Abstract

The Indian IT industry is being continuously disrupted by rapidly improving automation technologiesthat tend towards replacing repetitive IT support work and back-office tasks previously driven by humanactors. This increase in efficient automation-based technologies leverages software to carry out back-office tasks almost independently of human- where foreign organizations originally invested in. Thetrend of automating manual work practices in the industry has generated extreme debates over theirprojected influence on hiring patterns, employment strategies, job profiles, work practices, and the overalleconomy. Using a socio-technical framework, the thesis aims at investigating the manifold consequencesarising out of introducing automation techniques in the software Quality Testing (QT) segment of theIndian IT industry. Ethnographic methods were employed for the collection of qualitative researchdata, to identify key socio-economic factors influencing the decision to automate a testing environment.The resulting discourse has been viewed through an Information and Communications Technology forDevelopment (ICTD) lens, by primarily analyzing first-person responses of Quality Testers injectingvalue into the testing job profile and colligating these discourses with existing QT practices. Subsequently,the significance of designing improved QT work practices in combination with relevant skill-trainingstrategies has been detailed, to enable IT professionals to exploit their implicit knowledge, businessprocess knowledge, critical thinking, and computing skills while collaborating with automated QTprocedures.The second part of the thesis focuses on the reskilling and up-skilling required to take the edge off jobthreats in the IT industry owing to work automation. India is home to the largest under-25 demographicprofile in the world, requiring a widespread, skill-oriented educational model, equipping youth to thrivein highly dynamic job markets. As a response to the huge demand for technical education, a large privateskill tutoring ecosystem has sprung up in Ameerpet, Hyderabad, India, whose pedagogical model can beadopted by Massive Open Online Courses (MOOCs) to improve their underlying foundation of teachingtechniques. The thesis offers reasons as to why learners are inclined to enroll in the traditional physicalmodels of Ameerpet classrooms over online training courses. This further draws attention towards designrecommendations that can be incorporated in online learning platforms to entice learners who often getmarginalized in the more formal and competitive education system and opt for Ameerpet-like skillinghubs. The principal offering in this context would be to propose a shift in the perspective of MOOCsto include job readiness by escorting suggestions in course curriculum, course delivery, and marketingstrategies

Abstract

Livestreaming platforms enable content producers or streamers to broadcast creative content to a potentially large viewer base. Chatrooms form an integral part of such platforms, enabling viewers to interact both with streamer and amongst themselves. Streams with high engagement (many viewers and high active chatters) are typically considered engaging and often promoted to end users by means of recommendation algorithms, and exposed to better monetization opportunities via revenue share from platform advertising, viewer donations and third-party sponsorships. Given such incentives, some streamers make use of fraudulent means to increase perceived engagement by simulating chatter via fake “chatbots” which can be purchased from online marketplaces. This inorganic engagement can negatively influence recommendations, hurt streamer and viewer trust in the platform, and harm monetization for honest streamers. In this study, we tackle the novel problem of automating detection of chatbots on livestreaming platforms. To this end, we first formalize the livestreaming chatbot detection problem and characterize differences between botted and genuine chatter behaviour observed from a real-world livestreaming chatter dataset collected from Twitch.tv. We then propose SHERLOCK and BOTHUNT methods, which posits a two-stage approach of detecting chatbotted streams, and subsequently detecting constituent chatbots. Finally, we demonstrate effectiveness on both real and synthetic data: to this end, we propose a novel strategy for collecting labeled, synthetic chatter dataset (typically unavailable) from such platforms, enabling evaluation of proposed detection approaches against chatbot bahaviors with varying signatures. The SHERLOCK approach achieves 97% precision/recall on the real world dataset and +80% F1 score across most simulated attack settings and BOTHUNT achieves 86% accuracy for real world dataset and 93% accuracy across all attack settings. This thesis is a timely contribution to the area of computer science specially combating astroturfing, needed to mitigate the spread of fraudulent bot users on Live streaming Platforms. The results from this thesis can be used to build real world solutions to mitigate the spread of untrustworthy or botted streams, fake users, etc. on live streaming platforms in the future.

Abstract

We are intrigued by the problem of Web Accessibility. While it is somewhat intuitive to imagine the barriers a disabled person may face in accessing content on the web, they are not the only segments of users facing accessibility challenges. For instance, users with poor English abilities, or users with less domain exposure, or users with different thinking levels also face access barriers when reaching out to mainstream targeted public content. English-only text for the non-English users, technical jargon for the non-technical, scholarly material for the novice user, and local cultural references to those uninitiated may also be seen as barriers to accessibility. To such non-mainstream users,who are often in the minority, the content on the web – which is often designed for the majority – could, at times, be perceived as complex, foreign, incomprehensible and even inaccessible. In our work, we are focused on this aspect of the Web Accessibility problem. We adopt the existing social technique of Renarration as a mechanism to overcome the accessibility problem. At a social level, when humans communicate with a diverse group of listeners, they vary the content to suit the needs of differing communities of their users. For example, a child who is trying to discuss a new mod1 in a game may elaborate it more for a fellow gamer, but may instead simplify it for a parent. Similarly, a scholar may formalize an explanatory text for a fellow scholar, but may simplify or abstract the same to suit the needs of a conventional listener. We use the term renarration to describe this act of generating a variant version of the content from an original source. More formally, renarration can be treated as a semantic transformation function applied on a given web page to generate a variant. In our work, we have chosen to overcome some of the accessibility barriers on the web by applying the technique of renarration to it. And, we equate renarration of web content to a semantic transformation function. And finally, we aspire to find a web architecture that would facilitate such semantic transformation of web content. Given this, the problem statement for our research can now be stated as: What is that web architecture that would enable one or more volunteer users to manipulate, modify, process or transform published web content into one or more alternate views, such that each variant view now may deliver a different meaning to its targeted community of viewers? We move towards the solution space by reviewing the current approaches that are already in use, and also by exploring any earlier work from the e-publishing industry. The design of our solution is further informed by a series of nearly two dozen research undertakings consisting of multiple surveys and experiments. As part of our research, we also explore the theoretical underpinnings for semantic transformation. We study the notion of ”semantics” (as applied in Computer Science literature), and also the notion of ”transformations” as discussed in the mathematical disciplines of geometry and algebra. Through this work, we capture our notion of semantic transformation of web content in an abstract, symbolic notation. Citing ease of use for non-technical users, we focus on the notion of style sheets as one of the many ways to transform web content. As part of this study, we explore the general notion of style sheets and see how specific style sheets – namely, the popular XSLT and CSS style sheets – have been used on the web. We take an abstract view of CSS as a transformation function t operating on HTML marked content c and augmented by style information s, resulting in t = f(c,s). Our notion of semantic transformation is informed by this abstraction and is represented as yet another semantic transformation function t = f(c 0 , l, a, n) where f is still a transformation function, c 0 is now the semantically annotated source, l is the location and description of the semantic structure imposed upon the page by the user, a is the new set of actions that are inclusive of semantics, n represents the conditions that are to be applied, and t is the transformed target page. We call this new semantically oriented style sheet as Semantic Style Sheet or SSS. We take the core ideas behind CSS rule-set and use that to inform the design of our SSS. For instance, the notion of a rule-set underlying a CSS is given by selector : { property : value}. We enhance this rule-set in three dimensions, and infer a simplistic rule-set representation for SSS, which is given as locator : { ( action , condition ) } where {attribute : value} pairs are predefined for each of the locator, actions and conditions parameters. To automate the better instrumentation of a web page we found the conventional tree metaphor inadequate. We further explore other conceptual representations of a web page and present an ontological model as our r

Abstract

In this research work, we present three syntax-based computational methods that use the dependency structure of sentences for inference generation, summarization, and machine reading comprehension. Besides, we present an introductory dataset to aid the production of inferences from a response in a context. The methods described in this thesis utilize the dependency structure obtained from the parser that represents the dependency relations existing between the words of the sentence. This work explains how these relations are utilized to compute inferences from utterances, summarize documents, and answer questions based on context passages. The first method describes computing pragmatic inferences from news headlines that are stand-alone units of text carrying no context information. The different types of pragmatic inferences are entailment, presupposition, and implicature. News headlines are some minimal utterances that contain maximum information for which the speaker is the news editor, and the receiver is the newsreader. The inferences, such as presuppositions and conventional implicatures that are independent of the context, depend mainly on syntax. Hence, this approach uses dependency trees of the headlines to find the syntactic structure and to compute inferences out of them. The generated inferences about the news headlines could be useful for assessing the impact of the same on readers, including children. Utterances do not frequently exist in isolation, like in news headlines. Hence, we created a minimal dataset with implicated meanings of utterances in a context. In this work, 1k context-response utterance dialogue pairs having implicatures for the response utterance are collected and annotated with their implicated meanings. Since dialogues with implicatures are not easy to obtain, the data collection methods, challenges, findings, and sources of dialogue data of this genre are also explained. This dataset and further additions to it would improve the understanding capability of the machine and reduce the amount of conversational failures in human-computer interactions. The second method describes summarizing a passage based on syntax and dependency structure. The extractive summary of the passage is obtained by finding overlapping sentences from the dependency graph constructed by attaching the dependency trees of individual sentences in the passage and simultaneously prioritizing content word nodes such as verbs, nouns, adjectives, and adverbs, and discarding translative nodes such as prepositions and articles. The third method uses dependency trees to simulate a human approach while answering a question about a passage. While reading a passage to answer a question, humans usually try to identify the verb of action in the question and find the sentences with the same or synonymous verbs as the candidate answers. Simulating the human approach of finding the same or similar verb in the passage comparing to the verb in the question is followed for comprehending the passage to answer a question. The verb nodes of the dependency trees are compared to achieve this.

Abstract

In the era of structural genomics, with large number of protein structures becoming available, identification of domains is an important problem in protein function analysis as it forms the first step in protein classification. Domain identification has been an active area of research for over four decades and wide range of automated methods have been proposed. In the proposed network-based machine learning approach, NML-DIP, a combination of supervised (SVM) and unsupervised (k-means) machine learning techniques are used for domain identification in proteins. The algorithm proceeds by first representing protein structure as a protein contact network and using topological properties, viz., length, density and interaction strength (that assesses inter- and intra-domain interactions) as feature vectors in the first SVM to distinguish between single and multi-domain proteins. A second SVM is used to identify the number of domains in multi-domain proteins. Thus, it does not require a prior information of the number of domains. The k-means algorithm is then used to identify the domain boundaries that are assessed using CATH annotation. Performance of the proposed algorithm is evaluated on four benchmark datasets and compared with four state-of-the-art domain identification methods. The performance of the approach is comparable to other domain identification tools and works well even when the domains are formed with non-contiguous segments. The performance of the program is significantly improved for prior information about the number of domains. The algorithm is available at: https://bit.ly/NML-DIP.

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