journal port science research

Diabetes is one of the silent killer diseases that can effect if left without medication and a real change in lifestyle. 10.5% of adult people (10-79 years) have diabetic in the world according to the International Diabetes Federation (IDF) Diabetes Atlas (2021) reports [1]. And number getting higher. Thus, in this study, we aim to build a prediction model using Pima Indian Diabetes (PID) dataset. Dataset required heavy-duty processing because of its low-quality characteristics, such as lot missing values and imbalance. This paper shows how enhancing data quality can affectively reflect on models’ performance. Based on the conducted experiments, ensemble models such as Random Forest show highest performance (0.86% AUC-ROC) with highest encasement among all other model by around 4%.

The amount of information, specifically the information related to website environment, is increasing and becoming larger and larger day by day, thus, playing an important role in the discovery of diverse knowledge on the web. In this paper, our goal is the creation of a new dataset for web content mining that is used in the testing and evaluation of any new system before the production phase. Key characteristics for our dataset are semi-structured, size=4.05 MB, type: text, No. of rows: 298, No. of columns: 6, file type: .csv (comma separated value), domains: Computer, Mathematical, Physics, Chemistry Sciences. Python code will be used to read set of links from set of websites, then read and save the web page content as text of these links. Our dataset discussed based on (Dataset Overview and Scope, Data Quality and Robustness, Utility and Applications), and evaluated and showed the with its robust structure—comprising domain, website, and webpage data—it supports a variety of web content mining applications.

Public transport systems are one of the main pillars in achieving sustainable urban development and improving the quality of life in cities. Transport planning is closely related to the efficiency of the daily movements of the population, reducing the gap between housing and work areas, and enhancing access to public services and utilities, In this context, the importance of developing public transport planning strategies stands out as an effective tool for supporting orderly urban growth, reducing environmental, social and economic problems that may result from poor planning or poor transport infrastructure, The research supports the trends aimed at achieving sustainable urban development, by emphasizing the role of public transport in enhancing the quality of life and achieving social equality and spatial justice, this research seeks to answer a number of fundamental questions, including: how efficient are the current public transport planning strategies in Baghdad What is the impact of these strategies on the various dimensions of the population's quality of life How can these strategies be improved to achieve more inclusive and sustainable urban development, The research aims at providing an analytical framework for understanding the complex relationship between urban planning of transport and quality of life, and also highlights the importance of integrated planning that takes into account the socio-economic specificity of the city, Through the expected results, the research can provide practical recommendations to decision makers, contributing to the reformulation of urban and transport policies, commensurate with the requirements of the current stage and the future of Baghdad, This research is based on the descriptive analytical approach, where data are collected and analyzed to understand the reality of public transport planning and its impact on the quality of life, using quantitative and qualitative methodological methods.

The Internet of Things (IoT) has become a transformational strength in various fields, including health services, production and urban infrastructure. Although it enables automation and data exchange in real time, it also introduces sufficient risks that cannot be ignored. This article makes a comprehensive review of existing literature to detect the most pressure related challenges associated with IoT, including security weaknesses, privacy considerations, inter -Boundaries and questions of stability. This emphasizes how the growing number interacted equipment expands the surface of the cyber-attacks, often increased by old firmware, weak encryption and incompatible standards. In response, recent research has suggested integration of blockchain, artificial intelligence and slightly cryptography as a possible solution. However, practical purposes are interrupted by the lack of energy and scalable, the requirement for adaptive structure. The study also emphasized the role of new technologies such as edge calculation and 5G to remove delay and reliability problems. In addition, the data protection and generation -related moral and regulatory complications discuss. By synthesizing insights from recent studies, the paper suggests future research directions, aimed at developing energy networks, safe and standardized IoT ecosystem.

The persistent evolution of Windows malware presents a significant challenge to static‐analysis techniques, which often rely on handcrafted features and single‐modality models that struggle to generalize across diverse and obfuscated samples. This study proposes a novel Dual‐Branch CNN‐LSTM Residual Network that concurrently processes a uniform static feature vector as both a pseudo‐image and a sequential input, thereby capturing complementary spatial and temporal patterns without necessitating multiple preprocessing pipelines. The architecture incorporates residual connections in each branch to preserve gradient flow and facilitate deep learning. Experiments conducted on the EMBER dataset demonstrate that the proposed method attains an accuracy of 97.1 %, alongside a precision of 96.9 %, a recall of 97.1 %, and an F1-score of 97.0 %, surpassing existing single‐branch and traditional baseline models. These results underscore the capacity of dual‐branch residual fusion to improve detection performance while maintaining computational efficiency and robustness to feature obfuscation. The unified preprocessing scheme further simplifies cross‐dataset evaluation, paving the way for scalable deployment in real‐world Windows environments

The amount of information, specifically the information related to website environment, is increasing and becoming larger and larger day by day, thus, playing an important role in the discovery of diverse knowledge on the web. In this paper, our goal is the creation of a new dataset for web content mining that is used in the testing and evaluation of any new system before the production phase. Key characteristics for our dataset are semi-structured, size=4.05 MB, type: text, No. of rows: 298, No. of columns: 6, file type: .csv (comma separated value), domains: Computer, Mathematical, Physics, Chemistry Sciences. Python code will be used to read set of links from set of websites, then read and save the web page content as text of these links. Our dataset discussed based on (Dataset Overview and Scope, Data Quality and Robustness, Utility and Applications), and evaluated and showed the with its robust structure—comprising domain, website, and webpage data—it supports a variety of web content mining applications.

Abstract The primary goal of root canal treatment (RCT) is to expel the presence of any necrotic or vital tissue, microbes and their byproducts from the canal space before press forward with the following steps of the RCT procedures. Although this is difficult to attain, various strives had been practiced by employing chemical and mechanical methods to eliminate as much microorganisms as possible and make the canal space valid for the obturation materials to be received. The aim of this review is to demonstrate some of what new remedies that could be used as root canal disinfectant by summarizing the recent studies regarding the efficacy of different natural products against the most persistence microbiota that could be responsible for most of the failures after RCT. A comprehensive search has been performed in English language on published resources using Pub Med, Google Scholar, and Research Gate databases from 2010 to Dec 2024 by using the keywords: “root canal irrigant”, “cinnamon”, “neem oil”, “propolis”, “triphala” and “Enterococcus faecalis”. Thirty-two papers adopted in this review. Endnote reference management software was used for organization of citations. natural remedies demonstrated potential in reducing bacterial count especially when using synergism of various natural and chemical products, it shows remarkable effect in targeting resistant microbiota such Enterococcus faecalis nevertheless it must undergo comprehensive preclinical and clinical trials to substantiate the results before they can conclusively be recommended as intracanal irrigating solutions. Herbs are generally harmless when appropriately used, but they can be hazardous if taken incorrectly.

The essential process of collecting raw data called image reconstruction which can interpret and analyze several imaging modalities in order to form an understandable image format for humans. Thus, the goal of image reconstruction is to create a usable image with high quality allowing the inspection of internal for defects without damaging the item. It consists of several cascade process like, data acquisition, preprocessing, and the application of a reconstruction algorithm and post-processing to enhance its visual quality. This paper proposed an algorithm of combining wavelet transform with neural network for image reconstruction. Such combination offers several significant advantages by leveraging the strengths of both techniques. The proposed hybrid algorithm is very effective in several tasks like image super-resolution, denoising, and medical imaging reconstruction. The algorithm depends on an 8-level wavelet decomposition for feature extraction and Elman recurrent neural network for uncompleted image in small and big losing blocks. The reconstruction achieved 100% of accuracy even with a losing case of 75% from the original image.

Image restoration is a fundamental problem in low-level vision with applications in photography, surveillance, and archival imaging. This review synthesizes deep learning–based advances from 2018–2025, covering CNN (Convolutional Neural Network), GAN (Generative Adversarial Network), and Transformer families. This paper presents a unified taxonomy by degradation type (denoising, deblurring, super-resolution, dehazing/draining, JPEG deblocking, inpainting) and by model class. Representative architectures are summarized with their core design choices, training objectives, and computational characteristics. The comparison of common protocols, datasets (e.g., DIV2K, SIDD, GoPro, REDS), and metrics like PSNR (Peak Signal-to-Noise Ratio), SSIM (Structural Similarity Index), and LPIPS (Learned Perceptual Image Patch Similarity are given also). The review analyzes trade-offs between fidelity, perceptual quality, and efficiency. The identification of open challenges, robust generalization to real-world degradations, efficient high-resolution inference, reliable perceptual evaluation, and unified multi-degradation handling, and outline research opportunities are also considered. This review aims to serve as a unified reference for practitioners and researchers developing next-generation image restoration systems.