INTI Institutional Repository
Not a member yet
2178 research outputs found
Sort by
Virtual Reality in Waste Management: Evaluating Its Impact on Community Classification Behavior
No full textThe purpose of this study is to explore the impact of virtual reality (VR) technology on improving
community garbage sorting behavior through a questionnaire survey. Targeting residents of
varying ages, educational backgrounds, and lengths of residence in the community, the study
utilized VR technology for garbage classification education and behavior guidance. This
comprehensive method evaluated improvements in individuals' willingness, cognition, and
practices regarding garbage classification. We designed a multi-dimensional questionnaire and
employed a random sampling method to select residents who met specific classification criteria as
survey subjects. The research involved analyzing the influence of VR technology on enhancing
garbage classification cognition across different demographics, exploring how VR can shift
attitudes and willingness towards garbage classification, and investigating its role in promoting
actual sorting behavior and frequency. Methodologically, we implemented an immersive VR
experience that simulated various types of garbage and classification scenarios, followed by preand
post-intervention surveys to measure changes in cognition and behavior. Additionally, we
examined the interrelationship between VR technology and other influencing factors, such as
policy advocacy, educational background, and community environment. The findings indicate that
VR technology significantly enhances residents' understanding of garbage classification standards
and improves classification accuracy. Furthermore, the visual representation of the negative
environmental impacts of garbage, depicted through VR, profoundly heightened residents'
environmental awareness and willingness to engage in garbage classification. This study confirms
the practical application value and significant impact of VR technology in improving community
garbage sorting behavior, providing a scientific basis for its further promotion and application in
community waste management practices
Data-Driven on Resilient Network Security Against SYN Flood Attacks at PT PUSRI
No full textThe PT PUSRI Information Technology Services Department plays a vital role in supporting
operations and providing IT services across the company. To ensure secure internet access, robust
security measures have been implemented, with firewall filtering as a key strategy. This study
analyzes the effectiveness of firewall filtering in mitigating threats such as SYN flood attacks and
unauthorized access by focusing on data-driven insights into traffic patterns and threat prevention.
The firewall filtering system scrutinizes incoming TCP connections, manages critical ports (e.g.,
ports 22 and 80), filters IP address ranges, and continuously monitors suspicious network traffic
patterns. Data analysis of network activity revealed a significant reduction in security incidents.
By blocking illegitimate traffic and managing commonly targeted entry points, the system has
minimized disruptions caused by SYN flood attacks and unauthorized access attempts. Filtering
source IPs associated with malicious activities and analyzing traffic anomalies further strengthen
network security. The results demonstrate increased network stability and enhanced operational
efficiency at PT PUSRI, with data indicating fewer disruptions and threats. The department's
ability to analyze traffic patterns has enabled proactive threat mitigation, contributing to a secure
IT environment. This research highlights the strategic importance of integrating data analysis into
firewall filtering to sustain and improve network security while supporting seamless operational
activities
Carbon Emission under Industry 5.0
No full textIndustry 5.0 integrates people and machines into production to achieve more personalization,
possibilities, and sustainable development. Industry 5.0 has three core elements: Humancentric,
sustainability, and resilience. Humancentric emphasizes human-machine collaboration. Talent
is the core of industrial operation. Technology is to serve humans better, not to replace humans.
The sustainability of Industry 5.0 includes economic, environmental, social, and technological
sustainability. In these aspects, Industry 5.0 has new requirements and development directions
for sustainability. The carbon footprint runs through every link of the industry. Reducing carbon
emissions is the requirement of Industry 5.0 for environmental sustainability. The technological
innovation and progress of Industry 5.0, as well as the concept of sustainability, all affect and
reduce carbon emissions to varying degrees
The Factors Influencing Consumer Behaviour in the Purchase of Green Products in Windhoek, Khomas Region of Namibia
No full textIt is a global concern that environmental sustainability is in danger. Climate conditions in most
parts of the world cannot sustain agriculture and livestock, while water and energy shortages
remains a huge challenge. While enjoying products and services offered in the market, consumers
should protect their environment and maintain a healthy life style by purchasing green products
which are environmental friendly. Prospective green consumer’s expression of interest in green
products is not converted into actual purchase. The objective of this study is to examine the factors
that influence consumer behavior in the purchase of green products. The study adopted mixed
methods and a sample of 120 respondents was considered. SPSS was used for analysis. Qualitative
data was analyzed using thematic analysis. Statistical significant association was found between
the purchases of green products with the eight main predictors which are; Environmental attitudes,
perceived effectiveness of environmental problems, perceived environmental responsibility, green
products labelling, green product features, green product certification, environmental benefits of
green products, governments concern about the environment. The study found a negative
association between purchase of green products and consumers knowledge about environmental
benefits. By gathering this information, marketers would be able to understand the factors which
influence consumers in the purchase of green products. They would also be able to formulate
various strategies to effectively attract more green consumers to purchase green products as part
solution for environmental protection. The legislators, national policy makers and environmental
activists could utilize this information to promote a positive green consumerism
Comparison of ELM, LSTM, and CNN Models in Breast Cancer Classification
No full textClassification can significantly impact treatment decisions and patient outcomes. This
study evaluates and compares the performance of three machine learning models Extreme
Learning Machine (ELM), Long Short-Term Memory (LSTM), and Convolutional Neural
Networks (CNN) in breast cancer classification. ELM, known for its fast-learning speed and
strong generalization, is compared with LSTM, which is effective in capturing long-term
dependencies in sequential data, and CNN, which is renowned for its ability to automatically
extract features from images and structured data. The models were trained and tested on a breast
cancer dataset, focusing on accuracy and computational efficiency. The results revealed that
while CNNs demonstrated better accuracy in feature-rich data, LSTMs excelled in handling
sequential data patterns. On the other hand, ELM offers a good balance between training speed
and classification performance. This comparative analysis provides valuable insights into the
strengths and limitations of each model, contributing to the development of more effective
breast cancer diagnostic tools. In this case, LSTM outperformed ELM by 0.91%, outperformed
CNN significantly by 3.72%, and outperformed Improved LSTM by 0.91%. This indicate that
the LSTM model shows higher accuracy in breast cancer classification
Comparative Accuracy of Data Mining Models for Predicting Extreme Weather Events in West Sumatra
No full textWeather factors have a vital role in human activities, especially extreme weather phenomena.
Extreme weather can result in potential hydrometeorological disasters that cause loss of life and
property. Climate change is also contributing to the higher frequency of extreme weather events.
For this reason, research related to predicting extreme weather, especially very heavy rain, is
needed to anticipate its impact. Research related to the prediction of extreme weather events is
currently still being carried out using various models. By utilizing aerial observation data from
Radiosonde (RASON) and daily rainfall data at the Minangkabau Meteorological Station Padang
Pariaman, West Sumatra, extreme weather prediction modeling was carried out with the criteria
of heavy rain events having rainfall intensity above 50 mm/day or 50 mm/day. 24 hours. From the
data mining prediction model that has been carried out using the Support Vector Machine (SVM)
Model, in this case, the Support Vector Regression (SVR), the Mean Squared Error (MSE) value
is 502.88, and the R2 (Coefficient of Determination) score is 0.09. For the Artificial Neural
Network (ANN) model, the Mean Squared Error (MSE) value was 590.03, and the R2 (Coefficient
of Determination) score was -0.73 with an accuracy value of only 0.11 and a loss model value of
590. Meanwhile, for the data mining classification model using the Decision Tree Model, the value
obtained The model accuracy was 0.47, and the Naïve Bayes (NB) model obtained a model
accuracy value of 0.34. From the results of this comparison, it was found that the prediction model
using the Decision Tree Model was more accurate in predicting extreme rain events in the West
Sumatra region
Diabetic Retinopathy Detection Model using Hybrid of U-Net and Vision Transformer Algorithms
No full textDiabetic retinopathy is one of the leading causes of vision impairment noticed among
individuals with prolonged diabetes. Early-stage detection is very crucial for its treatment.
Now, we present a hybrid model which is a combination of U-Net algorithm used for image
segmentation and Vision Transformer for classification. The total integration offers a robust
model which helps in detecting various stages of diabetic retinopathy. We leverage the use of
U-Net algorithm in image segmentation process to delineate the regions of interest in retinal
images. Further, the outputs which are segmented are passed into Vision Transformer, which is
enhanced by Efficient Net, which is used across various severity levels involved in Diabetic
Retinopathy. The usage of transformer architecture helps improve feature extraction and
classification performance which ensures that our model captures all patterns in retinal images.
We have evaluated our model on APTOS Blindness detection dataset in which our model
outperforms traditional convolutional neural networks-based models. Hence, the hybrid
approach consisting of combination of both the algorithms demonstrates excellent robustness
and generalization which offers a promising application for diabetic retinopathy screening,
involving the potential to revolutionize early diagnosis in clinical settings
The Algorithm of Fear: Unpacking Prejudice Against AI and the Mistrust of Technology
No full textThe mistrust of AI seen in the media, industry and education reflects deep-seated cultural anxieties,
often comparable to societal prejudices like racism and sexism. Throughout history, literature and
media have portrayed machines as antagonists, amplifying fears of technological obsolescence and
identity loss. Despite the recent remarkable advancements in AI—particularly in creative and
decision-making capacities—human resistance to its adoption persists, rooted in a combination of
technophobia, algorithm aversion, and cultural narratives of dystopia. This review investigates the
origins of this prejudice, focusing on the parallels between current attitudes toward AI and
historical resistance to new technologies. Drawing on examples from popular media and recent
research, the article reveals how AI, despite outperforming humans in some creative tasks, is often
undervalued due to bias. The evidence shows that the tool can significantly augment human
creativity and productivity, yet these benefits are frequently undermined by persistent skepticism.
The article argues that this prejudice represents a critical barrier to the full realization of the
potential of the generative technology and calls for a reexamination of human-AI collaboration,
emphasizing the importance of addressing these biases both culturally and within educational and
professional frameworks
Driver Drowsiness Detection System
No full textAmong the leading causes of fatalities in traffic accidents is being sleepy while driving. Long-haul truck drivers, bus or overnight bus drivers, and drivers who operate their cars after midnight are more prone to encounter this issue. Accidents Senger’s worst Every year, car accidents involving drunk drivers result in several fatalities and serious injuries. Due to their enormous practical significance, identifying driver tiredness and its indication are therefore significant study areas. The acquisition system, processing system, and warning system are the three components or modules that make up the fundamental sleepiness detecting apparatus. The acquisition system takes a frontal facial video of the driver's and transmits it to the processing block for real-time analysis to identify weariness
VCVERSE - A Video Conferencing Website with Controls
No full textIn today’s digital age, remote communication and collaboration are becoming increasingly important. Video Conferencing platforms have gained popularity as they provide an immersive and interactive way to connect with others. This paper aims to develop a video chat website with a built- in notes controller, using Nodejs and Python. One of the special features of the video chat website is the integrated note taking feature. Users can download the files during a video call to improve collaboration and information sharing. These files are synchronized in real – time with all participants to ensure that everyone can refer to the important points discussed during the call. To enable real-time video communication, WebRTC (Web Real-Time Communication) technology is integrated into the website. WebRTC enables browser-based peer-to-peer video and audio communication without the need for additional plugins or software installations. The resulting video chat website with features will provide a user-friendly and collaborate platform for remote communication and teamwork. It can be used in various fields such as education, business meetings, and remote collaboration of distributed teams