Journal of Recent Innovation in Science and Technology

This study examines brain imaging to identify areas with tumors and categorizes these regions into three distinct types: meningioma, glioma, and pituitary tumors. This paper also compares different machine learning algorithms for the identification of brain tumors. The term "brain tumor" describes the excessive growth of cells in the brain, that can be either benign or malignant. In this study, machine learning algor...

Deepfake ("deep learning + fake" = DF) refers to the forged videos and audios generated using AI algorithms. While they can be a source of entertainment,theycanalsobeharmfulinvariousways.Manipulatingbothau- diosandvideosforharmfulpurposeshasbeen a concerning issue from the past more than 10 years. The ability todetect these videos and audios through AI detectors is a motivatingfactor in achieving the best results for...

In the data security the cryptography and steganography could be usefull for data security individually. But individual these security techniques are not enough to provide sufficient data security. In this paper we have shows that steganography and blockchain are used together to hide encrypted data inside image. The proposed method will solve two major drawbacks of the current existing security techniques, the large...

The Internet of Vehicles (IoV) represents a critical evolution in intelligent transportation systems. It is a key advancement in intelligent transportation systems, where vehicles connect and communicate effectively with each other, utilizing great infrastructure that enables real-time data exchange and various advanced features. The paper spells out the attack vectors—such as MITM, DoS, spoofing and malware-based in...

The rapid expansion of smart cities and widespread deployment of surveillance infrastructure have highlighted the need for intelligent systems capable of detecting suspicious and criminal activities in real-time. Traditional surveillance systems primarily rely on manual monitoring, which is error-prone and unable to scale with the increasing volume of video data. To address these challenges, this paper presents a nov...

One important issue that is quite relevant to the workplace in the fields of construction, mining, oil and gas, and heavy manufacturing is the problem of workplace safety as employees are often exposed to dangerous conditions. Other models of surveillance relying on manual oversight, or basic surveillance systems, typically lack real-time visibility, which results in action delays and unnecessary events. To solve thi...

This paper proposes a domain-adapted neural machine translation (NMT) system for Amharic-to-English translation, focusing on the issues of low-resource translation in a richly morphologically inflected language. We focus on the religious domain with the Tanzil corpus, a structured collection of Quranic verses which are translated into Amharic and English for coherence and semantic correspondence. To address the short...

In the evolving world, automation plays an important role to make the life easier. Enhancing the properties to reduce the time and efforts of human or an organization. The automation is leading to betterment of the world but there are some fields where automation is not yet opted. The project “IOT Based Smart water and EB meter for Domestic Utilities” is to leverage automation in local monitoring of domestic utilitie...

Quantum computers are capable of solving problems that classical computers cannot, particularly in the realm of cryptographic algorithms such as RSA, DSA, and ECC. Post quantum cryptography refers classical cryptographic algorithm that are designed to secure sensitive data. This research explores the application of post-quantum cryptographic techniques in healthcare systems, with a specific focus on integrating Quant...

The unforeseen growth of digital services has escalated energy requirements in the world data centers, and an environmental sustainability issue is a hot topic in cloud computing. Conventional parallelism to workload scheduling fails to consider real time carbon intensity and regional grid efficiency thus resulting in high carbon emission even in optimally performed computational work. The proposed work suggests a gr...

This research proposes an efficient method for automatic answer quality classification in online web forums using a Multi-Task BERT-Based deep learning framework. The primary objective is to accurately categorize user responses into low, medium, and high-quality classes by leveraging advanced language representation and relevant content features. Starting with Stack Overflow forum data collection, the methodology mov...

In modern internet commerce and digital retail, fashion classification and visual search are very important jobs. They make it possible to quickly recommend products, find them, and keep track of inventories. Even though deep learning has come a long way, current CNN (convolutional neural network) methods still have trouble with class disparities, overlapping categories, and picking up on fine-grained visual details...

Financial fraud is a serious problem in the digital economy, with billions being lost each year. Conventional fraud detection schemes are usually insufficient in real-time processing, false positives, and adaptive fraud pattern changes. This paper introduces a Hybrid system combining Block chain and Artificial Intelligence (AI) to improve fraud detection in financial transactions. Block chain provides data immutabili...

Software defect prediction is a crucial task for improving software reliability and reducing maintenance cost in large-scale software systems. One of the major challenges in defect prediction is severe class imbalance, where defective modules are significantly fewer than non-defective ones. Traditional machine learning models often fail to prioritize defect detection, leading to biased performance. This paper propose...

Fish diseases are a serious threat to the farming industry. To detect these diseases in the initial stage, a different machine learning model is proposed. This model has focused on identifying the fish diseases based on the water quality. To do this, we have used the “Aquaculture–Water Quality Dataset” data set havi15 physico-chemical parameters like PH, DO, hardness, solids, chloramines, iron, ammonia, nitrite, nitr...

Renewable energy systems are increasingly essential to sustainable power generation because they reduce dependence on fossil fuels and support low-carbon energy transition. However, the performance of solar, wind, and hybrid renewable systems is often limited by intermittency, nonlinear operating characteristics, environmental uncertainty, and integration challenges. These factors reduce energy extraction efficiency,...

The blended learning has become a common practice in higher education, yet its success is commonly assessed with a single measure like student satisfaction, academic achievement, or technology acceptance. The current paper presents a multi-stakeholder model that can be explained with the help of the following problem statement: The proposed framework will combine the satisfaction of teachers, students, academic perfo...

The purpose of this research is to design and train a deep learning-based surveillance network that can detect anomalous and suspicious behavior in real time using the Daily Crime Surveillance and Safety System (DCSASS). The system will enhance safety on the streets and enable detection of threats ahead through automation of anomaly detection of the video feeds. The methodology is systematic and organized and starts...

Cloud computing has significantly transformed the way people investigate security video images by enhancing the analytical ability of surveillance technology, scaling and efficiency. Ordinary video surveillance systems have limitations in storage, real-time processing, and analysis of data, cloud computing addresses these issues quite satisfactorily. This paper explores different types of cloud computing models, Infr...

Web service recommendation has become an essential research area due to the rapid growth of cloud computing and service-oriented architectures. Functional similarity alone is insufficient for selecting appropriate web services because multiple services often provide identical functionality with varying Quality of Service (QoS) characteristics. QoS-aware recommendation systems assist users in selecting services based...