Abstract

Novels are a mine of information stored in a narrative. Detective novels usually have a premise of a culprit and a detective consolidating the evidence. The key ingredient in a detective novel is obfuscation of the evidence so that the reader cannot easily determine the culprit. We formulate a computational problem here where we identify sentences containing potential evidence, if any, against each character in the novel. While novels and stories from other genres have a more linear narrative, detective novels reference information from different points in the story. In this genre, the author is motivated to reveal only partial information to a reader to keep them engaged. So first, we propose a method to gather evidence against every character by extracting relevant sentences which seem to implicate them in the crime and are scattered throughout the story. Thus by identifying evidence sentences against each character, we computationally generate an ‘evidence summary‘. We split the novel into pre and post culprit expose by identifying the reveal paragraph, and utilise the information post culprit expose to identify semantically similar sentences in their vector representations. We process each novel text as their graph representation, and employ different graph traversal techniques. Second, from the exercise of extracting evidence we identify and categorise three major ways in which popular authors in crime and detection genre embed evidence in their stories. We compare our algorithm results with human evaluators and qualitatively determine the different writing styles. Our results show we outperform the baseline method in extracting useful evidence sentence and categorising novels on the basis of clue obfuscation. For one of books in the dataset The Murder of Roger Ackroyd, our method obtains a score of 8/10 compared to a 3/10 baseline. Thus our contributions are two fold - we propose a method to extract evidence containing sentences, in a detective novel utilising the semantics of this genre, and also establish different ways in which authors obfuscate the evidence.

Abstract

Internet of things (IoT) devices are steadily becoming mainstream in our lives and simplifying themanner in which we perform everyday tasks. With billions of smart devices, embedded with all kinds oftransducers, communicating with each other and us humans via the internet, data is being generated atan alarming rate. Consequently, data analytics has become an integral part of the IoT ecosystem. SeveralIoT applications, including those that come under the umbrella of smart home, intelligent transportationsystem, smart healthcare and smart grid, rely on machine learning (ML) to gain inference from sensordata and aid in decision making. Apart from user applications, ML is also used in the lower layers,including the network layer and the medium access control (MAC) layer, to improve the efficiency ofIoT networks.The focus of this thesis is on the application of ML in making IoT systems smarter and more effi-cient. More specifically, a new ML-based paradigm for occupancy estimation is introduced along withan ML-based data transmission reduction scheme that is validated for occupancy applications. Havingknowledge of the occupancy status of rooms can help in automating lighting systems, cooling/heatingsystems as well as a myriad of other appliances throughout the building. The proposed occupancyestimation paradigm employs ML algorithms on a deployment of multiple non-intrusive sensor nodesin a room. Two new datasets were created in the process which are thoroughly investigated by ap-plying various preprocessing, feature engineering and ML techniques. Multiple performance metricslike accuracy, F1 score and confusion matrix are reported for a variety of homogeneous and heteroge-neous feature combinations. A novel ML-based data transmission reduction scheme is also proposed forapplication-specific IoT networks that takes the application into account when deciding the initiation oftransmission. Wireless data transmission is infamous for being the most energy consuming activity ofa sensor node. Therefore, intelligently reducing data transmissions can prolong the lifetime of battery-powered sensor nodes without comprising much on the data quality. To enable the proposed scheme forconstrained sensor nodes, the complexities of various ML algorithms are discussed, both theoreticallyand practically, from the perspective of constrained microcontrollers. One of the occupancy estimationdatasets along with a standard dataset for occupancy detection are used for validating the proposed datatransmission reduction scheme. Experimental results demonstrate a humongous reduction in the num-ber of data transmissions while upholding similar performance metrics. The proposed scheme is alsoshown to significantly outperform the Shewhart change detection algorithm for occupancy applications

Abstract

Intelligibility of speech is an important factor for effective speech communication. It refers to howclearly one can perceive the words/message from a speech signal. Environmental factors either atthe speaker’s end and/or at the listener’s end affect speech intelligibility. If the listener is in a noisyenvironment, while clean speech is being transmitted from the speaker’s end, one needs to modifythe clean speech to improve its intelligibility in the presence of noise. If the speaker is in a noisyenvironment, one needs to enhance the degraded speech to improve its quality and intelligibility beforeit is transmitted to the listener. In some other scenario, where the background at the speaker’s endis speech from another speaker, one needs to do speaker separation to improve the intelligibility of thedesired speaker. In order to improve speech intelligibility in these scenarios, it is necessary to understandthe factors responsible for intelligibility of speech. The objective of this thesis is to identify factorsresponsible for intelligibility of speech, and to modify the speech signal to enhance the intelligibility insome practical scenarios.A flexible analysis, manipulation and synthesis tool is needed for exploring the factors responsiblefor intelligibility. A signal processing method based on single frequency filtering (SFF) is used toanalyze the speech signals. In the SFF method, the speech signal is shifted in frequency by multiplyingit with a complex exponential signal, and is passed through a single frequency filter to get an outputat any desired frequency. The SFF output is represented using its magnitude (or envelope) and phasecomponents. The thesis shows that the original signal can be reconstructed with very low error, byusing the SFF outputs at sufficient number of equally spaced frequencies. This thesis also examines therelative significance of the SFF magnitude and the SFF phase towards speech intelligibility, by usingvarious parameter values of the SFF analysis.Different speaking styles such as Lombard speech (speech articulated in presence of noise) or clearlyarticulated speech are analyzed using the SFF analysis to determine the factors contributing to theintelligibility of speech. It is observed that the speech signal is more intelligible when the SFF magnitude has higher dynamic range locally (fine structure) and lower dynamic range globally (gross structure).Based on these observations, an algorithm is proposed to improve the intelligibility of clean speech inthe presence of noise. The algorithm comprises of four modifications on the SFF magnitude of theclean speech at fine and gross, and at temporal and spectral levels. The original SFF phase along withthe modified SFF magnitude is used to synthesize speech with improved intelligibility in noise. Thethesis also proposes another method using simple manipulations on the SFF envelopes to improve theintelligibility of clean speech in noise.To improve the intelligibility of speech degraded by noise, the high signal-to-noise ratio (SNR)property of the SFF analysis is exploited. The proposed algorithm involves estimation of a binary maskfrom the SFF outputs of the degraded speech by using different thresholding techniques. The binarymask assigns a value of one to the speech dominant Time-Frequency (T-F) bins and zero to others.Only the speech dominant T-F bins from the SFF envelope and phase of the noisy signal are used tosynthesize the signal. The thesis also studies the significance of ideal binary mask, clean magnitude andclean phase towards intelligibility improvement of degraded speech.When the interfering background is speech, speaker separation is required to increase the intelligibilityof the desired speaker. The SFF output can be used to extract the impulse-like events corresponding tothe glottal closure instants (GCIs) of the speaker. This property along with high spectral resolution of theSFF output is used for developing a speaker separation algorithm. The proposed algorithm uses signalsrecorded from two microphones. The time delay between the two microphones is computed using thecross-correlation between the impulse-like representations of the signals from the two microphones. Thecompensation of the delay between the two microphone signals reinforces the impulses correspondingto the desired speaker. The SFF on reinforced impulses highlights the harmonics of the speaker, andhence helps in selecting the frequency regions dominated by the speaker. The SFF phase modificationis done by using iterative phase reconstruction to further enhance the speech signals.The key contributions of the thesis are:1. Development of synthesis procedure for single frequency filtering (SFF) representation of speech.2. Examination of significance of SFF magnitude and phase towards speech intelligibility usingdifferent parameters inv

Abstract

With rapid urbanization, traffic congestion has become a severe problem in Indian cities with people spending a majority of their time stuck in traffic. While there are many reasons contributing to it - like bad road infrastructure, poor traffic management and heterogeneous traffic, a significant cause is identified as irrational driver behavior. These behaviors are mainly caused by various environmental factors like noise (both ambient and persistent honking), pedestrians, heterogeneous traffic, other vehicles not following rules, bad roads etc. The objective of the current study is to examine in particular two independent but conceptually linked external or environmental factors of honking and lane system on driver behavior. Of particular interest is the correlations between physiological changes, psychological states like anxiety/stress/frustration and decisions. A hypothesis based on observation and understanding of Indian roads, is that honking at high decibels though normalised and adapted by Indian road users is reflected on behavioral responses in addition to long term health effects. While there have been many studies addressing traffic congestion due to external factors, few cover driver behaviours caused due to these factors. In this study, we delve deeper into changes in driver behaviour due to one external attribute - that of persistent honking by a trailing vehicle. There have been studies on the effects of honking and most of them report better traffic flow because of honking. That is, honking is considered as an inter-vehicle or vehicle to pedestrian communication. The studies do not take into account changes in the driver behaviour due to honking - both honks of acoustic properties approved by certifying agencies and especially from non-standard honks as heard in traffic conditions in India where the current experiment was conducted. Honking, designed to be a tool for the drivers to communicate effectively and also to alert other road users, is often used on Indian roads as a mechanism to express frustration either due to traffic jams, a purely reflex action, a sense of entitlement (as a function of the cost/power of the vehicle) to the road and right of way etc., rather than to ensure safe driving. To analyse this effect, we looked at driver behaviour and his/her physiological measurements in the honking environment. These factors are inter-linked, as lane system in heterogeneous traffic leads to honking as traffic flow enabler or as aggression towards a smaller slow moving vehicle. As the first step, the validity of virtual simulators (with head mounted display and tactile controls) to present immersive experience and near real-life traffic conditions was tested. Hence, to study two environmental or external effects on driver behavior, the concept of lane adherence and honking was considered. We have chosen to simulate the real world rather than conduct a real-world experiment for two main reasons- 1. In real world traffic, we cannot ensure experimental control of honkingthat is, present the same or similar situations during the data collection time. Second, variation in the honking environment for each person creates inconsistencies in experiences and the data. To focus on the decision making aspect in driver behaviour, we need to ensure a similar environment to all participants. 2. It is difficult to impose traffic control in the real world. Creation of a controlled traffic environment multiple times, where different vehicles are moving synchronously, is difficult logistically and expensive. Thus, we solve this problem by using a Virtual environment, which can be controlled, manipulated and replicated as many times as needed. It provides a 360 degree 3D environment enabling different events like decision making and physiological data to be recorded synchronously. In the experiment for the lane system (experiment done with 30 participants), three scenarios were presented with the constant condition of the participant vehicle in the middle lane trailing a slow moving three-wheeler (autorickshaw). The time to reach the finish point, the decision to change lanes and errors in judgment were recorded. The results indicate that in heterogeneous traffic, roads with no lane marking allowed the driver to shift and overtake the slow vehicle while strict lane by barricades lead to high levels of irritation as per the self-report. The feedback on the simulator developed for this study was used as a basis for the Indian road scenario used in the second study. In the second study (experiment done with 45 participants) on the physiological and behavioral changes due to honking on the driver, pulse rate/ skin conductance and driving behavioral choices in the presented scenarios was recorded. We collected skin conductance/GSR values, as previous studies have shown that subjective high decibel noise affects the sympathetic nervous system (part of autonomic ne

Abstract

Crowd sensing with mobile agents is a popular way to collect data, especially in the context of smart cities where the deployment of dedicated data collectors is expensive and ineffective. Existing crowdsensing mechanisms are good for general purpose queries but lack any additional benefits for specialized settings. This mechanism focuses on spontaneous location specific queries, we call it Spontaneous Localized Settings. We define the required characteristics for this specific setting and evaluate existing mechanisms for the same. Agent participation in good numbers is quintessential for any crowdsensing mechanism to work. Since our setting is location specific and bounded by short time, it allows only agents nearby the query location to participate. Therefore, we emphasize on a fair rewarding mechanism and a secure and trustworthy framework to maximize agent participation. Consequently, fairness in reward dsitribution and trustworthy crowdsensing systems are the two central themes of this thesis. Peer prediction based mechanisms are widely used in crowdsensing systems to elicit truthful information from agents, however, they often fail to reward the participating agents equitably. Honest agents can be wrongly penalized if randomly paired with dishonest ones. In this work, we introduce selective and cumulative fairness. We characterize a mechanism as fair if it satisfies both notions and present FaRM, a representative mechanism we designed. FaRM is a Nash incentive mechanism that focuses on information elicitation for spontaneous local activities which are accessible to a limited number of agents without assuming any prior knowledge of the event. All the agents in the vicinity observe the same information. FaRM uses (i) a report strength score to remove the risk of random pairing with dishonest reporters, (ii) a consistency score to measure an agent’s history of accurate reports and distinguish valuable reports, (iii) a reliability score to estimate the probability of an agent to collude with nearby agents and prevents agents from getting swayed, and (iv) a location robustness score to filter agents who try to participate without being present in the considered setting. Together, report strength, consistency, and reliability represent a fair reward given to agents based on their reports. Furthemore, it requires trustworthy framework and to guarantee that the collected data are accurately acquired and reported. Trustworthy and transparent frameworks can be implemented via smart contracts on blockchain to enable robust crowdsensing mechanisms. To achieve this goal, we develop Orthos, a blockchain-based trustworthy framework for spontaneous location-based crowdsensing without assuming any prior knowledge about them. We employ game-theoretic mechanisms to incentivize agents to report truthfully and ensure that the information is collected at the desired location while ensuring the privacy of the agents. We evaluate existing mechanisms based on all desirable characteristics for the settings and identify RPTSC as the most suitable option. Orthos implements the RPTSC mechanism using smart contracts. Additionally, as location information is exogenous to RPTSC, we design the Proof-of-Location protocol to ensure that agents gather the data at the desired locations. We built the decentralized applicaiton based on Orthos protocol and examine its performance on Rinkeby Ethereum testnet and conduct experiments with live audience

Abstract

The processing of temporal information is an important facet of discourse comprehension, and has been studied in linguistic philosophy and natural language processing equally. Major developments in this field include event identification and classification guidelines such as ISO-TimeML, and datasets based on those guidelines, known as TimeBanks. Language specific TimeBanks not only provide insight into the event representation mechanism of a language but also provide a corpus for deep learning tasks in NLP based on events and time information. In this thesis, we establish the Hin-TimeBank, an ISO-TimeML reference corpus with guidelines modified to handle both language specific and language independent additions to the ISO-TimeML schema. We present a set of annotation guidelines and specification designed for the development of an extensible Hindi TimeBank, a manually annotated 1,000 article corpus, marked with events and states, their categories, and temporal expressions. We also highlight the modifications to ISO-TimeML required for the identification and classification of events and states in Hindi. Unlike ISO-TimeML, we introduce states as a distinct concept and provide categories of events and states based on these modified guidelines. The modifications to the ISO-TimeML schema and the associated TimeML event annotation guidelines stem from a Paninian perspective of the event semantics and the pertinent syntax, a perspective which has been previously unexplored. The reliability of the guidelines and specification is determined by the high inter-annotator agreement. Furthermore, we describe the development of a knowledge graph from an event annotated corpus by presenting a pipeline that identifies and extracts the relations between entities and events from Hindi news articles. Due to the semantic implications of argument identification for events in Hindi, we use a combined syntactic argument and semantic role identification methodology. To the best of our knowledge, no other architecture exists for this purpose. The extracted combined role information is incorporated in a knowledge graph that can be queried via sub-graph extraction for basic questions. The architectures presented in this thesis can be used for participant extraction and event-entity linking in most Indo-Aryan languages, due to similar syntactic and semantic properties of event arguments.

Abstract

Global warming, changes in precipitation levels have led us to keep an eye on water resources and to adopt new management strategies for their sustainability. Prediction of projected climatological variables accounting for greenhouse gases in the atmosphere, accurate projections of hydroclimatological variables under climate change is crucial for making adaptive measures and mitigation policies. An analysis of the changes in energy and water balance of a hydrologic system is required to establish these strategies and check their efficiency. Also an analysis of extreme variations in climate will give us a better picture as how a hydrologic system is interlinked with these events. Droughts are one such extreme events which can cause huge damage to ecosystems and society, if sufficient steps are not taken to assess and monitor them. Various meteorological drought indices have evolved to characterize the drought at larger scales. Meteorological drought indicators with precipitation and Potential Evapotranspiration (PET) can incorporate atmospheric water demand based on energy available in drought characterization, which are ideal for energy-limited regions, however, for water-limited regions where Actual Evapotranspiration (AET) is the major hydrological variable, therefore drought is defined by water availability rather than energy. Furthermore, at river basin scales meteorological drought assessments may not be enough to understand the water availability to the crops and other environmental aspects of the river systems. The present thesis aimed to develop a hydrometeorological drought prediction index by considering precipitation, evapotranspiration and runoff. The study mainly emphasized to understand the effect of various meteorological and hydrological variables on drought and how the inclusion of AET can outperform a drought index based solely on PET and P at a river basin scale. In this context, the study proposed hydrologically calibrated Actual Evapotranspiration (AET) considering precipitation, potential evapotranspiration and runoff. The hydrologically calibrated AET was further used in the formulation of Standardized Precipitation Evapotranspiration Index (SPEI) to develop hydrometeorological drought index, Standardized Precipitation Actual Evapotranspiration Index (SPAEI). The proposed drought index SPAEI imposes the effect of precipitation, Potential Evapotranspiration, Actual Evapotranspiration using operational meteorological data sets of precipitation and temperatures and surface runoff. The performance of PET and AET based drought indices was compared using historical droughts in terms of severity, areal extent, frequency and duration. The proposed AET based drought indices have effectively captured the historical drought years over the Krishna river basin. Inclusion of AET in the drought characterization along with precipitation and PET can drive the highly intensified drought events vi vii determined by SPEI into moderate and less frequent droughts with short durations. As SPAEI is more reasonable in reflecting surface water-energy balance it enables better characterization of meteorological and hydrological droughts at regional scales. Further, the study assessed the climate signals on drought assessment with Regional Circulation Model (RCM) outputs and Global Circulation Model(GCM) outputs. Meteorological climate projections for the future were obtained using statistical downscaling which involves establishing a relationship between predictands(local climate variables) and predictors(global coarse scale projections). This relationship is established using a set of statistical and machine learning techniques such as Quantile Bias Correction, K-means Clustering, Classification and Regression Trees(CART) and Support Vector Regression. The study observed that compared to RCM climate projections, GCM based statistical downscaling models have performed well in capturing the historical observations, indicating reliable predictions based on GCM based observations at river basin scales. Although, statistical downscaling models has proved to be reliable projections for climate change impact assessment studies, the RCM data sets provides ease of quick implementation with less computational effort. Therefore, the study suggested the use of RCM projections for preliminary understanding and GCM based projections for a detailed climate change impact assessment study. The projected drought characteristics based on GCM analysis has observed that while the intensity and duration of the drought has been found to be slightly increasing, the frequency and the drought areal extent have been increasing alarmingly over the Krishna river basin. With the GCMs, it has been estimated that there is a net increase of 25%-31% in the drought areal extent, an increase of 50%-90% in drought frequencies in Krishna river basin from the current to future periods. The climate change i

Abstract

Keywords: Adaptive noise cancellation, Kepstrum approach, Beamforming, Speech enhancement. Mobile telephony is one of the major ways of communication now a days around the world. Conversation and communication is possible from any place in the world at any point of time. Even though permanent reachability and connectivity is achieved, there is still scope of development and improvement in the way of communication mostly under noisy environment. The communication performance through mobiles significantly get affected when the surrounding environment contains noise interference like traffic or office or kitchen noises which can lead to poor speech quality both in subjective and objective measures. In this thesis, a novel method for enhancing the speech quality during noisy conditions is proposed. In contrast to classical noise cancellation and suppression methods, the proposed method uses the temporal and spectral dependencies of noise and speech signals. Therefore, the thesis titled, ”Speech Enhancement for Multi Microphone using Kepstrum Approach” presents a Kepstrum method for speech enhancement. The proposed method performs based on Kepstrum analysis, that provides a mathematical representation to speech enhancement applications. It can be applied to system identification applications where acoustic transfer function is unknown between two microphones. It is independent of acoustic path model order and provides mathematical representation with FFT based processing. The front end application of this method for speech enhancements provides an improved performance and noise cancellation with many favorable effects. The developed and proposed enhancement techniques in this thesis are evaluated both subjectively and objectively by means of speech intelligibility and auditory metrics. It is shown that proposed method achieves better results compared to the classical state of-the-art approaches with respect to both noise attenuation and speech distortions. Along with using the proposed method in mobile phones, it can also be used for any Internet of things (IoT), far-field communication, conferencing calls, hearing aids etc

Abstract

Natural Language Processing (NLP) is a challenging field in the intersection of Artificial Intelligence, Computer Science, and Computational Linguistics, concerned with the interaction between natural languages and computers. The understanding of syntax is a vital aspect of natural language processing. With the advent of social media platforms and their popularity in the Hindi heartland, a vast amount of text is generated on such platforms. Traditional NLP tools trained over corpora written in standard grammar are ill-suited for such texts. The reasons for this are their unconventional grammatical structure, non-standard spellings, abbreviations, and phenomena called code-mixing. Code-Mixing refers to the embedding of linguistic units such as phrases, words, or morphemes of one language into an utterance of another language. It is commonly observed in the day-to-day language of multilingual speakers and their utterances on social media platforms. Hence, there is a need to develop tools specifically for Hindi-English Code-Mixed Social Media Text. In this study, the problem of shallow parsing, often a pre-requisite to full parsing, of Hindi-English code-mixed social media text has been addressed. To create the input data for a shallow parser, we have built a language identifier, a normalizer, and a part-ofspeech tagger as well. Along with the tools, we have built a multi-level annotated corpus available to the research community free from restrictions posed by content sourced from social media platforms.

Abstract

Quantum mechanical properties like entanglement, discord and coherence act as fundamental resources in various quantum information processing tasks. Consequently, the technique of generating more resources from a few, typically termed as broadcasting, serves as promising candidate for the design of quantum networks. One way to broadcast resources could be using a cloning operations. In this thesis, broadcasting of quantum resources beyond 2 ⊗ 2 systems is investigated. In particular, in 2 ⊗ 3 dimension, a class of states not useful for broadcasting of entanglement is characterized for a choice of optimal universal Heisenberg cloning machine. The broadcasting ranges for maximally entangled mixed states (MEMS) and two parameter class of states (TPCS) are obtained to exemplify our protocol. A significant derivative of our protocol is that the cloning operation generates a qutrit (3 ⊗ 3) entangled pair with positive partial transpose on one of the local sides; and an absolutely separable qubit (2 ⊗ 2) pair on the other side of the input bipartite 2 ⊗ 3 dimensional resource state. Moving beyond entanglement, in 2 ⊗ d dimension, the impossibility to optimally broadcast quantum discord and quantum coherence (l1 -norm) is established. However, some significant illustrations are provided to highlight that non-optimal broadcasting of discord and coherence are still possible. In the later part of the thesis, we propose a new measure of relative incompatibility for a quantum system with respect to two non-commuting observables, and call it quantumness of relative incompatibility. In case of a classical state, order of observation is inconsequential, hence probability distribution of outcomes of any observable remains undisturbed. We define relative entropy of the two marginal probability distributions as a measure of quantumness in the state, which is revealed only in presence of two non-commuting observables. Like all other measures, we show that the proposed measure satisfies some basic axioms. Also, we find that this measure depicts complementarity with quantum coherence. The relation is more vivid when we choose one of the observables in such a way that its eigen basis matches with the basis in which the coherence is measured. Our result indicates that the quantumness in a single system is still an interesting question to explore and there can be an inherent feature of the state which manifests beyond the idea of quantum coherence.