Abstract

Statistical Machine Translation (SMT) is an automated approach to Natural-Language translation, that utilizes statistical models generated from the bilingual parallel corpora. The system is thus funda- mentally reliant on the bilingual parallel corpora, to translate text from one language to another. Ad- ditionally, in the past several decades, research in SMT has been focused on augmenting syntactic and linguistic information to the statistical models to generate better translations. Thus, construction of the aforementioned linguistic resources like bilingual parallel corpora and corpora enriched with syntactic and linguistic information plays a key role in building better SMT systems. SMT work for the English-Hindi languages are limited and have been resource deprived, especially for the Hindi language. The prime motivation for the research in this thesis is to bridge the gaps in the level of resources available for Hindi language and the English-Hindi language pair, from an SMT per- spective. The initial experiments at building a Hindi-English SMT system with Part-Of-Speech (POS) augmented models yielded unfavourable results, with translations that are no better than the plain statis- tical models. Root cause analysis revealed fundamental flaws like lack of better bilingual corpora and better syntactic models, which hinders the improvements to SMT system, thus setting the goal of this thesis towards addressing these issues. Firstly, we start by presenting several parallel corpora for English$Hindi and talk about their na- tures and domains. We also discuss briefly a few previous attempts in MT for translation from English to Hindi. The lack of uniformly annotated data makes it difficult to compare these attempts and pre- cisely analyse their strengths and shortcomings. With this in mind, a standard pipeline to provide uni- form linguistic annotations to these resources using the state-of-art NLP technologies is presented. The benchmark scores for various English!Hindi SMT systems are constructed using the aforementioned parallel corpora. A total of 1,37,578 sentences were cleaned and MT systems were benchmarked as part of this work. Subsequently which, this thesis talks about several digital text sources from different domains in English and Hindi languages which were processed with the intention of extracting parallel sentences. We faced several difficulties while extracting text content from different documents, especially the non- linear presentation of text in varying page layouts. We focus on this problem of linearizing the text from these digital sources by proposing a clustering based algorithm to eliminate the noise. The effort undertaken helped us process the raw sources available in different formats, different fonts and varying page layouts to produce 79,422 English and 68,584 Hindi sentences with comparable meanings across both languages. Lastly, a semi-automated framework is presented to enable speeding up dependency annotation task for corpora. We talk about the slow game of pass-the-parcel in between both the automation and hu- man sides which finally results in raw corpora being transformed into dependency annotated sentences. The methods of automation chosen to overcome the laborious and time-consuming process of corpora annotation are discussed. Along side which the errors and multiple analyses that result through the task of annotation and ways to recover are also discussed in detail. A total of 20,968 dependency annotated Hindi sentences and 7,120 Urdu sentences are created using the mentioned framework. Overall, the thesis tries to present three different efforts undertaken to quench the thirst for resources in the field of English$Hindi SMT.

Abstract

Complex noun sequences in Hindi can be formed by the sequences of nouns and genitives. In Hindi, the genitive marker is “k¯a”, and its allomorphic variations are “ke” and “k¯i”. When two or more nouns occur without any intervening post-positions, it is known as compound noun. Following are some examples of complex noun sequences: (1) “jil¯a cun¯ava adhik¯ar¯i” (district election officer), (2) “tila k¯i mit.h¯a¯i k¯i duk¯ana” (shop of sweets made with sesame) and (3) “upabhokt¯a ad¯alata ke vak¯ila” (consumer court’s lawyer). The rightmost noun is the head of the whole construction. The inner structure of the sequence can be quite complex. In it, (a) nouns within the sequence can modify the rightmost head or (b) the local head can modify another local head or the head of the complex noun sequence. For example, in (1), “adhik¯ar¯i” is the head and both “jil¯a” and “cun¯ava” are modifying “adhik¯ar¯i” thus having a structure (jil¯a (cun¯ava adhik¯ar¯i)). But, the complex sequence in (2) has a structure where “tila” modifies “mit.h¯a¯i” and “mit.h¯a¯i” in turn modifies “duk¯ana”. So the structure is ((tila k¯i mit.h¯a¯i) k¯i duk¯ana). More number of nouns within a sequence, more complex is the structure. From the Hindi Treebank data, we have obtained 85.37%, 12.54% and 1.80% of the sequences having three, four and five nouns respectively. In this thesis, we attempt to bracket the local sub-structure of a complex noun sequence which is termed as constituency parsing. Constituency parsing recursively builds the inner structure of the complex noun sequence. It is a very significant NLP task because the interpretation of sequence depends on the correct identification of its inner structure. We explore both syntactic and statistical method for predicting the bracketing of the complex noun sequences. In Hindi, the genitive marker agrees with the head of the sub-sequence modified by it. This clue has been used in our syntactic approach. In statistical approach, we have mainly exploited the affinity factor of a head and its modifier based on the frequency of occurring together in the corpus. The method has been augmented by introducing the semantic class information for the head and modifier nouns from Hindi WordNet. Finally, we combine the two methods and implement a hybrid approach for bracketing complex noun sequences. Using this, we have obtained 85.85% accuracy. In this thesis, we show that the identification of the inner structure of complex noun sequence helps in determining the translation. For this experiment, we take three-word noun compounds of English and translate them into Hindi. The strategy of the translation is determined by our observation of English-Hindi parallel corpora where we observe (and others have reported also) that English licenses multiword noun compound more frequently than what Hindi does. Hindi prefers syntactic phrases where a genitive post-position is inserted between the head and the modifier. In the case of compounds with three nouns, we propose that inner bracketing helps in determining the insertion of the genitive marker. For the left bracketing structure ((e1 e2) e3), we predict that the genitive will be inserted before e3. For the right bracketing structure (e1 (e2 e3)), the genitive will be inserted after e1. This hypothesis is tested, and we get the accuracy of 68.86%, 71.99% and 59.12% for BNC, ukWaC and ILCI corpus respectively.

Abstract

Of late, sentiment analysis has transpired to be a critical cog in a slew of diverse Natural Language Processing tasks like recommendation systems, question answering, and business intelligence products to name a few. At its core, sentiment analysis is the process of analyzing emotions in a given piece of text, where the excerpt at hand is predominantly classified as carrying either a positive or a negative polarity. While the study of sentiment analysis in English has been proliferating, to say the least, the task has hardly been probed in Telugu. In this thesis, we attempt to get down to the brass tacks of sentiment analysis for the language popularly known as the Italian of East. While sentiment analysis in itself poses tremendous challenges, an additional problem in Telugu, that has restrained people from conducting active research, is the availability of appropriate data. We thus address the latter first, to ensure that the former problem is tackled more effectively. To address data availability, using a set of well-defined annotation guidelines, we first manually annotate Telugu texts with either positive, negative or neutral tag. The annotated data is then used to carry the sentiment analysis task, where a variety of machine learning algorithms are employed to handle both binary (only positive and negative tags) and ternary (positive, neutral and negative tags) sentiment analysis classification problems. Our experiments reveal that while a tad complex classifier like Random Forests can rule the roost in the case of binary classification task, a simple classifier like logistic regression can come up trumps should the task be framed as a ternary classification problem. It is a known fact that learning algorithms improve with an increase in the amount of training data. However, manually annotating data is practically difficult and expensive. To address these issues, we employ a novel approach of Hybrid Query Selection Strategy to increase the annotated data, where a set of classifiers are adopted to annotate data. Experiments show that our approach effectively achieves this with a minimal error rate. We also use active learning to classify sentences according to their polarities, thereby achieving our end goal.

Abstract

Obtaining awareness about the state of the spectrum via sensing is crucial in many systems including cognitive radio (CR), cognitive radars, automotive sensing and communication where spectrum sharing is required. In the context of CR, spectrum sensing is a key enabler for obtaining spectrum awareness, which detects the activity of a licensed user or primary user (PU) in a particular band of interest to provide opportunistic usage of spectrum to the secondary users (SUs). In this thesis, we focus on cooperative energy detection (CED) in a CR network. CED is a distributed detection scheme where all the SUs employing energy detector (ED), collaborate to perform spectrum sensing to identify spectrum holes. A centralized soft combining approach is considered such that the SUs sends the energy value, calculated from the received signal, to the fusion center (FC). Using sum fusion rule and Neyman-Pearson (NP) criterion, the FC makes the global decision of whether the frequency band is occupied by the PU or not. However, implementing CED requires knowledge of noise variance (noise power) for setting the threshold. But in real world scenario, noise variance may change due to several reasons such as temperature, external interference, etc. As a result, slight change or deviation of noise variance from the assumed value leads to unpredictable performance in CED. Moreover, in the presence of noise uncertainty (NU), CED suers from performance limitation in the form of signal-to-noise-ratio (SNR) wall. SNR wall phenomenon in CED has been well investigated in literature but only considering homogeneous CR nodes having same NU parameters. In this thesis, we extend the concept of SNR wall in CED to a more general case by considering that all the participating SUs have dierent NU parameters. The generalized SNR expression for this case is derived and a new terminology called SP wall" is dened to explain the concept of SNR wall in this heterogeneous CR network. Handling NU in CED using traditional probabilistic methods have not borne any fruits beyond certain thresholds, which forced us to look for concepts and theories beyond standard Bayesian approach. In this context, Dempster-Shafer theory (DST) (also called evidence theory) provides a new dimension to the picture. It enables us to include uncertainty or ignorance as a quantity in the fusion process. The theory has the ability to quantify our lack of knowledge or how much we are uncertain about something, instead of ignoring them altogether. Using the tools of evidence theory, we forged a new CED algorithm for spectrum sensing under NU. In the proposed scheme, the SUs sends basic mass assignment (BMA) values or belief values to the FC, instead of the energy values. A novel method to compute the BMA values based on energy of the received signal is proposed. The uncertainty in noise variance is accounted by discounting the BMA values of each SU by the amount of trust associated with the SU, where the trust factor is inversely proportional to the amount of NU present in the SU. At the FC, Dempster combination rule is applied to fuse these discounted BMA values. Even in this case, NP criterion is employed for designing the detector at the FC. The nal test statistic is compared with the predened threshold (based on NP criterion) to make the global decision. Extensive simulation results have shown that the proposed DST based CED scheme is able to surpass the traditional soft combining based CED scheme and is also successful in lowering the SNR/SP wall barrier of CED.

Abstract

Internet is growing more with time and the popularity of social media is growing at a faster rate. There is huge growth of users using informal language on the internet as opposed to formal language. In a country like India where most users are bilingual or multilingual, the content available on social media is also code-mixed. Code mixing refers to the embedding of linguistic units such as phrases, words and morphemes of one language into an utterance of another language [26]. Social media stands as one of the closest available mirrors to the real world. It shows how users react to current events and engage with each other. This data provides evidence, objectivity and hidden insight to the world, which can be used for various purposes. Given the many benefits of social media understanding, it is important to develop tools useful for processing such data. There is a large body of work done on code mixed social media data by the research community all over the world but very less with respect to Indian languages. There is no work done on English- Telugu pair so far. This thesis describes the work done towards building a shallow parser pipeline for English-Telugu code mixed social media data as collected from Facebook. The data is annotated with language labels, normalized form of the word, POS tag of it and chunk level information for 10,207 words. Shallow parsing can be used as a pre processing tool for many Natural languge processing applications like summarization of posts/replies on social media, multi-lingual machine translation on microblogs, in building user friendly human computer interaction systems etc. Shallow Parsing pipeline consists of four modules, namely, Language Identification, Normalization, POS Tagger and chunker. Language Identification is the process of Identifying the language of every token in the text. This is the foremost step for any further processing of code-mixed text. Normalization is the process of translating the data into the standard form. Part-of-Speech Tagging is a primary and an important step for many Natural Language Processing Applications. POS Taggers and Shallow Parsers have reported high accuracies on grammatically correct monolingual data. POS tagging is considered as a classification problem and we use different classifiers like Linear SVMs, CRFs, Multinomial Bayes with different combinations of features which capture both context of the word and its internal structure. The work on experiments with combining monolingual POS taggers for POS tagging of this code mixed English-Telugu data is also reported. Chunking is also treated as a classification problem and we use various combinations of features to train the learning model.

Abstract

Information theory plays a vital role in today’s computational world. According to the past research, the capabilities of the quantum information processing exceeds that of the classical methods in most of the cases. However, there are few phenomena where quantum mechanics puts limitations such as’cloning’ information. In classical computers, we can copy the information from one place to another without any alteration. But, we cannot achieve the similar results following the quantum rules. This limitations of the quantum mechanics comes from ’no cloning theorem’ which says that it is impossible to copy an arbitrary pure state (information) perfectly. But the possibility of an imperfect cloning is never denied. Broadly, two types of quantum cloning machines have been discussed in past: approximate cloning machine, which gives imperfect copies and probabilistic cloning machines, which gives a perfect copy but only with some non-unit probability. The quality of the state cloned is measured in terms of ’fidelity of cloning’. The approximate cloning machines, whose fidelity depends on the input state, are called state dependent cloning machines. However, the state independent cloning machine copies any state with the same fidelity. In this work, we talk about the state independent approximate cloning machines. We extend the already existing 1 to N local cloning machine and give the cloning transformations to apply it non-locally. Along with the cloning of a state, one more phenomena is of interest here, that is, cloning of entanglement. Quantum entanglement is one of the peculiarities of quantum mechanics, which makes the phenomena such as quantum teleportation and super-dense coding possible. When we refer broadcasting of an entangled state, we mean creating more pairs of less entangled state from a given entangled state. One way of doing this is by applying local cloning transformations on each qubit of the given entangled state. This can also be done by applying global cloning operations on the entangled state itself. It is known that the broadcasting of entanglement into more than two entangled pairs is not possible using only local operations. Also, Inseparability is optimally broadcast when symmetric cloners are applied. This is mostly required when we perform distributed information processing tasks. It is natural to expect in a bi-partite situation that these newly created entangled states are less suitable in tasks like teleportation and super-dense coding than the parent state. However, the dependence of the usability of such states in information processing tasks on our ability of broadcasting is not well known. In this work we obtain several complementary relations manifesting the interdependence of their information processing capabilities and fidelity of broadcasting. We extend our investigation in a situation where vi vii instead of using 1-2 cloning, we have used 1-N cloning transformations both locally and non-locally. Eventually we find out the fidelity of broadcasting and the change in the information processing capacities for different values of N(3,4,5) and investigate how these complementary relations behave with the increase in number of copies(N).

Abstract

The field of data mining has evolved to help organizations find interesting knowledge from databases. Under data mining, different knowledge extraction approaches like association rules, classification and clustering have been proposed. Association rules are generated by analyzing the transactional databases using the support and confidence interestingness measures to identify the most important relationships among the items. Discovering frequent patterns is a key step in association rule mining. A pattern is called a frequent pattern if it satisfies the user-defined threshold on minimum support. Periodic-frequent patterns come under the class of frequent patterns which capture the temporal dimension of a pattern. In this thesis, we made efforts to improve the performance of mining periodic-frequent patterns. Periodic-frequent patterns are an important class of regularities that exist in a transactional database. A pattern is called periodic-frequent if it satisfies the thresholds of minimum support and maximum periodicity. Here, support is the frequency and periodicity is the maximum inter-arrival time of the pattern. In the literature, an algorithm called periodic-frequent pattern growth (PF-growth) was proposed which extracts the complete set of periodic-frequent patterns from transactional databases. Here, the transactional database is initially compressed into a prefix-tree like structure called periodic-frequent pattern tree (PF-tree), which is recursively mined to extract the patterns. The PF-tree explicitly maintains the transaction identifier information of each transaction. This enables the calculation of periodicity, but nevertheless the PF-tree size increases. In recent times, the amount of data generated from e-Commerce and social-networking sites are very huge. Mining periodic-frequent patterns from these datasets require large amounts of main memory and faster processing power. We propose the following two approaches to overcome these issues: (i) mining periodic-frequent patterns using the notion of period summary and (ii) a Map-Reduce based approach to extract periodic-frequent patterns. In the first approach, a novel compression technique called period summary is introduced to reduce the amount of memory consumed to extract periodic-frequent patterns. It is based on the observation that the periodic-frequent patterns can also be extracted by storing period summaries instead of transaction identifiers in the tree structure. The performance is improved as the memory required to store the period summaries is significantly less than the memory required to store the list of transaction identifiers. The process of merging period summaries is also introduced to find the support and periodicity values of a candidate pattern. Apart from memory optimization, the time consumed has also been lowered. This is because, the linear time-complexity for finding a candidate pattern’s periodicity using a list of transaction identifiers has been reduced to a constant time operation using period summaries. Experimental results on three real-world datasets show that the proposed approach using period summary performs better than the existing approach both in terms of memory and time. Further in the second approach, a Map-Reduce based approach to extract periodic-frequent patterns is proposed. As the real-world datasets are very huge, extraction of periodic-frequent patterns on a single machine takes a lot of time and in some cases it becomes difficult because of the memory constraints. The proposed approach is scalable and utilizes multiple machines by considering Map-Reduce framework. It consists of two Map-Reduce phases. In the first phase, all one-sized periodic-frequent patterns are derived and in the second phase, independent trees are constructed on different machines. These independent trees are mined parallely on different machines to find the complete set of periodic-frequent patterns. Further, we proposed the notion of partition summary to reduce the amount of data shuffled among the machines, which improves the performance. Experiments on Apache Spark’s distributed environment show that the proposed approach speeds up with increase in the number of machines. Also, the notion of partition summary significantly reduces the amount of data shuffled among the machines. Overall, the process of mining periodic-frequent patterns from transactional databases has been made efficient, both in terms of memory and time. This paves a way for various e-Commerce and social-networking sites to use the knowledge of periodic-frequent patterns in the areas of customer relation management, inventory management, recommendation systems and so on.

Abstract

Recently, the interest in Micro Aerial Vehicles (MAVs) and their autonomous flights has increased tremendously and significant advances have been made. The monocular camera has turned out to be most popular sensing modality for MAVs as it is light-weight, does not consume more power, and encodes rich information about the environment around. In this work, we present DeepFly, our framework for autonomous navigation of a quadcopter equipped with monocular camera. The navigable space detection and waypoint selection are fundamental components of autonomous navigation system. They have broader meaning than just detecting and avoiding immediate obstacles. Finding the navigable space emphasizes equally on avoiding obstacles and detecting ideal regions to move next to. The ideal region can be defined by two properties: 1) All the points in the region have approximately same high depth value and 2) The area covered by the points of the region in the disparity map is considerably large. The waypoints selected from these navigable spaces assure collision-free path which is safer than path obtained from other waypoint selection methods which do not consider neighboring information. In our approach, we obtain a dense disparity map by performing a translation maneuver. This disparity map is input to a deep neural network which predicts bounding boxes for multiple navigable regions. Our deep convolutional neural network with shortcut connections regresses variable number of outputs without any complex architectural add on. Our autonomous navigation approach has been successfully tested in both indoors and outdoors environment and in range of lighting conditions. We also propose a novel pipeline for detecting, localizing, and recognizing trees with a quadcoptor equipped with monocular camera. The quadcoptor flies in an area of semi-dense plantation filled with many trees of more than 5 meter in height. Trees are detected on a per frame basis using state of the art Convolutional Neural Networks inspired by recent rapid advancements showcased in Deep Learning literature. Once detected, the trees are tagged with a GPS coordinate through our global localizing and positioning framework. Further the localized trees are segmented, characterized by feature descriptors, and stored in a database by their GPS coordinates. In a subsequent run in the same area, the trees that get detected are queried to the database and get associated with the trees in the database. The association problem is posed as a dynamic programming problem and the optimal association is inferred. The algorithm has been verified in various zones in our campus infested with trees with varying density on the Bebop 2 drone equipped with fisheye wide angle vision. High percentage of successful recognition and association of the trees between two or more runs is the cornerstone of this effort. The proposed method is also able to identify if trees are missing from their expected GPS tagged locations thereby making it possible to immediately alert concerned authorities about possible unlawful felling of trees. We also propose a novel way of obtaining dense disparity map for quadcopter with monocular camera.

Abstract

In this thesis, we investigate spectral graph theoretic techniques especially heat-kernel embedding as a route to graph representation, in order to solve commonly known Pose-Graph applications in Robotics such as Simultaneous Localization and Mapping problem and mining Multi-Trajectory Pose Correspondences. The Simultaneous Localization and Mapping problem (SLAM) in robotics is typically modeled as a dyadic graph of relative pose measurements taken by the robot. The graph nodes store the values representing the absolute pose of the robot at a given point of time. An edge connecting two nodes represents robot movement and it stores the measurements taken by the robot sensor while moving between two nodes. The objective of the SLAM problem is to find the optimal global measurements best satisfying the noisy relative measurements [29]. This problem of optimal estimation on a graph given relative measurements is a well-studied problem , for which several results and algorithms are known [6, 7]. In this thesis, we explore the applications of spectral graph theory in assisting the problem of single and multi-robot SLAM. SLAM is generally solved as a least squares problem. Robust kernels which are less sensitive to outliers are used to deal with noise and outlier measurements. However, robust kernels tend to be dependent on initialization and can fail as the number of outliers increase. Therefore, it’s important to identify and prune the outlier (noisy) measurements represented by incorrect loop closure edges for an accurate pose estimate. Therefore, we propose a multi-scale Heat-Kernel analysis based loop closure edge pruning algorithm for the SLAM graph. We show that compared to other pruning algorithms, our algorithm has a substantially higher precision and recall when compared and is able to handle a large amount of outlier measurements. We have corroborated results on several publicly available datasets and several types of noise. Our algorithm is not restricted to SLAM graphs only, but has a much wider applicability to other types of geometric graphs. Furthermore, in the case of multi-robot SLAM problem, we consider the problem of finding pose matches between trajectories of multiple robots in their respective coordinate frames or equivalent matches between trajectories obtained during different sessions. Pose correspondences between trajectories are mediated by common landmarks represented in a topological map lacking distinct metric coordinates. Despite such lack of explicit metric level associations, we mine preliminary pose level correspondences between trajectories through a novel multi-scale heat-kernel descriptor and correspondence graph framework. These serve as an improved initialization for ICP (Iterative Closest Point) to yield dense pose correspondences. The set of models and framework proposed in this thesis could act as the basic building blocks in the future works attempting to advance the science of building smarter SLAM systems.

Abstract

A decade or so ago, setting up online businesses called for upfront investments in hardware and software. It also required regular expenses in, maintenance, upgrades etc. However, with the advent of cloud computing, this infrastructure was now able to be “rented” from a shared pool of resources which was present remotely. This was much cheaper than investing in one’s own hardware/software and provided many other advantages such as scalability, reliability, maintenance etc. Today, any new online business can launch its application with minimal costs, just by renting servers on a cloud. Load balancing means optimizing the distribution of workloads across multiple computing resources, to maximize the efficiency of each resource. Load balancing can be done at different layers of the stack, like application, network, CPU, disk etc. but in this thesis, we focus on improving it at the application layer and the network layer. We first look at an example of load balancing at the application layer. Most applications on the cloud are made to be horizontally scalable, i.e. addition of more number of servers would enable the application to handle more load. However, this also causes an increase in the costs to the business, for renting more number of servers. Therefore, it is important to distribute the load among servers smartly, so that a smaller number of servers are able to handle a given load. This requires good data distribution strategies and load balancing algorithms which adapt to the requests and the kind of data being accessed. Today, most of the companies which work with BigData use NoSQL databases to store huge volumes of data. They prefer NoSQL over relational databases because NoSQL databases are horizontally scalable, and have much better read-write performance due to the lack of a schema. Distributed Key-value stores are a type of NoSQL database which is used heavily in most applications, for storing billions of key-value pairs. Key-value stores are required to have a very high throughput as the applications using them need to perform millions of queries/updates per second. Having good load balancing algorithms helps in achieving a better throughput using the same number of servers. We analyze, compare and look at trade-offs in different load distribution schemes for consistent hashing in distributed key-value stores. Different traffic patterns, including an adversarial pattern, were constructed to test the load distribution. A simulator was made for each load distribution scheme and the load on each node was recorded. It was shown that increasing the number of consistent hash rings doesn’t change the load distribution characteristics in simple traffic scenarios, but in the case of adversarial traffic, increasing the number of hash rings leads to an improvement of around 15% in the load distribution statistics. Secondly, we look at an example of load balancing at the network layer. Nowadays, large datacenters are moving from a traditional network to a software-defined network. Software Defined Networking( SDN) lets the network administrator create his own software for defining rules to create flow routes. Since the network administrator knows about the topology and other specifications of the network, it is possible to make packets take different routes based on the various requirements, by just programming the OpenFlow controller. There are different kinds of applications with different requirements in a datacenter. Some require low latency and are not sensitive to bandwidth, others require low packet loss etc. Thus, each application has its own requirements profile. For example, a gaming server hosted on the cloud would require extremely low latency, but would not care about bandwidth. Video streaming services, on the other hand, are sensitive to bandwidth and packet loss. In the existing networks, it is very hard to control the routes that the packets take. We create an OpenFlow controller, which uses the requirements profile of each application using the network and tries to route traffic to optimize the network parameters that the application is most sensitive to. The controller is able to adapt to changing network conditions, and intelligently updates existing routes to accommodate for the network disruptions. We test it in different scenarios with different application requirements and study the improvements that the new controller gives over the existing one. We simulate and show that file transfer of 10MB on an unstable network took 168 seconds using a simple controller, and was optimized to 88 seconds using our controller. We also simulate video streaming on an unstable network and show that our controller adapts to these fluctuations in the network and pro-actively re-routes traffic, to make the stream non-lossy. We also looked at how we can optimize migration of virtual machines for load balancing by leveraging the knowledge of migration, on t