Matching Items (15)
Filtering by
- All Subjects: artificial intelligence
- All Subjects: Information Theory
- Creators: Berisha, Visar
- Resource Type: Text
Description
Spectral congestion is quickly becoming a problem for the telecommunications sector. In order to alleviate spectral congestion and achieve electromagnetic radio frequency (RF) convergence, communications and radar systems are increasingly encouraged to share bandwidth. In direct opposition to the traditional spectrum sharing approach between radar and communications systems of complete isolation (temporal, spectral or spatial), both systems can be jointly co-designed from the ground up to maximize their joint performance for mutual benefit. In order to properly characterize and understand cooperative spectrum sharing between radar and communications systems, the fundamental limits on performance of a cooperative radar-communications system are investigated. To facilitate this investigation, performance metrics are chosen in this dissertation that allow radar and communications to be compared on the same scale. To that effect, information is chosen as the performance metric and an information theoretic radar performance metric compatible with the communications data rate, the radar estimation rate, is developed. The estimation rate measures the amount of information learned by illuminating a target. With the development of the estimation rate, standard multi-user communications performance bounds are extended with joint radar-communications users to produce bounds on the performance of a joint radar-communications system. System performance for variations of the standard spectrum sharing problem defined in this dissertation are investigated, and inner bounds on performance are extended to account for the effect of continuous radar waveform optimization, multiple radar targets, clutter, phase noise, and radar detection. A detailed interpretation of the estimation rate and a brief discussion on how to use these performance bounds to select an optimal operating point and achieve RF convergence are provided.
ContributorsChiriyath, Alex Rajan (Author) / Bliss, Daniel W (Thesis advisor) / Cochran, Douglas (Committee member) / Kosut, Oliver (Committee member) / Richmond, Christ D (Committee member) / Arizona State University (Publisher)
Created2018
Description
In the past few decades, there has been a remarkable shift in the boundary between public and private information. The application of information technology and electronic communications allow service providers (businesses) to collect a large amount of data. However, this ``data collection" process can put the privacy of users at risk and also lead to user reluctance in accepting services or sharing data. This dissertation first investigates privacy sensitive consumer-retailers/service providers interactions under different scenarios, and then focuses on a unified framework for various information-theoretic privacy and privacy mechanisms that can be learned directly from data.
Existing approaches such as differential privacy or information-theoretic privacy try to quantify privacy risk but do not capture the subjective experience and heterogeneous expression of privacy-sensitivity. The first part of this dissertation introduces models to study consumer-retailer interaction problems and to better understand how retailers/service providers can balance their revenue objectives while being sensitive to user privacy concerns. This dissertation considers the following three scenarios: (i) the consumer-retailer interaction via personalized advertisements; (ii) incentive mechanisms that electrical utility providers need to offer for privacy sensitive consumers with alternative energy sources; (iii) the market viability of offering privacy guaranteed free online services. We use game-theoretic models to capture the behaviors of both consumers and retailers, and provide insights for retailers to maximize their profits when interacting with privacy sensitive consumers.
Preserving the utility of published datasets while simultaneously providing provable privacy guarantees is a well-known challenge. In the second part, a novel context-aware privacy framework called generative adversarial privacy (GAP) is introduced. Inspired by recent advancements in generative adversarial networks, GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrained minimax game between a privatizer and an adversary. For appropriately chosen adversarial loss functions, GAP provides privacy guarantees against strong information-theoretic adversaries. Both synthetic and real-world datasets are used to show that GAP can greatly reduce the adversary's capability of inferring private information at a small cost of distorting the data.
Existing approaches such as differential privacy or information-theoretic privacy try to quantify privacy risk but do not capture the subjective experience and heterogeneous expression of privacy-sensitivity. The first part of this dissertation introduces models to study consumer-retailer interaction problems and to better understand how retailers/service providers can balance their revenue objectives while being sensitive to user privacy concerns. This dissertation considers the following three scenarios: (i) the consumer-retailer interaction via personalized advertisements; (ii) incentive mechanisms that electrical utility providers need to offer for privacy sensitive consumers with alternative energy sources; (iii) the market viability of offering privacy guaranteed free online services. We use game-theoretic models to capture the behaviors of both consumers and retailers, and provide insights for retailers to maximize their profits when interacting with privacy sensitive consumers.
Preserving the utility of published datasets while simultaneously providing provable privacy guarantees is a well-known challenge. In the second part, a novel context-aware privacy framework called generative adversarial privacy (GAP) is introduced. Inspired by recent advancements in generative adversarial networks, GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrained minimax game between a privatizer and an adversary. For appropriately chosen adversarial loss functions, GAP provides privacy guarantees against strong information-theoretic adversaries. Both synthetic and real-world datasets are used to show that GAP can greatly reduce the adversary's capability of inferring private information at a small cost of distorting the data.
ContributorsHuang, Chong (Author) / Sankar, Lalitha (Thesis advisor) / Kosut, Oliver (Committee member) / Nedich, Angelia (Committee member) / Ying, Lei (Committee member) / Arizona State University (Publisher)
Created2018
Description
Deep neural networks (DNN) have shown tremendous success in various cognitive tasks, such as image classification, speech recognition, etc. However, their usage on resource-constrained edge devices has been limited due to high computation and large memory requirement.
To overcome these challenges, recent works have extensively investigated model compression techniques such as element-wise sparsity, structured sparsity and quantization. While most of these works have applied these compression techniques in isolation, there have been very few studies on application of quantization and structured sparsity together on a DNN model.
This thesis co-optimizes structured sparsity and quantization constraints on DNN models during training. Specifically, it obtains optimal setting of 2-bit weight and 2-bit activation coupled with 4X structured compression by performing combined exploration of quantization and structured compression settings. The optimal DNN model achieves 50X weight memory reduction compared to floating-point uncompressed DNN. This memory saving is significant since applying only structured sparsity constraints achieves 2X memory savings and only quantization constraints achieves 16X memory savings. The algorithm has been validated on both high and low capacity DNNs and on wide-sparse and deep-sparse DNN models. Experiments demonstrated that deep-sparse DNN outperforms shallow-dense DNN with varying level of memory savings depending on DNN precision and sparsity levels. This work further proposed a Pareto-optimal approach to systematically extract optimal DNN models from a huge set of sparse and dense DNN models. The resulting 11 optimal designs were further evaluated by considering overall DNN memory which includes activation memory and weight memory. It was found that there is only a small change in the memory footprint of the optimal designs corresponding to the low sparsity DNNs. However, activation memory cannot be ignored for high sparsity DNNs.
To overcome these challenges, recent works have extensively investigated model compression techniques such as element-wise sparsity, structured sparsity and quantization. While most of these works have applied these compression techniques in isolation, there have been very few studies on application of quantization and structured sparsity together on a DNN model.
This thesis co-optimizes structured sparsity and quantization constraints on DNN models during training. Specifically, it obtains optimal setting of 2-bit weight and 2-bit activation coupled with 4X structured compression by performing combined exploration of quantization and structured compression settings. The optimal DNN model achieves 50X weight memory reduction compared to floating-point uncompressed DNN. This memory saving is significant since applying only structured sparsity constraints achieves 2X memory savings and only quantization constraints achieves 16X memory savings. The algorithm has been validated on both high and low capacity DNNs and on wide-sparse and deep-sparse DNN models. Experiments demonstrated that deep-sparse DNN outperforms shallow-dense DNN with varying level of memory savings depending on DNN precision and sparsity levels. This work further proposed a Pareto-optimal approach to systematically extract optimal DNN models from a huge set of sparse and dense DNN models. The resulting 11 optimal designs were further evaluated by considering overall DNN memory which includes activation memory and weight memory. It was found that there is only a small change in the memory footprint of the optimal designs corresponding to the low sparsity DNNs. However, activation memory cannot be ignored for high sparsity DNNs.
ContributorsSrivastava, Gaurav (Author) / Seo, Jae-Sun (Thesis advisor) / Chakrabarti, Chaitali (Committee member) / Berisha, Visar (Committee member) / Arizona State University (Publisher)
Created2018
Description
With advances in automatic speech recognition, spoken dialogue systems are assuming increasingly social roles. There is a growing need for these systems to be socially responsive, capable of building rapport with users. In human-human interactions, rapport is critical to patient-doctor communication, conflict resolution, educational interactions, and social engagement. Rapport between people promotes successful collaboration, motivation, and task success. Dialogue systems which can build rapport with their user may produce similar effects, personalizing interactions to create better outcomes.
This dissertation focuses on how dialogue systems can build rapport utilizing acoustic-prosodic entrainment. Acoustic-prosodic entrainment occurs when individuals adapt their acoustic-prosodic features of speech, such as tone of voice or loudness, to one another over the course of a conversation. Correlated with liking and task success, a dialogue system which entrains may enhance rapport. Entrainment, however, is very challenging to model. People entrain on different features in many ways and how to design entrainment to build rapport is unclear. The first goal of this dissertation is to explore how acoustic-prosodic entrainment can be modeled to build rapport.
Towards this goal, this work presents a series of studies comparing, evaluating, and iterating on the design of entrainment, motivated and informed by human-human dialogue. These models of entrainment are implemented in the dialogue system of a robotic learning companion. Learning companions are educational agents that engage students socially to increase motivation and facilitate learning. As a learning companion’s ability to be socially responsive increases, so do vital learning outcomes. A second goal of this dissertation is to explore the effects of entrainment on concrete outcomes such as learning in interactions with robotic learning companions.
This dissertation results in contributions both technical and theoretical. Technical contributions include a robust and modular dialogue system capable of producing prosodic entrainment and other socially-responsive behavior. One of the first systems of its kind, the results demonstrate that an entraining, social learning companion can positively build rapport and increase learning. This dissertation provides support for exploring phenomena like entrainment to enhance factors such as rapport and learning and provides a platform with which to explore these phenomena in future work.
This dissertation focuses on how dialogue systems can build rapport utilizing acoustic-prosodic entrainment. Acoustic-prosodic entrainment occurs when individuals adapt their acoustic-prosodic features of speech, such as tone of voice or loudness, to one another over the course of a conversation. Correlated with liking and task success, a dialogue system which entrains may enhance rapport. Entrainment, however, is very challenging to model. People entrain on different features in many ways and how to design entrainment to build rapport is unclear. The first goal of this dissertation is to explore how acoustic-prosodic entrainment can be modeled to build rapport.
Towards this goal, this work presents a series of studies comparing, evaluating, and iterating on the design of entrainment, motivated and informed by human-human dialogue. These models of entrainment are implemented in the dialogue system of a robotic learning companion. Learning companions are educational agents that engage students socially to increase motivation and facilitate learning. As a learning companion’s ability to be socially responsive increases, so do vital learning outcomes. A second goal of this dissertation is to explore the effects of entrainment on concrete outcomes such as learning in interactions with robotic learning companions.
This dissertation results in contributions both technical and theoretical. Technical contributions include a robust and modular dialogue system capable of producing prosodic entrainment and other socially-responsive behavior. One of the first systems of its kind, the results demonstrate that an entraining, social learning companion can positively build rapport and increase learning. This dissertation provides support for exploring phenomena like entrainment to enhance factors such as rapport and learning and provides a platform with which to explore these phenomena in future work.
ContributorsLubold, Nichola Anne (Author) / Walker, Erin (Thesis advisor) / Pon-Barry, Heather (Thesis advisor) / Litman, Diane (Committee member) / VanLehn, Kurt (Committee member) / Berisha, Visar (Committee member) / Arizona State University (Publisher)
Created2018
Description
Speech nasality disorders are characterized by abnormal resonance in the nasal cavity. Hypernasal speech is of particular interest, characterized by an inability to prevent improper nasalization of vowels, and poor articulation of plosive and fricative consonants, and can lead to negative communicative and social consequences. It can be associated with a range of conditions, including cleft lip or palate, velopharyngeal dysfunction (a physical or neurological defective closure of the soft palate that regulates resonance between the oral and nasal cavity), dysarthria, or hearing impairment, and can also be an early indicator of developing neurological disorders such as ALS. Hypernasality is typically scored perceptually by a Speech Language Pathologist (SLP). Misdiagnosis could lead to inadequate treatment plans and poor treatment outcomes for a patient. Also, for some applications, particularly screening for early neurological disorders, the use of an SLP is not practical. Hence this work demonstrates a data-driven approach to objective assessment of hypernasality, through the use of Goodness of Pronunciation features. These features capture the overall precision of articulation of speaker on a phoneme-by-phoneme basis, allowing demonstrated models to achieve a Pearson correlation coefficient of 0.88 on low-nasality speakers, the population of most interest for this sort of technique. These results are comparable to milestone methods in this domain.
ContributorsSaxon, Michael Stephen (Author) / Berisha, Visar (Thesis director) / McDaniel, Troy (Committee member) / Electrical Engineering Program (Contributor, Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
Information divergence functions, such as the Kullback-Leibler divergence or the Hellinger distance, play a critical role in statistical signal processing and information theory; however estimating them can be challenge. Most often, parametric assumptions are made about the two distributions to estimate the divergence of interest. In cases where no parametric model fits the data, non-parametric density estimation is used. In statistical signal processing applications, Gaussianity is usually assumed since closed-form expressions for common divergence measures have been derived for this family of distributions. Parametric assumptions are preferred when it is known that the data follows the model, however this is rarely the case in real-word scenarios. Non-parametric density estimators are characterized by a very large number of parameters that have to be tuned with costly cross-validation. In this dissertation we focus on a specific family of non-parametric estimators, called direct estimators, that bypass density estimation completely and directly estimate the quantity of interest from the data. We introduce a new divergence measure, the $D_p$-divergence, that can be estimated directly from samples without parametric assumptions on the distribution. We show that the $D_p$-divergence bounds the binary, cross-domain, and multi-class Bayes error rates and, in certain cases, provides provably tighter bounds than the Hellinger divergence. In addition, we also propose a new methodology that allows the experimenter to construct direct estimators for existing divergence measures or to construct new divergence measures with custom properties that are tailored to the application. To examine the practical efficacy of these new methods, we evaluate them in a statistical learning framework on a series of real-world data science problems involving speech-based monitoring of neuro-motor disorders.
ContributorsWisler, Alan (Author) / Berisha, Visar (Thesis advisor) / Spanias, Andreas (Thesis advisor) / Liss, Julie (Committee member) / Bliss, Daniel (Committee member) / Arizona State University (Publisher)
Created2017
Description
RF convergence of radar and communications users is rapidly becoming an issue for a multitude of stakeholders. To hedge against growing spectral congestion, research into cooperative radar and communications systems has been identified as a critical necessity for the United States and other countries. Further, the joint sensing-communicating paradigm appears imminent in several technological domains. In the pursuit of co-designing radar and communications systems that work cooperatively and benefit from each other's existence, joint radar-communications metrics are defined and bounded as a measure of performance. Estimation rate is introduced, a novel measure of radar estimation information as a function of time. Complementary to communications data rate, the two systems can now be compared on the same scale. An information-centric approach has a number of advantages, defining precisely what is gained through radar illumination and serves as a measure of spectral efficiency. Bounding radar estimation rate and communications data rate jointly, systems can be designed as a joint optimization problem.
ContributorsPaul, Bryan (Author) / Bliss, Daniel W. (Thesis advisor) / Berisha, Visar (Committee member) / Kosut, Oliver (Committee member) / Tepedelenlioğlu, Cihan (Committee member) / Arizona State University (Publisher)
Created2017
Description
This work details the bootstrap estimation of a nonparametric information divergence measure, the Dp divergence measure, using a power law model. To address the challenge posed by computing accurate divergence estimates given finite size data, the bootstrap approach is used in conjunction with a power law curve to calculate an asymptotic value of the divergence estimator. Monte Carlo estimates of Dp are found for increasing values of sample size, and a power law fit is used to relate the divergence estimates as a function of sample size. The fit is also used to generate a confidence interval for the estimate to characterize the quality of the estimate. We compare the performance of this method with the other estimation methods. The calculated divergence is applied to the binary classification problem. Using the inherent relation between divergence measures and classification error rate, an analysis of the Bayes error rate of several data sets is conducted using the asymptotic divergence estimate.
ContributorsKadambi, Pradyumna Sanjay (Author) / Berisha, Visar (Thesis director) / Bliss, Daniel (Committee member) / Electrical Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Divergence functions are both highly useful and fundamental to many areas in information theory and machine learning, but require either parametric approaches or prior knowledge of labels on the full data set. This paper presents a method to estimate the divergence between two data sets in the absence of fully labeled data. This semi-labeled case is common in many domains where labeling data by hand is expensive or time-consuming, or wherever large data sets are present. The theory derived in this paper is demonstrated on a simulated example, and then applied to a feature selection and classification problem from pathological speech analysis.
ContributorsGilton, Davis Leland (Author) / Berisha, Visar (Thesis director) / Cochran, Douglas (Committee member) / Electrical Engineering Program (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Lossy compression is a form of compression that slightly degrades a signal in ways that are ideally not detectable to the human ear. This is opposite to lossless compression, in which the sample is not degraded at all. While lossless compression may seem like the best option, lossy compression, which is used in most audio and video, reduces transmission time and results in much smaller file sizes. However, this compression can affect quality if it goes too far. The more compression there is on a waveform, the more degradation there is, and once a file is lossy compressed, this process is not reversible. This project will observe the degradation of an audio signal after the application of Singular Value Decomposition compression, a lossy compression that eliminates singular values from a signal’s matrix.
ContributorsHirte, Amanda (Author) / Kosut, Oliver (Thesis director) / Bliss, Daniel (Committee member) / Electrical Engineering Program (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2021-05