographic Attacks ◽  
Image Encryption Algorithm

Background & Objective: Digital multimedia exchange between different mobile communication devices has increased rapidly with the invention of the high-speed data services like LTE-A, LTE, and WiMAX. However, there are always certain security risks associated with the use of wireless communication technologies. Methods: To protect the digital images against cryptographic attacks different image encryption algorithms are being employed in the wireless communication networks. These algorithms use comparatively less key spaces and accordingly offer inadequate security. The proposed algorithm described in this paper based on Rubik’s cube principle because of its high confusion and diffusion properties, Arnold function having effective scrambling power, blocking cipher with block encryption and permutation powers. The main strength of the proposed algorithm lies in the large key spaces and the combination of different high power encryption techniques at each stage of algorithm. The different operations employed on the image are with four security keys of different key spaces at multiple stages of the algorithm. Results & Conclusion: Finally, the effectiveness and the security analysis results shows that the proposed image encryption algorithm attains high encryption and security capabilities along with high resistance against cryptanalytic attacks, differential attacks and statistical attacks.

scholarly journals Towards a Glass New World: The Role of Ion-Exchange in Modern Technology

2021 ◽  
Vol 11 (10) ◽  
pp. 4610
Author(s):  
Simone Berneschi ◽  
Giancarlo C. Righini ◽  
Stefano Pelli
Keyword(s):  
Ion Exchange ◽  
Communication Networks ◽  
High Speed ◽  
High Performance ◽  
Low Cost ◽  
Modern Technology ◽  
Historical Background ◽  
Wide Range ◽  
Happy Marriage

Glasses, in their different forms and compositions, have special properties that are not found in other materials. The combination of transparency and hardness at room temperature, combined with a suitable mechanical strength and excellent chemical durability, makes this material indispensable for many applications in different technological fields (as, for instance, the optical fibres which constitute the physical carrier for high-speed communication networks as well as the transducer for a wide range of high-performance sensors). For its part, ion-exchange from molten salts is a well-established, low-cost technology capable of modifying the chemical-physical properties of glass. The synergy between ion-exchange and glass has always been a happy marriage, from its ancient historical background for the realisation of wonderful artefacts, to the discovery of novel and fascinating solutions for modern technology (e.g., integrated optics). Getting inspiration from some hot topics related to the application context of this technique, the goal of this critical review is to show how ion-exchange in glass, far from being an obsolete process, can still have an important impact in everyday life, both at a merely commercial level as well as at that of frontier research.

Sign in / Sign up

Export Citation Format

Share Document