Classification of Benign and Melanoma Skin Tumors Using Modified CNN with Transfer Learning

Paparao; Surendiran

doi:https://doi.org/10.54216/JISIoT.180229

Journal of International Economics Research | 2026

Practical Analysis and Econometric Results of the Rreasury Service Committee of Uzbekistan

This article analyzes the practical effectiveness of treasury mechanisms, which constitute a key institutional component of the public financial management system in Uzbekistan, using empirical and econometric methods. The study covers the period from 2015 to 2024 and examines indicators of state budget execution, the share of payments carried out through the treasury system, and measures of fiscal discipline. Time series analysis and regression models are employed to assess the impact of treasury control on the efficiency of budget execution. The results indicate that the strengthening of treasury mechanisms contributes to enhancing fiscal stability. The findings of the study provide a basis for developing scientific and practical recommendations aimed at improving public financial management under the conditions of Uzbekistan.

groups

Sholdarov Dilshod Azimiddin o'g'li mail -

Navruzova Go‘zal Olimjon qizi mail

link https://doi.org/10.54216/JIER.030101

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Journal of International Economics Research | 2026

Accounting for Business Combinations in Accordance with International Accounting Standards (IAS)

Business combinations represent a critical area of financial reporting due to their significant impact on financial position and performance. This study examines accounting for business combinations under International Accounting Standards, with particular emphasis on IFRS 3 Business Combinations and IAS 36 Impairment of Assets. Using comparative analysis, synthesis of empirical research, and illustrative financial data, the paper evaluates recognition, measurement, and disclosure practices, as well as their implications for transparency and comparability. The findings confirm that standardized accounting treatments improve decision usefulness of financial statements, while challenges remain in fair value measurement and goodwill impairment testing.

groups

Aripova Anna Mixaylovna mail

link https://doi.org/10.54216/JIER.030102

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

International Journal of BIM and Engineering Science | 2026

A Study of the Impact of Applying Building Information Modeling (BIM) on the Efficiency of Engineering Supervision in Syria

In recent years, the construction sector in Syria has witnessed increasing challenges related to the weak efficiency of engineering supervision, leading to increased costs, delayed completion, and recurring field conflicts between different disciplines. In light of the digital transformation taking place in the global construction sector, Building Information Modeling (BIM) has emerged as a modern technical solution capable of improving the quality and effectiveness of supervision. From this perspective, this study analyzed the impact of implementing Building Information Modeling (BIM) on enhancing the efficiency of engineering supervision in Syrian projects, by assessing its role in improving information quality, controlling schedules, and reducing errors and costs. The study adopted a descriptive analytical approach supported by a field study. A comprehensive questionnaire was developed, including 24 criteria covering all aspects of engineering supervision, and distributed to a sample of 90 supervising engineers in the public and private sectors. The results showed that adopting BIM clearly contributes to improving the accuracy of information and facilitating its exchange between parties, early detection of field conflicts prior to implementation, enhancing progress monitoring, and reducing rework rates. This increases supervision efficiency and achieves cost and time savings. However, the study revealed obstacles that limit the implementation of BIM in Syria, most notably weak digital infrastructure, a shortage of qualified personnel, the absence of regulatory policies supporting digital transformation, and weak training and qualifications in Syrian university curricula. The study concluded the need to adopt clear government policies mandating the use of BIM in major projects, develop specialized training programs for engineering supervisors, and establish a Common Data Environment (CDE) that supports digital integration among all parties. The results also confirmed that the shift to digital supervision using BIM is no longer just a technical option, but rather a strategic step to improve the efficiency of construction projects in Syria and ensure their sustainability.

groups

Alhsen Zeno mail -

Mohammed Ali Al-Shamali mail

link https://doi.org/10.54216/IJBES.120103

Volume & Issue

Vol. Volume 12 / Iss. Issue 1

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2026

Enhancing Product Recommendations through Large Language Model and Significant Latent Core Factor SVD: Insights from Amazon Reviews

Ecommerce Platforms specifically in Retail domain be it a brick and morter store or an online shopping application has enormous user data from the behavioral, click stream, page visits, abandoned carts, user think time or dwell time. And from the retail stores where the data captured from Internet of Things (IoT) with respect to the shelve movements, visitor counts, IoT signals arising from RFID tags, beacons, smart sensors, proximity to specific products, kiosk interactions, self-checkout kiosk provide enormous data for hyper personalization. Traditional Singular Value Decomposition (SVD) algorithms suffer with the data sparsity and computational complexity when fed with such large data. Also the SVD relies on the historical patterns to find latent features which may not be very much helpful for the cold start personalization. Consumer behaviors and patterns are non-linear, for ex- ample time spent near a shelf in a Retail Store or the time spent on a categories page in online application and with the filters of the categories. SVD might capture these main trends but will miss subtle high frequency signals that drive the hyper personalization. To overcome this problem, the proposed research employs a significant latent core factor SVD. The proposed technique includes decomposing a large and sparse matrix that captures real-time interactions between users and products into matrices that permit the proposed model to forecast personalized product recommendations based on existing data. Large Language Models (LLM) were used to improve the process of feature extraction post the data imputation after the initial data preprocessing. The proposed research employs the Amazon product review dataset to evaluate the proposed significant latent core SVD. When compared to traditional SVD and state-of-the-art methods such as LightGCN and BERT4Rec, the proposed significant latent core factor SVD achieves lower error rates.

groups

R. Dhayanidhi mail -

Rajalakshmi N. R. mail

link https://doi.org/10.54216/JISIoT.180228

Volume & Issue

Vol. Volume 18 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2025

An Intelligent Student Performance Monitoring System Using Interactive GUI and Multi-Criteria Evaluation

Student performance during the lecture needs to be closely watched to ensure effective learning takes place. This helps the lecturer monitor the performance of the students in real time. By observing the performance of the students, the lecturer can detect the ones who find performance difficult and assist them accordingly. Besides this, the lecturer can also modify the method of teaching whenever needed. By understanding that their performance can be checked through the system, the student remains motivated to perform even in class. The study will help to develop a system that can be used to monitor the performance of the student during the real time lecture using sound and image processing. The method of developing the system involves the use of two methods: image processing and sound processing. The image processing technique can be used to detect the image of the student, while the sound processing technique will be used to detect the sound of the student during the performance. In the proposed system, Gray Level Co-occurrence Matrix technique has been used along with the Viola-Jones method to detect images along with the weighted Euclidean distance method used in image processing. Additionally, the Mel Frequency Cepstral Coefficients method has been used to detect the relevant sound along with the classification method involving the K-Nearest neighborhood method. The experiment has shown the efficiency of the system developed because the accuracy of image and sound identification of the student was at an average of 89% and 90% respectively. All of this helped to ascertain the efficiency of the system in the development of the research study.

groups

M. E. ElAlmi mail -

A. F. Elgamal mail -

Samar O. AbouElwafa mail

link https://doi.org/10.54216/JISIoT.170231

Volume & Issue

Vol. Volume 17 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2026

A Unified Linear Algebra–Centric Framework for Integrating Query Processing and GPU-Accelerated Machine Learning

The increasing adoption of large-scale machine learning (ML) applications has exposed critical performance limitations in current data processing pipelines, particularly due to the separation between relational query execution and ML inference. This separation introduces redundant computations, excessive data materialization, and inefficient utilization of GPU Matrix Processing [10] resources. In this paper, we present a unified execution framework that integrates relational query processing and machine learning prediction by representing both as linear algebra operations. Leveraging algebraic properties such as associativity and distributivity, we introduce an operator fusion [8] strategy that enables query operators and ML models to be jointly executed on GPU Matrix Processing [10] architectures. This approach reduces intermediate data movement and enables end-to-end pipeline execution within a single linear algebra runtime. We analyze the computational complexity of the proposed fusion strategy and discuss its applicability to star-schema workloads commonly found in analytical systems. Experimental insights from prior studies indicate that linear algebra–based query execution combined with operator fusion [8] can yield substantial performance improvements over conventional GPU Matrix Processing [10]-accelerated pipelines, while maintaining scalability and portability. The proposed framework provides a viable foundation for future data-intensive systems that aim to unify analytics and machine learning on heterogeneous computing platforms. [1–3,14–16] This work unifies relational query processing and ML inference within a single algebraic runtime on GPUs, rather than coupling independent GPU-accelerated stages, thereby enabling cross-stage optimization and eliminating redundant materialization. Unlike existing GPU-accelerated databases and tensor-based query processors, the proposed framework provides a system-level unification of relational analytics and machine learning inference, rather than treating them as isolated or sequential stages. The framework is backend-agnostic and applicable to modern tensor runtimes and heterogeneous accelerator platforms, making it suitable for next-generation data-intensive systems.

groups

Abdulnaser Rashid mail -

Zahra I. Mahmoud mail -

Mawahib Elamin mail -

Amel H. Abdalla mail -

Adil O. Y. Mohamed mail

link https://doi.org/10.54216/IJNS.270240

Volume & Issue

Vol. Volume 27 / Iss. Issue 2

Details open_in_new

International Journal of BIM and Engineering Science | 2026

Integrating BIM and Artificial Intelligence for Multi-Dimensional Sustainability in Post-Conflict Reconstruction

Post-conflict reconstruction often prioritizes speed and cost over long-term sustainability, leading to environmental, social, and economic inefficiencies. This study proposes an integrated framework that combines Building Information Modeling (BIM) and Artificial Intelligence (AI) to enhance multi-dimensional sustainability in reconstruction projects. An exploratory explanatory case study methodology was adopted, analyzing two Syrian case studies—a service building in Tartous and the Al-Qarabis neighborhood in Homs—through BIM-based simulations and AI-driven optimization. BIM served as the core data platform, while AI facilitated scenario analysis and optimization across both design and operational stages. Sustainability indicators were explicitly mapped to relevant Sustainable Development Goals (SDGs 7, 9, 11, 12, and 13). Results indicate that BIM–AI integration significantly improves energy efficiency, operational performance, spatial adequacy, and life-cycle cost effectiveness, effectively translating sustainability from a conceptual goal into measurable outcomes. The framework provides empirical evidence for operationalizing Building Back Better principles and offers a transferable methodology applicable to other post-conflict reconstruction contexts. Future studies could explore the incorporation of additional AI-driven decision support tools or expand the framework to diverse post-conflict regions to further validate its applicability and impact.

groups

Alaa Hasanin mail -

Karel Pavelka mail

link https://doi.org/10.54216/IJBES.120104

Volume & Issue

Vol. Volume 12 / Iss. Issue 1

Details open_in_new

International Journal of BIM and Engineering Science | 2026

Parametric Sensitivity of Axial–Flexural Interaction in Reinforced Concrete Shear Walls for Optimized Design and Structural Efficiency

Purpose: This study develops a code-agnostic, mechanics-first framework to quantify the parametric sensitivity of axial flexural (N-M) interaction in reinforced concrete (RC) shear walls and to produce transferable rankings of key “design knobs” controlling N–M response metrics. Design/methodology/approach: A strain-compatibility, fiber-based sectional solver is formulated for rectangular, T, I/H, and U-shaped wall sections. The mechanics engine is decoupled from a modular code-profile layer (ACI-/EC2-/BS-consistent mappings) to enable cross-code comparisons. Interaction curves are normalized to isolate mechanics-driven shape effects, and scalar metrics are extracted at multiple axial levels (e.g., M^* (N^*=0.1,0.3,0.5), Mmax, and balanced-point indicators). Sensitivity is quantified using local elasticities, Morris screening, and Sobol variance-based indices; numerical reproducibility is verified through convergence and mesh-independence controls. Findings: Normalization collapses most cross-code variability in curve shape, while design-level curves retain separable safety-format differences. Sensitivity rankings vary with axial level and section family, revealing nonlinear interactions and regime shifts especially for irregular sections where flange participation can dominate near peak or balanced states. Practical implications: The framework supports cross-code traceability and efficiency-based design guidance (steel and boundary efficiency) across axial regimes, highlighting diminishing returns and marginal benefits. Originality/value: The study delivers a reproducible, code agnostic N–M engine integrated with rigorous global sensitivity analysis to bridge the gap between sectional mechanics and design-oriented decision-making.

groups

Islam Ibrahim Shoheb mail -

Moustafa Metwally mail -

Intan Rohani Endut mail

link https://doi.org/10.54216/IJBES.120105

Volume & Issue

Vol. Volume 12 / Iss. Issue 1

Details open_in_new

Journal of International Economics Research | 2026

A Dual-Bank Hybrid Predictive Model (DBHPM) for Financial Forecasting

Forecasting of the financial performance is significant mainly for the purpose of strategy formulation and identification of potential problems in banking institutions. This paper presents a new model of a predictive model for financial forecasting called the Dual-Bank Hybrid Predictive Model which consists of a Multiple Linear Regression and Random Forest Regression. This model is also validated on two actual financial datasets of Agrobank and NBU Bank from the year 2021 to 2025. It also relies on the analysis of such financial ratiosas Net profit, Equity, and Solvency which have been forecasted up to the year 2027. Specifically, while the DBHPM consists of linear modeling through MLR in the first step, and then, nonlinear residuals thru RFR in the second step of the analysis, the former provides increased generalizations and predictive strength as compared to the later stage solely. The experimental results show that DBHPM minimizes MAE and RMSE achieving the coefficient of determination (R2) amounting to 0.95 and above if compared to the models trained independently. Statistical modelling shows that the two banks go up with Agrobank at approximately 1.18 billion sum and NBU Bank at 3.66 billion sum of the net profit by the end of 2027. The outlined hybrid model presents the possibility of better predictive analytics financial modelling in the banking industry for purposes of, decision-making, risk alertness, and economic forecast.

groups

Samandarboy Sulaymanov mail

link https://doi.org/10.54216/JIER.030205

Volume & Issue

Vol. Volume 3 / Iss. Issue 2

Details open_in_new

Journal of Intelligent Systems and Internet of Things | 2026

Classification of Benign and Melanoma Skin Tumors Using Modified CNN with Transfer Learning

One of the most dangerous and deadly illnesses that people can face in their lives is cancer. Among all cancers, skin cancer is one of the most damaging, hazardous, and potentially fatal to a person's life. If not detected it and treated initially, it will extend to other body parts soon and lead to the deadliest situation.  It will spread quickly when the skin tissue areas are exposed to sunlight, mostly because skin cells in the designated location develop quickly. An automated skin tumor recognition system is the main requirement in order to detect skin cancer early, minimize time and effort, and save human lives. The most popular and successful methods for classifying skin cancer are the techniques of image processing and deep learning models. So, there is a need for an automated healthcare system to detect and classify skin lesions. We proposed a CNN model for classifying skin tumor images in our work. We have trained CNN models like AlexNet, VGG16, ResNet50, and Inceptionv3 using transfer learning techniques and observed the performance accuracies of all the models. The dataset used in our work contains two types of benign and melanoma skin tumor images, which are classified into two kinds through the Convolution Neural Network models. We used preprocessing techniques to clean our data, and data augmentation was also used to generate more data. As we know, deep learning models need more data to train and test the models. In all our model implementations, we have used all the features from the image while training the models for classification. Finally, we used the transfer learning techniques in our implementation models to improve the accuracy of each Image classification model. We trained the three models with different optimizers: Adam, Adadelta, and SGD. The proposed model (Modified AlexNet) provides better results, with approximately 96.75% for Training accuracy, 94.43% for Validation accuracy, and 94.11% for Testing Accuracy. The proposed model's performance results are compared with the state-of-the-art models like AlexNet, InceptionV3, VGG16, and ResNet50.

groups

Paparao Mekala mail -

Surendiran B. mail

link https://doi.org/10.54216/JISIoT.180229

Volume & Issue

Vol. Volume 18 / Iss. Issue 2

Details open_in_new