International Journal of Innovations in Science & Technology
Not a member yet
813 research outputs found
Sort by
Bio fusion: Advancing Biometric Authentication by Fusion of Physiological Signals
Full text linkBiometric authentication is becoming more popular due to its secure and reliable way of identifying individuals, offering clear advantages over traditional methods. Since physiological signals are unique and non-invasive, they have been widely researched for use in biometric systems. This study introduces a biometric identification system that combines machine learning with physiological signal fusion, using data from electromyography (EMG), phonocardiogram (PCG), and electrocardiogram (ECG). The data were collected from 32 participants using the BIOPAC MP-36 system. To remove power line interference and extract important frequency bands, Butterworth notch, and bandpass filters were applied to the raw signals. After pre-processing, two types of cepstral features were extracted: gamma tone cepstral coefficients (GTCCs) and Mel-frequency cepstral coefficients (MFCCs), which were analysed for their spectral properties. System performance was first tested by evaluating features from each signal individually. Then, the study examined the impact of combining pairs of signals— (ECG, PCG), (PCG, EMG), and (ECG, EMG)—using GTCC and MFCC features with different machine learning classifiers. Lastly, the GTCC and MFCC features from all three signals were combined to evaluate overall system performance. The results showed that MFCC-based features performed better than GTCC-based features for biometric authentication. The highest accuracy, 98.4%, was achieved using GTCC features with both the Fine K-nearest neighbour (KNN) and linear discriminant classifiers, while MFCC features reached 100% accuracy with the linear discriminant classifier. These findings highlight how effective cepstral features and signal fusion can be in enhancing biometric authentication performance
Machine Learning-Based Improvement of Smart Contract Security in Fog Computing Using Word2vec And Bert
Full text linkFog computing extends cloud computing services closer to users, improving efficiency and reducing latency. Smart contracts play a key role in authentication and resource access management within this framework. As the adoption of smart contracts in fog computing grows, ensuring their security has become a major challenge. This study enhances smart contract attack detection in fog computing using machine learning techniques. A dataset of 818 smart contracts was collected from “etherscan.io.” Feature extraction was performed using Word2Vec and BERT, while feature selection was done using the information gain method. The Random Forest (RF) and Extra Trees Classifier (ETC) achieved the highest accuracy of 0.91 with Word2Vec, while the LightGBM (LGBM) classifier attained 0.90 accuracy using BERT.
These results demonstrate the effectiveness of machine learning models in improving smart contract security within fog computing environments
Detection of Application-Layer Dos Attacks in IoT Devices Using Feature Selection and Machine Learning Models
Full text linkWith technological advancements, innovations like the Internet of Things (IoT) have become widespread, connecting more devices to the Internet. However, as the number of connected devices increases, cyber-attacks—especially Distributed Denial of Service (DDoS) attacks—are also becoming more frequent. This research explores these cyber threats, focusing on DDoS attacks, and proposes strategies to protect IoT devices. It specifically aims to detect DDoS attacks in IoT devices using feature selection methods and machine learning algorithms. The study targets attack detection at the application layer of IoT devices by analyzing a relevant dataset. By applying feature selection techniques and machine learning models, we strive to enhance the accuracy and efficiency of DDoS detection, ultimately improving IoT securit
Developing an Arabic-Urdu Ontology of Quranic Concepts: A Semantic Approach
Full text linkAn Arabic-Urdu ontology system dedicated to Quranic concepts represents a necessity for protecting the semantic value and making religious texts more accessible during Quranic study. Ontology-driven annotation tools show their ability to achieve precise translations and thematic searches by establishing their effects on the translation process. Researchers built this ontology using Protégé 5.6.4 which classifies Quranic concepts into twelve specific sections from Corpus.quran.com: Artifact, Astronomical Body, Event, False Deity, Holy Book, Language, Living Creation, Location, Physical Attribute, Physical Substance, Religion and Weather Phenomena. Validation of the ontology included expert evaluation and a HermiT computational assessment that led to user testing and an accuracy rate of 89.31%. The system uses SPARQL queries as a method to achieve both organized and efficient retrieval of Quranic knowledge. The analysis emphasizes the value of ontological structures as a means to connect Arabic and Urdu semantics which then improves both Quranic interpretation and computational linguistic understanding. While the methodology effectively maps Quranic concepts, challenges such as language nuances and theological precision persist, requiring further advancements in machine learning and natural language processing. Future research should focus on expanding ontology categories, integrating AI-based models, and enhancing phonetic mappings to improve the ontology’s adaptability and usability in diverse linguistic and cultural settings
XDP-ML: A Game-Changer in Intrusion Detection Systems for Modern Cybersecurity
Full text linkIntrusion Detection system (IDS) plays a vital role in cyber security. Traditional approaches are not good enough to detect properly the large threats. Machine learning provides a promising solution and good accuracy by providing large data adaptability. This paper introduced an IDS approach using the XDP framework for real-time network traffic analysis. Objective: The primary goal of this paper is to improve IDS accuracy and effectiveness by integrating the IDS with the fast XDP-based machine learning approach. Motivation: Traditional IDS methods are defenseless to advanced attacks, so modern and adaptive solutions should be improvised. The XDP framework\u27s processing of the data at high speed makes it more resilient and ideal for real-time traffic analysis, enhancing IDS performance. Methodology: The proposed approach is evaluated using the CIC-IDS2017 and UNSW-NB15 datasets, which contain multiple network traffic features and attack labels. Results: The XDP-based machine learning approach enables real-time analysis and adapts to evolving threats. The XDP-based approach achieves a high detection rate of 98% to 99% with a low false positive rate. The performance is consistent and fast, demonstrating the productivity of the approach. Combining the IDS with XDP-based machine learning approaches makes more robust and scalable solutions for intrusion detection. The clear and accurate results show that it can handle advanced and more complex threats
A Smart Prediction Platform for Agricultural Crops Using Machine Learning
Full text linkIt is very critical to have the economic development of emerging countries, like Pakistan. Pakistan, while being one of the world’s main suppliers of a wide range of commodities, continues to employ traditional techniques. Pakistani farmers have challenges not just in coping with changing climatic circumstances, but also in meeting increased demands for higher food output of excellent quality. Farmers must be mindful of shifting meteorological circumstances to produce quality crops. Operations are greatly affected by a variety of factors, including the availability of water, the type of soil, the climate, and fertilizer. Farmers in conventional farming must decide on all of these aspects. What to grow, how to use the irrigation schedule, and the kinds of fertilizer are all covered in this event. Decisions made by farmers are primarily dependent on their experience, which can lead to the waste of expensive resources like water, fertilizers, time, effort, etc. Additionally, cultivating crops that are not the best fit for a given soil type and climate by using standard farming methods might arise problems, which can reduce production and profit. The application of machine learning in crop prediction is very widespread. The most popular method is irrigation. The major goal of this paper is to efficiently develop an E-business online platform to enhance farmer’s productivity and circulation cycle. In this paper, we develop a platform for smart crop predictions. The platform will help farmers by assisting them in obtaining suggestions based on several metrics like humidity, temperature, pH, moisture, and rainfall. Additionally, the user of our platform will be able to get precise advice about what crop to plant depending on variables like humidity, pH, and other characteristics. The user will also be able to get connected with the buyers of their crops and meet their requirements in an efficient manner
An Enhanced Novel IoT-Based Car Accident Detection and Alert System
Full text linkThe excessive use of vehicles for our day-to-day tasks in this revolutionized era has become a necessity, making our lives convenient and technology-dependent. This rise in the use of vehicles has led to a greater number of road accidents that have affected the lives of humans dramatically resulting in an increased fatality rate. According to the World Health Organization, about 50 million people are injured due to road accidents every year. This is mainly due to the unavailability of timely emergency health services. Objective: This study is presented to address this critical issue by leveraging the unmatched capabilities of the Internet of Things (IoT). Novelty statement: A novel IoT-based car accident detection and alerting system considering various car parameters simultaneously for more precise results is proposed which is designed in two stages. First, the accident that has occurred is detected via sensors considering the key vehicle parameters like speed, pressure, acceleration, and gravitation force. Second, upon detecting an accident an emergency alert containing all relevant information regarding the driver, vehicle as well as the exact location of the accident calculated through a GPS module along with its severity is sent to the nearby hospital, police, and driver’s emergency contacts using the GSM module. The proposed approach is employed on a toy car to show its significance and outperforms the existing systems in terms of accuracy 98% and responsiveness
Analysis of Web Application Security: Integrating WAF and SSL/TLS for Enhanced CMS Protection
Full text linkContent Management Systems (CMS) such as WordPress, Joomla, and Drupal power a significant portion of the web, making them prime targets for cyber threats, including TLS downgrade attacks, SQL injection (SQLi), cross-site scripting (XSS), and brute force attempts. Traditional security mechanisms often fail to mitigate these sophisticated attacks, leading to data breaches and unauthorized access. This research implements a multi-layered security framework integrating Web Application Firewalls (WAFs), TLS 1.3 enforcement, AI-driven vulnerability detection, and enhanced security headers on a WordPress test environment. Security audits using OWASP ZAP, Nessus, and Burp Suite validated the effectiveness of each component. Results demonstrate an 80% reduction in brute force attacks, a 93% decrease in SQL injection attempts, and a 100% elimination of XSS vulnerabilities. The implementation of WAF filtering, real-time monitoring, and strict access controls significantly reduced the attack surface. This study provides a scalable, adaptive security model capable of evolving with emerging cybersecurity challenges, offering a vital contribution to web application security
Half a Century of Warming in Punjab, Pakistan: Statistical Evidence from 1970–2019
Full text linkRegional temperature gradients affect how climate change is defined and assessed from varying perspectives. In this research, temperature trends in the Province of Punjab from 1970 to 2019 were examined. To assess the changes in temperature, the monthly means of temperature (Tmean), maximum temperature (Tmax), and minimum temperature (Tmin) were analyzed using Sen\u27s slope estimator method. Several empirical techniques are applied to assess whether the trends are indeed significant, either positively or negatively, and to what extent diversity exists among different weather stations. Also considered are the expected values in the determination of a comprehensive account of temperature fluctuation and variation. The analysis indicates a significant increase in the mean temperature (Tmean) across Punjab, with a sharper increase from Northern Punjab to Southern Punjab. While maximum temperature (Tmax) shows a steep increase in southern and western regions, minimum temperature (Tmin) shows a predominantly increasing trend in Central Punjab. These findings are going to be useful to those making national policy who are trying to formulate strategies for climate change mitigation and adaptation. This study examines long-term temperature trends in Punjab, Pakistan, from 1970 to 2019 using Mann–Kendall and Sen’s slope estimator methods. Results show a statistically significant warming trend, with mean temperature increasing at 0.04°C per year. Southern and Western Punjab experienced higher rates of warming compared to Northern regions. Maximum temperatures increased more sharply in the south, while minimum temperatures rose more prominently in central Punjab, indicating a declining diurnal temperature range. These findings highlight regional climate disparities and underscore the need for targeted adaptation strategies
A Modified K-Nearest Neighbors Algorithm for the Detection of Heart Disease
Full text linkThe leading cause of mortality worldwide is heart disease, sometimes referred to as cardiovascular disease. It is a dangerous illness that impacts the heart and blood arteries. A significant amount of research and analysis has been done recently with the goal of improving the accuracy and dependability of heart disease data. In this discipline, machine learning is crucial since it provides medical diagnostic tools that may be used to forecast illness and enhance healthcare. In this study, heart disease detection is proposed by combining KNN with Jaccard and Cosine similarities. Further, the results of Jaccard and cosine integrated KNN are compared with the results of state-of-the-art models like KNN and decision trees. Python and its libraries are used for simulation purposes. After the simulation, it was found that Jaccard-based KNN (JKNN) had the best accuracy (97%) according to the study\u27s analysis of the Cleveland heart disease dataset. With 91% accuracy, the Cosine-based KNN (CKNN) likewise demonstrated strong performance. In a similar vein, the decision tree is inadequate for classifying heart disease because of its poor accuracy rate as 85%. Likely, KNN shows average results in the form of accuracy, as 86%. According to the results, the JKNN technique is the best model for this task, closely followed by CKNN. The use of machine learning in the diagnosis and prognosis of heart disease is affected by these discoveries