Arpan Pal

Energy Information Gateway for Home

Energy conservation or energy management is the buzz word today and it’s a real necessity for today’s world, in order to maintain high economy growth rate. Smart Meter technology is the first step towards achieving this goal. This paper discusses a novel low-cost Home Energy Information Gateway (HEIG) solution which can provide the Smart Meter display and communication interface through a Set Top Box like gateway device on the television and offer a varied range of benefits to the consumers and utility providers. The proposed solution provides a real-time view of the energy consumption at home on the Home Television. In addition it can also provide daily, monthly and annual energy usage statistics along with a mechanism to provide alerts when the energy consumption exceeds certain pre-defined thresholds. By interfacing with the utility provider’s portal over the web, it can provide a mechanism to introduce dynamic tariff and in future, as intelligent electrical appliances become available, a means to control the energy consumption of home electrical appliances from the Home Television itself. The main value provided by the proposed solution lies in its low-cost and low-power, which is an important parameter for deployment in Developing Countries.

Heart-trend: An affordable heart condition monitoring system exploiting morphological pattern

In this paper we leverage the power of smartphone to enable proactive in-house heart condition monitoring. We introduce Heart-Trend, a nonparametric model to analyze and detect heart abnormality conditions like arrhythmia from photoplethysmogram (PPG) signal. It does on-demand heart status monitoring using smartphones (can also be implemented in PC/ICU monitors) and facilitates timely detection of heart condition deterioration to permit early diagnosis and prevention of fatal heart diseases. Proposed robust anomaly analytics engine accurately detects the morphological trend to find abnormal heart condition in real time through machine learning based trend prediction. PPG signal is frequently corrupted by ambient noise, and motion artifacts, which lead to high amount of false alarms. We introduce precise denoising technique that identifies and eliminates the corrupted segments of clinical signal to minimize its impact on the decision process and analytics. We demonstrate that Heart-Trend ensures high detection capability with lower false alarm rates.

Adaptive Sensor Data Compression in IoT systems: Sensor data analytics based approach

Sensor nodes are embodiment of IoT systems in microscopic level. As the volume of sensor data increases exponentially, data compression is essential for storage, transmission and in-network processing. The compression performance to realize significant gain in processing high volume sensor data cannot be attained by conventional lossy compression methods. In this paper, we propose ASDC (Adaptive Sensor Data Compression), an adaptive compression scheme that caters various sensor applications and achieve high performance gain. Our approach is to exhaustively analyze the sensor data and adapt the parameters of compression scheme to maximize compression gain while optimizing information loss. We apply robust statistics and information theoretic techniques to establish the adaptivity criteria. We experiment with large sets of heterogeneous sensor datasets to prove the efficacy. Nonlinear lossy compression (Chebyshev) is extensively considered as the standard technique as well as experimental result with frequency domain compression like Discrete Fourier Transform (DFT) is shown as future scope of further improvement.

Recognition of who is doing what from the stick model obtained from Kinect

In this demo, authors are going to demonstrate a method of identifying the person and his/her activities such as sitting, standing and walking using the skeleton information (stick model) obtained from Kinect. This set up is deployed in a drawing room for the real-time Television Rating Point (TRP) measurement.

Design insights for a mobile based sensor application framework: for aiding platform independent algorithm design

Modern day smart phones are powerful connected sensory and computation nodes for crowd-sensing, urban-sensing and personal-sensing applications. We have developed an Internet of Things (IoT) platform that can seamlessly handle data from the wide variety of sensors available on mobile phones. It can store and run aggregated analysis on the data in real-time. However, mobile phones themselves are a very heterogeneous set of devices. Each phone comes with a different array of sensors with varying sensitivity and control functions. Also, there are multiple development environments and programming languages. A final problem is seamless prototyping of applications offline and then seamless partitioning of the algorithm between phone and the cloud. In this paper we present early design elements of a framework aimed at addressing these issues.

SPA: smart meter privacy analyzer: demo abstract

Smart meter data, invites intended or unintended malicious and potentially dangerous privacy breaching activities, like activity detection of the habitants though it has high potential to facilitate innumerable utilities. Here, we propose a novel solution SPA: Smart meter Privacy Analyzer for addressing the problem of privacy breaching risk minimization smart home energy management systems. It is an unsupervised learning based method along with robust statistics and information theoretic approaches. This abstract provides overview of design and implementation of our tool along with obtained results and most importantly evaluation of a trade-off point to realize optimal privacy-utility trade-off.

Shake meter: An Autonomous Vibration Measurement System using Optical Strobing: Demo Abstract

In this paper, we intend to demonstrate a novel system to measure the high-speed vibration of an anonymous vibrating object using COTS camera and optical strobing. The whole process is unobtrusive and frugal, can be used in machine inspection. The camera used has a frame rate of 30 frames per second (fps), so in conventional fashion, it is incapable to detain significant information about any vibration frequency which is not in the range of Nyquist theory of frequency (within a range of ±15 Hz). We have solved the challenge using optical strobing phenomena for capturing modulo (of division) between objects frequency and strobing frequency using camera. Motion in the video is tracked by conventional image processing technique. Finally, object vibration is calculated from the frequency plot and optical strobing frequency. Under most of the cases, the application estimates vibration frequency values, within a range of ±1.5% of error.

A Novel Approach to Unify Robotics, Sensors, and Cloud Computing Through IoT for a Smarter Healthcare Solution for Routine Checks and Fighting Epidemics.

This paper attempts to project a novel concept where medical sensors, cloud computing and robotic platform are unified to offer state-of-the-art healthcare solutions to a wide variety of scenarios. The proposed solution is most effective if there is scarcity of healthcare providers or if putting them in the field expose them into a high risk environment such as fighting epidemics. In addition, the proposed system will also benefit routine checks in quarantine wards of hospitals where human reluctance of performing routine task by the healthcare providers can be avoided. Finally, it can also assist a doctor as a decision support system by using machine’s capability of number crunching while it examines through patient’s complete history, goes through every medical test reports and then applies data mining for catching possible ailments from his/her symptoms.

Simultaneous Measurement and Correlation of PPG Signals Taken from Two Different Body Parts for Enhanced Biometric Security via Two-level Authentication

In this paper we present a novel, multi-mode physiological photoplethysmogram (PPG) signal based biometric security system to be deployed in conjunction with existing face and finger recognition systems for enhanced security. We propose a two-level authentication system and use two PPG signals collected through face and finger of the subject for cross-correlation. PPG signals are generated due to involuntary body processes and therefore cannot be mimicked. Conventional face and finger print recognition is performed as the first-level security clearance. However, both these can be breached by wearing 3D printed finger tips or masking the face by undergoing surgery or 3D printed wearable face masks. Therefore, a second level security based on involuntary PPG signals is employed for enhanced security. This simultaneous measurement of these heart signals and their correlation is used as a biometric criterion for second level authentication and corresponding results are presented in this paper.

Smartphone Sensing Framework

In this paper, we propose a novel smartphone sensing framework which allows heterogeneous and concurrent sensor access, energy-efficient task partitioning across smartphone and server, and allows integration in third-party applications following some simple rules and constraints. We demonstrate how the framework is able to reduce power-usage on the smartphone as well as maintains optimum network bandwidth usage, while not sacrificing on user experience and sensor accuracy.