Browse Items (11810 total)
Sort by:
-
Feature Based Fuzzy Framework for Sentimental Analysis of Web Data
Social mass media has emerged as a projectile platform for the evolution of web data. The sentimental Analysis where the huge textual online reviews are analyzed to extract the actual sentiment or emotions hidden in the reviews. In this paper an effective approach for sentimental analysis of web data is proposed which deploys the fuzzy based machine learning algorithm to accomplish fine-level sentiment analysis of huge online opinions by assimilating the fuzzy linguistic hedges influence on opinion descriptors. The seven layered categories are designed that uses SentiWordNet which has three stages: Pre-processing phase, Feature Selection Phase and Fuzzy based Sentiment Analysis phase. Various machine learning algorithms like AdaBoost, (IBK) K-Nearest Neighbour, (NB) Nae Bayes and (SVM)/SMO Support Vector Machine are used for classification. Jsoup is implemented for gathering web opinions which are subjected to initial processing task later applied with stemming and tagging. This fuzzy based methodology is investigated for Mobile, Laptops dataset, also compared with state-of-the-art approaches which demonstrate upper indication of 94.37% accurateness through Kappa indicators showcasing lesser error rates. The investigational outcomes are tested on training data using Ten-Fold cross validation which concludes that this approach can be efficaciously used in Sentimental analysis as an aid for online decision. 2019 IEEE. -
Waveform Analysis and Feature Extraction from Speech Data of Dysarthric Persons
Speech recognition systems provide a natural way of interacting with computers and serve as an alternative to the more popular but less intuitive peripherals (input / output devices). Tools employing the techniques of Automatic Speech Recognition (ASR) can be extended to serve people with speech disabilities so that they can overcome the difficulties faced in their interaction with general public. An attempt is made here to achieve this goal by mapping the distorted speech signals of people with severe levels of dysarthria to that of a normal speech and/or less severe dysarthric speech. The analysis is carried out by comparing the speech waveforms of the people with and without communication disorders and then extracting the features from the audio files. The differences in time, duration, frequency and PSD are used to facilitate the mapping of unintelligible speech data to intelligible ones. When reasonable accuracy levels are achieved in this mapping, the normal voice can be used as the substitute / surrogate of the original distorted voice. 2019 IEEE. -
A Survey on 5G Standards, Specifications and Massive MIMO Testbed Including Transceiver Design Models Using QAM Modulation Schemes
Massive MIMO (Multiple Input Multiple Output)is the advanced technology in 5G architecture which improves mobile and data wireless system parameters in multiple folds. The basic idea of this technology is to include huge number of antennas in the base stations serving limited user equipment. This will enhance the parameters like spectral efficiency, data rate, wireless devices connectivity, energy or power efficiency and also, significant reduction in interference and error rates. The Third Generation Partnership Project (3GPP)consortium, International Mobile Telecommunication (IMT)and various partner telecom companies are on the way to develop unified architecture to meet the proposed 5G standards by the year 2020. Initial test beds and field-trials are already in process at various universities and telecom companies considering Long Term Evolution (LTE)releases features in the 5G architecture framework. However, the research is still an open issue on improving the parameters. This research paper provides a detailed overview on 5G standards, specifications and Field trials and test beds implemented by various universities and telecom industry utilizing Massive MIMO technology. This literature survey paper aims to enlighten the researchers working in the area of Massive MIMO to understand the test bed and field trials designs existing till date. This paper also motivates to complete experiments on Bit error rate (BER)estimation in various modulation schemes for single transmitter-receiver as well as in MIMO configuration. The reduction in BER is observed when MIMO models are used for transceiver design. The hardware utilization and simulation work of the field trials and testbed provide different existing techniques to develop a transceiver system which meets 5G standard. 2019 IEEE. -
Wide band cascade RF amplifier for 0.01GHz to 6 GHz application
This paper presents a design of wide band cascade RF amplifier for 0.01 GHz to 6 GHz application using Hybrid Microwave Integrated (MIC) Technology. Wideband amplifier provides ultra-flat gain response of 1 dB for 4 GHz bandwidth and 3 dB for 6 GHz bandwidth. A coplanar wave guide (CPWG) is fabricated using printed circuit board technology and used for RF transmission line topology to convey microwave frequency signals. The output power at 1 dB compression is 17 dBm while the high gain is 22 dBm. The return loss shows below minimum -10 dB for all frequency and amplifier have good linearity and stability. The proposed amplifier can be used for L, S, and C band applications. 2019 IEEE -
Water Demand Prediction Using Support Vector Machine Regression
Water is a critical resource for sustainable economic and social development of a country. To maintain health hygiene, energy agricultural products, and the environment management water plays a key role. Water demand prediction is essential to analyze the requirement that indicate emergency state for water management decisions. This paper explores the water usage data for dairy plants to understand the spatial and temporal patterns for future water requirements, to optimize the water demand estimation. It uses concept of Machine learning algorithms to compare and achieve an effective and reliable system for water prediction. 2019 IEEE. -
Extractive Text Summarization Using Sentence Ranking
Automatic Text summarization is the technique to identify the most useful and necessary information in a text. It has two approaches 1)Abstractive text summarization and 2)Extractive text summarization. An extractive text summarization means an important information or sentence are extracted from the given text file or original document. In this paper, a novel statistical method to perform an extractive text summarization on single document is demonstrated. The method extraction of sentences, which gives the idea of the input text in a short form, is presented. Sentences are ranked by assigning weights and they are ranked based on their weights. Highly ranked sentences are extracted from the input document so it extracts important sentences which directs to a high-quality summary of the input document and store summary as audio. 2019 IEEE. -
Optimizing the efficiency of solar flat plate collector with trapezoidal reflector
Solar flat plate collectors are the most vital parts of a solar heating system. The collector plate absorbs the energy from the sun and transforms this radiation into heat and then transmit this heat into a fluid, it can either water or air. This research paper proposes a new technology to enhance the performance of the solar flat plate collector. A trapezoidal solar reflector is connected with the flat plate collector to enhance the amount of sunlight which hits the collector plate surface. The trapezoidal reflector concentrates both the direct and diffused radiation of the sun towards the flat plate collector. To maximize the concentration of incident radiation the trapezoidal reflector was permitted to change its inclination with the direction of sunlight. A prototype of a solar water heating system with trapezoidal reflector was constructed and achieved the improvement of collector plate efficiency by around 12%-13%. Thus the current solar heating system has the best thermal performance compared to the existing systems. 2019 Author(s). -
Analysis of Human Physiological Parameters Using Real-Time HRV Estimation from Acquired ECG Signals
The overall healthiness of the heart can be computed from Electrocardiogram. The healthiness of the heart depends on several lifestyle parameters, like as- stress, sleeping pattern, smoking habit etc. In this paper, an algorithm to determine Heart Rate Variability from the acquired ECG signal on a real-time basis is presented. Impacts of above-stated lifestyle parameters on cardiac health using Heart Rate Variability analysis are also computed. ECG signal gets contaminated with different sources of noises while acquisition. Multi-rate FIR Impulse Filter is used for de-noising of the acquired signal. Heart Rate Variability analysis and real-time plotting are done on de-noised output for accurate feature extraction. A simple robust hardware realizable algorithm was developed for analyzing obtained HRV to state different health conditions of the heart. 2019 IEEE. -
Despeckling of Ultra sound Images using spatial filters - A Fusion Approach
Ultra sound images are normally affected by speckle noise which is typically multiplicative in nature. This study proposes different fusion based despeckling methods for ultra sound images. The output of existing spatial domain despeckling methods viz. Lee filter, Bayesian Non Local Means (BNLM) filter and Frost filter are fused pairwise. Fusion is implemented in two steps, first an inter-scale stationary wavelet coefficient fusion followed by an intra-scale wavelet coefficient fusion. Analysis of these projected despeckling strategies are conducted using metrics like Peak Signal to Noise Ratio (PSNR), Equivalent Number of Looks (ENL), Structural Similarity Index (SSIM) and Universal Image Quality Index (UIQI). The results show that the performance of fusion based methods is better than the respective individual filters for despeckling ultra sound images. 2019 IEEE. -
Improved File Security System Using Multiple Image Steganography
Steganography is the process of hiding a secret message within an ordinary message extracting it at its destination. Image steganography is one of the most common and secure forms of steganography available today. Traditional steganography techniques use a single cover image to embed the secret data which has few security shortcomings. Therefore, batch steganography has been adopted which stores data on multiple images. In this paper, a novel approach is proposed for slicing the secret data and storing it on multiple cover images. In addition, retrieval of this secret data from the cover images on the destination side has also been discussed. The data slicing ensures secure transmission of the vital data making it merely impossible for the intruder to decrypt the data without the encrypting details. 2019 IEEE. -
Characterization of interval-valued fuzzy bridges and cutnodes
In this paper, we characterize interval - valued fuzzy bridges and interval-valued fuzzy cutnodes in terms of ? strong arcs. We discuss about the behaviour of arcs in a strongest path of an interval - valued fuzzy graph. An example is provided to prove that strongest paths are not in general related to strong paths in an interval - valued fuzzy graph. Finally we give a particular condition under which strong paths and strongest paths are equivalent. 2019 Author(s). -
A Study on Machine Learning Techniques for Internet of Things in Societal Applications
Until recent years, monitoring and analysing system inputs, responses were merely based on Sensor Systems. Gradually, Embedded Systems and other Data Resources including Remote Monitoring Units started gaining momentum. But, with advent of Internet of Things (IoT), the outlook and expectations are broadened. IoT introduced incredible volumes of structured and unstructured data of different formats. There is a need to investigate, the underlying concepts of Machine Learning, Internet of Things (IoT) and Embedded Systems. These domains grow and expand its frontiers at a very fast pace. This paper attempts to throw light on possibilities of combining different technological domains, for design and development of Smarter and Context Aware Intelligent Electronics Systems for Societal Utility. Effective implementation and realization of such systems by suitable fusion of essential inter-disciplinary concepts is expected to have considerable potential for societal impact in the years to come. 2019 IEEE. -
Experimental study of solar dryer used for drying chilly and ginger
Open air solar drying is one of the most popular methods for drying food products holds many drawbacks resulting in contamination of food products. This project is to transform the traditional method to an innovative, clean and cost-effective method to dry chilly and ginger, two being the top export commodity of India. Here a solar dryer is made which comprised of flat plate air heater, a chamber for drying and an air blower which induces forced convection. This system enhances the drying process even at low-intensity sunlight by assimilating heat storage materials. The equipment was tested in the meteorologicalcondition of the faculty of engineering, Christ (Deemed to be University) (latitude of 12.86N, a longitude of 77.43E) Bangalore, Karnataka. The process has reduced the moisture content from around 72.69% to 28.24% in the case of chilly and from 68.88% to 14.31% in the case of ginger within a period of 10 hours for a mass flow rate of 0.051kg/s. Average drier efficiency was estimated to be about 22%. The specific moisture extraction rate was estimated to be about 0.76 kg/kWh. This process resulted in a better moisture extraction rate, eliminating the defects caused by open sun drying. This process resulted in a better moisture extraction rate, eliminating the defects caused by open sun drying. 2019 Author(s). -
A Comparative Study of Spectral Indices for Surface Water Delineation Using Landsat 8 Images
Surface water delineation is an important step in performing change detection studies on water bodies with the help of multispectral images. Commonly used techniques for surface water delineation from multispectral images are single band density slicing, spectral index based, machine learning based classification and spectral unmixing based methods. This paper presents a comparative study of commonly used spectral indices Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), Modified Normalized Difference Water Index (MNDWI), Water Ratio Index (WRI), Normalized Difference Forest Index (NDFI), Enhanced water Index (EWI), Weighted Normalized Difference Water Index (WNDWI), Automated Water Extraction Index (AWEI), Tasseled Cap Water Index (TCW), Global Water Index (GWI)and Sum457 that were developed for water detection for their suitability and effectiveness when applied on Landsat 8 images. While all the above mentioned indices showed their usefulness in water detection, simpler and faster indices like GWI and Sum457 yielded comparable results to that of more complex ratios like EWI and WNDWI. 2019 IEEE. -
Securing Provenance Data with Secret Sharing Mechanism: Model Perspective
Elicitation about the genesis of an entity is referred to as provenance. With regards to data objects and their relationships the same is termed as data provenance. In majority of the instances, provenance data is sensitive and a small variation or adjustment leads to change in the entire chain of the data connected. This genesis needed to be secured and access is granted for authorized party. Individual control in preserving the privacy of data is common scenario and there are a good number of approaches with respect to cryptography. We propose a unique model, wherein the control of the data is available with multiple bodies however not with one; and when an access has to be granted for a genuine purpose, all the bodies holding their share will have to agree on a common platform. Combining these shares in a peculiar pattern allows the grant for accessing data. The method of allocating control to multiple bodies and allowing grant based on combining stakes is called as secret sharing mechanism. Division of the shares can be drawn from visual encryption approach. It provides transparencies for a given input message. This paper throws light on a framework associated to securing provenance via secret sharing security notion. 2019 IEEE. -
Fuzzy based Controller for Bi-Directional Power Flow Regulation for Integration of Electric Vehicles to PV based DC Micro-Grid
Utilization of Electric Vehicle as an auxiliary power source to a DC micro-grid for active power regulation is examined here. This paper focus on development of a Fuzzy based controller capable of regulating the bi-directional active power flow between a 10 kW DC Micro-grid and an Electric Vehicle. The system enables to balance the load on grid by performing peak shaving during peak hours and valley filling during off-peak hours. The load curve of Bangalore city for a typical day was taken as the reference and was used to implement the power flow control. The DC grid was designed for a 10 kW PV based micro-grid. The integrated DC micro-grid was simulated on MATLAB/Simulink platform and the obtained characteristics demonstrate that the power flow from grid to vehicle and vehicle to grid during the peak and off-peak periods respectively. The auxiliary battery pack was stressed only to 10.7 % of its 1C-rating leaving scopes for higher level power transmission possible between the systems. 2019 IEEE. -
A Dual Step Strategy for Retinal Thin Vessel Enhancement/Extraction
Blood vessel extraction from retinal images is a challenging and fundamental step in pathological analysis. Most of the vessel extraction algorithms face difficulty in the extraction of thin vessels. In this paper, a dual step strategy for retinal thin vessel enhancement/extraction is proposed. Since thin vessel pixels have intensities closer to the background non-vessel pixels, the first level enhancement algorithms usually suffers in its accurate extraction. This led to explore a novel idea of eliminating the effects of thick vessel pixels in a reference image, via replacing it with neighboring non-vessel pixels. By applying second level enhancement on the vessel subtracted image, thin vessels are projected and improvement in extraction is attained subjectively as well as objectively. 2019 IEEE. -
An Efficient HOG-Centroid Descriptor for Human Gait Recognition
Automatic recognition of human gait have gained much attention nowadays. Histogram of Oriented Gradient (HOG) is a widely adopted descriptor for object's shape analysis. In this paper, combination of HOG descriptor with silhouette centroid for human gait recognition is proposed. The resultant descriptor, namely HOG-Centroid, achieves better recognition performance on comparison with HOG descriptor individually as well as other existing gait recognition methods. Experiments are carried out with CASIA gait dataset B and cumulative matching scores of 95.3%, 98.1% and 99.2% are obtained for rank 1, rank 5 and rank 10 respectively. 2019 IEEE. -
Linear and non-linear analysis of solute-magneto convection in a couple stress fluid with porous medium under concentration modulation
The effect of concentration modulation and magnetic field in a couple stress fluid with porous medium and salted from above is studied using linear and non-linear analysis. Venezian approach based on perturbation method is used to obtain the expression for solute Rayleigh number and correction solute Rayleigh number. The expression for correction solute Rayleigh number is obtained as a function of couple stress parameter, Chandrashekar number, Darcy number and Schmidt number. The effect of parameters on symmetric and asymmetric concentration modulation are discussed in the paper. A non-autonomous Ginzburg-Landau equation with time periodic co-efficient is obtained to study the effect of parameters on mass transfer. It is found that onset of convection and mass transfer can be delayed or advanced by varying the parameters of the problem. Asymmetric modulation is found to be more stable than the symmetric modulation. 2019 Author(s). -
Sentiment Analysis on Time-Series Data Using Weight Priority Method on Deep Learning
Sentiment Analysis (SA)is the process to gain an overview of the public opinion on certain topics and it is useful in commerce and social media. The preference on certain topics can be varied on different time periods. To analyze the sentiments on topics in different time periods, priority weight based deep learning approaches like Convolutional-Long Short-Term Memory (C-LSTM)and Stacked- Long Short-Term Memory (S-LSTM)is explored and analyzed in this research. The research method focuses on three phases. In the first phase text data (review given by the customers on various products)is collected from social networking e-commerce site and temporal ordering is done. In the second phase, different deep learning models are created and trained with different time-series data. In the final phase the weights are assigned based on temporal aspect of the data collected. For the obtained results verification and validation processes are carried out. Precision and recall measures are computed. Results obtained shows better performance in terms of classification accuracy and F1-score. 2019 IEEE.