ITEGAM-JETIA

Evaluation of the Mechanical Properties of Concrete Mixed with Water-Soluble Polymer

Dele Roger Simeon — 2025-05-22

Polyvinyl alcohol (PVA) is a water-soluble polymer whose impact on concrete properties requires further investigation. Thus, this study established the appropriate dose and applicability of PVA to produce the foremost improvement in the mechanical characteristics of concrete. The study produced 40 concrete cubes and 12 cylinders of concrete specimens at 0%, 0.5%, 1%, 1.5%, and 2% doses of PVA. A number of tests were carried out on the specimens to ascertain their performances. The results showed that a 0.5% addition of PVA to the concrete mixture yields an optimal compressive strength of 24.98N/mm² after 28 days, while the tensile strength increased as the percentage of PVA increased. Besides, the bond strength of the PVA-modified concrete decreased as the proportion of PVA in the concrete mixture increased. The study concludes that a 0.5% addition of PVA to concrete is the ideal dose for enhanced compressive strength. Also, the study concludes that, while the tensile strength of concrete increases with increasing PVA doses, the bond strength of concrete and rebars decreases as the percentage of PVA increases. This implies that PVA is unsuitable for reinforced concrete structural works. The study therefore recommends that PVA should be applied for non-structural reinforced concrete works.

Revolutionizing Mass Production: A Dual Power Portable Photographic Silkscreen Pattern Equipment

Halima A. Sahim-Sali — 2025-05-22

This research endeavors to introduce and evaluate the efficacy of a newly designed Portable Photographic Silkscreen Pattern Equipment integrated with a dual power source. Engaging a cohort of 88 participants across various departments, alongside input from eight experts in Drafting Technology at Zamboanga City State Polytechnic College, a survey questionnaire facilitated data collection via a convenience sampling approach. The study unequivocally establishes the "highly acceptable" nature of the equipment in terms of design, functionality, and portability. Noteworthy attributes include its facilitation of pattern transfer to silkscreen for efficient mass production and its adaptable use of renewable energy, rendering it operational in diverse environments, including remote areas and educational institutions. The equipment's superior portability, robust construction, and systematic wiring organization enhance its practicality. Experimentally, processing silkscreen pattern emulsion exhibits a minor time disparity between alternating current (AC) and solar battery power, with a mere one-minute difference (4 minutes on AC, 3 minutes on solar power). This study heralds a promising innovation in pattern transfer technology, poised to revolutionize mass production while championing sustainability and operational adaptability.

Assessment of the potential for energy recovery in a sugar cane mill

Jorge Guevara Rodríguez — 2025-05-26

One of the problems identified in the sugar industry is the poor management of science and innovation. This paper aims to identify potential energy and water savings and opportunities to improve thermal efficiency in a sugar cane mill using energy analysis and heat integration methods. Methods of energy analysis and pinch analysis are applied using Aspen Energy Analyzer. The establishment of 10 energy performance indicators, which are not currently reported for this industry, will help to define an energy baseline and systematically measure efficiency in the industry. The current hot and cold supply requirements are not met for a minimum allowable temperature difference of 10°C. The design of the heat exchanger network allows 52.23% of the maximum recoverable energy to be recovered. There is a high excess of the current hot supply duty over the minimum hot duty, behaviour associated with the data extraction system. This study will allow us to continue the research with new heat exchangers and full inter-plant integration.

Operational factors influencing quality control in ore milling: a systematic review

Eliana de Jesus Lopes — 2025-05-22

Quality control in ball mill operations in the ore industry is crucial for ensuring the final product's quality and the equipment's efficient operation. Despite its relevance, there is a scarcity of studies on this topic. This bibliographic study, based on the PRISMA protocol, involved scientometric and qualitative bibliographic analysis. The analysis revealed that the topic is rarely addressed in the literature, resulting in a limited portfolio. The identified studies explore advanced techniques such as algorithms and mathematical modeling to optimize the grinding process and improve product quality. Research also discusses advanced control systems to ensure compliance in mill operations, leading to reduced variability in material granulometry, energy savings, and increased production. Furthermore, contributions include implementing virtual sensors to monitor cement fineness in real-time, optimizing operations, and enhancing the final product's quality. However, there is a notable lack of research focused on the particle separator, a crucial component in the grinding process. These findings provide valuable insights for the effective management and operation of ball mills in the mining industry and underscore the need for future research to address these gaps.

Improving inverter efficiency for electric vehicles: Experimental validation of the neural network-based SHE technique using RT-LAB

Seyf Eddine Bechekir — 2025-05-22

Inverters are essential for converting direct current to alternating current in electric vehicles, relying on pulse width modulation (PWM) for efficiency. This study presents a real-time Selective Harmonic Elimination PWM (SHE-PWM) algorithm using artificial neural networks, validated with the OP5600 RT LAB simulator. Unlike the traditional Newton-Raphson method, this approach employs a neural network trained on a database of pre-calculated switching angles, allowing for the precise elimination of specific harmonics while maintaining control of the signal’s fundamental component. Although it offers similar accuracy to Newton-Raphson, the neural method provides significantly faster processing. MATLAB/Simulink simulations and experimental results on the RT-LAB simulator confirm the algorithm’s capability to calculate optimal switching angles and produce high-performance PWM waveforms. The study highlights the neural network-based SHE technique's advantages, including its ability to model complex systems, robustness to noisy data, and versatility. This approach improves inverter performance and offers new optimization possibilities for various applications, including electric vehicles. The simulator results validate the alignment of real and simulated control signals.

Integrating VGG Re-trained Feature Extraction with Machine Learning for Knee Osteoarthritis Severity Levels Detection Using X-ray Images

Simeon Yuda Prasetyo — 2025-05-22

Knee osteoarthritis, a degenerative joint disease affecting weight-bearing joints such as the knees and hips, poses substantial diagnostic hurdles due to its complicated pathophysiology and development. Traditional diagnostic methods rely heavily on clinical examinations and imaging techniques like X-rays, which can be subjective and vary with clinician experience. To overcome these problems, new advances in machine learning (ML) and deep learning (DL) offer promising alternatives for improving the accuracy of knee osteoarthritis identification. This study proposes a novel methodology that combines retrained VGG models with various machine learning techniques. The Knee Osteoarthritis Dataset with Severity Grading is preprocessed, and features are extracted using fine-tuned VGG16 and VGG19 models. A number of machine learning models, including Naive Bayes, K-Nearest Neighbors, Decision Tree, Random Forest, Bagging, and AdaBoost, are then trained using these extracted characteristics. These models' performance is assessed using metrics including F1-score, recall, accuracy, and precision. The results reveal that the combination of VGG19 with fine-tuning and Random Forest achieves the best performance, with an impressive accuracy of 62.68%. This approach significantly improves diagnostic accuracy and holds potential for enhancing clinical decision-making and management of knee osteoarthritis, offering a robust tool for early detection and personalized treatment strategies.

Machine Learning Techniques for Identifying Textual Propaganda on Social Media: Development of a Detecting Digital Manipulation System

Belkacem Mostefai — 2025-05-27

The dissemination of propaganda on social media presents a significant challenge in today’s digital age. Utilizing advanced tools and diverse methods, propaganda aims to influence public opinion on a massive scale. Social media platforms serve as prime channels for such messages, leveraging sophisticated strategies to shape public perceptions and attitudes. This research aims to develop an advanced system capable of evaluating whether the content disseminated on these platforms qualifies as propaganda. The hypothesis suggests that it is possible to distinguish propaganda from non-propaganda texts on social media by analyzing specific linguistic features. Employing advanced linguistic analysis and machine learning methods, this detection system achieves approximately 70% accuracy, indicating its promising potential for effectively identifying propaganda. This approach could significantly enhance the transparency and reliability of online information, encouraging a more informed and critical use of social media.

Keywords: Propaganda Detection, Social media, Machine Learning Techniques, Linguistic Analysis, Digital manipulation,

Practical Implementation of a Smart Home Model Using Arduino and Sensors

Soufiane Hachani — 2025-05-22

This paper focuses on the design and implementation of a physical model of a smart home with automated control systems to enhance resource management, energy efficiency, and user comfort. The model, built using wood and cardboard as primary materials, integrates multiple sensors connected to an Arduino microcontroller for autonomous operation. The smart home functions include:

Regulating fan speed based on ambient temperature using a temperature sensor.

Managing the water tank via a water level sensor to ensure optimal filling.

Controlling outdoor lighting based on ambient light intensity detected by a light sensor.

Activating a security alarm by touch detection using a touch sensor.

Dynamic solar panel orientation based on time to maximize solar energy capture.

This work demonstrates a practical and feasible approach to exploring smart home technologies, with a focus on integrating automation and renewable energy into real-world scenarios. The proposed system serves as a scalable and sustainable model for future applications, bridging the gap between theoretical research and practical application.

Design and development of novel cooling arrangement for PV cell

Keval Chandrakant Nikam — 2025-05-26

The demand for sustainable energy has highlighted the importance of photovoltaic (PV) Cells in power generation. However, polycrystalline PV cell efficiency is hindered by temperature sensitivity. This leads to design a novel cooling system using cooling medium. The cooling system with and without baffles are preferred for experimentation. The ethylene glycol is in demand due to its availability and miscible nature in water at all concentration. The concentration of ethylene glycol is varied from 5%, 10%, 15% and 20% to study the evaporation rate of water. The requirement of water for cooling PV is also studied with and without adding ethylene glycol. With the help of ethylene glycol, the efficiency enhancement without compromising rate of evaporation is achieved. The outcome of the present paper indicates that efficiency of polycrystalline PV Cell is increased by 1.725% using novel cooling system with 20% of ethylene glycol concentration.

Numerical analysis of hygrothermal effects on low-velocity impact contact force in S-glass/polyester composite plates

Rabouh Mustapha — 2025-05-26

This study investigates the influence of hygrothermal environments on the contact force of S-glass fiber-reinforced polyester composite plates subjected to low-velocity impact. Finite element modeling and Design of Experiments (DOE) approach were used for analysis. The study validates numerical results against experimental data for both aged and non-aged samples, addressing durability and impact response in adverse environments.

Delineation of groundwater potential zones using integrated vertical electrical sounding and geospatial techniques in the basement complex of Ijesha Isu Ekiti, Southwestern Nigeria

Taofeek O. Ewumi — 2025-05-26

A combination of multi-criteria evaluation parameters has been deployed to delineate groundwater potential zones using integrated Vertical Electrical Sounding and geospatial techniques in the basement complex of Ijesha Isu Ekiti, Southwestern Nigeria. The area is underlain by migmatite-gneiss, amphibolities, biotite gneiss and the granitic components of the basement complex terrain with suspect groundwater prospects. Wenner vertical electrical soundings (VES) were conducted at 22 stations. The VES interpretation delineated the topsoil, weathered basement / partly weathered/fractured basement and the fresh basement bedrock with resistivity values ranging from 19 - 304, 16 - 417 and 8 - 2784 Ω-m, respectively. Integration of the attributes of the bedrock resistivity, weathered basement resistivity and the overburden thickness in a GIS environment enabled the classification of the study area into very low, low, medium and high groundwater potential zones covering areal extent of 0.004 km², 0.18 km², 1.85 km², and 1.32 km², respectively. A weighted combination of attributes would enhance the hitherto low success rate of groundwater targeting in a typical hard rock terrain.

Analysis of Lora Signal Propagation in Urban Environment

David Alan de Oliveira Ferreira — 2025-05-26

This paper analyzes LoRa signal propagation in an urban environment, based on RSSI collections conducted at various distances ranging from 10 to 1610 meters. The data were analyzed using the log-normal shadowing model, allowing the generation of path loss graphs. The coefficient of determination (R²) for the log-normal model was 0.9764, with an RMSE of 3.2872 and an MAE of 2.4020, indicating an excellent fit to the data. As a comparison between regression methods, the quadratic approximation presented an R² of 0.9117, RMSE of 6.1397, and MAE of 5.2137, reflecting lower performance. These results highlight the impact of distance on signal attenuation and confirm the effectiveness of the log-normal shadowing model in representing propagation in urban scenarios. The research contributes to understanding LoRa performance in dense environments, providing valuable insights for the planning and optimization of LoRa networks, as well as serving as a practical guide for future applications in the Internet of Things context.

Health classification of pumps using transformer-based deep learning

Arunachalam Shivaa T V — 2025-05-26

This paper develops a health classification system for pumps to enhance operational efficiency and reduce unplanned downtime, crucial for manufacturing and water treatment industries. Leveraging real-time data from temperature sensors and industrial accelerometer, the system captures vital pump health indicators. Data is collected via Data Acquisition (DAQ) modules and by using Deep Learning (DL) techniques such as Long Short-Term Memory (LSTM) networks and Transformers; the pump health classification is achieved. These DL models excel at understanding complex temporal and spatial patterns in sensor data, essential for accurate fault detection. Through a comparative analysis of LSTM and Transformer models, their efficacy in pump health classification is assessed. This approach emphasizes the importance of sophisticated data analysis and deep learning in industrial maintenance practices. By providing fault detection, the system aims to significantly reduce maintenance costs, optimize resource usage, and enhance the safety and reliability of industrial operations.

Energy impact of lighting system replacement in a public education institution

Fernando Alberto Benger — 2025-05-26

Lighting loads represent a significant percentage of global energy consumption, becoming an important issue to analyze in order to contribute to a more efficient use of electrical energy. This work presents an analysis of the lighting energy demand in the buildings of the College of Engineering - UNCPBA along with a proposal for improvement using LED technology. A survey of each of the buildings and spaces has been carried out to identify the current lighting conditions of the different College work areas and the associated energy consumption. The analysis includes the impact in terms of energy and lighting quality, replacement costs and return on investment. The calculation of greenhouse gases (GHG) and their environmental impact is also presented. The results of the study indicate that the transition to LED lighting would result in approximately 60% savings in electrical energy consumption at the College. The study draws conclusions regarding the efficiency of the lighting process and the reduction of environmental impact.

Analytical and numerical modeling of the transient behavior of an earth connection during the injection of an electromagnetic wave

Mohammed Chebout — 2025-05-26

This paper is devoted to the study and modeling of the behavior of a grounding system. The latter is used for the protection of electrical installations and equipment against surges and various disturbances affecting these systems. The methods used for modeling are multiple for this, an analysis and a synthesis of these methods has been made. In this work, the Agrawal model was used, which is based on the line theory. The finite integration technique was used under the CST Software for the purpose of verifying the first results. At the end, the different factors that influence the response of grounding systems were studied to evaluate the impulse performance. First, we start by determining the current distribution along the excited electrode in order to characterize the grounding radiation over time. The last part of this work is based on a parametric study that takes into account the electrode burial depth as well as the resistivity jump between the electrode and the surface. The results obtained by our analytical model are compared and validated by the CST/EMC software. Good agreements are found between these approaches.

AI-Driven Fire Detection and Suppression System with Real-Time Remote Monitoring

Metahri Dhiyaeddine — 2025-05-26

Fire detection and suppression are essential for the safety of monitored environments. Our project aims to develop an intelligent solution using artificial intelligence AI to optimize these processes. We integrate algorithms to process signals from gas and flame sensors via Arduino and use AI to analyze camera signals to improve accuracy. When a fire detected, a signal sent to an automatic extinguisher for immediate intervention. Additionally, we have designed a remote monitoring platform in Python, enabling real-time system management from a control center. This platform offers proactive management and instant visibility into the status of monitored environments, thereby enhancing overall security. A thorough analysis confirms that our Fire detection System FDS is robust and effective for fire detection and management, ensuring rapid and precise responses, and thus contributing to the safety and peace of mind of users. This system is particularly suited for deployment in high-risk and high-occupancy buildings such as hotels, shopping markets, office complexes, industrial facilities, and residential apartments, ensuring enhanced safety and peace of mind for users

The Using Bayesian Networks and Fuzzy Logic to Predict Warehouse Planning Disruption Risks

Kerouich Abdelilah — 2025-05-26

Le rôle principal des gestionnaires d’entrepôt est d’établir un calendrier adapté aux différentes circonstances. L’arrivée tardive des véhicules, le manque de moyens de manutention et la pénurie de fournitures d’emballage sont autant d’éléments qui affectent cet horaire. C’est pourquoi l’une des exigences de la gestion de la qualité dans les opérations d’entreposage est d’anticiper les différentes situations probables. Cet article se concentre sur l’analyse des risques qui peuvent être associés à la manutention de marchandises dans un entrepôt, de la réception à la livraison. Chaque risque a deux effets négatifs : le premier est l’ajout de coûts supplémentaires et le second est la perte de confiance des clients. Dans cette optique, la recherche présentée dans cet article se concentre sur la création d’un modèle prédictif permettant d’anticiper ces risques, en utilisant une approche qui estime le degré de perturbation du calendrier préétabli, sur la base d’une analyse prédictive combinant réseaux bayésiens (BN) et logique floue. Le modèle a été validé et les paramètres influençant le risque étudié ont été identifiés en analysant la littérature spécialisée et en examinant des scénarios issus d’une enquête auprès des professionnels du secteur de l’entreposage. Les résultats aident les planificateurs à minimiser l’impact des perturbations, réduisant ainsi le temps nécessaire au traitement des marchandises dans l’entrepôt.

PatchDetect: Breast Cancer Detection combining Unet-ResNet-50 and Patch Embedding LSTM

Hadj Ahmed Bouarara — 2025-05-26

This study presents a novel framework for breast cancer detection, combining patch embedding, feature extraction using a pre-trained Convolutional Neural Network (CNN) model (ResNet50), Long Short-Term Memory (LSTM) networks for image sequence analysis, and Fully Connected Layers for final classification. The model's performance was optimized using various hyperparameters, achieving an accuracy of 94%, recall of 93%, precision of 92%, and F-measure of 92% while maintaining a minimal error rate of 6%. The findings emphasize the importance of integrating pre-trained CNNs with sequential analysis via LSTMs for feature-rich and temporal data like mammographic patches. The study also highlights the impact of parameter tuning on classification performance, paving the way for more accurate, automated, and non-invasive breast cancer diagnostic tools.

Sustainable solutions for urban infrastructure: The environmental and economic benefits of using recycled construction and demolition waste in permeable pavements

Eliomar Gotardi Pessoa — 2025-05-26

This study explores the economic and environmental implications of using recycled construction and demolition waste (CDW) in permeable pavements, presenting it as a viable solution for promoting sustainable urban development. As urbanization intensifies, both the volume of CDW and the demand for resilient, flood-mitigating infrastructure are rising. Permeable pavements made from recycled concrete, ceramic bricks, reclaimed asphalt, and industrial waste offer a dual benefit—minimizing environmental degradation and enhancing pavement performance. The findings from various studies indicate that these materials, when properly processed and chemically stabilized, can replace virgin aggregates in pavement base and subbase layers without compromising structural integrity. The paper highlights improvements in mechanical properties, stormwater infiltration, and pollutant removal when using permeable systems, even when recycled materials are incorporated. In particular, innovations such as the use of geopolymer concrete and secondary aluminum dross (SAD) fillers have shown to enhance compressive strength and moisture resistance in asphalt mixes containing RCA. Moreover, life cycle assessment (LCA) methods validate the environmental gains of these practices, from reduced carbon emissions to lower resource extraction rates. Despite these advantages, technical challenges such as pore clogging, leaching risks, and material variability persist. Addressing these through standardization, further field trials, and continued innovation will be key to expanding the adoption of CDW in permeable pavements. Ultimately, the integration of recycled materials into urban infrastructure emerges as a promising strategy to reduce construction waste, conserve natural resources, and build cities that are both sustainable and resilient.

Analysis of the performance of helical piles under various load and geometry conditions

Eliomar Gotardi Pessoa — 2025-05-26

The study by [7] analyzed the load capacity of moderately sized helical piles, considering configurations such as shaft diameter, plate diameter, and penetration depth. The results showed that increasing the shaft diameter and modifying the helical plates significantly improved load capacity. The configuration of the plates had a greater impact on performance than the shaft diameter. Other studies complemented these findings, such as [8], which emphasized the importance of plate position for pull-out resistance. Study [9] highlighted the impact of helix pitch on lateral load capacity, while [10] examined the spacing between the helices and its effect on load distribution. Helix deflection, as shown by [11], was also a critical factor in pile performance. Additionally, studies on pile groups [13] and pressure grouted helical piles [14] provided valuable insights for optimizing the design of these foundations. Research by [15] on combined loads revealed a positive correlation between helix diameter and load capacity. Overall, the studies demonstrated that geometric factors and soil characteristics are essential for optimizing the performance of helical piles, especially in applications in challenging environments like offshore wind platforms.