Articles
9 Documents
Search results for
, issue
"Vol. 4 No. 1 (2025): March 2025"
:
9 Documents
clear
<![CDATA[Convolutional Arabic handwriting recognition system based BLSTM-CTC using WBS decoder ]]>
<![CDATA[Rabi, Mouhcine]]>;
<![CDATA[Amrouche, Mustapha]]>
<![CDATA[ International Journal of Advanced Science and Computer Applications Vol. 4 No. 1 (2025): March 2025 ]]>
Publisher : <![CDATA[Utan Kayu Publishins ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47679/ijasca.v3i2.52
<![CDATA[Arabic handwriting recognition (AHR) poses major challenges for pattern recognition due to the cursive script and visual similarity of Arabic characters. While deep learning demonstrates promise, architectural enhancements may further improve performance. This study presents an offline AHR approach using a convolutional neural network (CNN) with bidirectional long short-term memory (BLSTM) and connectionist temporal classification (CTC). By enhancing temporal modeling and context representations without segmentation requirements, this BLSTM-CTC-CNN framework with an integrated Word Beam Search (WBS) decoder achieved 94.58% accuracy on the IFN/ENIT database. Results highlight improved efficiency over prior works. This demonstrates continued advancement in sophisticated deep learning techniques for accurate AHR through specialized modeling of Arabic script cursive properties and decoding constraints. This research represents an advancement in the continuous development of progressively intricate and precise systems for handwriting recognition.]]>
<![CDATA[Enhanced Vigenere And Affine Ciphers Surrounded By Dual Genetic Crossover Mechanisms For Encrypting Color Images ]]>
<![CDATA[EL BOURAKKADI, Hamid]]>;
<![CDATA[TABTI, Hassan]]>;
<![CDATA[CHEMLAL, Abdelhakim]]>;
<![CDATA[KATTASS, Mourad]]>;
<![CDATA[JARJAR, Abdellatif]]>;
<![CDATA[BENAZZI, Abdelhamid]]>
<![CDATA[ International Journal of Advanced Science and Computer Applications Vol. 4 No. 1 (2025): March 2025 ]]>
Publisher : <![CDATA[Utan Kayu Publishins ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47679/ijasca.v4i1.57
<![CDATA[This paper introduces an enhanced technique for encrypting color images, surpassing the effectiveness of genetic crossover and substitution methods. The approach integrates dynamic random functions to bolster the integrity of the resulting vector, elevating temporal complexity to deter potential attacks. The enhancement entails amalgamating genetic crossover using two extensive pseudorandom replacement tables derived from established chaotic maps in cryptography. Following the controlled vectorization of the original image, our method commences with an initial genetic crossover inspired by DNA behavior at the pixel level. This process is followed by a confusion-diffusion lap, strengthening the relationship between encrypted pixels and their neighboring counterparts. The confusion-diffusion mechanism employs dynamic pseudorandom affine functions at the pixel level. Subsequently, a second genetic crossover operator is applied. Simulations conducted on various images with varying sizes and formats demonstrate the resilience of our approach against statistical and differential attacks.]]>
<![CDATA[Crop yield prediction by Mestrial Environ Netsual Network (MENN) ]]>
<![CDATA[Kumar, R.Mathusoothana]]>
<![CDATA[ International Journal of Advanced Science and Computer Applications Vol. 4 No. 1 (2025): March 2025 ]]>
Publisher : <![CDATA[Utan Kayu Publishins ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47679/ijasca.v4i1.59
<![CDATA[Crop yield prediction methods can roughly predict actual yield, although better yield prediction performance is still sought. In the existing methodologies the crop yield prediction outcomes are based on the past experience data and failed to predict the exact outcomes of the crop yield. Hence, a hybrid approach namely Crop yield prediction by Mestrial Environ Netsual Network (MENN) has been proposed to overcome the challenges in the existing approaches and to predict the crop yield with impeccable manner. In previous techniques, the change in phenotype as well as genes in the seed and the plant pathology are not combined as a new model. Hence, Mestrial Neural Network (MNN) has been proposed which consist of Task allocation layer, Subset-net layer and Integrated yield estimation layer to predict the sowing seed gene along with the phenotype and pathology. Also, incorporated pathology module examines the phenotype of respected sowing seed selected for the prediction of yield value. Moreover, while combining the statistical data and image data for the prediction, the generalization ability of prediction model was affected by reason of the images that shared the same timestamp as the statistical data were eliminated as part of the procedure for creating the dataset utilized in the existing approaches. Hence, a novel, Yield Environ Netsual Network (YENN) has been proposed which is consists of two deep networks; (i) Deep Q network (DQN) and (ii) VGG16 for the generalization ability as well as the elimination of data caused by the same timestamp is rectified. Here, VGG-16 is utilized for processing the given input images. As a result, the proposed model well examine the potential disease based on the gene and environment conditions and effectively predict the yield value of crops.]]>
<![CDATA[Automated Handwritten Equation Solver ]]>
<![CDATA[Hussien, Shereen A.]]>;
<![CDATA[Azim, Ahmed M. Abd el]]>;
<![CDATA[Hagag, Ahmed]]>
<![CDATA[ International Journal of Advanced Science and Computer Applications Vol. 4 No. 1 (2025): March 2025 ]]>
Publisher : <![CDATA[Utan Kayu Publishins ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47679/ijasca.v4i1.60
<![CDATA[Mathematics has an important role in person’s life, so solving the mathematical equations is an essential. Solving mathematical expressions is not restricted to just students but also for mathematicians, physicists and scientists. Solving the mathematical equations is an interesting process.The traditional method of solving math expressions is unsatisfactory as the user should learn different rules and approaches for each mathematical equation. Also, these methods may take long time in complex or obscure problems which makes them subject to user errors and mistakes. The challenging in mathematical expressions must be written in a specific format, users prefer to write them on paper as an easy entering way than other computerized tools. This paper used the technology to introduce a new method over the traditional one using pen and paper. The equation handwriting easiness is blended (merge/integrate) with the advanced computer technologies speed to solve the equations with flexible robust way. An interface introduces that allows capturing the equations contained in an image then solving it without making the user dive into the complex rules. Various types of equations could be entered to this application (linear/nonlinear/quadratic) with achieving a convenient accuracy 95.7%.]]>
<![CDATA[a Proposed Machine learning model for predicting Egyptian Parliament Election Results ]]>
<![CDATA[doaa alkhiary]]>;
<![CDATA[Samir Saleh]]>;
<![CDATA[Mohamd Marie]]>
<![CDATA[ International Journal of Advanced Science and Computer Applications Vol. 4 No. 1 (2025): March 2025 ]]>
Publisher : <![CDATA[Utan Kayu Publishins ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47679/ijasca.v4i1.61
<![CDATA[Political life and election have become one of the most important comments on social media sites. Governments have shown a keen interest in predicting the results of elections, whether presidential or parliamentary. The purpose of this study is to predict the results of the Egyptian Parliament elections using sentiment analysis, specifically Support Vector Machines (SVM), Naive Bayes, Decision Trees, and Random Forests in the context of machine learning. In this study, a sentiment analysis approach is employed to analyze public sentiment towards political parties and candidates leading up to Parliament elections. The sentiment analysis techniques are utilized to classify sentiment from textual data collected from Tweeter; Data were obtained in November 2020 before and during election days. The study utilizes a machine learning framework to train and test the models using a labeled dataset of sentiment-labeled political texts. The findings of this study reveal that sentiment analysis using machine learning can effectively predict the results of Parliament elections. The accuracy and performance of each technique are evaluated and compared to determine the most accurate and reliable predictor of election outcomes. This study contributes to the existing literature by applying sentiment analysis techniques to predict Parliament election results. The use of machine learning algorithms in combination with sentiment analysis, offers a novel approach to election forecasting. The findings of this study can be valuable for political analysts, election strategists, and policymakers seeking to understand public sentiment and predict election outcomes accurately.]]>
<![CDATA[A New Agricultural Drought Index to Characterize Agricultural Drought Using Data Mining Techniques ]]>
<![CDATA[Wankhede, Shubhangi]]>;
<![CDATA[Armstrong, Leisa]]>;
<![CDATA[Tripathy , Amiya Kumar]]>
<![CDATA[ International Journal of Advanced Science and Computer Applications Vol. 4 No. 1 (2025): March 2025 ]]>
Publisher : <![CDATA[Utan Kayu Publishins ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47679/ijasca.v4i1.63
<![CDATA[Drought monitoring is a critical task as its occurrence and extent vary according to many factors like drought type, risk, agricultural losses, and impact. Monitoring drought is important because the footprint of this hazard is larger than that of other natural hazards. Many drought indices are developed to monitor complex drought conditions. The intensity and severity of drought in a particular region and at a particular time can be tracked by the drought indicator. In this research, a new agricultural drought index, Yield-Evapotranspiration Drought Index (YEDI) is developed using crop yield, potential, and reference crop evapotranspiration. Data mining and Neural Network techniques have been used to model the drought index. The agricultural and climatic data used is selected from the year 1983 to 2015 (33 years) from the period of June to October (Kharif period) for Maharashtra state in India. The drought index generates the positive values which are further divided into a range of high, medium, and low intensities of drought. SPI and SPEI indices are used for validation against YEDI. Results show that there is a correlation between YEDI and SPEI whereas a low correlation is between YEDI and SPI. YEDI proves to be useful for agricultural drought monitoring.]]>
<![CDATA[Enhance Teaching using Google Classroom as a Digital Tool ]]>
<![CDATA[Dahal, Prasanna]]>;
<![CDATA[Zaghlool, Lubna]]>
<![CDATA[ International Journal of Advanced Science and Computer Applications Vol. 4 No. 1 (2025): March 2025 ]]>
Publisher : <![CDATA[Utan Kayu Publishins ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47679/ijasca.v4i1.86
<![CDATA[Google Classroom is gaining popularity as an online Learning Management System (LMS) and with the suite of free tools that comes with Google for Education, it is worthwhile knowing about.[1] Google Classroom is a fantastic platform to use because it works really well alongside the other apps in Google Suite for Education such as Gmail, Google Calendar, Google Docs, Google Slides, and Google Meet. The ease of having all these handy tools in one place helps to keep things as simple as possible when teaching online. Google Classroom can be used for most parts of delivering a lesson, from setting tasks, adding files, and marking student assignments [2] In this work we explain how to Create Google classroom, invite students to the class, add assignments and materials, Grade the assignments and leave feedback. The aim of the work is to enable teachers to create an online classroom area in which they can manage all the documents that their students need. Teachers can make assignments from within the class, which their students complete and turn in to be graded]]>
<![CDATA[AN IOT-BASED FRAMEWORK FOR EFFICIENT SOLAR POWER GENERATION AND INTEGRATION IN AUTOMOTIVE: INTEGRATION IN AUTOMOTIVE ]]>
<![CDATA[Sri Priya, V.]]>;
<![CDATA[Dr. S.Brindha]]>
<![CDATA[ International Journal of Advanced Science and Computer Applications Vol. 4 No. 1 (2025): March 2025 ]]>
Publisher : <![CDATA[Utan Kayu Publishins ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47679/ijasca.v4i1.103
<![CDATA[Objective: We suggest an Internet of Things (IoT)-based system that uses edge intelligence to anticipate power production effectively and monitors electricity substations and smart solar installations. It ensures dependable and effective power distribution inside industrial Internet of things settings, improving sustainability, safety, and energy management in smart buildings. It also improves decision-making and reduces volatility. Method: Create and execute an IoT-enabled power monitoring system for smart solar panels and substations that incorporates edge intelligence for instantaneous prediction and decision-making. Deploy an IoT-enabled solar charging station for smart homes and Industry 4.0 applications, and use the cloud for sensor data analysis and control. Findings: In order to effectively manage load for commercial, electric, residential, and industrial vehicles, the suggested framework improves the efficiency and dependability of power production and distribution in industrial IoT contexts. The system increases overall efficiency via the mitigation of power fluctuations and eventualities. Furthermore, IoT integration enhances smart building energy management safety and sustainability of energy resources as well as reduced the overall cost by 95% when comparing to the traditional devices. Novelty: For smart solar systems and substations, a novel framework combines edge intelligence with IoT. It includes a sophisticated IoT-based control system that improves power distribution network decision-making. In addition to taking an integrated strategy to energy management and enabling real-time monitoring and prediction of power production in industrial IoT contexts, it emphasizes sustainability, safety, recycling, and reuse in smart buildings.]]>
<![CDATA[Integrating OCR and NLP Techniques for Accurate Text Extraction and Plagiarism Detection in Image-Based Content ]]>
<![CDATA[Kumar, Palvadi Srinivas]]>;
<![CDATA[Prasad, Krishna]]>
<![CDATA[ International Journal of Advanced Science and Computer Applications Vol. 4 No. 1 (2025): March 2025 ]]>
Publisher : <![CDATA[Utan Kayu Publishins ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47679/ijasca.v4i1.105
<![CDATA[In the digital age, images often contain valuable text-based information, including numbers, symbols, and other data. Efficient extraction and verification of this content is critical, particularly in academic and content-driven domains where originality is paramount. This paper presents a novel approach to detecting plagiarism in text embedded within images. The proposed method leverages Optical Character Recognition (OCR) to extract text from images and applies Natural Language Processing (NLP) techniques to evaluate the originality of the extracted content. By comparing the text against a comprehensive database of existing sources, the system is capable of identifying potential plagiarism while distinguishing between original and copied content. This approach ensures that not only text in conventional documents but also in images is scrutinized for authenticity, enhancing the reliability of plagiarism detection in diverse content formats. The proposed solution offers an efficient and automated pipeline for image-based text extraction and plagiarism detection, applicable in educational, legal, and content creation environments.]]>
