Browse Items (11807 total)
Sort by:
-
Recognition of Green Colour Vegetables' Images Using an Artificial Neural Network
Image processing is used in all the domains including agriculture. In this paper, we have introduced a computationally simple and small feature vector, as a tool for the recognition of green colour vegetable images. The RGB colour system is used and the feature set is computationally economic and performs well on locally available vegetable images. For recognition of vegetable images, an ANN-based classifier is deployed. The recognition percentage is in the scale of 74-100 for 15 vegetable types. This work finds application in the packing of vegetables, food processing, automatic vending. 2019 IEEE. -
LENN: Laplacian Probability Based Extended Nearest Neighbor Classification Algorithm for Web Page Retrieval
Web page prediction is the area of interest that enables to tackle the problem of dealing with the massive collection of the web pages, mainly, in retrieving the highly relevant web pages. The hectic challenge of the web page prediction methods relied on time-effective and cost-effective management. The problem of dealing with the issue is tackled using the efficient web page retrieval algorithm. The paper proposes a new classifier called, Laplacian probability based Extended Nearest Neighbor (LENN)that is formed through the integration of the Laplacian probability with the Extended Nearest Neighbor (ENN)classifier. The proposed LENN classifier determines the nearest web pages of the query. Accordingly, the web page retrieval is done in three important steps, such as pre-processing, feature indexing and web page retrieval. The key words are stored in the database for performing the feature match such that the highly relevant web page is retrieved based on the maximum value of the score. The experimentation using five benchmarks prove that the proposed method is effective compared with the existing methods of web page retrieval. The maximum precision, recall, and F-measure of the proposed method is found to be 98%, 96.7%, and 97.3%, respectively. 2019 IEEE. -
Accident Detection Using Convolutional Neural Networks
Accidents have been a major cause of deaths in India. More than 80% of accident-related deaths occur not due to the accident itself but the lack of timely help reaching the accident victims. In highways where the traffic is really light and fast-paced an accident victim could be left unattended for a long time. The intent is to create a system which would detect an accident based on the live feed of video from a CCTV camera installed on a highway. The idea is to take each frame of a video and run it through a deep learning convolution neural network model which has been trained to classify frames of a video into accident or non-accident. Convolutional Neural Networks has proven to be a fast and accurate approach to classify images. CNN based image classifiers have given accuracy's of more than 95% for comparatively smaller datasets and require less preprocessing as compared to other image classifying algorithms. 2019 IEEE. -
Non invasive methods of blood glucose measurement: Survey, challenges, scope
Noninvasive body parameters monitoring and disease detection is one of the emerging research area now a days. In this paper a review on Non-invasive methods of blood glucose measurement has been made. A comparative study has been made which describes the methodology incorporated in the published literatures, research challenges and the used tools. This paper also describes about the factors which highly impacts the non-invasive measurement. Finally, a deep learning based noninvasive measurement method compatible with IOT is mentioned. This paper serves as a proper reference for future researchers working in non-invasive blood glucose measurement domain in selecting appropriate non-invasive method algorithm for glucose monitoring non-invasively. 2019 Bharati Vidyapeeth, New Delhi. Copy Right in Bulk will be transferred to IEEE by Bharati Vidyapeeth. -
A Deterministic Key-Frame Indexing and Selection for Surveillance Video Summarization
Video data is voluminous and impacts the data storage devices as there are CCTV surveillance videos being created every minute and stored continuously. Due to this increase in data there is a need to create semantic information out of the frames that are being stored. Video Summarization is a process that continuously monitors changes and helps in reducing the number of frames being stored. This work enables summarization to be carried out based on selecting threshold-based system that can select key-frames ideally suit for storage and further analysis. Initially a Global threshold based on Otsus method is carried out for all frames of a surveillance video and based on the set threshold a retrospective comparison is done on each frame based on statistical methods to converge on determining the keyframes. A similarity index is generated based on the iterative comparison of frames based on global and local threshold comparison. The local threshold is indexed based on Analysing Method Patterns to Locate Errors(AMPLE), An-derbergs D(AbD), Cohens Kappa(CK), Tanimoto Similarity(TS), Tversky feature contrast model(TFCM), Pearson coefficient of mean square contingency(Pmsc). The Global threshold is updated each time a keyframe is selected based on the comparison of local and global threshold. The results are compared with five surveillance videos and six methods to identify keyframes Selection Rate is the metric used for calculating the performance. 2019 IEEE. -
Inphase and outphase concentration modulation on the onset of magneto-convection and mass transfer in weak electrically conducting micropolar fluids
The paper analyses the effect of concentration modulation at the onset of solute magneto-convection and heat transfer in a weak electrically conducting fluid by carrying out a linear and non-linear analysis. The Venezian approach is assented encompassing the correction Solute Rayleigh number and wave numbers for meagre amplitude concentration modulation. A multiscale method is applied to convert the analytically untraceable Lorenz model to an analytically traceable Ginzburg-Landau equation which is solved to quantify mass transfer through Sherwood number. It is observed that concentration modulation results in sub-critical motion however out-of-phase concentration modulation is more stable compare to others. 2019 Author(s). -
Comparative study of Breakdown Phenomena and Viscosity in Liquid Dielectrics
Liquid dielectrics are extensively used in electrical apparatus which are operating in distribution and transmission systems. The function of electrical equipment strongly depends on the conditions of liquid dielectric. Liquid dielectrics used are the most expensive components in power system apparatus like transformers and circuit breakers. A failure of these equipment would causes a heavy loss to the electrical industry and also utilities. Insulation failures are the leading cause of transformer failures and thus the liquid dielectrics plays a major role in the safe operation of transformers. One of the main causes for the failure of transformers is due to the presence of moisture. In this work, the life of insulating medium is estimated by comparing the Breakdown strength and Viscosity of different pure oils with that of the contaminated oils (which contains moisture) and also finding the alternative for mineral oil. vegetable oils which are reliable, cost-effective and environmental friendly even when they are contaminated. 2019 IEEE. -
ChIPSeq Analysis with Bayesian Machine Learning
ChIP-sequencing, otherwise called ChIP-seq, is a technique used to identify protein co-operations with DNA. A crucial advancement to the field of bio-informatics, ChIP sequencing is conducted in research labs around the world to get a better understanding of the way transcription factors and other associated proteins influence the gene in many biological processes and in tackling disease states. ChIP-seq is predominantly a field under the domain of biotechnology, however recent advancements and development of tools to process ChIP data have turned the study into one involving bio-informatics, allowing computer scientists and lab technicians to work on an otherwise scholarly field of biochemistry, molecular biology, microbiology and biomedicine. This report illustrates the predominant work-flow undertaken to sequence chromatin from a cell and to gain insights on the gene/protein of interest. Another aspect added is to use Machine Learning with Bayesian statistical techniques for Peak Calling. The different stages enumerated in this paper have been completed either with the R language or on a Web Server titled Galaxy.org. 2019 IEEE. -
IoT Based Water Management Using HC-12 and Django
Water is one of the important needs for a human being. Life on Earth is possible due to the presence of water on its surface. Even though 71% of Earth's surface is covered with water, the availability of water in certain areas is very less. So, the people in these areas must reserve water for ensuring a steady availability. These problems can be rectified with the help of Internet of Things (IOT). IOT is a global infrastructure with certain standards and communication protocols by which virtual and physical things can interact and exchange data by connecting to each other. In this paper, we propose a system for monitoring the availability of water, based on the water level in the storage system. Water level is measured with the help of a waterproof ultrasonic sensor and when the level reaches a threshold value, a notification is sent to the user or to the vendor to take the necessary action. The live feed data is sent to a relational database for storing and analyzing the data to predict when the water will run out, and to make sure that the water storage system gets refilled before that point of time. After processing the raw data from the sensors, the system can generate a fusion chart that can show or indicate the amount of water inside each storage system. With this, the user can have an idea of how much water is left in each of the storage system. The main aim of the proposed system is to showcase the functionalities and uses of different sensors and modules used in an IOT based system with the application of Wireless Sensor Network (WSN). In this present scenario, the world is filled with data both relevant and irrelevant, wherein the data for predicting a water crisis is less. So, through the proposed system we are generating a dataset for the prediction of a water crisis in an organization or a community. 2019 IEEE. -
Sentiment Analysis on Indian Government Schemes Using Twitter data
People use social media for entertainment, fetching information, news, business, communication and many more. Few of such social media applications are Facebook, Twitter, WhatsApp, Snapchat and so on. Twitter is one among the micro blogging websites. We are using Twitter mainly because it has gained a lot of media attention. The text written is referred to as tweets, where a common man can tweet or can write their hearts out. We would be fetching the direct responses from the public and hence the data is more real-time. First step is to fetch the tweets on a particular scheme using python language code followed by the cleaning process then comes the creation of bag of words. Later these bags of words are given as an input to the algorithms. Finally, after training the algorithms, we will be getting the sentiment of the public on that scheme. 2019 IEEE. -
Inter Frame Statistical Feature Fusion for Human Gait Recognition
Researches showed that gait is unique for individuals and human gait recognition gained much attention nowadays. The sequence of gait silhouettes extracted from the video sequences has its own significance for gait recognition performance. In this paper, a novel inter frame feature discriminating the individual gait characteristics is proposed. Consecutive frames within a gait cycle are divided into equal number of blocks and corresponding block differences are calculated. It can preserve the minute temporal variations of the different body parts within each block and the cumulative difference provide a unique feature capable of discriminating individuals. To avoid synchronization problems, secondary statistical features are extracted from the primary inter frame variations. Finally, feature level fusion schemes are applied on these statistical features with existing features extracted from CEI representation. The efficiency of the proposed feature is evaluated on widely adopted CASIA gait dataset B using subspace discriminant analysis. The experimental results show that our proposed feature has better recognition accuracy in comparison with existing features. 2019 IEEE. -
Enhancements in anomaly detection in body sensor networks
Anomaly detection in Body Sensor Networks (BSNs), have recently received much attention from the healthcare community. This is partly due to the development of sensor based real-time tracking and monitoring networks. These networks have been responsible not only for ensuring critical medical treatment at times of emergency, but have also made it easier for health-care personnel to administer critical treatment. In this paper we consider improvements to existing machine learning methods that detect anomalous sensor measurements. The improved methods are a step in the right direction in ensuring unduly overheads due to faulty sensors don't interfere while administering life-critical treatment in a limited resources scenario. 2019 IEEE. -
Power Efficient e-Bike with Terrain Adaptive Intelligence
Electric bicycles or e-bikes are gaining momentum in the market as they are offering a smooth, noiseless and pollution free option for individual transportation in cities as well as in countryside. E-bikes are usually with a battery powered electric motor drive with an additional option for pedaling. In this work a low cost e-bike was designed and developed with a brushless DC hub motor with controllers. For smart control, smartphone was used a console and the e-bike can be controlled using a mobile application which was connected to the e-bike through Bluetooth. The controller will pick the gradient of the terrain and will control the power of the motor, which results in energy saving. Predicted range of the e-bike, speed, acceleration and total distance covered were displayed in the console along with the geographical position on the map and throttle control options. The bike with the proposed control tested and the results were giving a reduction in current drawn from the battery. 2019 IEEE. -
A Proposal of smart hospital management using hybrid Cloud, IoT, ML, and AI
There has been a rapid shift in the medical industry from the service point of view. More importance is being given to patient care and customer satisfaction than ever before. The need to keep the customers happy with the hospital's service has increased rapidly and one way they can improve a patient's experience, even more is if they integrate cloud, IoT, ML, and AI into their system. This would help the medical sector to achieve customization which would enable them to address the needs of their customers more efficiently and offering personalized solutions. In this paper, we are proposing a novel model which focuses on a smart hospital information management system that runs by using hybrid cloud, IoT, ML, and AI. This system would be beneficial not only from the hospitals perspective but also from the patient's side as well. Patients and doctors unique ID would make the entire process a lot more efficient and easier. The advances happening in the field of AI and ML due to cloud-based computing is extremely beneficial for the medical industry. By integrating these components along with IoT it is possible for multi-specialty hospitals and super specialty hospital to be able to set up a smart hospital information management system. 2019 IEEE. -
Proposal of smart home resource management for waste reduction and sustainability using AI and ML
A research indicated that electricity is obliterating extra non-renewable sources for its production. In that, as per Centre for Policy Research (CPR), about 25% of the total production is diverted to meet the daily consumption in an Indian household. Not only this but also, waste management has become an important issue to deal with. According to Municipal Solid Waste (MSW) of India, waste generation in Indian urban communities extends between 200 - 870 grams per day, contingent on the localities' standard of living and the area of the city. Therefore, in this paper we propose a concept that focuses on a sustainable solution using Artificial Intelligence and Machine Learning algorithms for waste and carbon footprint reduction in a home. This concept explains a solution availed with the help of a proposed model called Home Resource Management (HoReM) that is imbibed in a Smart home. 2019 IEEE. -
Role of Filters in Speckle Reduction in Medical Ultrasound Images- A Comparative Study
To diagnose and predict complex disorders in human body, various Medical Imaging Techniques are used. Widely accepted technique among them is the Ultrasound imaging modality, because of its low cost and noninvasive nature. But the images produced by ultrasound scanning are of low quality and amenable to faster degradation due to the presence of speckle noise. This led to various studies for effectively removing speckle noise from ultrasound images. In this paper, an endeavor is made for a comparative analysis of chosen set of post filtering methods for Speckle reduction, VIZ Anisotropic Diffusion, Wavelet, Adaptive Median Filter, Hybrid Algorithm, Modified Fourier Transform and Sparse Code Shrinkage using ICA. The different methods are tested on a collection of ultrasound images and their performance evaluated with the Normalized Cross Correlation metric (NCC), Peak Signal to Noise Ratio (PSNR), Structural Content (SC), Universal Quality Index (UQI), Edge Preservation Index (EPI) and Structural Similarity Index (SSI). Further relative execution time of different approaches are also analyzed. On analysis of the values of different metrics and execution time, Wavelet Based Hybrid Thresholding is found to outperform the other filters considered. 2019 IEEE. -
Challenges and Opportunities: Quantum Computing in Machine Learning
Many computing applications are being developed and applied in almost every aspect of life and in every discipline. With increasing number of problems and complexities, there is requirement for more computational power, faster speed and better results. To overcome these computational barriers, quantum computers, which are based on principles of quantum mechanics were introduced. Faster computation is the main reason behind the evolution of quantum computers which is achieved by using quantum bits instead of bits as quantum bits store both the values 1 and 0 together in superposition. The article focuses on basics of quantum computing in brief and the underlying phenomenon behind quantum computers. Also this article exposes recent trends and the problems that are being faced in this quantum technology. The major impact of quantum machine learning is also discussed. The quantum machine learning is providing better application in this modern field. This article analyses the different research gaps and possible solutions in quantum computing. Recent days quantum computing is implemented in different applications which is also described. 2019 IEEE. -
Epileptic Seizure Prediction from EEG Signals Using DenseNet
Epilepsy is a disorder in which the normal electrical pattern in the brain is disrupted causing seizures or loss of consciousness. Seizure is harmful during various events like swimming or driving. The electroencephalogram (EEG) is the measurement of electrical activity received from the nerve cells of the cerebral cortex. Forthcoming seizures can be predicted from scalp EEG signal to improve the quality of life. The study proposes a method of automatic epileptic seizure prediction from raw EEG signal. The raw EEG signal is converted into EEG signal image for automatic extraction of features and classification of inter-ictal and pre-ictal state using Dense Convolutional Network (DenseNet). This classification process is carried out in a manner similar to the process followed by a medical practitioner without resorting to hand-crafted features. The public CHB-MIT EEG database is used for training, validation, and testing. An EEG signal for 1 second duration is taken as one sample. The accuracy for the classification of inter-ictal and pre-ictal state is achieved up to 94% by using 5-Fold cross validation. However, the accuracy is not up to the mark for the presence of common artifacts caused by eye-blinking and muscle activities during EEG recordings. Hence, a 30 seconds pool based technique is used for decision on correct state identification. The proposed pool based technique provides an average specificity of 95.87% and a false prediction rate of 0.0413/hour. It also provide average sensitivities of 100%, 97%, and 90% for the time slots 0 - 5 minutes, 5 - 10 minutes, and 10 - 15 minutes before the seizure event. 2019 IEEE. -
Multilevel Security and Dual OTP System for Online Transaction Against Attacks
In the current internet technology, most of the transactions to banking system are effective through online transaction. Predominantly all these e-transactions are done through e-commerce web sites with the help of credit/debit cards, net banking and lot of other payable apps. So, every online transaction is prone to vulnerable attacks by the fraudulent websites and intruders in the network. As there are many security measures incorporated against security vulnerabilities, network thieves are smart enough to retrieve the passwords and break other security mechanisms. At present situation of digital world, we need to design a secured online transaction system for banking using multilevel encryption of blowfish and AES algorithms incorporated with dual OTP technique. The performance of the proposed methodology is analyzed with respect to number of bytes encrypted per unit time and we conclude that the multilevel encryption provides better security system with faster encryption standards than the ones that are currently in use. 2019 IEEE. -
Optimization of cutting parameters and prediction of surface roughness during hard turning of H13 steel with minimal vegetable oil based cutting fluid application using response surface methodology
The manufacturing industries in modern era are competing to reduce cost of production by employing innovative techniques, one being hard turning. In hard turning process, the work piece is heat treated to the required hardness in the initial stage itself and near net shape is arrived directly by hard turning process. Hard turning reduces manufacturing lead time by excluding the normal cost incurring processes such as, turning, heat treatment, finish grinding etc. In this experimental investigation hard turning process is assisted with minimal cutting fluid application technique, which reduces cutting fluid usage to a minimum of 6-8 ml/min. Soya bean oil based emulsion was used to make the hard turning environment friendly. The oil was prepared by adding additives, which will enhance the desirable properties of the oil for hard turning. Response surface methodology was used for optimization of cutting parameters and for the prediction of surface roughness. A central composite design was implemented to estimate the second-degree polynomial model. The cutting parameters considered for experimentation were cutting speed, feed rate and depth of cut. The surface roughness was considered parameter for prediction. Surface roughness predicted by the response Surface Methodology matched well with the experimental results. Published under licence by IOP Publishing Ltd.