http://repository.iiitd.edu.in/xmlui/handle/123456789/123 Sat, 20 Jun 2026 08:44:10 GMT 2026-06-20T08:44:10Z http://repository.iiitd.edu.in/xmlui/handle/123456789/197 Title: An smartphone-based algorithm to measure and model quantity of sleep Authors: Gautam, Alvika; Naik, Vinayak; Gupta, Archie; Sharma, SK Abstract: Sleep quantity affects an individual’s personal health. The gold standard of measuring sleep and diagnosing sleep disorders is Polysomnography (PSG). Although PSG is accurate, it is expensive and it lacks portability. A number of wearable devices with embedded sensors have emerged in the recent past as an alternative to PSG for regular sleep monitoring directly by the user. These devices are intrusive and cause discomfort besides being expensive. In this work, we present an algorithm to detect sleep using a smartphone with the help of its inbuilt accelerometer sensor. We present three different approaches to classify raw acceleration data into two states - Sleep and Wake. In the first approach, we take an equation from Kushida’s algorithm to process accelerometer data. Henceforth, we call it Kushida’s equation. While the second is based on statistical functions, the third is based on Hidden Markov Model (HMM) training. Although all the three approaches are suitable for a phone’s resources, each approach demands different amount of resources. While Kushida’s equation-based approach demands the least, the HMM training-based approach demands the maximum. We collected data from mobile phone’s accelerometer for four subjects for twelve days each. We compare accuracy of sleep detection using each of the three approaches with that of Zeo sensor, which is based on Electroencephalogram (EEG) sensor to detect sleep. EEG is an important modality in PSG. We find that HMM training-based approach is as much as 84% accurate. It is 15% more accurate as compared to Kushida’s equation-based approach and 10% more accurate as compared to statistical method-based approach. In order to concisely represent the sleep quality of people, we model their sleep data using HMM. We present an analysis to find out a tradeoff between the amount of training data and the accuracy provided in the modeling of sleep. We find that six days of sleep data is sufficient for accurate modeling. We compare accuracy of our HMM trainingbased algorithm with a representative third party app SleepTime available from Google Play Store for Android. We find that the detection done using HMM approach is closer to that done by Zeo by 13% as compared to the third party Android application SleepTime. We show that our HMM training-based approach is efficient as it takes less than ten seconds to get executed on Moto G Android phone. Wed, 17 Sep 2014 08:14:38 GMT http://repository.iiitd.edu.in/xmlui/handle/123456789/197 2014-09-17T08:14:38Z http://repository.iiitd.edu.in/xmlui/handle/123456789/196 Title: ACCORD : an analytical cache contention model using reuse distances for modern multiprocessors Authors: Hemani, Rakhi; Banerjee, Subhasis; Guha, Apala Abstract: Simultaneous execution of multiple threads on multicores is necessary for good resource utilization. However, such utilization calls for accurate models to predict the impact on performance due to contention of shared resources, primarily the last level cache and memory. The major challenges in developing such a model for commercial multicore machines are the unavailability of cache implementation details and the scalability of the performance prediction model for multiple threads. In this paper we propose a cache contention model addressing both these challenges. We leverage observed cache behaviour and reuse distance profile of applications for this purpose. We implement our model on a Xeon Sandy Bridge multicore and observe an RMS error of less than 0.06, for single threaded and multi-threaded workloads. Further we compare the effectiveness of using ACCORD model against the popular LRU Model and find that ACCORD is upto 2.7 times more accurate. Mon, 15 Sep 2014 10:56:05 GMT http://repository.iiitd.edu.in/xmlui/handle/123456789/196 2014-09-15T10:56:05Z http://repository.iiitd.edu.in/xmlui/handle/123456789/160 Title: Consumer privacy and targeted pricing with stochastic valuations Authors: Mishra, Shreemoy Abstract: I study the market for consumer information. Firms cannot commit to privacy, so buyers anticipate disclosure of purchase history for targeted pricing. In the literature, strategic rejections of informative o ers make purchase data worthless, which is paradoxical given the large investments in data analytics. I show that buyers' uncertainty regarding future preferences allows full separation of types, leading to valuable purchase data. Buyers of any given type are assumed to share similar expectations about the evolution of future valuations. Preference uncertainty generates consumer-to-consumer externalities, which is why strategic consumers are sometimes better o when they remain unaware of targeted pricing. When preferences are transitory, rms have an incentive to raise consumer awareness about targeted pricing. Wed, 16 Jul 2014 11:30:00 GMT http://repository.iiitd.edu.in/xmlui/handle/123456789/160 2014-07-16T11:30:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/138 Title: Face anti-spoofing via motion magnification and multifeature videolet aggregation Authors: Bharadwaj, Samarth; Dhamecha, Tejas I; Vatsa, Mayank; Singh, Richa Abstract: For robust face biometrics, a reliable anti-spoofing approach has become an essential pre-requisite against attacks. While spoofing attacks are possible with any biometric modality, face spoofing attacks are relatively easy which makes facial biometrics especially vulnerable. This paper presents a new framework for face spoofing detection in videos using motion magnification and multifeature evidence aggregation in a windowed fashion. Micro- and macro- facial expressions commonly exhibited by subjects are first magnified using Eulerian motion magnification. Next, two feature extraction algorithms, a configuration of local binary pattern and motion estimation using histogram of oriented optical flow, are used to encode texture and motion (liveness) properties respectively. Multifeature windowed videolet aggregation of these two orthogonal features, coupled with support vector machine classification provides robustness to different attacks. The proposed approach is evaluated and compared with existing algorithms on publicly available Print Attack, Replay Attack, and CASIA-FASD databases. The proposed algorithm yields state-of-the-art performance and robust generalizability with low computational complexity. Tue, 03 Jun 2014 05:50:38 GMT http://repository.iiitd.edu.in/xmlui/handle/123456789/138 2014-06-03T05:50:38Z