7 research outputs found
Bioactive Conserve from Unconventionally Processed Cumin Seeds
No full textThis Dissertation / Report is the outcome of investigation carried out by the creator(s) / author(s) at the department/division of Central Food Technological Research Institute (CFTRI), Mysore mentioned below in this page
Using ISO/IEC 12207 to analyze open source software development processes: an E-learning case study
No full textTo date, there is no comprehensive study of open source software development process (OSSDP) carried out for open source (OS) e-learning systems. This paper presents the work which objectively analyzes the open source software development (OSSD) practices carried out by e-learning systems development communities and their results are represented using DEMO models. These results are compared using ISO/IEC 12207:2008. The comparison of DEMO models with ISO/IEC 12207 is a useful contribution; as it provides deeper understanding to-wards the OS e-learning system development
Mitigating technical challenges in brain-computer interfaces for stroke rehabilitation
No full textBrain-computer interfaces (BCIs) provide a means of non-muscular communication by translating brain activity into the control of external devices. Motor imagery (MI) has attracted significant attention among various non-invasive BCI paradigms using electroencephalogram (EEG) for its potential in stroke rehabilitation. However, MI-based BCIs encounter challenges in real-time applications for stroke patients, primarily due to limited reliability and robustness. Additionally, the scarce availability of clinical data impedes the development of cross-subject models for MI detection in stroke patients. Furthermore, the current MI-BCIs do not adequately facilitate the restoration of distal hand functions, which are essential for enhancing the quality of life for individuals with motor impairments. This thesis proposes solutions to address these technical challenges in BCIs for stroke rehabilitation using deep learning (DL) methods. Furthermore, a novel experimental protocol is introduced to enable clinically relevant practical applications of BCIs in stroke patients.
The research begins with an extensive literature review focusing on the impact of EEG discrepancies on the performance of BCIs. The review delves into channel selection and transfer learning techniques that aim to enhance the resilience of EEG-BCIs. Recently, there has been a surge in studies investigating subject-independent models in the domain of MI-BCI. This trend is driven by the superior predictive capabilities of subject-independent models based on DL compared to subject-specific models. However, the literature review highlights a significant gap in the research, as most studies in this area have focused primarily on healthy subjects, with limited inclusion of stroke patients. Furthermore, the review encompasses relevant studies exploring MI decoding from the same limb.
With the goal of selecting the optimal set of EEG channels to enhance overall classification performance in DL-based MI-BCIs, the author proposes subject-independent channel selection using layer-wise relevance propagation (LRP) and neural network pruning. Traditional approaches to channel selection have focused predominantly on subject-specific optimization, whereas subject-independent methods are essential for the utilization of DL models trained on cross-subject data. The proposed methodology not only achieves a significant reduction in the number of channels but also maintains subject-independent classification accuracy, while ensuring interpretability in terms of underlying neural mechanisms.
Furthermore, in consideration of the limited availability of clinical data to train BCI algorithms, the research investigates the feasibility of employing DL models pre-trained on data from healthy individuals to detect MI in stroke patients, while also taking into account the inter-subject variability between the healthy and stroke populations. Through domain adaptation, the transfer learning approach demonstrates improved MI detection accuracy in stroke patients, surpassing subject-specific models. Interpretability analysis using transfer models determines channel relevance patterns that indicate contributions from the bilateral motor, frontal, and parietal regions of the cortex towards MI detection in stroke patients. Furthermore, the healthy-to-stroke transfer learning achieves comparable performance to stroke-to-stroke transfer learning, highlighting its potential to enhance the clinical use of BCI algorithms.
Finally, a novel BCI experiment utilizing a robotic exoskeleton for unilateral hand motor attempt (MA) tasks is introduced. The focus of stroke rehabilitation is often the recovery of distal hand function. A mere act of opening and closing the hand has the potential to bring about significant enhancements in the quality of life experienced by individuals who have suffered from stroke. In this research study, MA-EEG data collected from healthy subjects is employed to develop subject-specific and subject-independent DL models. The results highlight the importance of this experiment in driving advancements in stroke rehabilitation.
This thesis makes novel contributions to the field by optimizing EEG-BCIs for stroke rehabilitation through subject-independent channel selection, transfer learning from healthy to stroke populations, and a new BCI experiment for same-hand MA-EEG decoding. The findings pave the way for more reliable, applicable, and interpretable BCIs, enhancing their potential for clinical use and rehabilitation purposes.Doctor of Philosoph
Notice of Violation of IEEE Publication Principles - Efficient implementation of QRD-RLS algorithm using hardware-software co-design
No full textClustered Architecture for Adaptive Multimedia Streaming in WiMAX based Cellular Networks
No full textAbstract—In the recent years, there has been an increasing demand for high quality multimedia services over wireless networks. Triple play services (voice, data and video) require data-rates of the order of several megabits per second (Mbps). However, the large transmission distance and the limited battery power of the hand-held wireless device serves as a major bottleneck. There has been no successful mechanism developed till date that would provide live video streaming over wireless networks. In this paper, a novel cluster-based double dumbbell topology is proposed for adaptive multimedia streaming in WiMAX-based multihop cellular networks. The performance of the network is evaluated for a two-hop model and compared with a traditional single-hop cellular design. Extensive simulations have been carried out in terms of different kinds of network traffic and over different protocols. It is observed that the performance of the proposed cluster-based design for WiMAX networks is significantly superior to the one-hop design, not only in terms of the perceived quality, but also in terms of the loss rate and the average bit rate
An analysis of the software development processes of open source E-learning systems
No full textIn recent years there has been a rapid increase in demand for e-learning systems. The software development process plays a crucial role in the design and development of a high-quality e-learning system. However, to date, there is no comprehensive comparative study of open source software (OSS) development process for different OS e-learning systems. This hinders the development of a generalized OSS development process, a key requisite for rapidly developing high-quality OS e-learning systems. This paper provides a full analysis of different existing and successful OS e-learning software systems and the best practices followed in the e-learning development. In particular, this paper investigates the software development activities of Moodle, Dokeos and ILIAS. An activity flow representation that describes their current development practices is constructed individually for all three OS e-learning systems. Further, a comprehensive comparative analysis is carried out that leads to an explicit identification of various development stages of the three OS e-learning systems
Strategic evaluation of vaccine candidate antigens for the prevention of Visceral Leishmaniasis
No full textAbstractInfection with Leishmania parasites results in a range of clinical manifestations and outcomes, the most severe of which is visceral leishmaniasis (VL). Vaccination will likely provide the most effective long-term control strategy, as the large number of vectors and potential infectious reservoirs renders sustained interruption of Leishmania parasite transmission extremely difficult. Selection of the best vaccine is complicated because, although several vaccine antigen candidates have been proposed, they have emerged following production in different platforms. To consolidate the information that has been generated into a single vaccine platform, we expressed seven candidates as recombinant proteins in E. coli. After verifying that each recombinant protein could be recognized by VL patients, we evaluated their protective efficacy against experimental L. donovani infection of mice. Administration in formulation with the Th1-potentiating adjuvant GLA-SE indicated that each antigen could elicit antigen-specific Th1 responses that were protective. Considering the ability to reduce parasite burden along with additional factors such as sequence identity across Leishmania species, we then generated a chimeric fusion protein comprising a combination of the 8E, p21 and SMT proteins. This E. coli –expressed fusion protein was also demonstrated to protect against L. donovani infection. These data indicate a novel recombinant vaccine antigen with the potential for use in VL control programs
