Priyanka Mary Mammen | University of Massachusetts Amherst (original) (raw)
Uploads
Papers by Priyanka Mary Mammen
Sleep deprivation is a public health concern that significantly impacts one’s well-being and perf... more Sleep deprivation is a public health concern that significantly impacts one’s well-being and performance. Sleep is an intimate experience, and state-of-the-art sleep monitoring solutions are highly-personalized to individual users. With a motivation to expand sleep monitoring capabilities at a large scale and contribute sleep data to public health understanding, we present WiSleep, a system for inferring sleep duration using smartphone network connections that are passively sensed from WiFi infrastructure. We propose an unsupervised ensemble model of Bayesian change point detection, validating it over a user study among 20 students living in campus dormitories and a private home. Our results find WiSleep outperforming prior techniques for users with irregular sleep patterns while yielding an average 88.50% accuracy within 60 minutes sleep time error and 39 minutes wake-up time error. This is comparable to client-side methods, albeit utilizing coarse-grained information. Additionally...
Proceedings of the 4th ACM International Conference on Systems for Energy-Efficient Built Environments, 2017
Motivating users to save energy is considered to be the holy grail of smart energy management. Ho... more Motivating users to save energy is considered to be the holy grail of smart energy management. However, many studies have shown that changing user behavior from an energy standpoint is a very difficult problem. Furthermore, in countries such as the United States, users do not have sufficient monetary incentives to become energy conscious, given the low cost of electricity, and more generally, energy. In this paper, we study this issue in a developing economy and present a user study of 41 apartments in a high-rise apartment complex in India. Through a combination of fine-grain energy meter usage data and detailed user surveys, we find that these users may be no more energy conscious or motivated to adopt energy efficiency measures than their counterparts in Western nations. Our study challenges the belief that energy prices are higher in developing regions and hence, users in developing regions tend to be more energy-aware than those elsewhere. Consequently, and importantly, we argu...
Proceedings of the Tenth International Conference on Information and Communication Technologies and Development, 2019
Rapid urbanization with haphazard growth pattern often leads to intensification of built-up areas... more Rapid urbanization with haphazard growth pattern often leads to intensification of built-up areas. The built-up areas increase the ambient air temperature and results in heat stress conditions thereby causing adverse health impacts. Therefore, mitigation of urban warming has become a major concern for urban administrators. Accurate identification of heat stressed areas has been difficult due to the low spatial or temporal resolutions of data collected through conventional methods. Hence, in this paper, we have applied an ICT based solution by deploying low cost sensor modules at various building typologies to continuously monitor and capture the diurnal thermal variations in air temperatures. With diurnal temperature profile, we could assess 1) the thermal gradient of varied built typologies and, 2) using spatial analytics, we could analyse the spatial variability of hotspots in the study area. ICT based data-driven approach provides a novel solution to thermal monitoring and inform...
Motivated by recent advancements in Deep Reinforcement Learning (RL), we have developed an RL age... more Motivated by recent advancements in Deep Reinforcement Learning (RL), we have developed an RL agent to manage the operation of storage devices in a household and is designed to maximize demand-side cost savings. The proposed technique is data-driven, and the RL agent learns from scratch how to efficiently use the energy storage device given variable tariff structures. In most of the studies, the RL agent is considered as a black box, and how the agent has learned is often ignored. We explain the learning progression of the RL agent, and the strategies it follows based on the capacity of the storage device.
ArXiv, 2021
Sleep deprivation is a public health concern that significantly impacts one’s well-being and perf... more Sleep deprivation is a public health concern that significantly impacts one’s well-being and performance. Sleep is an intimate experience, and state-of-the-art sleep monitoring solutions are highly-personalized to individual users. With a motivation to expand sleep monitoring at a large-scale and contribute sleep data to public health understanding, we present WiSleep, a sleep monitoring and analytics platform using smartphone network connections that are passively sensed from WiFi infrastructure. We propose an unsupervised ensemble model of Bayesian change point detection to predict sleep and wake-up times. Then, we validate our approach using ground truth from a user study in campus dormitories and a private home. Our results find WiSleep outperforming established methods for users with irregular sleep patterns while yielding comparable accuracy for regular sleepers with an average 79.5% accuracy. This is comparable to client-side based methods, albeit utilizing only coarse-graine...
Proceedings of the 18th Conference on Embedded Networked Sensor Systems, 2020
The proliferation of mobile sensing devices due to advances in the Internet of Things has the pot... more The proliferation of mobile sensing devices due to advances in the Internet of Things has the potential to transform the individual-centric health monitoring to community-scaled health monitoring. Contrary to the state-of-the-art mobile health sensing, which focuses on individuals, my research focuses on scaling mobile health technologies to community scale, where we monitor the health of an entire community or population of users. The benefits of adopting community-scale sensing are two folds; firstly, it enables aggregate public health monitoring of large groups which can answer broader health problems; secondly, it improves personalized health monitoring with fine-grain monitoring of individuals.
Proceedings of the Eleventh ACM International Conference on Future Energy Systems, 2020
With a rampant increase in the urban population, especially in megacities, the number of high ris... more With a rampant increase in the urban population, especially in megacities, the number of high rise buildings is increasing rapidly. Both high rise buildings and lifestyle changes have resulted in high energy consumption. Heating, Ventilation, and Air Conditioning (HVAC) contribute the most to energy consumption in high-rise buildings. As thermal comfort is the major driving factor for the functioning of HVAC systems in a space, it is essential to understand how indoor environmental conditions vary across buildings' dimensions. Traditional approaches rely on simulations to understand the spatial and temporal variations of indoor conditions. Visualization offers opportunities to find solutions for complex thermal variations in buildings because of variation in environmental conditions owing to orientation, height, etc. In this paper, we adopt a data-driven approach that considers the difference in indoor temperature depending on the floor level in a building. Temperature sensors kept on different floors in a building lead to real-time observations. The visualization from Open source Visualization Platform' (Grafana) revealed interesting variations in temperature at different floors of a high-rise building, based on which recommendations could be made to reduce energy consumption.
Proceedings of the Ninth International Conference on Future Energy Systems, 2018
Power shortage is a serious issue in developing nations. During periods of high demand, utilities... more Power shortage is a serious issue in developing nations. During periods of high demand, utilities need to motivate the consumers to curtail their consumption for maintaining grid stability and avoiding blackouts or brownouts. Identification of suitable candidates is essential for such events, as the budget set aside by utilities for Demand Response (DR) events for providing incentives to the consumers should not exceed the added production cost due to peaks. Similarly, from the consumers' point of view, participation comes with the compromise to their convenience. Hence, the selection criteria should be such that it minimizes the peaking cost to the utility without affecting consumer comfort. In this paper, we present SmarDeR, a smart DR consumer selection strategy which considers several factors and consolidates them into a single function which can work in different modes to strategically choose the candidates for the DR event based on the goals specified by the utility. We evaluate different policies and metrics for approaching the right consumers for participating in the DR events. Thereby, we can maintain a fair distribution of requests among the most relevant and reliable users. Experiments with smart-meter data from apartments in our campus demonstrates the effectiveness of our SmarDeR approach.
2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), 2016
In modern days security issues play a vital and integral part of information technology and its r... more In modern days security issues play a vital and integral part of information technology and its related applications such as ATM and smart cards. Cryptography has evolved as a important element of security process. Elliptic curve cryptography is used to develop a variety of scheme for security purpose. Point addition and point doubling arithmetic used in elliptic curve is applicable for prime field. When same arithmetic performs over extension field it increases the complexity of the application but enhances the security in the field of communication technology. This paper communicates Weierstrass equation as the root of elliptic curve. Also described the group operation on elliptic curve that is point addition and point doubling used for encryption application based on prime field Fp. The proposed work is based on elliptic curve group operations solved in extension field Fp2. This new approach is verified using System for Algebra and Geometry and Experimentation (SAGE) open source software.
ArXiv, 2021
Federated Learning (FL) is a concept first introduced by Google in 2016, in which multiple device... more Federated Learning (FL) is a concept first introduced by Google in 2016, in which multiple devices collaboratively learn a machine learning model without sharing their private data under the supervision of a central server. This offers ample opportunities in critical domains such as healthcare, finance etc, where it is risky to share private user information to other organisations or devices. While FL appears to be a promising Machine Learning (ML) technique to keep the local data private, it is also vulnerable to attacks like other ML models. Given the growing interest in the FL domain, this report discusses the opportunities and challenges in federated learning.
Sleep deprivation is a public health concern that significantly impacts one’s well-being and perf... more Sleep deprivation is a public health concern that significantly impacts one’s well-being and performance. Sleep is an intimate experience, and state-of-the-art sleep monitoring solutions are highly-personalized to individual users. With a motivation to expand sleep monitoring capabilities at a large scale and contribute sleep data to public health understanding, we present WiSleep, a system for inferring sleep duration using smartphone network connections that are passively sensed from WiFi infrastructure. We propose an unsupervised ensemble model of Bayesian change point detection, validating it over a user study among 20 students living in campus dormitories and a private home. Our results find WiSleep outperforming prior techniques for users with irregular sleep patterns while yielding an average 88.50% accuracy within 60 minutes sleep time error and 39 minutes wake-up time error. This is comparable to client-side methods, albeit utilizing coarse-grained information. Additionally...
Proceedings of the 4th ACM International Conference on Systems for Energy-Efficient Built Environments, 2017
Motivating users to save energy is considered to be the holy grail of smart energy management. Ho... more Motivating users to save energy is considered to be the holy grail of smart energy management. However, many studies have shown that changing user behavior from an energy standpoint is a very difficult problem. Furthermore, in countries such as the United States, users do not have sufficient monetary incentives to become energy conscious, given the low cost of electricity, and more generally, energy. In this paper, we study this issue in a developing economy and present a user study of 41 apartments in a high-rise apartment complex in India. Through a combination of fine-grain energy meter usage data and detailed user surveys, we find that these users may be no more energy conscious or motivated to adopt energy efficiency measures than their counterparts in Western nations. Our study challenges the belief that energy prices are higher in developing regions and hence, users in developing regions tend to be more energy-aware than those elsewhere. Consequently, and importantly, we argu...
Proceedings of the Tenth International Conference on Information and Communication Technologies and Development, 2019
Rapid urbanization with haphazard growth pattern often leads to intensification of built-up areas... more Rapid urbanization with haphazard growth pattern often leads to intensification of built-up areas. The built-up areas increase the ambient air temperature and results in heat stress conditions thereby causing adverse health impacts. Therefore, mitigation of urban warming has become a major concern for urban administrators. Accurate identification of heat stressed areas has been difficult due to the low spatial or temporal resolutions of data collected through conventional methods. Hence, in this paper, we have applied an ICT based solution by deploying low cost sensor modules at various building typologies to continuously monitor and capture the diurnal thermal variations in air temperatures. With diurnal temperature profile, we could assess 1) the thermal gradient of varied built typologies and, 2) using spatial analytics, we could analyse the spatial variability of hotspots in the study area. ICT based data-driven approach provides a novel solution to thermal monitoring and inform...
Motivated by recent advancements in Deep Reinforcement Learning (RL), we have developed an RL age... more Motivated by recent advancements in Deep Reinforcement Learning (RL), we have developed an RL agent to manage the operation of storage devices in a household and is designed to maximize demand-side cost savings. The proposed technique is data-driven, and the RL agent learns from scratch how to efficiently use the energy storage device given variable tariff structures. In most of the studies, the RL agent is considered as a black box, and how the agent has learned is often ignored. We explain the learning progression of the RL agent, and the strategies it follows based on the capacity of the storage device.
ArXiv, 2021
Sleep deprivation is a public health concern that significantly impacts one’s well-being and perf... more Sleep deprivation is a public health concern that significantly impacts one’s well-being and performance. Sleep is an intimate experience, and state-of-the-art sleep monitoring solutions are highly-personalized to individual users. With a motivation to expand sleep monitoring at a large-scale and contribute sleep data to public health understanding, we present WiSleep, a sleep monitoring and analytics platform using smartphone network connections that are passively sensed from WiFi infrastructure. We propose an unsupervised ensemble model of Bayesian change point detection to predict sleep and wake-up times. Then, we validate our approach using ground truth from a user study in campus dormitories and a private home. Our results find WiSleep outperforming established methods for users with irregular sleep patterns while yielding comparable accuracy for regular sleepers with an average 79.5% accuracy. This is comparable to client-side based methods, albeit utilizing only coarse-graine...
Proceedings of the 18th Conference on Embedded Networked Sensor Systems, 2020
The proliferation of mobile sensing devices due to advances in the Internet of Things has the pot... more The proliferation of mobile sensing devices due to advances in the Internet of Things has the potential to transform the individual-centric health monitoring to community-scaled health monitoring. Contrary to the state-of-the-art mobile health sensing, which focuses on individuals, my research focuses on scaling mobile health technologies to community scale, where we monitor the health of an entire community or population of users. The benefits of adopting community-scale sensing are two folds; firstly, it enables aggregate public health monitoring of large groups which can answer broader health problems; secondly, it improves personalized health monitoring with fine-grain monitoring of individuals.
Proceedings of the Eleventh ACM International Conference on Future Energy Systems, 2020
With a rampant increase in the urban population, especially in megacities, the number of high ris... more With a rampant increase in the urban population, especially in megacities, the number of high rise buildings is increasing rapidly. Both high rise buildings and lifestyle changes have resulted in high energy consumption. Heating, Ventilation, and Air Conditioning (HVAC) contribute the most to energy consumption in high-rise buildings. As thermal comfort is the major driving factor for the functioning of HVAC systems in a space, it is essential to understand how indoor environmental conditions vary across buildings' dimensions. Traditional approaches rely on simulations to understand the spatial and temporal variations of indoor conditions. Visualization offers opportunities to find solutions for complex thermal variations in buildings because of variation in environmental conditions owing to orientation, height, etc. In this paper, we adopt a data-driven approach that considers the difference in indoor temperature depending on the floor level in a building. Temperature sensors kept on different floors in a building lead to real-time observations. The visualization from Open source Visualization Platform' (Grafana) revealed interesting variations in temperature at different floors of a high-rise building, based on which recommendations could be made to reduce energy consumption.
Proceedings of the Ninth International Conference on Future Energy Systems, 2018
Power shortage is a serious issue in developing nations. During periods of high demand, utilities... more Power shortage is a serious issue in developing nations. During periods of high demand, utilities need to motivate the consumers to curtail their consumption for maintaining grid stability and avoiding blackouts or brownouts. Identification of suitable candidates is essential for such events, as the budget set aside by utilities for Demand Response (DR) events for providing incentives to the consumers should not exceed the added production cost due to peaks. Similarly, from the consumers' point of view, participation comes with the compromise to their convenience. Hence, the selection criteria should be such that it minimizes the peaking cost to the utility without affecting consumer comfort. In this paper, we present SmarDeR, a smart DR consumer selection strategy which considers several factors and consolidates them into a single function which can work in different modes to strategically choose the candidates for the DR event based on the goals specified by the utility. We evaluate different policies and metrics for approaching the right consumers for participating in the DR events. Thereby, we can maintain a fair distribution of requests among the most relevant and reliable users. Experiments with smart-meter data from apartments in our campus demonstrates the effectiveness of our SmarDeR approach.
2016 International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), 2016
In modern days security issues play a vital and integral part of information technology and its r... more In modern days security issues play a vital and integral part of information technology and its related applications such as ATM and smart cards. Cryptography has evolved as a important element of security process. Elliptic curve cryptography is used to develop a variety of scheme for security purpose. Point addition and point doubling arithmetic used in elliptic curve is applicable for prime field. When same arithmetic performs over extension field it increases the complexity of the application but enhances the security in the field of communication technology. This paper communicates Weierstrass equation as the root of elliptic curve. Also described the group operation on elliptic curve that is point addition and point doubling used for encryption application based on prime field Fp. The proposed work is based on elliptic curve group operations solved in extension field Fp2. This new approach is verified using System for Algebra and Geometry and Experimentation (SAGE) open source software.
ArXiv, 2021
Federated Learning (FL) is a concept first introduced by Google in 2016, in which multiple device... more Federated Learning (FL) is a concept first introduced by Google in 2016, in which multiple devices collaboratively learn a machine learning model without sharing their private data under the supervision of a central server. This offers ample opportunities in critical domains such as healthcare, finance etc, where it is risky to share private user information to other organisations or devices. While FL appears to be a promising Machine Learning (ML) technique to keep the local data private, it is also vulnerable to attacks like other ML models. Given the growing interest in the FL domain, this report discusses the opportunities and challenges in federated learning.