Machine Learning for Road Traffic Accident Prediction
Sumit Gupta1 and Dr. Awadesh Kumar2, 1 Department of Computer Science, Institute of Science, BHU, India, 2 Department of Computer Science, MMV, BHU, India
Road safety and accidents have been big global concerns, and everyone is working to address the issue of road safety and accidents, which has been a big worry for many years. In every country on earth, there is traffic and reckless driving. This has a negative impact on a lot of pedestrians. They become victims, although having done nothing wrong. The number of traffic accidents is rising quickly due to the enormous increase in road cars. Accidents like these result in harm, impairment, and occasionally even fatalities. Numerous things like weather changes, sharp curves, and human error all contribute to the high number of traffic accidents. Road accidents result in serious but occasionally invisible injuries that subsequently have an impact on ones health. Using a machine learning system, this study seeks to analyse traffic incidents in order to anticipate and reduce.
Machine learning algorithm, Supervised Learning Feature Analysis, Road Accident.
Identification of Network Intrusions Using Decision Tree and Deep Learning for Detecting Anomalies
Dr. Garima Sinha1, Guru Sai Chandhan Madapakula2, Asritha Mudunuri3, Vishnu Vardhan Reddy G4, M S N S Vivek5 and Swetha Reddy Kadimetla6, 1Associate Professor, Department of Computer Science, JainUniversity, Bengaluru, India, 2B.Tech 4th year, Dept. of Computer Science, JainUniversity, Bengaluru, India, 3B.Tech 4th year, Dept. of Computer Science, JainUniversity, Bengaluru, India, 4B.Tech 4th year, Dept. of Computer Science, JainUniversity, Bengaluru, India, 5B.Tech 4th year, Dept. of Computer Science, JainUniversity, Bengaluru, India, 6B.Tech 4th year, Dept. of Computer Science, JainUniversity, Bengaluru, India
In todays world, everything is done online. Without a network, the entire world would be unable to function. With the massive increase in the use of computer networks and the vastly increased variety of applications they currently support, network security issues are increasing, since all systems suffer from security vulnerabilities which might increase attacks that could negatively impact the economy. As a result, detecting vulnerabilities in the network system has become more important, and it must be done as precisely as possible in real-time. Here we will create and train a model that uses the Decision Tree classifier to detect whether a network packet is being attacked. The NIDS is intended to monitor the whole network. It has visibility into all network flow and By considering both the metadata and packet content, a more comprehensive perspective can be obtained, allowing for a greater understanding of the context and enabling the identification of more widespread security threats. The addition of anomaly detection to NIDS through the use of deep learning algorithms improves the systems ability to detect intrusions.
Network IDS, Decision Tree, Anova F-Test, Recursive Feature Selection, Matlab.
I-mask: Mask With Integrated Monitoring System
Kartikeya Kushwaha, Mihir Sharma, Parth Bansal, Dept of ECE, ABES Engineering College, Ghaziabad, Uttar Pradesh, India
The main purpose and concept of this idea is to create an integrated monitoring system attachable to a wearable mask in order to monitor real time health related parameters such as body temperature, blood saturation level, blood pressure and heart rate. This IoT enable mask collected data from the sensor inbuilt in the mask and send these data to the central monitoring system for the display and monitoring. A power management system is also required for to reduce power consumption of the device. This I-Mask system reduce man power requirement of the hospital and better patient management and monitoring with extra level of care to the patient.
IoT, Mask, Personal Health, Sensors, Arduino, Blink app.
Encryption of Images on Iot: a Performance Analysis of Aes and Chacha20
Nasar Al Siyabi, University of Reading, Reading, UK
In this paper, we compare the performance of Advanced Encryption Standard (AES) and Chacha20. We used images for the performance analysis and computed 1) correlation, 2) histogram, 3) entropy, and 4) mean-square error (MSE) for comparing the two schemes. We also compared the execution times of both schemes. We used all three key sizes, 128 bits, 192 bits and 256 bits, for AES. Our results show that AES192 outperforms Chacha20 as well as AES128 and AES256.
IoT, AES, ChaCha20, correlation, entropy, MSE.
Blockchain Based Enterprise Application for Land Registration
Pratham Vats, Himanshu Singh and Nakul Jain, Amity School of Engineering and Technology , AMITY University , India
The current Land Registration System makes transferring property ownership in connection with a land
purchase a time-consuming process. Because all of the countrys data is kept in one location, there are
security concerns as well. In some instances, faulty or insufficient registration results in land litigation
and ownership disputes. In this study, a blockchain-based land registration system is designed to get
around the land registration systems stated restrictions. Block-level data storage that is decentralised in
order to prevent land ownership issues, chain offers security and allows for the safe storage of landowner
data.As land is a valuable asset, using block chain technology can considerably improve this sector s
work implementation and characteristics for a smooth and hassle-free work flow to establish a
trustworthy system. A governance systems essential department for storing records of land ownership
is the land written record system. There are several flaws in the current system that cause conflict and
corruption. A significant number of Courts and significant government resources enforcement
organisations are addressing these issues.The use of blockchain technology could prevent these
omissions and list the issues relating to land written record system, such as record tempering,
Mercantilism of a consistent plot of property to a single purchaser. Land register is a system that keeps
track of the primary claims to ownership made by various governmental entities, i.e., it keeps track of
land possession records. However, there are several issues and flaws in the current system that contribute
to corruption and disputes. In order to solve these issues, we frequently use Blockchain
technology.Blockchain is used to counter these loopholes. It is used to find out the problems connected
with land register system like tempering of records & commerce of identical piece of land to quite one
vendee. The term "land register system" refers to the system that keeps track of the primary areas of
possession that various governmental entities claim. The hold on record will be utilised as the evidence
for the claim in order to prevent any potential fraud and ensure smooth transitions as needed.
SHA-256 Algorithm , Decentralized Ledger , Private Key Encryption.
Land Registration System Using Blockchain
Priyesh Raj Singh, Prateek Kumar, Niranjan Singh,Department Of Information Technology Galgotias College Of Engineering And Technology ,Uttar Pradesh, India
Land administration system is important for the management, allocation, and handling related to land, affecting a wide range of stakeholders. However, one of the biggest challenges in land administration systems is maintaining the accuracy of the data stored within them. Inaccuracies can arise from a variety of factors such as errors in data collection, processing, and misuse. These inaccuracies can lead to issues such as data tampering, lengthy registration times for transactions, and the potential for double-spending, all of which can undermine the integrity of the land administration system. To address these challenges, this research paper proposes the use of blockchain technology, specifically the blockchains contract written in the Solidity programming language. The smart contract is written in the main logic of the implementation. These contracts are logical implementations to determine the owner, seller, and the transfer of the land. The proposed solution uses a distributed ledger system to ensure the accuracy of data in the land administration system. The system verifies the users record through government officials and assigns a unique hash value to each submitted block of data. When a transaction for the transfer of ownership is initiated, a separate block is created with a unique hash value that is connected to the previous value, creating a sequence of blocks that are chained together. The hashing algorithm employed generates a fixed-size message digest, where each hashed value uniquely represents a complete set of transactions contained in a specific block.
associated with this paper include blockchain, smart contract, Ethereum, hashing, public ledgers, cipher, chain linking, consensus protocol, cryptography, decentralized application, encryption, and digital signature. This research paper concludes that blockchain technology has the capability to address the challenges faced by land administration systems, and the proposed smart contract implementation can improve the accuracy and reliability of these systems, benefiting a broad variety of stakeholders.
Results of our research indicate that by using blockchain we can improve efficiency, transparency, and security, and reduce fraud. The advantages of using blockchain in the land transactions system can eliminate of intermediaries, reduce transaction costs, and increase the speed of transactions. Furthermore, smart contracts in blockchain-based land registration systems could ensure that transactions are executed automatically once the conditions specified in the contract are met.
Blockchain-based Software Subscription and Licenses Management System
Hithru De Alwis, Shamila De Silva, Kasun De Silva, Adeesha Wijayasiri, and Eranga Perera, Department of Computer Science & Engineering, University of Moratuwa
As software becomes increasingly integral to various aspects of daily life, there is a pressing need for efficient and secure software licensing systems. Traditional licensing models often fall short in transparency, security, and flexibility in license management. This research proposes a blockchain-based software subscription and license management system to address these issues. Utilizing the Ethereum blockchain, this system employs smart contracts to automate the enforcement of licensing agreements,
facilitating secure, transparent, and efficient license management. Through the use of ERC721 and ERC20 token standards, the system allows for the creation and transfer of license tokens. This study was motivated by the growing popularity of subscription licenses, the legal implications of the UsedSoft court case, and the inherent advantages of blockchain technology, including immutability and decentralization. The research
objectives include designing a blockchain-based subscription license model, analyzing the UsedSoft court case and its impact on software license transfers, developing smart contracts for various software licensing models, and creating demo softwares that use blockchain-based licenses for activation. Evaluations indicate that the proposed system efficiently handles license issuance, transfer, and management. The system represents a pioneering approach in software license management, aligned with contemporary software
Blockchain, Smart Contracts, Ethereum, Software Licensing, Software Subscriptions, License Transfer, License Activation.
Impacting Underdeveloped Communities Using Decentralised Ledger Technology
Lorae Knight, De Montfort University
Melan DLT presents a data-generating social media platform designed to create monetary value and trust within economically disadvantaged nations. Through the use of peer-topeer transactions, e-commerce and a stabilized dual coin system, the Melan DLT will achieve an effortless economic ecosystem to empower, inspire and entertain all users. This paper looks into the need for such a technology, dissects distributed ledger technologies (DLT) currently available and finally outlines some of the possible components which will be used to build the proposed system. This paper is intended for research to aid a technical design brief and therefore is not a final disclosure of the Melan DLT design system.
Blockchain, DLT, ESG, DAG, big data.
Data Privacy Protection and Security of Digital Twin in Healthcare Using Cloud Computing and Blockchain
Johnson Muungano, Department of Computer and Engineering,Jain (Deemed-to-be University), Bangalore, India
A digital twin is a technology that facilitates seamless data integration between physical and virtual machines on both sides. This article explores the challenges, applications, and technologies involved such as Artificial Intelligence (AI), the Internet of Things (IoT), and digital twins—health, education, automotive, aerospace, etc. Various industries are constantly looking for new technologies to benefit their industries. Digital twin technology has great potential to meet the needs of this industry. However, to increase the availability of digital twin data, it is vital to consider sharing data securely with other data users. To solve this problem, a digital twin data-sharing network model is proposed. This proposed network model uses cloud computing for efficient data sharing and blockchain for verification. A communication scheme is designed for the proposed model to ensure data privacy and security in wireless channels. To ensure the security of the proposed protocol, informal methods for security analysis and formal methods such as BAN logic and AVISPA simulation tools are used. The proposed protocol is compared with related protocols to demonstrate its applicability in a digital twin environment.
Digital twin (DT), Mutual authentication and key agreement, Blockchain, Healthcare, Data Owner (DO), Data User (DU), Cloud computing, BAN logic, AVISPA.
Enhancingpredictivemodelswithfuzzymathematics: a Comparative study
Yogeesh N11Assistant Professor and HOD of Mathematics,Government First Grade College, Tumkur-572102, Karnataka, India
This research paper investigates the application of fuzzy mathematics in predictive modelling for financial
market prediction and healthcare diagnostics. Fuzzy logic, known for its ability to handle uncertainty and
linguistic variables, is utilized to design and implement two distinct fuzzy logic-based models. The first
model focuses on financial market prediction, using fuzzy sets, membership functions, and fuzzy rules to
capture complex relationships between market indicators and sentiment. The models linguistic
interpretability empowers stakeholders to make informed investment decisions based on its predictions.The second model centers on healthcare diagnostics, employing fuzzy sets and membership functions to represent medical indicators and symptoms. Fuzzy rules, derived from expert knowledge and medical
guidelines, map input variables to potential medical conditions. The Sugeno-type fuzzy inference system
provides flexibility in handling intricate relationships, producing accurate diagnostic outcomes. The
models ability to deal with vague data and provide linguistic explanations enhances trust among
healthcare professionals and patients.Overall, the findings demonstrate the advantages of fuzzy mathematics in both domains, including
handling uncertainty, incorporating expert knowledge, and improving interpretability. The research
contributes to practical applications in financial analysis and medical diagnostics, paving the way for
future research in hybrid models and wider applications of fuzzy mathematics in predictive modelling.
Fuzzy mathematics, predictive modelling, financial market prediction, healthcare diagnostics, linguistic
interpretability, uncertainty, expert knowledge, fuzzy logic, Sugeno-type fuzzy inference system.
Xiaohan Feng, Graduate School of Information Sciences and Arts, Toyo University, Kawagoe,Saitama, Japan
AI opens up new possibilities, enabling anyone to effortlessly generate visually stunning images without
the need for artistic skills. However, it also leads to the creation of more stereotypes when using large
amounts of data. Consequently, stereotypes are becoming more prevalent and serious than ever before.
Our belief is that we can use this situation in reverse, aiming to summarize stereotypes with AI and then
subvert them through elemental exchange.
In this study, we have attempted to develop a less time-consuming method to challenge character
stereotypes while embracing the concept of "exchange." We selected two character archetypes, namely the
"tyrant" and the "mad scientist," and summarized their stereotypes either by generating AI images or by
asking questions to ChatGPT. Additionally, we conducted a survey of real historical tyrants to gain
insights into their behavior and characteristics. This step helped us comprehend the reasons behind
stereotyping in artwork depicting tyrants. Based on this understanding, we made choices about which
stereotypes to retain. The intention was to empower the audience to better evaluate the identity of the
character. Finally, the two remaining character stereotypes were exchanged, and the design was
The purpose of this study is to explore different ways of using AI to subvert stereotypes more efficiently and
effectively. It will also enumerate the advantages and disadvantages of each approach, helping creators
select the most appropriate method for their specific situations. Moreover, this research will serve as a
valuable reference and inspiration for subsequent studies on stereotype-related topics.
Multidisciplinary, Artificial Intelligence, Arts & Design History, Stereotypes.
Brands, Verticals and Contexts: Coherence Patterns in Consumer Attention
John Hawkins, Playground XYZ, Australia
Consumers are expected to partially reveal their preferences and interests through the media they consume. The development of visual attention measurement with eye tracking technologies allows us to investigate the consistency of these preferences across the creative executions of a given brand and over all brands within a given vertical.In this study we use a large-scale attention measurement dataset to analyse a collection of digital display advertising impressions across a variety of industry verticals. We evaluate the extent to which the high attention contexts for a given brand’sads remain consistent for that brand, and the extent to which those contexts remain consistent across many brands within an industry vertical.The results illustrate that consumer attention on advertising can vary significantly across creatives for a specific brand, and across a vertical. Nevertheless, there are coherence effects across campaigns that are stronger than random, and that contain actionable information at the level of industry vertical categorisation.
Whats in a Domain? Anaylsis of Url Features
John Hawkins, Playground XYZ, Australia
Many data science problems require processing log data derived from web pages, apis or other internet traffic sources. URLs are one of the few ubiquitous data fields that describe internet activity, hence they require effective processing for a wide variety of machine learning applications. While URLs are structurally rich, the structure can be both domain specific and subject to change over time, making feature engineering for URLs an ongoing challenge. In this research we outline the key structural components of URLs and discuss the information available within each. We describe methods for generating features on these URL components and share an open source implementation of these ideas. In addition, we describe a method for exploring URL feature importance that allows for comparison and analysis of the information available inside URLs. We experiment with a collection of URL classification datasets and demonstrate the utility of these tools. Package and source code is open on https://pypi.org/project/url2features.
Machine Learning, Feature Engineering, Web Search, Semantic Web, Data Science.
Chunker Based Sentiment Analysis for Nepali Text
Dr. Archit Yajnik, Ms. Sabu Lama Tamang, Department of Mathematics, Sikkim Manipal Institute of Technology, Rangpo, Sikkim
The article represents the Sentiment Analysis (SA) of a Nepali sentence. Skip-gram model are used for the word to vector encoding. In the first experiment the vector representation of each sentence is generated by using Skip-gram technique followed by the Multi-Layer Perceptron (MLP) classification and it is observed that the F1 scores of 0.6486 are achieved for positive-negative classification with 68% accuracy. Whereas in the second experiment the verb chunks are extracted using Nepali parser and carried out the similar experiment on the verb chunks. The F1 scores of 0.6779 are observed for positive -negative classification with 85% accuracy. Hence, Chunker based sentiment analysis is proven to be better than sentiment analysis using sentences.
skip –gram model, MLP classification, parser, verb chunk.
Towards Kyrgyz Stop Words
Ruslan Isaev, Gulzada Esenalieva, and Ermek Doszhanov, Ala-Too International University, Bishkek
The concept of stop words introduced by H.P. Lun in the mid-20th century plays a huge rolein today’s NLP practice. Stop words are used to reduce noisy text data, remove uninformative
words, speed up text processing, and minimize the amount of memory required to store data.The Kyrgyz language is an agglutinative Turkic language for which no scientific study of stopwords has been previously published in English. In our study, we combined frequency analysis with
rule-based linguistic analysis. First, we found the most frequently used words, set a threshold, and
removed words below the threshold. So we got a list of the most frequently used words. Then we
reduced the list by excluding from the list all words that do not belong to the category offunctionwordsof the Kyrgyz language. Finally, we got a list of 50 words that can be considered stop wordsin the Kyrgyz language. In our analysis, we used a single corpus of sentences collected and posted
as an open source project by one of the local broadcasters.
stop words, Kyrgyz language, frequency analysis, Turkic stop words, NLP.