INTI Institutional Repository
Not a member yet
2178 research outputs found
Sort by
Artificial Intelligence in Engineering Education: A Review of Pedagogical Innovations
No full textThis study critically evaluates the integration of artificial intelligence (AI) into engineering
education, with a specific focus on its transformative role within the Digital-Intelligent Era.
Drawing on General Systems Theory (GST), this research synthesizes insights from 82 empirical
studies spanning 2011 to 2024, exploring AI's impact on the evolution of educational frameworks.
The study identifies six key application domains of AI within engineering education, including
intelligent tutoring systems, adaptive learning platforms, virtual laboratories, and personalized
curriculum design. It highlights the synergy between AI and other emerging technologies, such as
5G, Cloud Computing, and Big Data, driving pedagogical innovation and enhancing the learning
experience. Additionally, the paper addresses challenges related to the implementation of AI-based
educational strategies, including infrastructure limitations, resistance to change, and equity
concerns. Finally, it offers strategic solutions to overcome these challenges, fostering a more
inclusive and effective educational environment
Machine Learning for Fake News Detection Analysis
No full textThe COVID-19 outbreak has required some health and financial decisions to be made in an
unwieldy manner. This has spread uncertainty and lies all over the world. The transmission of
false information has been compounded by the problems with fake news. Many of them gave
up on newspapers, magazines, and other print media in favor of Internet pleasure. Online
entertainment has become the primary news source for a sizable percentage of the population
due to its ease of access, low cost, and rapid spread. In some circumstances, bogus information
spreads faster than true information to gain popularity over internet entertainment and divert
people from the underlying issues. People spread false information using online entertainment
for commercial and political benefit. To avoid a harmful influence on society, it is critical to
immediately recognize bogus information in all systems. To demonstrate the efficiency of the
grouping on the dataset, we produced and tested numerous AI computations independently for
this assignment, which looks into research on the recognition of fake news. The Jupyter
Notebook stage of this project was used, and the execution was assessed
The Crop Price Prediction Using Machine Learning: Preliminary Stage
No full textThe objective of our research is mostly concerned with agriculture. Farmers are the key players
in agriculture. Knowing how much a crop will cost will enable you to make smarter judgments,
which will reduce the losses and lower the risk of price changes. An ML model that forecasts
agricultural prices in advance while accurately analyzing the crop may be able to solve this
issue. A predictive system, a statistical method combining machine learning and data collecting,
is used in many applications, including healthcare, retail, education, and government sectors.
Its usage in the agriculture sector has comparable relevance. The back-end predictive model
for this project is created utilizing machine learning algorithms. The steps involved in creating
a predictive model are data collecting, data cleaning, data mining, and validation. The goal is
to give farmers an intuitive user interface, and this model should correctly forecast crop market
value given the real-time variables provided
Comparative Analysis of Pneumonia Detection from Chest X-Ray Images Using CNN And Transfer Learning
No full textA widespread bacterial or viral infection of the respiratory tract, pneumonia affects many people. particularly in developing and impoverished countries where pollution, unsanitary living conditions, and overcrowding are all too common, as well as a lack of medical infrastructure. Pneumonia produces pleural effusion, which is a condition in which fluids fill the lungs and create breathing problems. Early detection of pneumonia is critical for ensuring a cure and improving survival rates. The most common method for detecting pneumonia is chest X-ray imaging. As opposed to that, examining chest X-rays can be challenging and vulnerable to subjective fluctuation. A computer-aided diagnosis method for automatic pneumonia detection utilizing This research includes the creation of chest Images from X-rays. To evaluate which model is superior, an experiment was conducted utilizing a publicly accessible database on all three models. A Convolutional Neural Network (CNN) model was developed to address the lack of readily available data. together using transfer learning strategies like Mobile Net and VCG. On a dataset of accessible pneumonia X-rays, the method was tested. This research shows which neural network algorithm is optimal for detecting pneumonia, and how medical practitioners might use it in the actual world. Keywords: Pneumonia, Chest X-ray, Deep Learning, Convolutional Neural Network (CNN), Mobile Net, VCG, ReLU, Max pooling
Analyzing the Web-Based Library Information System at SMKN 1 Talang Ubi
No full textIn the rapidly evolving field of information technology, the transition from manual to computerized systems has become essential for improving efficiency and accessibility. This study focuses on the analysis, development,and evaluation of a Web-Based Library Information System at SMK Negeri 1 Talang Ubi, aimed at modernizing library management through automation. The system facilitates processes such as book borrowing, member registration, and data management, with the added benefit of remote accessibility. The system was developed using the Web Engineering methodology, which includes stages of Customer Communication, Planning, Modeling, Construction, and Delivery & Feedback. UML (Unified Modeling Language) tools were employed for system design, and PHP, HTML, and MySQL were utilized for programming and database management. Usability testing with 100 participants revealed positive outcomes: 80% rated the system's navigation and design as "Excellent" or "Good," and 80% found the user interface consistent across different sections. However, 10% of participants experienced issues with device accessibility, indicating a need for further improvements in cross-device compatibility. Overall, 80% of users were satisfied with their experience. The Web-Based Library Information System at SMK Negeri 1 Talang Ubi has successfully enhanced library management through improved efficiency and accessibility. The high satisfaction rates among users highlight the system's strengths, although addressing cross-device accessibilityissues remains a priority. This study provides a valuable framework for other educational institutions seeking to implement similar web-based solution
Effect of Extracorporeal Shock Wave Therapy in Conjunction with Kinetic Chain Based Exercises on Pain, Kinesiophobia, and Functional Outcome in Chronic Subacromial Pain Syndrome Participants -A Case Series
No full textBackground and Objectives: Chronic Subacromial Pain Syndrome (CSAPS) is a common
condition characterized by persistent shoulder pain and functional limitations. Despite existing
non-operative treatments, patients often experience chronic pain, fear of movement
(kinesiophobia) and impact shoulder function. The primary objective of this study is to evaluate
the effects of extracorporeal shock wave therapy in conjunction with kinetic chain-based exercises
on pain, kinesiophobia, and shoulder functional outcomes in individuals with CSAPS.
Methodology: This case series included ten participants with unilateral shoulder pain lasting at
least three months. Participants received extracorporeal shock wave therapy biweekly for six
weeks alongside a structured kinetic chain exercise program. Outcome measures included the
Numeric Pain Rating Scale for pain, the Tampa Scale for fear of movement, and the Shoulder Pain
and Disability Index for functional assessment. Pre- and post-intervention data were analyzed
using paired t-tests to determine statistical significance.
Results and Discussion: Statistically significant improvements (p<0.05) were observed after the
intervention. The average NPRS score reduced from 7.5±0.84 to 1.90±0.99, showing a significant
reduction in pain. The SPADI scores exhibited a significant improvement, decreasing from
66.79±9.48 to 51.90±8.90, indicating a reduction in both shoulder pain and disability. The TSK
scores decreased from 48.10±3.03 to 37.60±4.47, indicating a decrease in kinesiophobia.
Conclusion: The combination of ESWT and kinetic chain exercises resulted in significant
enhancements in pain reduction, reduction in fear of movement, and improvement in shoulder
function. This demonstrates the potential effectiveness of this integrated strategy in controlling
CSAPS
Adoption of Innovative Livestock Technologies: Potentials and Constraints among the Smallholder Farmers
No full textThe study was undertaken to know the features of implementation and identify the conveniences and limitations of innovative livestock technologies to facilitate the researchers and farmers for refining the adoption level as well as to enhance the animal and poultry productivity. The north-central part of Bangladesh was chosen and 4 different agro-ecological zones were selected for the study. Categorical data were gathered from the selected farmers through oral interviews and they were presented graphically.Technologies were developed mostly for research and industrial uses by the researchers but they were not adopted sufficiently by the farmers. Farmers adopted the technologies mainly to get more production and income generation. Farmers had easy access to improved breeds and vaccines and moderate access to off-farm activities and transport facilities. Lack of availability of disease control technologies and absence of proper demonstration were the common and frequent constraints for the smallholder adopters. Also, inadequate information for access to technologies, lack of technical knowledge and absence of reliable technical assistance were the remarkable problems in adoption. It is recommended that farmers should have easy access to extension offices, providing input subsidies and special financial interventions for the higher rate of adoption of innovations by the smallholders
Evaluating Machine Learning Algorithms for Fake Currency Detection
No full textCurrency is a critical asset in any economy, yet it is vulnerable to counterfeiting, undermining its
value and disrupting economic stability. Counterfeit currency is particularly prevalent during
economic transition, such as demonetization, as fake notes are circulated to mimic real currency.
Due to the subtle similarities between genuine and fake notes, distinguishing between them can be
challenging. Consequently, financial institutions like banks and ATMs require robust automated
systems to accurately detect counterfeit currency. In this study, we evaluate the effectiveness of
six supervised machine learning algorithms—K-Nearest Neighbor, Decision Trees, Support
Vector Machine, Random Forests, Logistic Regression, and Naive Bayes—in detecting the
authenticity of banknotes. Additionally, we examine the performance of LightGBM, a gradientboosting
algorithm, in comparison to these traditional methods. Our findings contribute to
developing reliable, automated systems for counterfeit detection, and enhancing financial securit
KopiCulture: Unveiling Customer Loyalty in Malaysia's Coffee Market through Clustering Algorithms for Local Cafe Insights
No full textIn recent years, the coffee market in Malaysia has expanded significantly, propelled by an
expanding cafe culture and consumer demand for unique coffee experiences. It is crucial for coffee
retailers, such as global chains and local cafes, to comprehend customer loyalty in this dynamic
environment. This study aims to identify customer loyalty patterns in the Malaysian coffee market,
focusing on the Malaysia Starbucks customer survey dataset. Using clustering algorithms such as
KMeans, KMeans with Principal Component Analysis (PCA), single linkage, complete linkage,
DBScan, and DBScan in conjunction with PCA, we identify distinct customer segments based on
loyalty patterns. Our findings give Starbucks and local coffee shops valuable insights, allowing
them to tailor their marketing strategies and improve customer retention efforts. Through this
analysis, we contribute to the expanding body of knowledge on customer loyalty in the context of
the Malaysian coffee market and offer implications for coffee retailers seeking to thrive in this
competitive environment
Optimization Algorithms: A Comparison Study for Scheduling Problem at UIN Raden Fatah's Sharia and Law Faculty
No full textThe rapid advancement of information and communication technology significantly impacts
various sectors, including education, by enhancing administrative and academic processes through
sophisticated algorithms and systems. At Raden Fatah State Islamic University Palembang,
specifically within the Faculty of Sharia and Law, technology is pivotal in managing complex
course scheduling challenges due to increasing student numbers and curriculum intricacies. This
study examines the effectiveness of optimization algorithms in improving the efficiency and
quality of academic scheduling. We focus on two prominent optimization techniques, Genetic
Algorithms (GA) and Ant Colony Optimization (ACO), chosen for their capability to address the
complex optimization problems typical in academic settings. The research encompasses a
systematic approach, beginning with a clear definition of constraints and objectives, followed by
designing and implementing both algorithms to address the scheduling issues at the Faculty of
Sharia and Law. Our experimental evaluation compares the performance of GA and ACO across
multiple metrics, including execution time, memory usage, fitness, and adaptability to dynamic
conditions. Results indicate that while GA generally offers faster solutions, it requires more
memory and shows variability in achieving optimal fitness levels. Conversely, ACO, though
occasionally slower, consistently produces higher quality solutions with greater memory
efficiency, making it more suitable for resource-constrained environments. The best results from
the experiments highlight that ACO outperformed GA in terms of overall solution quality and
resource efficiency, with an execution time of 19.27 seconds and 14,218.14 KB. Specifically, ACO
consistently achieved near-optimal fitness scores with significantly lower memory usage
compared to GA. This demonstrates ACO's robustness and suitability for handling complex
scheduling problems where resource conservation is crucial. The choice between GA and ACO
should be influenced by specific situational requirements—GA is recommended where speed is
critical, while ACO is preferable in settings requiring high-quality, resource-efficient solutions.
Future research should explore refining these algorithms, possibly through hybrid approaches that
leverage the strengths of both to enhance their effectiveness and adaptability in complex
scheduling scenarios. This study not only informs the academic community about effective
scheduling practices but also sets a benchmark for future technological implementations in
educational institutions