List of Content
Back to Listing
| Title | Abstract | Action(s) |
|---|---|---|
| EVALUATING OBE STUDENTS LEARNING CAPACITY IN HIGHER EDUCATION: TOWARDS COMPREHENSIVE FRAMEWORK | Outcome-Based Education (OBE) is adopted in higher education to make sure that students acquire knowledge and skills that are useful for their future profession. Several strategies based on theoretical frameworks have been developed to improve education in higher education over the past two decades. Outcome-Based Education (OBE) aims to establish specific learning objectives that students are expected to achieve by the end of their educational journey and is also helpful for professional careers. Therefore, OBE approach develops the practical experience of students by integrating educational knowledge with practical skills. There is a lack of studies on the investigation of students' learning capacity and practical skills of OBE graduates in a real environment. To fill the research gap, this study aims to measure attainment of students' learning capacity and practical skills in OBE. Survey research is used to achieve research objectives. The survey respondents are employers of OBE graduates. A total of 140 employers participated in the survey. The result analysis of survey demonstrate that OBE graduates possess practical skills and learning capacity that enables them to effectively perform in real work environment. The research provides a systematic approach to assessing educational outcomes and guides the practitioners towards effectiveness of OBE. In the future, researchers can specifically measure student’s performance in OBE and assess other factors like organization objectives, teaching strategies, and assessment methods in OBE. |
|
| EFFORT ESTIMATION IN AGILE SOFTWARE DEVELOPMENT USING ENSEMBLE LEARNING MODEL | In the domain of software development, effort estimating is an essential procedure that entails projecting the size and schedule of a particular project. It becomes necessary to create an estimate before beginning any software project. Obtaining the required approvals and evaluating the project depends on this preliminary assessment. The importance of this procedure cannot be emphasized since a project's success or failure is solely dependent on how precisely and accurately effort is estimated. There are various cost and effort methods and techniques. These techniques have been utilized to construct several effort estimation models that are used in the software development process in the traditional model. This research explores the application of ensemble learning techniques, specifically stacking, to enhance the accuracy of effort estimation in Agile environments. Stacking involves combining multiple diverse base estimators to create a meta-estimator that outperforms individual models. This study includes a crucial step for gathering datasets because old dataset size is small and old. The proposed approach is assessed using real-world Agile project datasets, proving the advantages of the stacking model over agile software development estimation techniques. |
|
| Intelligent Feedback Controller Design For DC-DC Converter | In this research, a feedback control system for DC-DC converter is designed using artificial intelligence. PID control is widely used as the control method for DC-DC converters. The PID parameter tuning process parameters remains hard in nonlinear case scenarios. As in such scenarios system needs to handle disturbances during load changes and operate under dynamically changing conditions. The system control response with the inclusion of AI technology leads to an improvement in the operation of DC-DC converters through their feedback system and improved the overall ripple on output line. Also, it helps the system to become more stable across different loads at the same time and achieve maximum performance. Furthermore, the proposed AI-based controller has been successfully applied to a real-time Voltage-to-Grid (70V-380V) case scenario, replacing the PID controller in a Neutral Point Clamped (NPC) converter topology. This shows the versatility and effectiveness of this control technique in complex power conversions. Replacement of AI based control with PID helps system in continuous learning and adaptation and as a result real-time control, reduction in output voltage ripple, and enhanced system adaptability under dynamic load conditions and making it suitable for current applications of DC-DC converters. |
|
| MULTI OBJECT TRACKING USING NON-LINEAR FILTERING TECHNIQUES | In this research, the problem of redundant detections of tracks in distributed sensor networks for multi-object tracking is addressed. Measurement noise and network-induced errors often result in multiple detections of the same object, complicating the accurate estimation of object count and position. This makes it challenging to accurately determine the true number of objects and their locations. Track-to-track association algorithms help address this issue. Many such algorithms have been developed and can be broadly categorized into two types: statistical algorithms and clustering-based algorithms. A key clustering-based approach is the fuzzy track-to-track association algorithm, which is the focus of this research. A variation of this algorithm is tested on data generated from a model simulating a multi-sensor, multi-target environment. In real-world sensors, errors typically arise in azimuth, elevation, and range, so this thesis proposes an error model based on these parameters. The association algorithm’s resolutions are also grounded in this realistic error model. Additionally, time synchronization is critical before performing track association. This thesis employs a linear predictor to synchronize tracks before association, and the performance of the algorithm is analyzed under these conditions. |
|
| DUPLICATE BUG REPORT DETECTION USING DATA AUGMENTATION TECHNIQUE | In software projects, developers, testers, and end users identify bugs and report the bugs to the triager. To manage these bug reports, various Bug Tracking Systems (BTS) such as Bugzilla or Jira are used. One bug may be reported by multiple persons to the system which generate Duplicate Bug Reports in the system. Duplicate Bug Report Detection (DBRD) is very important because it results in a significant depletion of human resources. Many researchers proposed a range of machine learning techniques to detect the duplicate bug reports. The existing techniques performs well when a large number of bug reports are used as a training dataset but the performance of existing techniques significantly decreased for small dataset. To overcome this challenge, the data augmentation technique is used to increase the number of bug reports for the projects having small number of bug reports as training data. Various data augmentation techniques like synonym replacement, random insertion, component shuffling and class balance are used to increase the bug data. To validate the performance of data augmentation technique for duplicate bug detection, we used various deep learning models e.g. CNN, LSTM and BERT. We also compare the results of various deep learning techniques to analyze which model performs better with the augmented bug reports data. Our results show that data augmentation improved the results for all three models in term of accuracy, precision, recall, F1-socore and AUC score. The accuracy achieved on augmented data is 94.77%, 94.77% and 96.30% for LSTM, CNN and BERT respectively. |
|
| MRI BASED BRAIN TUMOR CLASSIFICATION AND DETECTION THROUGH MULTI-MODAL DEEP LEARNING TECHNIQUES | Machine learning and deep leaning methods have substantially advanced the efficacy of disease diagnosis in healthcare setups, by facilitating precise and early prognosis of disease, enabling timely intervention and resource optimization. One of the key field where it is stated beneficial is brain tumor diagnosis, a most serious disease which can adversely impact the people of any age group. Despite of significant advancements in the field of deep learning in visual data processing there are still challenges. The research highlighted important challenges in brain tumor scrutiny; comprising morphological uncertainty, tumor heterogeneity, class imbalance, data scarcity, and model accuracy. Besides these challenges the processing of various medical imaging modalities; i.e the data which is obtained from different medical devices like MRI, CT, and PET have inconsistent features, the accuracy results are variant and inadequate. By considering these factors, the research is based on development of two deep learning models; the LSTM model and hybrid 2D UNET + LSTM model to accurately identify and classify four types of brain tumor. Firstly, MRI images are preprocessed using N4ITK bias field correction to eliminate intensity inhomogeneties and to boost their qualities. Then the proposed Hybrid model combine the 2D UNET and LSTM networks, with 2D UNET having four convolutional blocks with variable number of 3x3 sized filters. The networks and layers arrangements are chosen after extensive experimentation. Model performance was accessed using various key metrics including precision, recall, F1 score and specificity. The results demonstrate a significant accuracy of 99.12% of hybrid 2D U-Net + LSTM which outperforms the standalone LSTM model. Additionally, comparative analysis with existing research is performed which notices the better outcomes of the proposed models. Therefore, the research helps in advancing tumor classification accuracy and reliability in medical research |
|
| ARole-Based Framework for integrating Emotional Intelligence in Agile Teams during Requirement Changes | Requirement engineering is a foundational yet challenging aspect of the software development lifecycle (SDLC), particularly within traditional models such as Waterfall, where rigid structures hinder effective change management. While Agile methodologies embrace change, they often introduce emotional complexities that impact individual well-being, team dynamics, and overall performance. Existing literature primarily focuses on the role of Emotional Intelligence (EI) among developers in handling requirements changes, leaving a significant gap in understanding the role-specific emotional needs of other key Agile roles namely, the Product Owner (PO), SCRUMMaster(SM), and the Development Team. This study bridges this gap by identifying the emotional challenges experienced by each Agile role during requirement changes. A survey methodology is used to collect the emotional challenges faced by agile teams during requirement change handling, along with an interview to collect the solutions to each challenge. A total of 202 participants contributed insights through the survey, offering a rich dataset to support the development of a structured, role-specific EI framework. It finds out the role-based emotional reactions, identifies related Emotional Intelligence (EI) competencies, and analyzes demographic effects. The study identified and provided solutions to the RCM challenges, providing ground to develop an Agile Role-Based Emotional Intelligence (ARBEI) Framework. This framework provides practical strategies to foster emotional resilience during requirement change handling. Although the study is limited by its Agile-specific focus and short-term evaluation of EQ training, it opens multiple directions for future research, including cross methodology and cross-industry comparisons. Ultimately, this research highlights the necessity of embedding emotional awareness and EI competencies into Agile practices to enhance both team dynamics and the success of RCM processes |
|
| ARole-Based Framework for integrating Emotional Intelligence in Agile Teams during Requirement Changes | Requirement engineering is a foundational yet challenging aspect of the software development lifecycle (SDLC), particularly within traditional models such as Waterfall, where rigid structures hinder effective change management. While Agile methodologies embrace change, they often introduce emotional complexities that impact individual well-being, team dynamics, and overall performance. Existing literature primarily focuses on the role of Emotional Intelligence (EI) among developers in handling requirements changes, leaving a significant gap in understanding the role-specific emotional needs of other key Agile roles namely, the Product Owner (PO), SCRUMMaster(SM), and the Development Team. This study bridges this gap by identifying the emotional challenges experienced by each Agile role during requirement changes. A survey methodology is used to collect the emotional challenges faced by agile teams during requirement change handling, along with an interview to collect the solutions to each challenge. A total of 202 participants contributed insights through the survey, offering a rich dataset to support the development of a structured, role-specific EI framework. It finds out the role-based emotional reactions, identifies related Emotional Intelligence (EI) competencies, and analyzes demographic effects. The study identified and provided solutions to the RCM challenges, providing ground to develop an Agile Role-Based Emotional Intelligence (ARBEI) Framework. This framework provides practical strategies to foster emotional resilience during requirement change handling. Although the study is limited by its Agile-specific focus and short-term evaluation of EQ training, it opens multiple directions for future research, including cross methodology and cross-industry comparisons. Ultimately, this research highlights the necessity of embedding emotional awareness and EI competencies into Agile practices to enhance both team dynamics and the success of RCM processes |
|