Academy Journal for Basic and Applied Sciences

Transfer Learning Model for Offline Handwritten Arabic Signature Recognition

Eisha Rzage — 2025-02-09

The verification of handwritten signatures is a significant area of research in computer vision and machine learning (ML). Handwritten signatures serve as unique biometric identifiers, making it essential to distinguish between genuine and forged signatures. This binary classification task is crucial in legal and financial contexts to prevent fraud and protect customers from potential losses. However, verifying offline handwritten signatures is challenging due to variations in handwriting influenced by factors such as mood, fatigue, writing surface, and writing instrument. This research paper focuses on recognizing offline handwritten Arabic signatures using deep learning (DL), specifically transfer learning (TL) technique which is called “Inception-V3 TL model”. Three distinct datasets are used to build a model for recognizing signatures. The first dataset is referred to as Dataset1. It is an English signature dataset called "CEDAR" which contains 1,320 genuine and 1,320 forged signatures. Dataset1 is publicly available at: https://www.kaggle.com/datasets/shreelakshmigp/cedard ataset .The second dataset is referred to as Dataset2. It is a new Arabic signature dataset created for this research which contains 1,320 genuine and 1,320 forged signatures. The third dataset is referred to as Dataset3. It is created by merging the English and Arabic signature datasets (Dataset1 and Dataset2). The Inception-V3 TL model is trained on these distinct datasets (Dataset1, Dataset2, and Dataset3). Both normal training and k-fold cross-validation (CV) methods are applied to evaluate the model’s performance, ensuring robustness and reliability. The Inception-V3 model achieved impressive accuracies of 97.48% on the Dataset1, 98.23% on Dataset2, and 97.85% on Dataset3, demonstrating its effectiveness in distinguishing between genuine and forged signatures.

Evaluation of the prevalence of different types of cancer according to the Misrata Oncology Centre data during the period 2018-2022

Alhmmali A.M. Abdalla — 2025-02-09

Cancer is a disease in which some of the body’s cells grow out of control and spread to other body parts. cancer is an ongoing global challenge. It is a leading cause of disease worldwide. Most cancer deaths each year are related to lung, colorectal, stomach, and breast cancers. Detection of disease in early stages, enabling more effective treatment and reducing morbidity and mortality. This study aimed to assess the prevalence of different types of cancers in Libya. Methods: A retrospective study was carried out, the data was collected by visiting the Oncology Centre in Misrata, reviewing the records, and recording data on the prevalence of different types of tumours from 2018 to 2022. Results: The number of cases rises every year, the overall number of cancer cases is rising annually: 1198 cases were reported in 2018, 1143 cases in 2019, 1422 cases in 2020, 1533 cases in 2021, and 1640 cases in 2022. The breast cancer was the most prevalent type of cancer during the period 2018-2022, the following results were recorded 21.45%, 20.9%, 22.6% 24.9% and 23.7% respectively. Followed by colon cancer was recorded at 16.4%, 15.7%, 17.2%, 18.4% and 15.6 respectively, followed by lung cancer was recorded at 7.8%, 7.9%, 10.6%, 8% and 9%. the fourth to ten grades are often confined between lymphoma, ovary, prostate, leukemia, pancreas, sarcoma and brain tumor. According to our results, we concluded that there is a clear increase in the number of cases of various types of cancer in Libya every year. Early detection is the first line of defence against this dangerous disease. People need to be sensitised to regular check-ups. The government should provide the requirements for detection and treatment.

Arabic Speech Recognition using a Combined Deep Learning Model

Fathiyah Habeeb — 2025-02-09

Speech recognition is a valuable tool in various industries; however, achieving high accuracy remains a major challenge, despite the rapid growth of the speech recognition market. Arabic in particular lags behind other languages in the field of speech recognition, requiring further attention and development. To address this issue, this research uses deep neural networks to develop an automatic Arabic speech recognition model based on isolated words technology. A hybrid model, which is originally developed by Radfar et al. [1] for English speech recognition, is adopted and adapted to be used for Arabic speech recognition. This model combines the strengths of recurrent neural networks (RNNs), which are critical in speech recognition tasks, with convolutional neural networks (CNNs) to form a hybrid model known as ConvRNN. A specific model for Arabic speech recognition which is referred to as “Arabic_ConvRNN” model has been developed based on “ConvRNN” model. The adopted model is trained using an Arabic speech publicly available dataset of isolated words, along with a custom-generated dataset specially prepared for this research. The performance of the built model has been evaluated using standard metrics, including word error rate (WER), accuracy, precision, recall, and F-measure (also referred to as f1- score). In addition, K-fold cross-validation method has been employed to ensure robustness and generalizability. The results demonstrated that Arabic_ConvRNN model achieved a high accuracy rate of 95.7% on unseen data, with a minimal WER of about 4.3%. These findings highlight the model's effectiveness in accurately recognizing Arabic speech with minimal errors. Comparisons with similar models from previous studies further validated the superiority of Arabic_ConvRNN model. Overall, the Arabic_ConvRNN model shows great promise for applications requiring accurate and efficient Arabic speech recognition. This research contributes to narrowing the gap in Arabic speech recognition technology, offering a robust solution for accurately converting Arabic speech into text.

Enhancing the Growth of Wheat (Triticum aestivum L.) Through Putrescine Application Under Drought Stress Conditions

Adeel Abdulkarim Altuhaish — 2025-02-09

Drought stress is one of the main factors restricting growth and development in subtropical area where wheat is being grown. Field experiments were conducted in the Aren field -toralbaha district, Lahj governorate, Yemen to study the effects of putrescine application on the morphological and physiological characters of plants under drought conditions. The experiments was arranged using a randomized complete block design with two factors (1) putrescine treatment (0, 1.25, and 2.5 mM) and (2) drought stress (DS) consisting of 50% water irrigation and 100% well watering (WW). One week prior to heading and one week following the anthesis stage, the aerial portions of the plant were sprayed with putrescine. Some characteristics of morphology and physiology were observed and analyzed. The Results indicated that drought stress had a substantial impact on the majority of growth parameters; however, putrescine treatment significantly increased plant growth, with the exception of plant height. More malondialdehyde (MDA) content and less superoxide dismutase (SOD) activity during drought stress. Putrescine, interestingly, was able to raise SOD activity and lower MDA concentration in both conditions. The effects of drought stress were seen in leaf relative water content, total soluble sugar, and proline. The amount of proline, total soluble sugar, and relative water content all rose after putrescine treatment. There was a suggestion that putrescine could enhance the development and resilience of wheat cultivated in drought stress condition.

Comparative Study of Hydroelectric Power Production between Wadi Ghan Dam and Wadi Majinin Dam in the Western Mountain Region of Libya

Zakariya Khalleefa Ramadhan Tinneesh — 2025-02-09

This paper presents the study if could design of a hydroelectric power station utilizing dam resources in the Western Mountain region of Libya. Monthly data spanning three years was analyzed for each dam, focusing on energy production comparisons between Wadi Ghan and Wadi Majinin dams from 2010 to 2012. Key factors examined include dam size, height, and water storage capacity, all impacting energy production efficiency. Designed with a targeted production capacity of 30 MW per day, the project incorporates pumps to recycle discharged water, preventing loss and optimizing resources. Data analysis was conducted using Excel. The economic viability of the project is promising, as the station will enhance regional electricity supply while reducing dependence on conventional energy sources. As a renewable and clean source, hydroelectric power minimizes harmful emissions and mitigates negative environmental impacts. Establishing the station is also expected to support local infrastructure, stimulate the economy, and create job opportunities. In the operational phase, hydroelectric power generation is anticipated to have lower costs compared to traditional energy sources.Furthermore, raising the dam's water level is projected to boost energy output by increasing storage capacity and enhancing hydrostatic pressure on the turbines, thus improving turbine efficiency and overall energy generation. These optimizations align with the project’s objectives, contributing to increased energy output, economic viability, and the enhanced performance of the hydroelectric power station.

Odd Lindley Log Compound Rayleigh Distribution with Some Statistical Properties

Marwah Ahmed Aefa — 2025-02-09

In the current study a new family of distributions called the odd Lindley Log compound Rayleigh distribution is introduced and studied. Some statistical properties of the new distribution including moments, moment generating function and Renyi entropy are derived. Parameter estimations are obtained via the maximum likelihood method and the observed information matrix is derived. Finally, a real dataset is used to illustrate the importance and flexibility of the new proposed distribution.

Adaptation of Land Use Plans to climate change after the Wadi Derna flood

Jamila Sulaiman Al-Arabi — 2025-02-09

This study followed a literal context model for geoengineering operations, starting with inventorying and evaluating the works and topographical, purposeful, and planning data in the master plan for land use for the coastal city of Derna, for the planning years 1980- 2000, with updating the proposed land use plan for the year 2009, to be done through analysis of digital maps and satellite images. (Pleades) integrated into the geographic information system environment (GIS- ArcMap10.8). In line with the geomorphological nature and the drainage pattern of the valleys, taking into account the effects of climate change, studying the impact of the destruction that the city was exposed to after the flood, and simulating the flood with the three-dimensional digital models available in the (ArcScene 10.8) system. It is proposed to designate reliable protection areas to reduce the risk of flooding on the banks of the valleys. With an emphasis on employing protection areas around the valley within the city for recreational and sports uses and green areas. This study also concluded that it is necessary to realize the effects of climate extremes, take into account the risks of flood disasters when carrying out land use plans in the future, and Consulting local experts with specialization in relevant fields such as geology, soil and water, environment, and climate, to integrate their expertise with specialists in the field of land use planning, To arrive at a proposal that serves the objectives of urban planning with standards compatible with climate change.

The Impact of Poor Planning on the Implementation of Construction Projects (An Applied Study on the Municipality of Maslata from 2020 - 2024 AD)

Mustafa Al-Taher Abdul Aziz — 2025-02-09

This study aims to shed light on the extent of the impact of poor planning on the delay in the implementation of construction projects in the municipality of Maslata, specifically in the period from 2020 to 2024 AD. The study focused on identifying the reasons for poor planning in the implementation of construction projects in the municipality of Maslata, as more than 65 km of asphalt were paved in several areas within the municipality, and these projects faced several reasons in their implementation, which led to a delay in the specified timetable for the project. The study community consisted of a sample of managers, heads of departments and engineers of construction project implementation sites for some of the implementing companies within the municipality, where the descriptive approach was used to describe the problem of poor planning and the analytical approach in analyzing the data resulting from the questionnaire. The researchers relied on the questionnaire and personal interviews to collect the study data, as a number of (40) questionnaires were distributed, and a number of (27) questionnaires were retrieved, i.e. a recovery rate of (%67.5), and this data was fed into the statistical program (SPSS) and processed to produce the results. The study reached a set of results, the most important of which is that planning for these projects is not good, due to circumstances beyond the control of the implementing companies, as well as internal circumstances, including lack of experience in setting the timetable, and lack of future expectations. The study also presented a number of recommendations, the most prominent of which was the need for some external parties to cooperate with the companies implementing construction projects, as well as collecting the necessary information and analyzing data before setting the project timetable, and the flexibility to adapt to what is expected to happen in the future.

Libyan Public Primary Schools between reality and ambition to become child-friendly schools, according to UNICEF standards - Case study: Public Primary Schools in the Capital, Tripoli

Mariam M T Shibub — 2025-02-09

In light of the great and increasing interest shown by developed countries in the quality of education by expanding their educational institutions to keep pace with the progress and development of modern methods of education; moving away from traditional education and creating an educational environment that is compatible with technological development and its requirements. In addition, the quality of education can be improved through an advanced school environment that adopts educational policies that will enhance children's academic and behavioral outcomes. Therefore, it was necessary to shed light on the issue of public primary schools in Libya where they stand in the global development of education, and the extent to which they can be developed to become child-friendly schools. To keep up with this development, a problem surfaced, which is the failure of the built environment of primary schools in Libya to mismatch with the global development in modern teaching methods, as they depend on indoctrination and memorization methods in conveying information to students, not on participation and understanding. This problem is considered one of the most important reasons that led to the decline and deterioration of the education quality, as Libya has been included since 2015 among the (unclassified) countries that do not have the simplest standards of quality in education according to the Primary Education Quality Index included in the Global Competitiveness Report issued annually by the World Economic Forum (Davos). The importance of the research paper lies in shedding light on this problem to improve the quality of education in Libya and its educational outcomes. In addition to raising the educational system's performance by identifying the most important design needs for it to become child-friendly schools by evaluating random samples of public primary schools located in the Libyan capital, Tripoli, as a case study. One of the most important objectives of this paper is to reach requirements to determine the standards that must be taken into account when designing public primary schools. This paper relied on the (inductive) approach to determine the needs of primary schools, by studying the child-friendly school standards included in the United Nations Children's Foundation (UNICEF) guide. The (deductive) approach is also used in the current situation of some primary schools within Tripoli city to evaluate them and identify their suitability for applying the UNICEF Guide standards for child-friendly schools. Also, identifying the shortcomings and problems that these schools suffer from. The most important methods used to analyze the results were (Personal Construct Psychology and Eco-analyses) and (Microsoft Excel). The research paper reached some recommendations to the authorities responsible for the education sector to reconsider the terms and standards for designing schools to be implemented in the future. In addition to reaching some requirements and standards for improving the existing environment of public primary schools as an educational development unit to become child-friendly schools to achieve comprehensive community development.