RANDOMIZED DYNAMIC TRICKLE TIMER ALGORITHM FOR INTERNET OF THINGS

 Author :  Muneer Bani Yassein

Affiliation :  Jordan University of Science and Technology

Country :  Jordan

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  8, 18, February, 2018

Abstract :

Routing Protocol for Low Power and Lossy Networks (RPL) is one of the most utilized routing protocols. It designed to adapt with thousands of nodes in energy-constrained networks. It is a proactive distance vector protocol which has two major components objective function and trickle algorithm. Our work focus on the trickle timer algorithm, it is used to control, maintain and follow the control messages over the network. Short listen problem is the main blot in trickle algorithm. Several studies focused on enlarging the listen period. However, as it was suffering from node starvation when the period is short, it suffers from time and energy wasting when the period is enlarged. Notice that the time and power consumption are sensitive factors in Low Power and Lossy Networks. In this paper, we propose a randomized dynamic trickle algorithm, it contributes in the improvement of trickle and solving the above-mentioned problems by controlling the t variable in a dynamic randomly way, where t is the border line between listening and transmitting period. The performance of the proposed algorithm is validated through extensive simulation experiments under different scenarios and operation conditions using Cooja 2.7 simulator. Simulation results compared with the standard trickle timer algorithm based on convergence time, packet delivery ratio (PDR) and power consumption performance metrics. The results of the simulations denote a high improvement in term of convergence time, power consumption and packet delivery ratio

Keyword :  Routing Protocol for Low Power and Lossy Networks(RPL), Internet of Things (IoT), Trickle Timer Algorithm.

For More Details :  https://airccj.org/CSCP/vol8/csit89814.pdf

A PREFERMENT PLATFORM FOR IMPLEMENTING SECURITY MECHANISM FOR AUTOMOTIVE CAN BUS

 Author :  Mabrouka Gmiden

Affiliation :  Computer and Embedded System Lab (CES)

Country :  Tunisia

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  8, 18, February, 2018

Abstract :

The design of cryptographic mechanisms in automotive systems has been a major focus over the last ten years as the increase of cyber attacks against in-vehicle networks. The integration of these protocols into CAN bus networks is an efficient solution for leaving security level, but features of CAN bus make the performance requirements within cryptographic schemes very challenging. In the literature most of academic researches focused on designing security mechanisms for the CAN bus. Yet, very few research proposals are interested in analyzing performances requirements by using cryptographic protocols. In this paper, we investigate effects of implementing cryptographic approaches on performance by proposing an analysis methodology for implementing cryptographic approach in CAN bus communication and measuring real-time performances. Next, we propose our system which presents a tool for determining the impact of implementing of cryptographic solutions. On the other hand we have proposed an intrusion detection system using the same platform. Our tool allows the implementation of any security strategy as well as the real-time performance analysis of CAN network.

Keyword :  CAN bus, In-vehicle Network, Security, Analysing

For More Details :  https://airccj.org/CSCP/vol8/csit89813.pdf

Call for Papers - 4th International Conference on Artificial Intelligence, Soft Computing And Applications (AISCA 2020)

 4^th International Conference on Artificial Intelligence, Soft Computing And Applications (AISCA 2020)

https://aisca2020.org/index.html

November 28~29, 2020, Dubai, UAE

Important Dates

Submission Deadline : November 08, 2020

Authors Notification : November 15, 2020

Registration & Camera-Ready Paper Due : November 18, 2020

Contact Us :  aisca@aisca2020.org

More Details : https://allconferencecfpalerts.com/cfp/view.php?eno=22487

NEAR-DROWNING EARLY PREDICTION TECHNIQUE USING NOVEL EQUATIONS (NEPTUNE) FOR SWIMMING POOLS

 Author :  B David Prakash

Affiliation :  IAG Firemark

Country :  Singapore

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  8, 18, February, 2018

Abstract :

Safety is a critical aspect in all swimming pools. This paper describes a near-drowning early prediction technique using novel equations (NEPTUNE). NEPTUNE uses equations or rules that would be able to detect near-drowning using at least 1 but not more than 5 seconds of video sequence with no false positives. The backbone of NEPTUNE encompasses a mix of statistical image processing to merge images for a video sequence followed by K-means clustering to extract segments in the merged image and finally a revisit to statistical image processing to derive variables for every segment. These variables would be used by the equations to identify near-drowning. NEPTUNE has the potential to be integrated into a swimming pool camera system that would send an alarm to the lifeguards for early response so that the likelihood of recovery is high.

Keyword :  Near-drowning Detection, Drowning Detection, Statistical Image Processing, K-means Clustering, Swimming Pools

For More Details :  https://airccj.org/CSCP/vol8/csit89812.pdf

VIDEO SEQUENCING BASED FACIAL EXPRESSION DETECTION WITH 3D LOCAL BINARY PATTERN VARIANTS

 Author :  Kennedy Chengeta

Affiliation :  University of KwaZulu Natal

Country :  South Africa

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  8, 18, February, 2018

Abstract :

Facial expression recognition in the field of computer vision and texture synthesis is in two forms namely static image analysis and dynamic video textures. The former involves 2D image texture synthesis and the latter dynamic textures where video sequences are extended into the temporal domain taking into account motion. The spatial domain texture involves image textures comparable to the actual texture and the dynamic texture synthesis involves videos which are given dynamic textures extended in a spatial or temporal domain. Facial actions cause local appearance changes over time, and thus dynamic texture descriptors should inherently be more suitable for facial action detection than their static variants. A video sequence is defined as a spatial temporal collection of texture in the temporal domain where dynamic features are extracted. The paper uses LBP-TOP which is a Local Binary Pattern variant to extract facial expression features from a sequence of video datasets. Gabor Filters are also applied to the feature extraction method. Volume Local Binary Patterns are then used to combine the texture, motion and appearance. A tracker was used to locate the facial image as a point in the deformation space. VLBP and LBP-TOP clearly outperformed the earlier approaches due to inclusion of local processing, robustness to monotonic gray-scale changes, and simple computation. The study used Facial Expressions and Emotions Database(FEED) and CK+ databases. The study for the LBP -TOP and LGBP-TOP achieved bettered percentage recognition rate compared to the static image local binary pattern with a set of 333 sequences from the Cohn–Kanade database.

Keyword :  Local binary patterns on Three Orthogonal Planes (LBPTOP) · Volume Local Binary Patterns(VLBP)

For More Details :  https://airccj.org/CSCP/vol8/csit89811.pdf

A MACHINE LEARNING APPROACH TO DETECT AND CLASSIFY 3D TWO-PHOTON POLYMERIZATION MICROSTRUCTURES USING OPTICAL MICROSCOPY IMAGES

 Author :  Israel Goytom

Affiliation :  Ningbo University

Country :  China

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  8, 18, February, 2018

Abstract :

For 3D microstructures fabricated by two-photon polymerization, a practical approach of machine learning for detection and classification in their optical microscopic images is state and demonstrated in this paper. It is based on Faster R-CNN, Multi-label classification (MLC) and Residual learning framework Algorithms for reliable, automated detection and accurate labeling of Two Photo Polymerization (TPP) microstructures. From finding and detecting the microstructures from a different location in the microscope slide, matching different shapes of the microstructures classify them among their categories is fully automated. The results are compared with manual examination and SEM images of the microstructures for the accuracy test. Some modifications of ordinary optical Microscope so as to make it automated and by applying Deep learning and Image processing algorithms we can successfully detect, label and classify 3D microstructures, designing the neural network model for each phase and by training them using the datasets we have made, the dataset is a set of different images from different angles and their annotation we can achieve high accuracy. The accurate microstructure detection technique in the combination of image processing and computer vision help to simulate the values of each pixel and classify the Microstructures.

Keyword :  Multi-label classification, Faster R-CNN Two-Photon Polymerization, computer vision, 3D Microstructures

For More Details :  https://airccj.org/CSCP/vol8/csit89810.pdf

AN ELASTIC-HYBRID HONEYNET FOR CLOUD ENVIRONMENT

 Author :  Nguyen Khac Bao

Affiliation :  Soongsil University

Country :  Korea

Category :  Computer Science & Information Technology

Volume, Issue, Month, Year :  8, 18, February, 2018

Abstract :

When low-interaction honey net systems are not powerful enough and high-interaction honey net systems require a lot of resources, hybrid solutions offer the benefit’s of both worlds. Affected by this trend, more and more hybrid honey net systems have been proposed to obtain wide coverage of attack traffic and high behavioral ideality in recent years. However, these system themselves contain some limitations such as the high latency, the lack of prevention method for compromised honey pots, the waste of resources and the finger printing problem of honey pot that hinder them to achieve their goals. To address these limitations, we propose a new honey net architecture called Efficient Elastic Hybrid Honey net. Utilizing the advantages of combining SDN and NFV technologies, this system can reduce the response time for attack traffic, isolate compromised honey pots effectively, defeat the finger printing problem of honey pots, and optimize the resources for maintenance and deployment. Testing our system with real attack traffic, the results have showed that Efficient Elastic-Hybrid Honey net system is not only practical, but also very efficient.

Keyword :  Honey net, Honey pot, Elastic, Hybrid, Software defined Networking, Network Function Virtualization

For More Details :  https://airccj.org/CSCP/vol8/csit89809.pdf