Revathi Sundarasekar

Wearable sensor devices for early detection of Alzheimer disease using dynamic time warping algorithm

Alzheimer disease is a significant problem in public health. Alzheimer disease causes severe problems with thinking, memory and activities. Alzheimer disease affected more on the people who are in the age group of 80-year-90. The foot movement monitoring system is used to detect the early stage of Alzheimer disease. internets of things (IoT) devices are used in this paper to monitor the patients’ foot movement in continuous manner. This paper uses dynamic time warping (DTW) algorithm to compare the various shapes of foot movements collected from the wearable IoT devices. The foot movements of the normal individuals and people who are affected by Alzheimer disease are compared with the help of middle level cross identification (MidCross) function. The identified cross levels are used to classify the gait signal for Alzheimer disease diagnosis. Sensitivity and specificity are calculated to evaluate the DTW algorithm based classification model for Alzheimer disease. The classification results generated using the DTW is compared with the various classification algorithms such as inertial navigation algorithm, K-nearest neighbor classifier and support vector machines. The experimental results proved the effectiveness of the DTW method.

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. Array-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.

Big Data Analytics in Healthcare Internet of Things

Nowadays, wearable medical devices play a vital role in many environments such as continuous health monitoring of individuals, road traffic management, weather forecasting, and smart home. These sensor devices continually generate a huge amount of data and stored in cloud computing. This chapter proposes Internet of Things (IoT) architecture to store and process scalable sensor data (big data) for healthcare applications. Proposed architecture consists of two main sub-architecture, namely, MetaFog-Redirection (MF-R) and Grouping & Choosing (GC) architecture. Though cloud computing provides scalable data storage, it needs to be processed by an efficient computing platforms. There is a need for scalable algorithms to process the huge sensor data and identify the useful patterns. In order to overcome this issue, this chapter proposes a scalable MapReduce-based logistic regression to process such huge amount of sensor data. Apache Mahout consists of scalable logistic regression to process large data in distributed manner. This chapter uses Apache Mahout with Hadoop Distributed File System to process the sensor data generated by the wearable medical devices.

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.

Big Data Security Intelligence for Healthcare Industry 4.0

Nowadays, sensors are playing a vital role in almost all applications such as environmental monitoring, transport, smart city applications and healthcare applications and so on. Especially, wearable medical devices with sensors are essential for gathering of rich information indicative of our physical and mental health. These sensors are continuously generating enormous data often called as Big Data. It is difficult to process and analyze the Big Data for finding valuable information. Thus effective and secure architecture is needed for organizations to process the big data in integrated industry 4.0. These sensors are continuously generating enormous data. Hence, it is difficult to process and analyze the valuable information. This chapter proposes a secure Industrial Internet of Things (IoT) architecture to store and process scalable sensor data (big data) for health care applications. Proposed Meta Cloud-Redirection (MC-R) architecture with big data knowledge system is used to collect and store the sensor data (big data) generated from different sensor devices. In the proposed system, sensor medical devices are fixed with the human body to collect clinical measures of the patient. Whenever the respiratory rate, heart rate, blood pressure, body temperature and blood sugar exceed its normal value then the devices send an alert message with clinical value to the doctor using a wireless network. The proposed system uses key management security mechanism to protect big data in industry 4.0.

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.

Stealthy attack detection in multi-channel multi-radio wireless networks

In recent years, the lack of network traffic analysis and flexible network topologies reduce the performance of the multi-channel multi-radio wireless networks. As high scalability of its participants and routing structure, multicast communication of wireless networks is vulnerable to stealthy attacks. Stealthy packet dropping disrupts the packet from reaching the destination through malicious behavior at an intermediate node. A network table is maintained in each hop to transfer the data packet from source to destination. The main contribution of this paper is to use that network table to monitor the drastic changes incoming packet as well as an outgoing packet. More specifically, we have proposed Cumulative Sum algorithm (CuSum) with bootstrap analysis method to monitor the changes in the network packet transmission. We have used NS-2 network simulator to simulate the proposed CUSUM algorithm with a bootstrap method is compared with various other existing change detection methods such as such as Binary Segmentation (BinSeg), Pruned Exact Linear Time (PELT) and Segment Neighborhood (SegNeigh) method. The simulation results proved the efficiency of the proposed CuSum with bootstrap analysis method.

Internet of Things with Maximal Overlap Discrete Wavelet Transform for Remote Health Monitoring of Abnormal ECG Signals

In this paper, MODWT is used to decompose the Electrocardiography (ECG) signals and to identify the changes of R waves in the noisy input ECG signal. The MODWT is used to handle the arbitrary changes in the input signal. The R wave’s detctected by the proposed framework is used by the doctors and careholders to take necessary action for the patients. MATLAB simulink model is used to develop the simulation model for the MODWT method. The performance of the MODWT based remote health monitoring system method is comparatively analyzed with other ECG monitoring approaches such as Haar Wavelet Transformation (HWT) and Discrete Wavelet Transform (DWT). Sensitivity, specificity, and Receiver Operating Characteristic (ROC) curve are calculated to evaluate the proposed Internet of Things with MODWT based ECG monitoring system. We have used MIT-BIH Arrythmia Database to perform the experiments.

Ant colony optimization algorithm with Internet of Vehicles for intelligent traffic control system

Abstract Vehicles present on the Internet of Vehicles (IoV) can communicate with each other in order to determine the status of the road and vehicle in real time. These parameters are used to estimate the average speed and identify the optimal route to reach the destination. However, the government traffic departments are unable to use these valuable traffic data and thus more traffic jam, congestion and road accident occurs. In order to overcome this issue, this paper proposes an effective traffic control system with the help of IoV technology. The proposed method is demonstrated in the study are of Vellore district, Tamil Nadu, India. The street maps are segmented into number small number of distinct maps. Ant colony algorithm is applied to each map in order to find the optimal route. In addition, Fuzzy logic based traffic intensity calculation function is proposed in this paper to model the heavy traffic. The proposed IoV based route selection method is compared with the existing shortest path selection algorithms such as Dijikstra algorithm, Kruskals algorithm and Prims algorithm. The experimental results proved the good performance of the proposed IoV based route selection method.