Abstract

The goal of rendering in computer graphics is the synthesis of photorealistic images from abstract virtual scene descriptions. Among the many rendering methods, path tracing along with physically accurate material modeling has emerged as the industry standard for photorealistic image synthesis. Path tracing is, however a computationally expensive operation. Moreover, physically accurate material modeling requires iterative parameter tuning and visualization using path tracing. This quickly becomes a bottleneck for the tuning of a large number of parameters found in most physically accurate material models, and artists end up spending a lot of time waiting for path tracing to converge. This dissertation proposes to leverage the learning power of neural networks to plausibly approximate path tracing for: (a) quick material visualization while editing, (b) out-of-the box material recovery using inverse rendering. The traditional workflow for tuning material parameters and visualization is typically followed by modifications to lighting for better understanding the behaviour of the material. We thus incorporate the ability to modify the environment lighting in our neural material visualization framework. This significantly aids in understanding the behaviour of the material thus aiding the process of parameter tuning, which we demonstrate with a user study. Most real-world materials are spatially varying, which is that their behaviour varies across the surface of the geometry. While previous works in this area dealt with uniform materials, we propose improvements for handling spatially varying materials. We design our neural network architecture to be light-weight, having 10× lesser trainable parameters than the state-of-the-art, while also producing better visualizations. We also build a tool to demonstrate real-time parameter tuning and visualization of materials. Finally, we extend the above work to handle general 3D scenes in specific lighting scenarios. This is done by training a small fully connected neural network on a simple scene in the local tangent frame. Training in the local tangent frame decouples geometric complexity from training which implies that the network generalizes to any geometry. We embed this network in a standard path tracer to evaluate direct illumination at each path vertex. We thus not only obtain noise free direct illumination but also out-of-the box gradients of the rendering process, which can be used for inverse rendering. We show that these gradients can be used for plausibly recovering the material of a target scene. We conclude by discussing various practical aspects of our method.

Abstract

Recent advances in networking sites, the Internet revolution has changed everything, right from businesses to healthcare to education to the ways of communicating with our friends. The Internet has opened doors for people to express themselves, write their thoughts about a particular topic, share an experience online for other people to read without much hassle. Even before going out, order something, or watching a show/movie, people tend to check the online reviews first. And it is feasible and practical also because anyone wouldn’t want to spend their time, money, and other resources on something that isn’t worth it. With so many reviews, tweets, and content available online, it is also important to process them in such a way that they can be used by everyone productively. One use-case could be as the word limit for online reviews on sites like IMDb, Zomato, and Amazon is pretty significant (10, 000 characters for IMDb, Amazon has a limit of 5, 000 words ∼ 23, 500 characters) some reviews tend to be longer. While the reviewer elaborates on their experience, from a reader point of view, what really important is, what aspects of the given target entities the reviewer liked/disliked. This is where the need for Aspect-based Sentiment Analysis arises. Aspect-Based Sentiment Analysis (ABSA) aims to extract the aspects of the given target entities and their respective sentiments. The main issue is, the amount of data is so huge that manually processing the data on such a vast scale is impossible. E.g., Twitter alone sees an average of 6000 tweets per second, roughly 500 million tweets per day. Hence, we look for some fast, automated methods that can do the processing almost in real-time. In this thesis, we propose a deep-learning enabled model, TEASER, based on an extract-then-classify framework for extracting the aspects and detecting the respective sentiment attached. We also conduct extensive experiments on the 3 existing datasets (Restaurant14, Restaurant15, Laptop14) to show that TEASER performs better than the existing models. In chapter 4, we present two novel datasets in the domain of movie reviews, Movie20, and moviesLarge. Movie20 is a supervised dataset of 1162 sentences manually annotated by two human annotators, whereas moviesLarge is a pseudo-labeled dataset of 14373 sentences. With the help of Semi-supervised learning, we benchmark TEASER on the Movie20 dataset. We also evaluate the results of TEASER on the Movie20 dataset thoroughly and try to reason the gaps in predicted output and gold annotation.

Abstract

Pattern mining is an important task of data mining and involves the extraction of interesting associations from large databases. In the literature, pattern mining approaches have been investigated to extract the different kinds of patterns such as frequent patterns, sequential patterns, periodic patterns, utility patterns and coverage patterns from transactional databases. The pattern mining approaches have been widely employed to improve the performance of applications in the areas of recommendation systems, e-commerce, customer relation management, internet advertising, decision support systems, social media and so on. One of the key issues of developing pattern mining algorithms is as follows: a pattern mining algorithm has to process a huge volume of transactional dataset. Research efforts are going on to develop pattern mining algorithms to operate on large datasets by exploiting different parallel processing paradigms, namely shared memory, shared disk, shared-nothing, GPUs, incremental, MapReduce and Grid. Typically, a given transactional database D gets updated due to the addition and/or deletion of transactions. Consequently, some of the previously discovered patterns may become invalid, while some new patterns may emerge. To extract the new knowledge we should mine the database every time it gets updated. One of the main issues is to mine huge Dynamic Databases for every time instant from scratch is computationally costly. The concept of incremental mining is evolved to solve the issue of mining patterns for every instant efficiently for Dynamic Databases and has become an active research area. When the database is updated, with Incremental mining, there is an opportunity to improve the performance by limiting the computation to updated parts of the database and with the required additional processing. In the literature, Incremental mining approaches have been investigated to extract different kinds of patterns such as frequent patterns, sequential patterns, periodic patterns and utility patterns from transactional databases. In this thesis, we propose an improved approach for extracting Coverage Patterns for Dynamic Databases under the incremental paradigm. Given a transactional database, the coverage pattern mining involves the extraction of multiple sets of items, where each set (covers a certain percentage of transactions) satisfies relative frequency, coverage support and the overlap ratio constraints. The applicability of coverage patterns has been demonstrated in improving the performance of search engine advertising, banner advertising and visibility mining. In the literature, a level-wise iterative coverage pattern mining (CPM) and a pattern growth approach have been proposed.In this thesis, we propose a Comprehensive Coverage Pattern Mining (CCPM) approach, for efficiently extracting Coverage Patterns under the incremental paradigm, when a set of transactions are added only, set of transactions are deleted only and both set of transactions are added and deleted from the original database. For each case, we have identified a set of rules by identifying the potential opportunities to avoid unnecessary processing as compared to the rudimentary option of the processing from the scratch. Furthermore, it has been observed that, when a set of transactions are added and/or deleted from the original database, if the order of items in the frequency list (Flist) of the database is changed, additional patterns have to be validated and require additional processing. Based on the rules and by considering the issue of change in the order of items in the Flist, we have proposed improved approaches to extract coverage patterns, by considering the case of (i) addition of transactions (ii) deletion of transactions and (iii) addition and deletion of transactions. We have also performed extensive experiments on two real click-stream datasets and one synthetic dataset and demonstrated the overall effectiveness of our proposed approach.

Abstract

The recent advances in Machine Learning and other data driven techniques have transformed domains like robotics, computer vision and natural language processing. These algorithms are now also being applied to a wide array of chemistry problems as well. One such class of machine learning algorithms is deep generative modelling which has found its application in de novo molecule generation. Generating lead molecules in silico, helps reduce the wastage of limited computational and laboratory resources by reducing the number of generated bad leads. For every task, the lead molecules may exist in different regions of the chemical space which would have to be explored appropriately. The drug discovery process is long, arduous and expensive while also being plagued by the problems caused by bad leads especially for novel targets and the design of new inhibitors for novel targets is now more important than ever especially in the current scenario with the world being plagued by COVID19. Drug molecules must possess certain properties to be effective so that they can be considered for further validation. Conventional computational approaches such as high-throughput virtual screening require extensive combing through existing database and evaluating all the molecules in them in the hope of finding possible hits that possess the required properties. However, existing libraries of druglike molecules, advances in deep generating modelling and optimization techniques like reinforcement learning has provided a new avenue to tackle this problem. In this thesis, a computational strategy is proposed for the de novo generation of molecules with high binding affinities to the specified target and other desirable properties for drug-like molecules using reinforcement learning. A deep generative model built using a stack-augmented recurrent neural network initially trained to generate drug-like molecules is optimized using reinforcement learning to start generating molecules with desirable properties like LogP, Quantitative Estimate of Drug Likeliness,Topological Polar Surface Area, and Hydration Free Energy along with the binding affinity. For multiobjective optimization, a novel strategy was also devised in which the property being used to calculate the reward is changed periodically. In comparison to the conventional approach of taking a weighted sum of all rewards, this strategy shows an enhanced ability to generate a significantly higher number of molecules with desirable properties while also exploring new regions of the chemical space for multiple targets.

Abstract

Radio frequency (RF) sensing is emerging as an alternative for quantitative analysis of bio-samples due to its advantages over conventional techniques. It is robust, reusable, portable, less cumbersome and the quantity of sample is typically in micro-litres. Planar resonant sensors like complementary split ring resonators (CSRR) and inter-digitated capacitors (IDC) are the most excellent choices for biosample detection due to simple design, low cost fabrication, compactness and effortless integration with other components for lab on chip development for various RF applications. CSRR based RF sensor has been designed of size 38 x 32 mm2 is designed with resonant frequency at 1.51 GHz. The designed sensor is fabricated on a 1.6 mm thick FR4 substrate with copper of thickness 0.035 mm on both sides. Quantitative analysis of sucrose, glucose, fructose and L-Lysine have been performed using Keysight Vector Network Analyzer (VNA). Although this sensor is advantageous in various aspects, existing sensors still suffer from a lack of sensitivity in detecting minuscule changes in the dielectric constant. The major work presents the optimization of RF cavity design using binary particle swarm optimization (BPSO) for quantitative analysis of L-Lysine, extendable to any bio-sample. The design of the sensor is broken into fragments called cells. A combination of the cells constitutes a cell pattern resulting in a RF design. The cell pattern is optimized in such a way using BPSO to achieve maximum sensitivity for a particular set of dimensions of the sensing region. Usually, sensors are designed in the presence of air which has a dielectric constant of ∼1. In contrast, most bio-samples have solvents associated with them. Water and its based solvents having dielectric constant ∼79 are most commonly used for bio-sample detection. Therefore, we perform optimization of RF designs like CSRR and IDC for achieving enhanced sensitivity in the presence of the solvent above sensing region, unlike air-based reference. Detecting small changes in the concentration of the sample under test (SUT), which contributed to a minuscule change in the dielectric constant of the solution, has been achieved through optimized RF sensors. The final sensors have been fabricated using the low-cost PCB technology on a FR-4 substrate of dielectric constant ∼4.3. An enhancement of 47.38× for the CSRR and 2.03× for the IDC in the detection of L-Lysine at frequencies 2.18 GHz and 0.72 GHz, respectively has been achieved when compared to sensitivities of their traditional counterparts. Moreover, the sensors have been tested to detect sucrose and glucose, and promising results have been obtained. This methodology, called solvent based optimization, can be extended for enhancement of the sensitivity of any planar RF sensor, making it a suitable contender for optimization of next-gen RF bio-sensors. This work shows great potential in various biomedical, agricultural, and pharmaceutical applications

Abstract

Allostery is the process of regulation of a protein caused by the binding of a ligand at a distant region from the active site. It is one of the most widely studied properties of proteins and biological systems. Ligand binding at allosteric sites lead to a conformational change in the protein, propagated via changes in protein dynamics that alter the capability of the protein to bind to ligands or molecules at active sites. Allostery is required by biological systems to carry out several crucial functions like hormone binding to receptors, protein regulation to name a few. While traditional view of allostery considers large conformational and structural changes, the concept of dynamic allostery challenges this assumption, wherein ligandinduced changes in protein dynamics could produce allosteric communication between distinct binding sites, even in the absence of macromolecular conformational changes. In this thesis, we have considered PDZ domain of protein PSD-95 as our model system to understand the mechanism of dynamic allostery and identify residues involved in allostery. PDZ domains are evolutionary conserved protein-protein interaction modules associated with cellular signaling and are implicated in the localization of membrane receptors and ion channels. The analysis involves using two popular approaches, Molecular dynamics simulations and network-based approach. We show that the combined MD and networkbased approaches together provide a better insight on possible allosteric communication pathways on ligand binding and also is able to improve the prediction of allosteric sites as compared to either of the methods individually. Additionally, in the extension of the webserver, NAPS, we developed interaction energy networks for the analysis of protein structures and support the analysis of MD trajectories such as construct and compare network-based features of protein structures from intermediate time-steps of the MD simulation.

Abstract

Always-on agents are those agents which are like daemon programs that are always on and can do tasks as and when they arrive. These agents are idle when there is no task assigned to them. Further, those agents that work on a task also wait for some event or task completion, and hence, are also idle for short durations while executing the tasks. The question arises what should the agent be doing when it is idle. In this thesis, we conduct an empirical analysis to show improved decision-making capabilities by agents when they exploit their idle time. We analyze scenarios where (i) the agents analyze their past tasks regarding decisions taken and their impact and where (ii) the agents cooperate with other agents to improve their decision-making. Performance improvement can be measured by considering an increase in success rate, avoiding strategies that may not work, quicker decision making, etc. While executing a task, our always-on agent stores pertinent details of the task done in a database, such as decisions taken, paths of execution of the task, goodness of them, etc. The agent uses different strategies to use this stored knowledge. We present and evaluate three strategies that always-on agents can use (i) Frequent Decision Strategy (FDS) - the agent stores the prior executions and their frequency of success and failure, repeats the most frequent successful decision taken during prior executions of the task, (ii) Analyzed Decision Strategy (ADS) - the agent analyses prior executions that were successful or not, stores in the database the goodness of various alternatives and chooses the best alternative and (iii) Online Analysis Decision Strategy (OADS) - the always-on agent while executing its task, during its idle time analyses the possible future situations and prepares the list of best possible decisions that can be taken in future. The FDS and ADS are used when the agent is not doing any task and is off-line. In contrast, OADS generates new mock tasks to consider possible alternative task execution situations to expand its decision-making scenarios while having a task at hand. We conduct our empirical study on always-on agents playing Connect-4 games to check the viability and improved decision-making. We also present idle time analysis in always-on cooperative agents. We propose a Multi-agent Framework that always-on cooperative agents can use in their idle time to improve decision-making. We formulate scenarios in which the agent has a rationale to cooperate with other agents (i) Exception Handling - the agent cooperates to handle situations in which it does not know what to do, (ii) Confidence Boosting - the agent cooperates to boost confidence in actions it wants to take, (iii) To obtain Different Experiences - the agent cooperates to obtain different experiences. We conduct an empirical study on always-on cooperative agents using the Multi-agent Framework and show improved decision-making.

Abstract

Spontaneous speech is a particular type of speech setting where a speaker speaks without preparing in advance. This makes the speaker think about what to say on the spot, formulate the utterances and then produce the speech. Such a setting often leads to abrupt breaks or discontinuities in the normal conversation flow called disfluencies. Disfluencies can provide information regarding the speaking style, speaker identity and language fluency, which can be useful for several speech-based applications. For automatic speech recognition (ASR) systems, the presence of these disfluencies leads to a higher word error rate, since most ASR systems are developed on non-spontaneous read speech data. Thus, the detection of disfluencies in spontaneous speech becomes an essential task for many applications. For training any machine learning system, one need data. In this thesis, we introduce IIITH-IED dataset for disfluencies in spontaneous lecture-mode speech, and then use it to develop frame-level automatic disfluency detection systems. Finally, we propose a transfer learning method to detect disfluencies in spontaneous lecture mode speech using three frame-level automatic disfluency detection systems trained on stuttered speech. Compared to baseline systems, proposed method gives an average improvement of 2.25% across all disfluencies and all detection systems.

Abstract

The extent of damage in a structure can be estimated numerically using Nonlinear analysis (NA). On the basis of the applied forces, NA can further be classified as Static Non-linear (Pushover Analysis) and Dynamic Non-linear (Time History Analysis). The response of a structure can be predicted effectively using Non-linear analysis, provided adequate assumptions are made. The efficacy of Non-linear analysis depends on the accurate assumptions pertaining to types, locations and pattern of non-linear hinges. Various hinge definitions that are generally used for NA of a structure includes Axial, Shear, Flexural or Torsional force-deformation relationships. However, these force-deformations are seldom mutually exclusive, and can be coupled to achieve a better numerical simulation of actual behaviour, and failure mechanism. The most common combination of hinge definition applied for NA of 2D frames is P-M2 hinges (P-M2-M3 in case of Space Frames). As per the literature, the three most common modes of failure in low and medium rise structures are Shear failure, Flexural failure, and a combination thereof. This observation emphasizes the need to consider the combination of shear and flexural hinge definitions during analysis, to better estimate the behaviour and effectively predict the failure pattern of a structure. The literature also suggests an inversely proportional relationship between the shear and moment capacity of a section beyond first yield. The prevalent practice in a typical design office requires an engineer to define a flexural hinge (in terms of moment-rotation/curvature relationship) for a section, and assigning a value for ultimate shear strength causing brittle failure, and thereby neglecting the effect of shear on the non-linear behaviour of the section. These observations form the primary objective of the work presented here, which is to develop a Shear-Moment interaction behaviour for a Reinforced Concrete (RC) section. Among the commonly constructed RC structures, Open Ground Storey (OGS) structures have swiftly become the most preferred type of RC buildings, primarily owing to large open spaces on the ground level. However, structural engineers deem OGS as a form of vertical irregularity, and advice special care while designing, to prevent collapse, especially in seismic prone areas. The literature consists of a plethora work on modelling of infill panels, especially in case of an OGS building. Various models exist to effectively simulate the effect of infill wall panels, the most common of which are single strut model, double struct model and three strut model. However, in a typical design office, buildings are generally analysed as bare frames, thereby neglecting the effect of infill panels, and leading to incorrect estimation of behaviour of the building. This practice, when employed for an OGS building leads to further deviation of analysis results from the actual behaviour. Furthermore, when designed as bare frames, the buildings having OGS exhibit higher strength as well as stiffness on the storeys above the ground storey. Since the OGS is both a soft and a weak storey, it will incur higher stresses, leading to significant damage. The damage sustained by the structural members in the OGS depends primarily on the ductility of columns, relative lateral stiffness and strength with respect to the adjacent upper storeys. Further, the height of the building having an OGS has a significant effect on its behaviour. The various factors governing the behaviour of a building having OGS can be combined together to obtain a Amplification Factor (AF), that can be used as a multiplication factor to modify the demand on the OGS. This forms another important objective of the present work. The AF will primarily depend upon: 1) Material property of masonry, 2) Design type of RC building, 3) Percentage of openings present in upper floors, and 4) Aspect ratio of the building. In present study, an attempt is made to determine the shear capacity of reinforced concrete section with respect to different deformation levels and to understand the effect of shear-moment interaction of reinforced concrete section in nonlinear zone while performing nonlinear analysis of the structure. Alternatively shear hinge of V-Ø type is proposed in place of existing one value of shear capacity and its effect on nonlinear response of the infilled RC structure because of change in shear failure mechanism is studied. Also an attempt is made to compute design amplification factor (DAF) for safety of OGS during seismic events considering different parameters aforementioned mentioned above and numerical correlation of same with DAF is done using linear regression analysis.

Abstract

A major customer demand in the software industry today is quality at speed. Systems and Software Development Lifecycle processes (SDLC) are central to the work in IT Organizations that guide product and service development and act as vehicles for building the engineering deliverables (ISO/IEC 12207, 2017; ISO/IEC 15288, 2015). Despite adopting standard processes, IT organizations continue to face enormous quality-related challenges in developing engineering deliverables primarily because the standards outline “what” tasks to be carried out but not the “how” part of developing solutions. There is a lot of reliance on the knowledge and expertise of the people involved in the SDLC to build quality solutions for the stated problem. More specifically, early SDLC phases such as proposals, requirements are document-centric and manually intensive. The essential knowledge related to the domain and solutions is buried in various kinds of documents in shared repositories. Subject Matter Experts (SME) refer to and reuse content from these documents while preparing solutions for a given problem in early SDLC. The only technological help is often a “Ctrl-F” on individual documents to search and pick up relevant information. Even though downstream SDLC phases like coding and testing have long been recognized as focus areas for productivity, and automation exists in terms of code generation and test automation, the technology and automation paradigms are under-exploited in early SDLC phases. The responsibility for solution development during the early SDLC phases lies entirely with the SMEs, and the whole process is entirely manual. There is a huge gap in process infrastructure support for the early SDLC. AI in software development lifecycle is an emerging area of research with a focus on applying intelligent tools and techniques to improve/ accelerate/ disrupt the life cycle. As part of the “AI in SDLC” paradigm, technologies such as natural language processing (NLP), rule-based reasoning are widely explored. This thesis investigates how specific processes in early SDLC can be digitally reimagined to facilitate the transformation from a manual approach to an automated approach. This thesis proposes a generic intelligent Systems/ software Process INfrastructure (iSPIN) framework focusing on extracting solution knowledge into machine-processable models and building intelligent recommender systems for a given problem in the early phases of SDLC. The key contributions of this research are: i) Literature and Field Studies on Quality Models and SDLC Practices to understand the quality challenges and establish the quality gaps in SDLC ii) iSPIN framework for building intelligent technology infrastructure for early SDLC phases iii) A generic SDLC System meta-meta-model (SDLC_MMM) for solution development iv) Case Study1: iSPIN implementation and evaluation for “Request for proposal (RFP) response” process v) Case Study2: iSPIN implementation and evaluation for “Requirements” process The major contribution of this work is the iSPIN framework with crucial building blocks to build an intelligent process infrastructure. A set of technology enablers are proposed comprising an SDLC System meta-meta-model, AI-based knowledge extraction, and intelligent solution recommender. The SDLC system meta-meta-model (SDLC_MMM) captures the essential SDLC process elements and their interactions. AI-based knowledge extraction parses the natural language (NL) documents and automatically extracts key knowledge elements with associated knowledge classification and context tagging. Finally, an intelligent solution recommender analyzes the specific problem in the SDLC phase, determines applicable concerns, recommends relevant knowledge, and automatically composes a machine-first “SDLC output” document as per the required document format providing significant productivity benefits. iSPIN is implemented as a proof of concept (PoC) technology and validated as part of two early SDLC processes for the below use cases - i) For automatically generating a Response to a clientsupplied Request for Proposal (RFP) / Request for Information (RFI) response ii) For generating context-sensitive user stories from diverse Requirements Specifications. For the first use case, The efficacy of the approach has been demonstrated on a set of RFP/RFIs. Based on the case study implementation, it has been observed that for any RFx received from the client, iSPIN can potentially generate 50%-70% of RFP/RFI response automatically. This capability of “Machine First RFP/RFI Response” is a huge value-add for the Presales teams. For the second use case, demonstrated results on two products and 90 requirement specification documents. The model extraction efficiency is very good, with 97% accuracy. While iSPIN has been conceived, developed, and validated for the early SDLC processes, the guiding principles, SDLC_MMM, and the iSPIN framework