REMOTE SENSING IMAGE CLASSIFICATION USING FUZZY RULE CLASSIFIER

¹M.Saranya, ²S. Kalaiselvi, ³Dr.K.G. Srinivasagan
¹ PG-Scholar, Department of CSE-PG, National Engineering College Kovilpatti,Tamilnadu,India.
² Assistant Professor, Department of CSE-PG National Engineering College Kovilpatti,Tamilnadu,India.
³ Professor and Head , Dept of CSE-PG, National Engineering college,Kovilpatti,Tamilnadu,India.

     Land cover of the earth’s land surface has been changing since time immemorial and is likely to continue to change in the future. These changes are occurring at a range of spatial scales from local to global and at temporal frequencies of days to millennia. Both natural and anthropogenic forces are responsible for the change. Natural forces such as continental drift, glaciations, flooding, tsunamis and anthropogenic forces such as conversion of forest to agriculture, urban sprawl, and forest plantations have changed the dynamics of land-use/land-cover types throughout the world. The main intention of the classification is to group the pixels in the image into form the several land cover classes, or “themes”. And then the categorized data is used to produce the thematic map of land cover classes. Image classification is one of the most important parts in image processing. Image segmentation is the process of dividing the images into regions with similar attributes. The proposed research consists of three phases. First phase, the image segmentation is done by Self Organizing Map (SOM). Second phase, feature extraction is done by Gray Level Coocurrence Matrix methods. Finally the classification is done by fuzzy rule based classification. The final output is land use and land cover map, with labels of corresponding classes.

View full abstract...

QUANTIFYING ANONYMITY TRADE-OFF USING NASH EQUILIBRIUM APPROACH

J. Darwin¹, R. Anantha Kumar^2
1 PG scholar, Department of CSE, Kalasalingam Institute of Technology, Krishnankoil, Tamilnadu, India.
² Assistant Professor, Department of CSE, Kalasalingam Institute of Technology, Krishnankoil, Tamilnadu, India.

     In this paper proposed the Quantifying anonymity using conditional entropy of the routes given the adversary’s observation, the problem of optimizing anonymity is posed as a two-player zero-sum game between the network designer and the adversary. Game theory applied to study the optimal performance tradeoffs and equilibrium strategies. Using independent schedule however, requires dummy transmissions by the relays. The results are applied to study the relationships between anonymity, the fraction of monitored relays and the fraction of hidden relays in large networks.

View full abstract...

A STUDY ON THE REDUCTION OF NON VALUE ADDED ACTIVITY OF FEEDERS IN A SEMI AUTOMATION INDUSTRY

M.M.Devarajan ¹, Dr.R.Muruganandham ^2
1Assistant Professor, Department of MECH, Vickram College of Engineering, Madurai, Tamilnadu, India.
² Assistant Professor, Department of MECH, Thiagarajar College of Engineering, Madurai, Tamilnadu, India.

     This article deals with the research carried out at a SEMI AUTOMATION INDUSTRY where most of their work process was done manually by their feeders. Feeders carry out manual loading and unloading of parts in the industry. Due to lack of plan order and feeder’s improper work, missing parts, rework, the production line stops. This line stoppage leads to less material handling which causes less production than the fixed level of production. By evolving the data, feeders contribute 60% in the value added activity. Hence to reduce the remaining non value added activity of the feeders, the major non value added activity is identified by analysing the data obtained during time study. Critical path method is used to create the exact or absolute path for the process of material handling. ARENA is implemented to study the newly created process is acceptable or not. This study involves in identifying the non value added activity and reducing the critical activity by changing the material handling process using arena to improve the production rate.

View full abstract...

A MODIFIED UNIDIRECTIONAL 3-PHASE MULTILEVEL HYBRID PWM RECTIFIER FOR POWER CONVERSION

A.J.Bhuvaneshwari¹, K.Saravanan^2
1PG Scholar, Department of ECE, Raja College of Engineering & Technology,Madurai, India,
²Assistant Professor,Department of EIE, Sethu Institute of Technology, Virdhunagar,India,

     A Pulse width modulation (PWM) rectifier consists of three switching legs and remains one of the popular Power Factor Control rectifiers. This paper proposes a new circuit topology for a unidirectional multilevel PWM rectifier for AC-DC conversion. A PWM rectifier can reduce the harmonic current dramatically because, the grid current is able to control. The proposed method forms a new circuit which is the combination a diode clamp-type topology and a flying capacitor-type topology. In this topology, the number of switches and clamping capacitor and diodes are reduced. Further, the proposed scheme can obtain good performance, as same as a conventional multilevel circuit. This paper describes about the features of the proposed topology; the Space vector modulation control strategy. The proposed converter achieved a total harmonic distortion of 9.6% for the input current and efficiency of 84.4% are simulated with Mat lab / Simulink model.

View full abstract...

CLASSIFICATION OF EEG SIGNALS FOR LIMB MOVEMENTS AND IMAGINARY TASKS USING SOFT COMPUTING TECHNIQUES

R.Kottaimalai ¹, J.Goldwyn Sudhakar ², T.ElizabethRani^3
1 Assistant Professor. Dept of ECE ,Sree Sowdambika College of Engineering, Aruppukottai, India
² Assistant. Professor. Dept of EIE, Sree Sowdambika College of Engineering, Aruppukottai, India.
³ Asstistant Professor. Dept of EIE, Sree Sowdambika College of Engineering, Aruppukottai, India.

     The people who have lost movement or language function due to traffic accidents or neuromuscular disease, necessitating large numbers of care assistants to support severely disable patients who have almost no voluntary control of body movements. Brain-Computer interface (BCI) is a direct communication pathway between a human brain and an external device. Such systems permit people to communicate through direct measurements of brain activity, without requiring any movement. The task of the BCI is to identify and predict behaviorally induced changes or cognitive states in a user‘s brain signals. Brain signals are recorded from electrodes placed on the scalp. In this report the Soft Computing technique like ANFIS was applied on the EEG signals which are taken during six limb movement tasks and also during six imaginary tasks, and the data are taken for classification. From the test results it is observed that the probability of correct classification has been increased for the limb movements by using ANFIS and for feature extraction we use wavelet transform.

View full abstract...