Priyan Malarvizhi Kumar

A new architecture of Internet of Things and big data ecosystem for secured smart healthcare monitoring and alerting system

Abstract Wearable medical devices with sensor continuously generate enormous data which is often called as big data mixed with structured and unstructured data. Due to the complexity of the data, it is difficult to process and analyze the big data for finding valuable information that can be useful in decision-making. On the other hand, data security is a key requirement in healthcare big data system. In order to overcome this issue, this paper proposes a new architecture for the implementation of IoT to store and process scalable sensor data (big data) for health care applications. The Proposed architecture consists of two main sub architectures, namely, Meta Fog-Redirection (MF-R) and Grouping and Choosing (GC) architecture. MF-R architecture uses big data technologies such as Apache Pig and Apache HBase for collection and storage of the sensor data (big data) generated from different sensor devices. The proposed GC architecture is used for securing integration of fog computing with cloud computing. This architecture also uses key management service and data categorization function (Sensitive, Critical and Normal) for providing security services. The framework also uses MapReduce based prediction model to predict the heart diseases. Performance evaluation parameters such as throughput, sensitivity, accuracy, and f-measure are calculated to prove the efficiency of the proposed architecture as well as the prediction model.

Machine Learning Based Big Data Processing Framework for Cancer Diagnosis Using Hidden Markov Model and GM Clustering

AbstractThe change in the DNA is a form of genetic variation in the human genome. In addition, the DNA copy number change is also linked with the progression of many emerging diseases. nArray-based Comparative Genomic Hybridization (CGH) is considered as a major task when measuring the DNA copy number change across the genome. Moreover, DNA copy number change is an essential measure to diagnose the cancer disease. Next generation sequencing is an important method for studying the spread of infectious disease qualitatively and quantitatively. CGH is widely used in continuous monitoring of copy number of thousands of genes throughout the genome. In recent years, the size of the DNA sequence data is very large. Hence, there is a need to use a scalable machine learning approach to overcome the various issues in DNA copy number change detection. In this paper, we use a Bayesian hidden Markov model (HMM) with Gaussian Mixture (GM) Clustering approach to model the DNA copy number change across the genome. The proposed Bayesian HMM with GM Clustering approach is compared with various existing approaches such as Pruned Exact Linear Time method, binary segmentation method and segment neighborhood method. Experimental results demonstrate the effectiveness of our proposed change detection algorithm.n

Intelligent face recognition and navigation system using neural learning for smart security in Internet of Things

Most of the advancements are now carried out by interconnecting physical devices with computers; this is what known as Internet of Things (IoT). The major problems facing by blind people fall in the category of navigating through indoor and outdoor environments consisting of various obstacles and recognition of person in front of them. Identification of objects or person only with perceptive and audio information is difficult. An intelligent, portable, less expensive, self-contained navigation and face recognition system is highly demanded for blind people. This helps blind people to navigate with the help of a Smartphone, global positioning system (GPS) and a system equipped with ultrasonic sensors. Face recognition can be done using neural learning techniques with feature extraction and training modules. The images of friends, relatives are stored in the database of user Smartphone. Whenever a person comes in front of the blind user, the application with the help of neural network gives the voice aid to the user. Thus this system can replace the regular imprecise use of guide dogs as well as white sticks to help the navigation and face recognition process for people with impaired vision.In this paper, we have proposed a novel image recognition and navigation system which provides precise and quick messages in the form of audio to visually challenged people so that they can navigate easily. The performance of the proposed method is comparatively analyzed with the help of ROC analysis.

A novel three-tier Internet of Things architecture with machine learning algorithm for early detection of heart diseases

Abstract Among the applications enabled by the Internet of Things (IoT), continuous health monitoring system is a particularly important one. Wearable sensor devices used in IoT health monitoring system have been generating an enormous amount of data on a continuous basis. The data generation speed of IoT sensor devices is very high. Hence, the volume of data generated from the IoT-based health monitoring system is also very high. In order to overcome this issue, this paper proposes a scalable three-tier architecture to store and process such huge volume of wearable sensor data. Tier-1 focuses on collection of data from IoT wearable sensor devices. Tier-2 uses Apache HBase for storing the large volume of wearable IoT sensor data in cloud computing. In addition, Tier-3 uses Apache Mahout for developing the logistic regression-based prediction model for heart diseases. Finally, ROC analysis is performed to identify the most significant clinical parameters to get heart disease.

HIoTPOT: Surveillance on IoT Devices against Recent Threats

Honeypot Internet of Things (IoT) (HIoTPOT) keep a secret eye on IoT devices and analyzes the various recent threats which are dangerous to IoT devices. In this paper, implementation of a research honeypot is presented which is used to learn the recent tactics and ethics used by black hat community to attack on IoT devices. As IoT is open and easy for accessing, all the intruders are highly attracted towards IoT. Recently Telnet based attacks are very famous on IoT devices to get easy access and attack on other devices. To reduce these kinds of threats, it is necessary to know in details about intruder, therefore the aim of this research work is to implement novel based secret eye server known as HIoTPOT which will make the IoT environment more safe and secure.

Enhanced DTLS with CoAP-based authentication scheme for the internet of things in healthcare application

As health data are very sensitive, there is a need to prevent and control the health data with end-to-end security solutions. In general, a number of authentication and authorization schemes are available to prevent and protect the sensitive data, which are collected with the help of wearable Internet of Things (IoT) devices. The transport layer security (TLS) protocol is designed to transfer the data from source to destination in more reliable manner. This protocol enables a user to overcome the no lost or reordered messages. The more challenge with TLS is to tolerate unreliability. In order to overcome this issue, Datagram transport layer security (DTLS) protocol has been designed and used in low-power wireless constrained networks. The DTLS protocol consists of a base protocol, record layer, handshake protocol, ChangeCipherSpec and alert protocol. The complex issue with the DTLS protocol is the possibility of an attacker could send a number of ClientHello messages to a server. This scenario would cause a denial-of-service (DOS) attack against the server. This DoS attack enables new connection between the attacker and server, increasing attacker bandwidth, and allocation of resources for every ClientHello message. In order to overcome this issue, we have proposed a smart gateway-based authentication and authorization method to prevent and protect more sensitive physiological data from an attacker and malicious users. The enhanced smart gateway-based DTLS is demonstrated with the help of Contiki Network Simulator. The packet loss ratio is calculated for the CoAP, host identity protocol, CoAP-DTLS and CoAP-enhanced DTLS to evaluate the performance of the proposed work. Data transmission and handshake time are also calculated to evaluate the efficiency of the enhanced DTLS.

Speech recognition with improved support vector machine using dual classifiers and cross fitness validation

In this research, a new speech recognition method based on improved feature extraction and improved support vector machine (ISVM) is developed. A Gaussian filter is used to denoise the input speech signal. The feature extraction method extracts five features such as peak values, Mel frequency cepstral coefficient (MFCC), tri-spectral features, discrete wavelet transform (DWT), and the difference values between the input and the standard signal. Next, these features are scaled using linear identical scaling (LIS) method with the same scaling method and the same scaling factors for each set of features in both training and testing phases. Following this, to accomplish the training process, an ISVM is developed with best fitness validation. The ISVM consists of two stages: (i) linear dual classifier that finds the same class attributes and different class attributes simultaneously and (ii) cross fitness validation (CFV) method to prevent over fitting problem. The proposed speech recognition method offers 98.2% accuracy.

An Automatic Tamil Speech Recognition system by using Bidirectional Recurrent Neural Network with Self-Organizing Map

Speech recognition is one of the entrancing fields in the zone of computer science. Exactness of speech recognition framework may decrease because of the nearness of noise exhibited by the speech signal. Consequently, noise removal is a fundamental advance in automatic speech recognition (ASR) system. ASR is researched for various languages in light of the fact that every language has its particular highlights. Particularly, the requirement for ASR framework in Tamil language has been expanded broadly over the most recent couple of years. In this work, bidirectional recurrent neural network (BRNN) with self-organizing map (SOM)-based classification scheme is suggested for Tamil speech recognition. At first, the input speech signal is pre-prepared by utilizing Savitzky–Golay filter keeping in mind the end goal to evacuate the background noise and to improve the signal. At that point, Multivariate Autoregressive based highlights by presenting discrete cosine transformation piece to give a proficient signal investigation. And in addition, perceptual linear predictive coefficients likewise separated to enhance the classification accuracy. The feature vector is shifted in measure, for picking the right length of feature vector SOM utilized. At long last, Tamil digits and words are ordered by utilizing BRNN classifier where the settled length feature vector from SOM is given as input, named as BRNN-SOM. The experimental analysis demonstrates that the suggested conspire accomplished preferable outcomes looked at over exist deep neural network–hidden Markov model algorithm regarding signal-to-noise ratio, classification accuracy, and mean square error.

Paillier homomorphic cryptosystem with poker shuffling transformation based water marking method for the secured transmission of digital medical images

Digital watermarking is a technique that provides security and authentication for digital image transmission. In general, patient reports are stored in the form of a medical image. A medical image shared through the Internet can be easily modified by an unauthorized user. In order to overcome this risk, we have proposed a method, namely, Paillier homomorphic cryptosystem with poker shuffling transformation-based watermarking method for ensuring security for the digital medical images. In this paper, the watermarking process initially is done at an encrypted DWT-DCT domain. Paillier homomorphic cryptosystem is used for encrypting the original image. The watermark image is scrambled using poker shuffling transformation to generate the scrambled image. This is followed by the encryption of the scrambled image. The embedding process is used for generating an encrypted watermark image. The extraction process involves the decryption of encrypted watermark image for getting the original and the watermark image. The medical data is collected from the private hospitals. The experimental results have established the improvement in the robustness of our proposed watermarking system in an encrypted DWT-DCT domain apart from providing security for the digital image transmission.

Cloud and IoT based disease prediction and diagnosis system for healthcare using Fuzzy neural classifier

Abstract Recently, the mobile health care (m-healthcare) applications with Internet of Things (IoT) are providing the various dimensionalities and the online services. These applications have provided a new platform to the millions of people for getting benefit over the health tips frequently for living a healthy life. After the introduction of IoT technology and the related devices which are used in medical field, strengthened the various features of these healthcare online applications. The huge volume of big data is generated by IoT devices in healthcare environment. Cloud computing technology is used to handle the large volume of data and also provide the ease of use. In this scenario, cloud based applications are playing major role in this fast world. These medical applications are also used the Cloud Computing technology for secured storage and accessibility. For availing better services to the people over the online healthcare applications, we propose a new Cloud and IoT based Mobile Health care application for monitoring and diagnosing the serious diseases. Here, a new framework is developed for the public. In this work, a new systematic approach is used for the diabetes diseases and the related medical data is generated by using the UCI Repository dataset and the medical sensors for predicting the people who has affected with diabetes severely. In addition, we propose a new classification algorithm called Fuzzy Rule based Neural Classifier for diagnosing the disease and the severity. The experiments have been conducted by the standard UCI Repository dataset and the real health records which are collected from various hospitals. The experimental results show that the performance of the proposed work which outperforms the existing systems for disease prediction.