M Tech Dissertations

Permanent URI for this collectionhttp://drsr.daiict.ac.in/handle/123456789/3

Browse

Filters

2021 - 20222

Settings

Author: search.filters.author.Gupta, SiddhantStart date: 2010

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Indoor Localization Using Ambient Magnetic Fields
    (Dhirubhai Ambani Institute of Information and Communication Technology, 2022) Gupta, Siddhant; Sasidhar, Kalyan
    For over a decade, Indoor Localization has been a crucial topic among researchers. A multitude of localization solutions has been provided so far, including radio frequency based solutions like WiFi, Bluetooth and RFID based localizing and positioning systems. These infrastructure based solutions require a set of additional devices to be installed, which comes with challenges like huge installation costs. These solutions are device dependent. Also, attenuation in signal strength throughout the day leads to a major error in localization. A recent addition to this system is magnetic field based localization techniques. The solution lies in exploiting the ambient magnetic fields present inside buildings and their unique variations caused by the presence of ferromagnetic objects such as pillars, doors, and elevators. Smartphone based built in magnetometers have been the default data sensing platforms. The data collected from smartphones are used by deterministic or probabilistic algorithms for estimating locations. However, the performance of these algorithms depends on the diversity in the sensor models built- in the smartphones, diversity in the users using the phones, and diversity across space and time. There is a dearth of analyses of how these diverse factors affect the performance of magnetic field based solutions. We assess the impact of the four diversity parameters on the dynamic time warping algorithm in estimating the users� location. We discuss our findings from experiments conducted across three different buildings and eight different sensor models with five users.
  • Thumbnail Image
    ItemOpen Access
    Deep Learning for Severity Level-based Classification of Dysarthria
    (2021) Gupta, Siddhant; Patil, Hemant A.
    Dysarthria is a motor speech disorder in which muscles required to speak somehow gets damaged or paralyzed resulting in an adverse effect to the articulatory elements in the speech and rendering the output voice unintelligible. Dysarthria is considered to be one of the most common form of speech disorders. Dysarthria occurs as a result of several neurological and neuro-degenerative diseases, such as Parkinson’s Disease, Cerebral palsy, etc. People suffering from dysarthria face difficulties in conveying vocal messages and emotions, which in many cases transform into depression and social isolation amongst the individuals. Dysarthria has become a major speech technology issue as the systems that work efficiently for normal speech, such as Automatic Speech Recognition systems, do not provide satisfactory results for corresponding dysarthric speech. In addition, people suffering from dysarthria are generally limited by their motor functions. Therefore, development of voice assisted systems for them become all the more crucial. Furthermore, analysis and classification of dysarthric speech can be useful in tracking the progression of disease and its treatment in a patient. In this thesis, dysarthria has been studied as a speech technology problem to classify dysarthric speech into four severity-levels. Since, people with dysarthria face problem during long speech utterances, short duration speech segments (maximum 1s) have been used for the task, to explore the practical applicability of the thesis work. In addition, analysis of dysarthric speech has been done using different methods such as time-domain waveforms, Linear prediction profile, Teager Energy Operator profile, Short-Time Fourier Transform etc., to distinguish the best representative feature for the classification task. With the rise in Artificial Intelligence, deep learning techniques have been gaining significant popularity in the machine classification and pattern recognition tasks. Therefore, to keep the thesis work relevant, several machine learning and deep learning techniques, such as Gaussian Mixture Models (GMM), Convolutional Neural Network (CCN), Light Convolutional Neural Network (LCNN), and Residual Neural Network (ResNet) have been adopted. The severity levelbased classification task has been evaluated on various popular measures such as, classification accuracy and F1-scores. In addition, for comparison with the short duration speech, classification has also been done on long duration speech (more than 1 sec) data. Furthermore, to enhance the relevance of the work, experiments have been performed on statically meaningful and widely used Universal Access-Speech Corpus.