Abstract

The non invasive measurement of chromophores in blood is in great need for diagnosis of major health hazards. Frequent monitoring of blood glucose levels, along with blood urea will allow early detection of diabetes, liver dysfunction and renal diseases. The non invasive instrument used for accomplishing these tasks must meet several criteria like, accuracy and precision of the measurement. Many efforts have been made by many research groups all over the world in making the procedure as much less invasive as possible by trying to reduce the blood drawn for test to micro liters or by reducing the cross sectional area of the suction needle. The device should be portable, low-cost and reliable overtime. There are many modes of diagnosis that satisfy these criteria but most of them are still in a developmental stage. Although many methods have been proposed and are available in literature, near infrared (NIR) spectroscopy has the advantage of meeting these rigorous demands.Initially, based on the intrinsic property of the analyte molecule, the NIR spectroscopy has been carried out and the wavelength of peak absorption has been identified. Using the identified wavelength a finger clip comprising of sensor and detector has been developed for collecting the in vivo PPG (photoplethsymograph) signals. These non invasive signals are used for estimating the concentration of specific blood analyte. Various statistical techniques have been used for carrying out the calibration of the in vivo signals obtained from the photoplethsymograph based sensing circuit. Secondly, these signals are calibrated using artificial neural networks to predict the analyte concentration. As typical blood analytes, blood glucose and urea are used to establish the proposed methodology to noninvasively estimate the blood parameters. Altogether 282 patients were available for measurement of glucose out of which for 100 samples the reference values are measured using Accucheck glucometer and for remaining 182 samples the reference values are measured using traditional lab based method. For the first 100 samples the testing has been carried out after taking informed consent from patients out of which 50 patient data have been used for training the neural networks and testing has been carried out on remaining 50 patients. The training of neural networks has been done offline using MATLAB and then implemented on FPGA to minimize the design circuitry. For estimating the concentration of urea in blood, samples are collected from total of 70 patients. For this invasive urea measurement is carried out using lab based method. For estimating the blood glucose concentration, the data has been calibrated using two types of neural network architectures conventional neuron model and the inverse delayed (ID) neuron model and the results are compared. It is found that the mean square error in estimating the glucose concentration was found to be 1.89mg/dL using ID function model of neuron as against 5.48mg/dL using conventional neuron model with 10 neurons in hidden layer for each model. In a similar way the blood urea concentration has been estimated and the mean square error is found to be 2.23mg/dL. For measuring the blood urea concentration, the artificial neural network based regression analysis has been carried out. However, different components in blood, although having different absorption spectrum, there is some overlap between absorption spectra of different components. Hence the photoplethsymography output is subjected to different statistical techniques like artificial neural networks(ANN), principal component analysis(PCA). Finally, an attempt has been made to identify the optimal orientation of optode pair with respect to the skin surface using Rayleigh Rice Vector Pertubation Surface Scattering theory, surface roughness models for skin surface roughness have been created and optimal orientation of the optode pair with the skin surface has been theoritically estimated. The results of the theoritical estimation has also been suitably verified with the help of experiments both in the case of reflective and transmissive photoplethsymography.

Abstract

Advertisements (ads) are often filled with strong affective content covering a gamut of emotions intended to capture viewer attention and attempt to convey an effective message. However, most approaches to computationally analyze the emotion present in ads are based on the text modality and only a limited amount of work has been done on affective understanding of advertisements videos from the content and user-centric perspectives. This work attempts to bring together recent advances in deep learning (especially in the domain of visual recognition) and affective computing, and use them to perform affect estimation of advertisements. We first create a dataset of 100 ads which are annotated by 5 experts and are evenly distributed over the valence-arousal plane. We then perform content-based affect recognition via a transfer learning based approach to estimate the affective content in this dataset using prior affective knowledge gained from a large annotated movie dataset. We employ both visual features from video frames and audio features from spectrograms to train our deep neural networks. This approach vastly outperforms the existing benchmark. It is also very interesting to see how human physiological signals, such as that captured by Electroencephalography (EEG) data are able to provide useful affective insights into the content from a user-centric perspective. Using this time series data of the electrical activity of the brain, we train models which are able to classify the emotional dimensions of this data. This also enables us to benchmark this user-centric performance and compare it to the content-centric deep learning based models, and we find that the user-centric models outperform the content-centric models, and set the state-of-the-art in ad affect recognition. We also combine the two kinds of modalities (audiovisual and EEG) using decision fusion and find that the fusion performance is greater than either single modality, which shows that human physiological signals and the audiovisual content contain complementary affective information. We also use multi task learning (MTL) on top of the features of each kind to exploit the intrinsic relatedness of the data and boost the performance. Lastly, we validate the hypothesis of better affect estimation being able to enhance a real world application by supplying the affective values computed by our methods to a computational advertising framework to get a video program sequence with ads inserted at emotionally relevant points, determined to be appropriate based on the affective relevance between the the program content and the ads. Multiple user studies find that our methods significantly outperform the existing algorithms and are very close (and sometimes better than) human level performance. We are able to achieve much more emotionally relevant and non disruptive advertisement insertion into a program video stream. In summary, this work (1) compiles an affective ad dataset capable of evoking coherent emotions across users; (2) explores the efficacy of content-centric convolutional neural network (CNN) features for affect recognition (AR), and find that CNN features outperform low level audio-visual descriptors; (3) study user-centric ad affect recognition from Electroencephalogram (EEG) responses (with conventional classifiers as well as a novel CNN architecture for EEG) acquired while viewing the content that outperform content descriptors; (4) Examine a multi-task learning framework based on CNN and EEG features which provides state of the art AR from ads; (5) Demonstrates how better affect predictions facilitates more effective computational advertising in a real world application.

Abstract

In recent years, Internet connected devices have increased signicantly. Technologies such as Internet of Things and Cloud Computing are enabling more and more devices to connect to the Internet. With rise in number of Internet connected devices, new computational paradigms such as Edge computing and Fog Computing are emerging. People are even voluntarily providing their Internet connected devices for computation and storage. These connected devices are not only communicating with the central cloud resource, but also with other connected devices using variety of protocols. All these changes are making the network infrastructure very complex, dense and heterogeneous. In this dynamically altering and growing scenario, existing traditional network infrastructures are inadequate. To fulfill the growing data requirements, the network service providers need to update the infrastructure hardware and software parameters dynamically. They need to manage co-operation, co-ordination and co-existence among diverse network types. For this, novel self configuring resource management techniques are required. Networks built on foundations of software defined paradigm provide the solution for above mentioned challenges. In this direction, we have presented novel methods for allocating resources at different levels of network infrastructure. In the rst part, computational resources optimization for IoT devices has been done. IoT device density is increasing and current philosophy of processing requests at cloud is not appropriate for emerging IoT domains such as health care and real time control. We have considered to use variety of devices available at the network access layer. This includes the devices voluntarily given by users, dedicated edge servers and cloud infrastructure. The proposed system learns the optimal operating parameters during initial runs. Using the knowledge acquired in the learning phase, an integer linear programming problem is formulated to minimize the mean time to complete the request for all the IoT nodes. The solution of the formulated problem provides fair resource allocation for all the IoT nodes. Later, considering the unreliable nature of the voluntary devices, the learning and formulation has been extended to incorporate probability of failure of these devices. A multi-objective optimization problem has been formulated and solved using Genetic algorithm. Second part covers the economic way to configure the physical infrastructure of a software defined wireless network (SDWN). In a SDWN, the radio units can be configured dynamically. This feature gives the flexibility to change the operating parameters on the go. Resources can be allocated dynamically as per operating conditions. Utilizing these features, cost effective way to configure access layer of modern network is presented. An integer linear programming problem, with objective of cost minimization and indirect quality of service constraints, has been formulated and solved. In the third part, we have looked into the problems related to time optimization in spectrum sensing. As it is expected to have dense populated wireless IoT devices, spectrum must be utilized effectively. In a SDWN, the signal processing happens in software. It gives an opportunity to perform spectrum sensing in software using innovative ways. In our approach, the historical occupancy records of the channels are considered for sensing time allocation. The problem is formulated and solved using integer linear programming with special practical constraints. The problem is also formulated using quadratic programming method and interesting observations have been presented.

Abstract

Text-to-speech (TTS) synthesis is typically carried out in two ways: (1) By concatenating waveform segments of units (often dubbed unit selection synthesis (USS)) and (2) By predicting speech parameters from text using statistical models (also called statistical parametric speech synthesis systems (SPSS)). Most commercial TTS systems use USS approach as it produces highly natural speech. However, the USS approach requires the recorded waveforms to be stored which demands memory, but the statistical approach alleviates this by modeling the speech compactly in a parametric form. Also, using the waveform directly offers little scope to alter the characteristics to produce different varieties like speakers, genders, voice-qualities, languages, etc. On the other hand, the parameters of a statistical model can be suitably transformed to produce the desired variations. The above advantages (compactness and flexibility) come at the cost of the speech sounding slightly robotic than the unit-selection counter-part. A typical SPSS system has several components namely text feature extraction, speech parameter extraction, aligning text and speech features, a text feature-to-speech parameter regression model and a duration prediction model. Each of these components are independently hand-engineered making the SPSS system susceptible to errors in any one of them. The loss in naturalness of SPSS output has been majorly attributed to the limitations of the regression model (also dubbed acoustic model) to capture the complexity of mapping from text features to speech parameters and the representations used for text and speech data. In addition, the use of separate alignment model leads to erroneous averaging in acoustic modeling. In this thesis, we address the issues of acoustic modeling, textual representation, acoustic representation, multilingual multispeaker synthesis and end-to-end synthesis with implicit text feature extraction and alignment model within the SPSS framework. Techniques developed to address these issues include the use of recurrent neural networks for acoustic modeling, contextual representation using hidden layeroutput, unit-level acoustic representation using recurrent auto-encoder, language and speaker codes, and windowing based attention modeling for end-to-end synthesis using sequence-to-sequence (seq2seq) neural networks. The major conclusions of this thesis work are: • Recurrent neural networks improve the acoustic modeling by capturing required amount of context and generating smooth parameter trajectories than the deep neural network based SPSS. • Speaker and language codes can be used to build multilingual and multispeaker synthesizer using single recurrent neural network. Building a single model for multiple languages and speakers offers a compact model which is also capable of polyglot synthesis. • A unit-level acoustic representation can be derived using a seq2seq auto-encoder. This representation is also useful in building a unit-level SPSS. • An end-to-end TTS system can be trained from characters to speech waveform directly using seq2seq with attention model. As a result, much of the hand-engineered components of SPSS system can be substituted by a single seq2seq neural network thereby reducing the effect of independent errors.

Abstract

Advances in medical field and imaging systems have resulted in a series of devices that sense, record, transform and process digital data. In the case of human eyes this digital data is fundus images, which are images of the back part of our retina. Automatic analysis of these images is required to process large amount of data and help doctors make the final diagnosis. Retina images has 3 major visible landmarks: Optic disk(OD), macula and blood vessels. In retina images, OD appears as a bright elliptical structure, macula appear as a small dark region and blood vessel appears as dark tree branch like structure. In this thesis, we have proposed methods for detection of retina landmarks. Accurate detection of OD and macula is important as computer assisted diagnosis systems uses location of these landmarks for understanding the retina image and using clinical facts about retina for improving diagnosis. Retina landmark detection also aids in assessing the severity of diseases based on the locations of abnormalities relative to these landmarks. We first used retina atlas for OD and macula detection. The idea of retina atlas is inspired by brain 3D atlas [34]. We create 2 retina atlases: intensity atlas and probability atlas, by annotating public datasets locally. We use probabilistic atlas for OD and macula detection but detection rates and accuracy of the system is low. To achieve better detection, we than used Generalized motion patterns(GMP) [14][23] for OD and macula detection. The GMP is derived by inducing motion to an image, which serves to smooth out unwanted information while highlighting the structures of interest. Our GMP based detection is fully unsupervised and its results outperformed all other unsupervised methods. The results are comparable to that of supervised methods. The proposed GMP based system is completely parallelizable and handles illumination differences efficiently. Blood vessels are another important retina landmark and we find that the current research uses evaluation measure like sensitivity, specifity, accuracy, area under curve and matthew correlation coefficient for evaluating vessel segmentation performance. We find several gaps in current evaluation measures and propose local accuracy, which is an extension of [39]. We show that local accuracy is especially useful in settings, where segmentation of weak vessels and accurate estimation of vessel width is required.

Abstract

After the emergence of internet, online advertising has evolved as a major form of advertising in this century. The most important types of online advertising are sponsored search, contextual advertising and banner advertising. Banner advertising or display advertising is one of the predominant modes of online advertising. In this thesis, we present the approaches to improve the performance of display advertising. The three important stakeholders in display advertising are advertiser, publisher and user. The publisher manages the ad space of the website(s) and several advertisers demand ad slots for advertisements. The advertiser aims to reach/spread the ad to the maximum number of targeted users of the website whereas the publisher aims to maximize the revenue by satisfying the demands of increased number of advertisers. The users visit web pages and the corresponding ads. The major issues involved in display advertising scenario are developing efficient approaches (i) for the publisher to meet the demands of the maximum number of advertisers, (ii) to schedule the ads to ad slots of web pages (iii) for auctioning and charging of ad slots (iv) for targeting ads and (v) for managing guaranteed and non-guaranteed contracts. In this thesis, we have made efforts to develop efficient ad allocation approaches for the publisher and a scalable management framework for display ad space management. Firstly, we propose an improved approach for ad slot allocation by exploiting the notion of coverage patterns. In the literature, an approach is proposed to extract the knowledge of coverage patterns from the transactional databases. In the display advertising scenario, we propose an efficient ad slot allocation approach by exploiting the knowledge of coverage patterns extracted from the clickstream transactions. We explore the factors in adapting the knowledge of coverage patterns to benefit display advertising. Using the knowledge of coverage patterns extracted from a website clickstream transactional database, we identify supply of expected user visits to available ad slots of the website. Coverage patterns extracted from website clickstream transactional database contains a set of distinct web pages with corresponding coverage or percentage of users. With this information, we develop an efficient ad slots allocation approach which helps the publisher in selecting appropriate sets of web pages that satisfy coverage demands of advertisers and at the same time reduces repeated display of ads to users of the website. The proposed allocation framework, in addition to the step of extraction of coverage patterns, contains mapping, ranking and allocation steps. The experimental results on both synthetic and real world clickstream datasets show that the proposed approach could meet the demands of increased number of advertisers and reduces the boredom faced by user by reducing the repeated display of advertisements. Secondly, we propose a framework to harvest the pages views of the web. It can be observed that online advertising provides an opportunity for product sellers and service providers to reach customers and has become a key factor in the growth of economy. It is a major source of revenue most importantly for the search engine and social networking sites. Currently, the number of websites registered comes to a billion. Each day, a typical website receives the number of visitors ranging from hundreds to millions. In a few years, the relative association of users with internet as well as the number of websites will grow exponentially. In this context, it is possible for a product seller or service provider to reach every potential customer through display advertising. We propose that rather than managing a single website, the publisher manages the aggregated advertising space of a collection of websites. In this framework, websites can be divided into clusters based on the topic (or any other interesting measure) and the interested publishers can manage the aggregated advertisement space of the cluster. The proposed framework can provide wider opportunity for the publishers to play an active role in connecting the sellers with potential buyers. As a result, the advertisement space could be expanded significantly and it will provide the opportunity for increased number of publishers to market the aggregated advertisement space of millions of websites in an organized way. It will also help in balancing the management of banner advertising market in a transparent and controlled way. Overall, in this thesis we have shown that the knowledge of coverage patterns extracted through clickstream transactions of the websites helps in efficient allocation of available display ad space to advertisers. In addition, we have proposed a scalable plan to exploit the banner advertisement space of the entire web. We hope that the proposed approaches enthuse the ad management companies to adopt and enable sellers to connect with

Abstract

As the largest online encyclopedia, Wikipedia provides a large number of human-edited articles that are linked to named entities. For growing the Wikipedia content, determining whether such entities require their own Wikipedia article and then producing these articles by hand is a laborious task. The limited number of active contributors and the huge time spent in collecting the information and editing is making this manual process slow and difficult. Our thesis presents an automated solution for both determining whether a named-entity warrants its own article in Wikipedia and thereby creating one using a semi-supervised approach. Wikipedia requires a keen investigation about which articles to be included for it to maintain its indispensability. To prevent unnecessary articles from being included, official guidelines of Wikipedia demand these named entities meet “notability” standards for their article inclusion. We investigated automation around notability for named entities by using reliability and entity salience features. Evaluations of our notability determination system provide evidence that our solution can replace the manual decisions made by the reviewers for the inclusion of an article using the notability rules. We also developed a semi-supervised automatic generation of Wikipedia articles as an alternative to its manual creation. A framework was created to generate a Wikipedia article for a named entity, which not only looks similar to other Wikipedia articles in its category but also aggregates the information about diverse aspects related to that named entity from the Web. In particular, a semi-supervised method is used for determining the headings and identifying the content for each heading in the Wikipedia article generated. Additional important contributions here include reducing the manual effort in collecting relevant training data by extracting it from the wiki-dump and increasing the reliability of the content by introducing parameters modeled on the reliability of a site based on existing Wikipedia articles belonging to the same category. Our experiments showed the viability of our solution as an alternative to the previous approaches that used supervised or unsupervised methods. Such an automation for both notability and article creation in Wikipedia can help in paving a path for a future where maintaining consistent growth in the Wikipedia is automatic and requires very little human-interference.

Abstract

The field of computer vision is rapidly expanding and has significantly more processing power and memory today, than in previous decades. Video has become one of the most popular visual media for communication and entertainment. In particular, automatic analysis and understanding the content of a video is one of the long-standing goals of computer vision. One of the fundamental problems is to model the appearance and behavior of the objects in videos. Such models mainly depend on the problem definition. Typically, in many scenarios, the change in problem statement is followed by the changes in the annotation and its complexities. Creating large-scale datasets in this scenario using the manual annotation process is monotonous, time-consuming and non-scalable. In order to address this challenge and strive towards practical large scale annotated video datasets, we investigate methods to autonomously learn and adapt object models using temporal information in videos. Even though the vision community has advanced in field of problem solving but data generation and annotation is still a tough problem. Data annotation is expensive, tedious and involves a lot of human efforts. Even after data annotation, it is essential to validate the goodness of annotations, which again is a tiresome process. To address this problem, we investigate methods to autonomously learn and adapt the object models using temporal information in videos. This involves learning robust representations of the video. The aim of this thesis is two-fold, first we propose solutions for efficient and accurate object annotation mechanisms in video sequences and secondly, to raise awareness in the community about the importance and attention it deserves. As our first contribution, we propose an efficient, scalable and accurate object bounding box annotation method for large scale complex video datasets. We focus on minimizing the annotation efforts simultaneously increasing the annotation propagation accuracy to get a precise and tight bounding box around object of interest. Using a self training approach, we propose a combination of semi-automatic initialization method with an energy minimization framework to propagate the annotations. Using an energy minimization system for segmentation gives accurate and tight bounding boxes around the object. We have quantitatively and qualitatively validated the results on publicly available datasets. In the second half, we propose annotation scheme for human pose in video sequences. The proposed model is based on a fully-automatic initialization, from any generic state-of-the-art method. But the initialization is prone to error due to the challenges in video data type. We exploit the availability of redundant information from the redundant data type. The model is build on the temporal smoothness assumption in videos. We formulate the problem as a sequence-to-sequence learning problem, the architecture uses Long Short Term Memory encoder-decoder model to encode the temporal context and annotate the pose. We show results on state-of-the-art datasets.

Abstract

The objective of a language identification system is to identify the language in a given spoken utterance. Based on the availability of corresponding text to a given utterance, the approach for language identification can either be implicit or explicit. In an implicit case, we only have access to the acoustic signal and statistical models are built over the features extracted from the acoustic signal. In an explicit case, corresponding text is available for the given utterance and rule-based approaches are used to identify the language. This thesis presents an implicit approach based on deep neural network (DNN) models for language identification. DNN models have been recently proposed for the task of language identification. In this thesis, DNN models have been explored in the Indian scenario. While DNN based approach is inherently a frame based one, we propose an attention mechanism based DNN architecture for utterance level classification there by efficiently making use of the context at model level. This approach can be viewed as an alternative to the state-of-the-art Gaussian mixture model based iVector baseline system. On contrary to previously published works using DNNs in LID, DNN equipped with attention mechanism has the advantage of discriminative end-to-end training without any generative component or post-averaging of posterior probabilities obtained at frame level. Several experiments have been performed on a dataset consisting 13 of the official Indian languages with 120 hours of training data. Evaluation of models were performed on 30 hours of testing data with about 2.5 hours for each language. Equal error rate (EER) per language is used as the performance metric. From the results, it is found that the DNN with attention mechanism outperforms the regular DNN and i-vector baseline system indicating the effectiveness of the attention mechanism. Further, a combination of excitation source and vocal tract system features have been explored for the task of language identification. A better performance gain has been achieved by combining the features using a late fusion mechanism. This result indicates the complementary nature of the excitation source information to that of the widely used vocal tract system information.

Abstract

Knowledge of the structure and dynamics of biomolecules is essential for elucidating the underlying mechanisms of biological processes. Given the stochastic nature of many biological processes, like protein unfolding, it’s almost impossible that two independent simulations will generate the exact same sequence of events, which makes direct analysis of simulations difficult. Statistical models like Markov Chains, transition networks etc. help in shedding some light on the mechanistic nature of such processes by predicting long-time dynamics of these systems from short simulations. However, such methods fall short in analyzing trajectories which are oblivious to temporal information, for example, Monte Carlo simulation methods. In this thesis we propose a probabilistic algorithm, borrowing concepts from graph theory and statistical mixture models, to extract folding pathways from molecular dynamic trajectories. A suitable vector representation was chosen to represent each frame in the macromolecular trajectory (as a series of interaction and conformational energies) and dimensionality reduction was performed using principal component analysis (PCA). The trajectory was then clustered using a density-based clustering algorithm, where each cluster represents a metastable state on the potential energy surface (PES) of the biomolecule under study. A graph was created with these clusters as nodes and the most probable path of (un)folding from an initial folded state to a final unfolded state is conceived as the widest path along this graph. We have tested our method on RNA hairpin unfolding trajectory in aqueous urea solution. Our method makes the understanding of the mechanism of unfolding in RNA hairpin molecule more tractable. As this method doesn’t rely on temporal data it can be used to analyze trajectories from Monte Carlo sampling techniques and replica exchange molecular dynamics (REMD). This work is an effort in the direction towards harnessing the full potential of enhanced sampling methods, which until now, is mostly limited to evaluating equilibrium properties of the system