Rukmini M.S.S.,Vignans University |
Bala Gayathri Devi D.,Vignans University
Proceedings - 2016 2nd International Conference on Cognitive Computing and Information Processing, CCIP 2016 | Year: 2016
This paper describes regarding device of domestic appliances depends on humanoid application supported raspberry pi. In initial stage Home automation has been recalled associated an application has been developed within the and stage that is focused on the humanoid method. Mobile devices area unit glorious in providing a programme in an an exceedingly home automation approach. And will be ready to communicate with a home automation network via associate internet however ineffectual to instantly be to bear with devices within the network, as these devices in all probability place into impact low power consumption protocols almost like ZigBee, Wi-Fi etc. During this paper focuosed on dominant home appliances through humanoid gismo utilizing Wi-Fi as communication protocol further more as raspberry pi as server system. Programme has created for the humanoid gismo that permits for the user to stay connected with the Raspberry pi. The Raspberry pi doubtless to be interfaced with a relay card that controls the house instrumentation going for walks in residence. The buyer communicates with the corresponding relay. © 2016 IEEE.
Devi Bodapati J.,Vignans University |
Veeranjaneyulu N.,Vignans University
2016 International Conference on Signal and Information Processing, IConSIP 2016 | Year: 2016
The problem of high dimensionality has been gaining increased focus in the recent literature on pattern recognition. This is due to the increase in the availability of the high volumes of data in various fields. Multiple sensors are being used to extract the data and each sensor gives multiple features. On the other side performance of a classifier depends on the type of features that are used to represent the data. But storing the high dimensional data is a challenge as they occupy more space and also demands more computational resources. In generative models like Gaussian Mixture Model(GMM) based classification there is a direct correlation between the number of features used to represent the data and the number of parameters that are to be estimated. This is where the dimensionality reduction would be helpful. This paper aims to demonstrate the performance of different classifiers in the reduced subspace. Based on the literature it has been observed that non-linear projection is helpful for classification than linear projection of the data. The major objective of this paper is to show the performance of different classifiers in the reduced space after linear and non-linear projection of the data. To reduce dimensionality PCA, KPCA and Auto encoder based techniques are used and to compare the performance in original and reduced space, Classification models like Gaussian Mixture Models (GMM), Artificial Neural Network (ANN) and Support vector machine (SVM) based classifiers are used. © 2016 IEEE.
Ramanjaneyulu B.S.,Vignans University |
Gopinathan E.,National Institute of Technology Calicut
Proceedings of 2016 International Conference on Advanced Communication Control and Computing Technologies, ICACCCT 2016 | Year: 2016
When wireless communication technologies are used in industrial networking, interference to these wireless devices is a major problem. This problem is more in ISM bands. Using licensed bands for industrial sensors and controllers by way of opportunistic spectrum access is being explored in the recent times. But searching by these wireless devices for the available vacant spectrum is a hectic task as many of these devices are very small and operate with limited computing powers. Hence in these kinds of environments it would be better if spectrum sensing task is carried out by more capable devices like access points and share it to all the surrounding tiny wireless devices. It will be more appropriate if the available vacant spectrum details can be obtained from a server like resource. It can alleviate the sensors from carrying out such hectic spectrum sensing activity. It is explored in this work to assess the interference levels in such environments and propose a solution to access licensed bands in opportunistic manner. © 2016 IEEE.
Bodapati J.D.,Vignans University |
Veeranjaneyulu N.,Vignans University
Advances in Intelligent Systems and Computing | Year: 2017
Outlier detection also popularly known as anomaly detection is the process of recognizing whether the given data is normal or abnormal. Some of the applications of this outlier detection are: network intrusion detection, fraud detection, database cleaning, etc.; In most situations, there is scarcity of abnormal data where as plenty of normal data is available. This is the biggest challenge of novelty detection. The characteristics of abnormal or outlier data are often unknown beforehand. Density estimation methods can be used for novelty detection tasks. These methods work only when the assumed data distribution is same as the underlying data distribution which may not be known in advance. C-SVDD and ν-SVDD are used for novelty detection tasks in our experiments. Experiments are performed on a toy data set of bivariate and overlapping classes and real-time multivariate data. Different kernels are also used for experimental studies. All experiments shows that RBF (Gaussian) kernel gives better performance than the other types of kernels. Experimental results on both artificial and real-world data are reported to illustrate the promising performance of outlier data detection. © Springer Nature Singapore Pte Ltd. 2017.
Annapurna K.,Vignans University |
Ramanjaneyulu B.S.,Vignans University
2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings | Year: 2016
Accurate sensing of the spectrum is one of the prime requirements for efficient functioning of cognitive Radio systems. But accurate sensing is a complex process, as signals of different modulations, coding methods and power levels along with fading and noise are present in the given radio environment. Collaborative sensing techniques can help to improve the sensing accuracy. One such collaborative sensing mechanism is proposed in this work where several cognitive radios having GPS capability contribute to the database of 'spectrum occupancy', corresponding to the sensing information at various Geographic locations. The secondary users that want to avail the spectrum obtain this information from the server and analyze the environment by combining this information with the locally sensed information. This method can help to implement efficient spectrum assignment strategies to cognitive radios. A scenario where such information from the database is used to optimize the bandwidth utilization at a given geographical location, is explored in this work. The simulation results of the system show that the proposed mechanism can help to improve the throughput of secondary network. © 2016 IEEE.
Srivastava A.,Indian Institute of Technology Kharagpur |
Adamala S.,Vignans University
Indian Journal of Ecology | Year: 2016
The objective of this study was to analyse the physio-chemical and nutritional quality of a tray dried tomato powder with three chemical treatments namely potassium meta-bisulphite (KMS), calcium chloride (CaCI2) and combination of these two at different concentrations. The results indicated that the moisture content of tomato slices decreased rapidly with the increase in drying time from 1 hr to 10 hr using different concentrations of KMS, CaCI2 and KMS+CaCI2. At 11 hr, the moisture content attained a steady state for all the samples. Further, the quality of processed tomato powder with different KMS, CaCI2 and KMS+CaCI2 concentrations was tested in terms of lycopene (mg/100 gm), ash content (%), dehydration ratio, rehydration ratio, pH, % recovery, and vitamin C along with the raw controlled sample. It is concluded that overall quality of tomato powder was good in combination of KMS+CaCI2 as compared to KMS and CaCI2. Similarly, 0.2g KMS+1.0g CaCl2/100g concentration gave better quality than the 0.1 g KMS+0.5g CaCI2/100g and 0.3g KMS+1.5g CaCI2/100g.
Rao P.M.V.,Vignans University |
Subba Rao V.V.,Jawaharlal Nehru Technological University Kakinada
Journal of Composite Materials | Year: 2011
An analytical formulation is developed to estimate the strength of the fiber metal laminates (FML) consisting of cross-ply glass fiber reinforced plastic layers and aluminum sheets. Classical lamination theory is taken as basis for the formulation. A new degradation model based on Tsai-Hill terms is developed and used with analytical formulation to assess the progressive failure. Appropriate features are incorporated in the model to distinguish the matrix failure, the fiber matrix debonding, the fiber failure, and the failure of the isotropic layer. The formulation is used to predict the failure behavior of a FML under in-plane off-axis loading. Different strengths associated with the failure of the laminate like stress at first ply failure and yielding of isotropic layer are investigated. The results show that the new degradation model facilitated the detailed estimation of failure progression. These values of predicted strength are more accurate and closer to the actual experimental results than that of the values predicted by any other model. © 2010 The Author(s).
Murthy P.B.G.S.N.,Vignans University
Journal of Intelligent Manufacturing | Year: 2016
In this paper, statistical models were developed to investigate effect of cutting parameters on surface roughness and root mean square of work piece vibration in boring of stainless steel. A mixed level design of experiments was prepared with process variables of nose radius, cutting speed and feed rate. According to design of experiments, eighteen experiments were conducted on AISI 316 stainless steel with PVD coated carbide tools. Surface roughness, tool wear and vibration of work piece were measured in each experiment. A laser Doppler vibrometer was used to measure vibration of work piece in the form of acousto optic emission signals. These signals were processed and transformed in to different frequency zones using a fast Fourier transformer. Analysis of variance was used to identify significant cutting parameters on surface roughness and root mean square of work piece vibration. Predictive models like response surface methodology, artificial neural network and support vector machine were used to predict the surface roughness and root mean square of work piece vibration. Cutting parameters were optimized for minimum surface roughness and root mean square of work piece vibration using a multi response optimization technique. © 2016 Springer Science+Business Media New York
Satyanarayana D.,Vignans University |
Pramiladevi M.,Andhra University
International Journal of Industrial and Systems Engineering | Year: 2016
The multi-criteria flow shop scheduling problem with sequence dependent setup times (SDST) is one of the most difficult class of scheduling problems. Efficient supervision of heuristics with SDST is one of the significant features to enhance the performance of manufacturing system. In this work, we have formulated multi-criteria decision-making flow shop scheduling problem. It consists of weighted sum of total weighted squared tardiness, makespan, total weighted squared earliness and number of tardy jobs. It is a very effective decision-making for scheduling jobs in modern manufacturing environment. In the present work, three efficient special heuristics based hybrid genetic algorithms (i.e., SHGA1, SHGA2, and SHGA3) are proposed for multi-criteria SDST. Experiments are conducted on the benchmark problems (Taillard, 1993). The performance of three SHGAs are tested, analysed and compared with the help of a defined performance index, known as relative percentage deviation (RPD). The maximum size of the problem is limited to 100 jobs and ten machines. From the results and analysis, the performance of SHGA3 found to be the best. Copyright © 2016 Inderscience Enterprises Ltd.
Musala S.,Vignans University
International Journal of Applied Engineering Research | Year: 2014
Now a days Manchester encoding format is widely used in Ethernet, RFID and Near Field Communications. In this paper, six Manchester encoders are proposed using pass transistor logic and current sink and current source inverters. All the proposed circuits are simulated and compared with the existing circuits by Cadence 180 nm CMOS technology with the supply voltage range of 0.6 V to 1.8 V, from audio range of frequency to 5 GHz frequency. The simulation results show that the proposed Manchester encoders achieve a high performance and better driving capability with less number of transistors when compared to the existing circuits. © Research India Publications.