C. R. Srinivasan ¹, R. Senthilnathan ², P. Subhasree ³, R. Sivaramakrishnan ³, R. Srividya ¹, P. Karthikeyan ³

Affiliations
1 Faculty of Manipal Institute of Technology, Manipal University, Manipal - 576104, Karnataka, IN
2 Department of Mechatronics Engineering, SRM University, Kattankulathur - 603203, Tamil Nadu, IN
3 Division of Mechatronics, Department of Production Technology, MIT Campus, Anna University, Chennai-600025, Tamil Nadu, IN

Abstract

Objectives: Trajectory planning is the most vital procedure in every continuous path control based application of robotic arm type manipulators. This paper presents the methodology adopted for planning a trajectory required to be followed by the eye-in-hand camera mounted near the end-effector of a six axis manipulator. The basic purpose is to acquire a sequence of images by translating the camera along the optical axis of the camera which is meant to be used by an algorithm inspired by Shape from Focus (SFF). Methods/Statistical Analysis: The movement of the camera (the end effector) is controlled in the task space of the robot a Cartesian space approach is presented where-in the inverse kinematics computations needs to be performed at run time. All the trajectory planning and simulation of the robot’s movements are demonstrated in the simulation where the cues for camera motion are obtained from the SFF-inspired algorithm. Since the SFF-inspired algorithm requires a linear trajectory to be followed by the camera and manipulator is an all-revolute joint based one, careful understanding of the workspace of the robot for singularities is of prime importance. The ability of the manipulator to orient in three axes at the various reachable positions of the workspace is estimated by a manipulability measure. The linear trajectory to be followed by the end-effector is planned in the region of the workspace which has the highest manipulability. Findings: The paper describes the various steps involved in the process of understanding the manipulability of the workspace and planning of the trajectory in accordance with the manipulability index. The details of the trajectory planning to meet the requirements are clearly illustrated. Application/Improvements: Though the intended purpose of planning the trajectory is specific to a computer vision task, the methodology demonstrated is applicable for any application involving linear trajectories. The scope for future work in continuation of the current work is in the direction of dynamics affected trajectory planning.

Keywords

Linear Trajectory, Manipulability, SFF, Trajectory Planning.

Full Text

   

J. Amudhavel ¹, V. Brindha ¹, B. Anantharaj ², P. Karthikeyan ¹, B. Bhuvaneswari ³, M. Vasanthi ¹, D. Nivetha ¹, D. Vinodha ⁴

Affiliations
1 Department of CSE, SMVEC, Pondicherry - 605107, Tamil Nadu, IN
2 Department of CSE, TCET, Vandavasi - 627425, Tamil Nadu, IN
3 Department of CSE, Pondicherry University, Pondicherry - 605014, Tamil Nadu, IN
4 Department of CSE, SMVEC, Pondicherry - 605107, Tamil Nadu

Abstract

Background/Objectives: To analyze and monitoring the activity of nodes using an IDS Intrusion Detection System which provide security to the system. Findings: In this research, a network building was made with simple node formation with a fitting technique. So that it is easy for a user or beginner to understand the asymptotic dominion factors, due to the wide growth of nodes on network. Intrusion detection system is made of several nodes. These nodes are grouped and combined as a network. Since each node in a network has unique characteristics they may have high chance of attack from malware during the communication between systems. Applications/Improvements: Network of topology is done by creating and connecting various sub networks. Sub networks traffic is cleared and monitored with the package of IDS. It works on synchronous message transfer mode which provides acknowledgement to sender and receiver. All sub networks is managed by its corresponding system and further provide update to the master node on the network. Due to this broadcast of messages all other nodes may be in safe state of avoidance from attacker.

Keywords

Ad-Hoc Network, Conversation Exchange Dynamics, Intrusion Detection System, Intrusion Prevention System, Network Security

Full Text

   

S. P. Sundar Singh Sivam ¹, V. G. Uma Sekar ¹, K. Saravanan ², S. RajendraKumar ¹, P. Karthikeyan ¹, K. Sathiya Moorthy ¹

Affiliations
1 Department of Mechanical Engineering, SRM University, Kattankulathur, Chennai - 603203, Tamil Nadu, IN
2 Department of Mechatronics Engineering, SRM University, Kattankulathur, Chennai - 603203, Tamil Nadu, IN

Abstract

Objectives: To study the yield behavior and plastic flow of an anisotropic sheet metal during forming operations, various mathematical formulations of the plastic state of the sheet metals have been proposed, known as yield functions. Different yield functions pertain to different criteria and have different characteristics. Methods/Statistical Analysis: There are several yield criteria proposed for the study of yield behaviors of sheet metals. This paper aims at reviewing the most frequently and commonly employed for the purpose yield criteria i.e. Hill 1948, Barlat 1989, Hill 1990 and BBC 2000. The study is focused on discussing the form of each criterion, their implementation details and comparing their predictive accuracies. Findings: The methods followed to obtain the yield surface diagram have been reviewed and discussed. Application/Improvement: Inference has been drawn based upon the agreement between theoretical and experimental value for a particular case.

Keywords

Accuracy Index, Anisotropic Coefficients, Yield Criteria.

Full Text

   

A. Sheik Abdullah ¹, S. Selvakumar ², P. Karthikeyan ¹, M. Venkatesh ³

Affiliations
1 Department of Information Technology, Thiagarajar College of Engineering, Madurai – 625015, Tamil Nadu, IN
2 Department of Computer Science and Engineering, G.K.M. College of Engineering and Technology, Chennai – 600063, Tamil Nadu, IN
3 Department of Medicine, Theni Government Medical College and Hospital, Theni – 625531, Tamil Nadu, IN

Abstract

The objective of this research work focus towards the identification of best variant between decision tree algorithm such as Weighted Decision Trees (WDT), C4.5 Decision Trees and C5.0. Methods: Decision tree has a number of variants such as ID3, Weight based decision tree, C4.5 and C5.0 algorithms. This research work focus towards the predictive performance analysis of weight based decision tree with information gain as the splitting criterion. The algorithm proceeds iteratively with the assignment of weights over the training instances to determine the best among the data attributes. Thereby, the attribute with best weight values can be significantly determined by an improvement over its accuracy. Results: The experimental results proves that among the variants of decision trees the algorithm corresponding to C4.5 provides the highest accuracy of about 71.42% and R2 value of about 0.265 respectively and for real world data the accuracy is about 48.69%. The effectiveness of the decision tree algorithm can be still improved by adopting certain feature selection techniques with the combination of decision tree algorithm. Conclusion: The determined results show that Decision tree algorithm suits well for medical data problems. The efficiency of the algorithm can still be improved by applying Decision Trees for various real world data problems such as Diabetes, Cancer classification with feature selection paradigms. But still a larger set of real world data has to be investigated.

Keywords

C4.5 Decision Tree Algorithm, Data Classification, Heart Disease, Predictive Analysis, Weighted Decision Tree,

Full Text