Journal of Soft Computing and Computer Applications

In seismically active areas, earthquake prediction is essential for minimizing potential damages
and preserving lives. However, precise forecasts are complicated to achieve because of seismic
events’ complex and unpredictable nature. The current study presents an advanced prediction
approach to address such issues, combining Convolutional Neural Networks (CNNs) and Attention
Mechanism (AM). The primary goal is to improve the accuracy of the earthquake predictions and
the generalizability across various mainland Chinese regions. AM layer emphasizes significant
features for improving the prediction performance, whereas CNNs are utilized to extract spatial
features of seismic data. The efficiency and effectiveness of the proposed approach were evaluated
by comparing it with several well-known models. Results showed that the proposed approach
performed consistently better than others in nine regions, with a reduced Root Mean Square
Error (RMSE) and Mean Absolute Error (MAE) as well as higher R-squared (R2
) scores, especially
in substantial seismic variability regions. Moreover, the proposed approach outperformed the
conventional techniques in Region One, achieving an RMSE of 0.020, an MAE of 0.015, and
an R2 value of 0.960. In regions susceptible to seismic events, this all-encompassing approach
presents a promising path for earthquake prediction, boosting readiness and risk management
methods.

Cybersecurity is a crucial component of the security system that guards against unauthorized
access to digital transactions. Blockchain is a decentralized ledger used to securely exchange
digital currencies and conduct trades and transactions. Blockchain technology has led to significant changes in electronic transactions. The enormous potential is being exploited in many
areas such as financial services, real estate, supply chain, and the Internet of Things. Despite
being a security system, it has suffered from security threats to sensitive data. Phishing and 51%
attacks can circumvent blockchain security, highlighting the need for thorough user education
and awareness. Additionally, blockchains based on digital transactions require more robust and
resilient cybersecurity solutions to protect their software and databases. This paper focuses on the
latest research on blockchain in cybersecurity, its various applications in digital transactions, and
potential challenges including security issues such as various types of cyberattacks and scalability
in blockchain technology. This study aims to improve knowledge about the cyberattacks that
blockchain security and transaction privacy face. It also strives to summarize the strengths and
weaknesses of previous studies in general, and discuss the various challenges and security issues
faced, in particular. In each study, new solutions were proposed that could be used for future
development and potential future research solutions were identified.

Detecting event anomalies is crucial for surveillance systems, as it enables the identification of
occurrences in videos, both temporally and spatially. It can identify deviations from patterns
without requiring human oversight by learning from past information to distinguish normal
behavior and pinpoint irregularities. Early detection of arson fires is critical to mitigating damage,
public safety, property, and the environment, as well as saving lives and aiding in law enforcement
investigations. The objective of this study is to evaluate a system for detecting events using the
You Only Look Once version 9 (YOLOv9) model in surveillance videos with a focus on identifying
incidents of arson. This involved gathering and organizing data, adding annotations, enhancing
the dataset through model training methods, assessing the model’s performance, and comparing
results while considering the dataset quality and diversity as well as environmental factors.
In the arson category, the model scored 0.552 in precision, which means there is a tradeoff
between precision and recall with threshold 0.5. Additionally, it demonstrated a precision of
1.00 with a confidence of 0.933, meaning it can make predictions with certainty. Finally, the
results demonstrate that the model is capable of detecting arson in surveillance systems. The next
step will be to broaden the scope of data and improve the model to make it more effective and
reliable in other conditions and scenarios.

The face recognition system is a biometric technique that replaces traditional passwords and
personal identification. This research is dedicated to presenting a study of some facial recognition
systems. Since it is unlikely to replicate and is more stable over time, the domain of facial
feature extraction has proven to be more effective in attaining exact facial recognition, which
is important, especially in intelligent security surveillance systems. Face recognition systems
encounter several challenges, primarily related to pose variations, illumination conditions, and
occlusions such as hair, glasses, and so on. To address these challenges, enhance performance,
and boost the accuracy and speed of identification, a wide range of mechanisms were developed
to carry out the face recognition function, which converts the face image into a digital feature that
allows for effective comparison and storage. This survey highlights more than 25 face recognition
systems. The review analyzed the systems based on performance metrics, classifier efficiency,
and feature extraction techniques, as well as their strengths, weaknesses, and suitability for
real-time applications. It also described the most popular databases used to test the performance
of face recognition systems. Additionally, recommendations for future research directions in face
recognition have been offered.

Responsibility for maintaining election transparency over time and ensuring democratic values
intact is held by the Iraqi Independent High Electoral Commission (IHEC). However, transferring physical election votes from election centers is a critical duty, where many challenges
appear regarding accountability and security measures. This study proposes a system that utilizes
blockchain technology to solve any challenges or difficulties and ensure an effective and improved
election process by providing its highest trustworthiness and legitimacy and ensuring a decentralized security process. This system offers unique blockchain characteristics such as immutability,
decentralization, and transparency, providing an extra level of security to the data against fraud
attacks and providing anti-tamper. This system includes three main components: the first includes
Internet of Things (IoT) scanners for election centers, which are responsible for saving physical
voting results encrypted using homomorphic encryption algorithms. The second includes IHEC
servers, which collect votes from multiple election centers and verify the authenticity of each one.
The third is blockchain, which is used to securely transfer votes between these two components
to ensure transparency and accountability that voters have voted and that no vote can be altered
without being detected. As a result, the proposed system efficiently utilizes a lightweight private
blockchain, Proof of Secret Sharing (PoSS) consensus. Compared to blockchain systems, it shows
faster Transaction Per Second (TPS) of 37.84%, 84.14% in verification time, 87.39% in the final
time, CPU usage of 73.94%, and CPU user time of 0.29%.

The ability to predict students’ performance in educational settings like schools and universities
is crucial. A key objective of this effort is to increase academic outcomes and prevent dropout
rates, among other benefits. Automating student activities, encouraged by information collected
from any technology-based learning tool, has an important role in the process here. Those big
quantities of information ought to be completely studied theoretically and processed for gaining
worthy insights concerning a student’s background as well as interacting with scientific missions,
facilitating the development of advanced ways and algorithms to predict students’ performance.
The current study reviews several contemporary mechanisms to analyze how a student behaves,
along with a specific concentration on mechanisms of video analysis. Twenty-six research papers
published between 2018 and 2023 were under review. The review focused on the significance
of video analysis in comprehending how a student behaves and presents insight into future
tendencies in this regard. The outcomes propose that the incorporation of those mechanisms
could improve educational results by providing data-driven backup for every process of decision-making.