International Journal of Engineering and Manufacturing @ijem
Journal articles - International Journal of Engineering and Manufacturing
All articles: 649
Scientific article
The organic compound used as corrosion inhibitor was benzaldehyde. The use of organic compounds as corrosion inhibitors is of potential interest due to their abundant availability, cost effectiveness, and environmental acceptability. However, this study investigates the inhibition effect of this organic compound (benzaldehyde) on the corrosion of aluminium in phosphoric acid solution. Experiments were performed by varying the temperature and concentration of the compound under study. The results obtained from the study shows that the organic compound (benzaldehyde) is a potential inhibitor for the corrosion of aluminium in phosphoric acid solution. The inhibition efficiency was found to increases progressively as the concentration of the inhibitor increases but decreases when the temperature rises. Activation energy values for the corrosion process was found to be 32.61 kJ/mol in uninhibited phosphoric acid solution which increased to 49.53 kJ/mol in the presence 0.1 M concentration of the inhibitor. The values of the rate constant and half live were 9.12 × 10-3 hr-1 and 75.94 hr in uninhibited phosphoric acid solution which changed to 4.56× 10-3 and 151.80 hr in the presence of 0.1 M inhibitor concentration. Kinetics of the reaction in uninhibited and in the presence of the inhibitor revealed that the process follows a first order reaction. The evaluated enthalpy (ΔH) gave positive values which indicate that the heat of adsorption process on the surface of aluminum was endothermic. The negative values of entropy (ΔS) signified that the activated complex at the rate determining step is an association, not dissociation. Evaluated values of free energy of adsorption (ΔGads) were all negative, implying spontaneity of the process and were around and less than -20 kJ/mol, indicative of physisorption of the adsorption process.
Free
Investigation on Extended Number Field
Scientific article
This paper expands the field of complex number to general plural. Discussion on the forth power generalplural is emphasized, then creates the four fundamental operations of arithmetic and calculus which can be applied to the project.
Free
IoT Based Smart Shower to Minimize Home Water Usage
Scientific article
Water waste, particularly in home shower systems, remains a significant global concern, with showers accounting for substantial water consumption. This research proposes an IoT-based solution to mitigate water wastage using smart technology. According to surveys, the average shower duration is approximately 8 minutes, with a flow rate averaging 8 Liters per minute, resulting in significant water use per shower. Our approach integrates IoT technology, utilizing Arduino as a gateway device for data management. Water usage data is collected and stored in a cloud-based platform, Thing Speak, enabling users to monitor consumption patterns daily, monthly, and annually. The system employs hardware components including a solenoid valve, Arduino microcontroller, ESP 8266 WiFi module, LCD display, and sound player, complemented by software components like the Arduino IDE and ThinkSpeak database. Operationally, upon activation, the system controls water flow for the initial four minutes before alerting users to conserve water through visual and auditory cues. This study’s methodology involves the design and implementation of an IoT-enabled smart shower system, demonstrating its efficacy in reducing water consumption through real-time monitoring and user feedback. Results indicate a significant reduction in water usage compared to conventional shower systems, thereby highlighting the potential of IoT technology in promoting sustainable water management practices at the household level.
Free
IoT leak detection system for building hydronic pipes
Scientific article
Building’s Air Conditioning systems require moving liquids for dweller comfort. Clogged pipes, system degradation can cause pressure buildups, leaks and other faults which leads to damage to the building. Most of the leaks in the commercial building occur due to poor maintenance and/or material degradation. Visual inspection is most predominantly used to solve this problem in the industry. This paper introduces the Internet of Things technology to detect leakage in building’s hydronic pipes with the support of sensors, fault detection method and mechanical control. The system consists of: Microcontroller, Windows application and website application. Internet of Things technology was used to monitor and control the hydronics using microcontroller’s capability of connecting to main server which is used to transmit the data to the cloud. The prototype was successfully built and tested. Promising results show that leaks above 2ml/s could be detected after 4 seconds specifically for the built small-scale system while control and monitor feature could be implemented with Internet of Things technology.
Free
Scientific article
Electroencephalogram (EEG)-based seizure detection is a challenging time-series classification problem because EEG signals are nonlinear, non-stationary, and temporally heterogeneous. This study presents a unified comparison of classical machine-learning, neural and deep-learning, convolutional-kernel time-series, and probability-level ensemble models using the Epileptic Seizure Recognition benchmark dataset. The 11,500 EEG segments were reconstructed into 500 recording groups, and recording-grouped nested cross-validation was applied to prevent segments from the same recording from crossing training and test partitions. Depending on the modelling paradigm, segments were represented either by 67 handcrafted time-, frequency-, and nonlinear-domain features or by ordered 178-sample EEG sequences. Recording-level average precision was used as the primary evaluation metric, supported by ROC-AUC, threshold-dependent measures, Brier score, bootstrap confidence intervals, ablation analysis, explainability, and computational-efficiency benchmarking. RBF-SVM achieved the highest average precision of 0.997985 and ROC-AUC of 0.999475. MultiRocket produced the lowest family-representative Brier score of 0.006148, while MLP achieved the lowest standalone inference latency after feature extraction. The selected meta-ensemble produced strong threshold-dependent performance but did not improve overall precision–recall ranking. Paired bootstrap analysis found no statistically significant differences among the family representatives after multiple-comparison correction. These findings demonstrate that handcrafted-feature and time-series models can both achieve strong recording-level performance when evaluated under a consistent, leakage-controlled protocol. Because verified patient identifiers were unavailable, the results should not be interpreted as evidence of patient-independent clinical generalization.
Free
Light-Fidelity (Li-Fi) Based Patient Monitoring System
Scientific article
The healthcare landscape is rapidly evolving with the integration of advanced technologies to enhance patient care, monitoring, and overall medical practices. In this era of innovation, Light-Fidelity (Li-Fi) has emerged as a promising solution with the potential to revolutionize patient monitoring systems. This research aims to address current limitations in Li-Fi-based patient monitoring systems, such as data security concerns and the inability to provide continuous monitoring without on-site medical personnel. It is driven by the urgent need to tackle critical healthcare challenges arising from a significant shortage of medical personnel, particularly in certain regions and countries. The objective is to develop a Li-Fi-based patient monitoring system that can remotely and continuously monitor patient vital signs and medical data. The methodology involves a comprehensive approach that integrates advanced technology, data collection, data processing, and web application development. Results indicate that the developed system prioritizes performance and security, with evaluations based on latency, security vulnerabilities, and data throughput. This research advances Li-Fi's potential in healthcare, paving the way for innovative applications that can enhance patient care, improve healthcare outcomes, and potentially transform the entire healthcare industry.
Free
Scientific article
This paper presents a comprehensive study encompassing both liquefaction susceptibility evaluation and slope stability analysis of embankment soil adjacent to road. The paper focuses on the vulnerability of embankment soil to liquefaction-related failures. It examines the liquefaction vulnerability of embankments ML-CL soil, previously considered non-liquefiable but raising concerns post-1999 Kocaeli Earthquake. The paper evaluates liquefaction susceptibility using Chinese Criteria and Modified Chinese Criteria based on index test results of embankments soil samples. The soil at various depths was found to be not susceptible to liquefaction as per Chinese criteria, whereas the second evaluation as per Modified Chinese criteria gave different and more specific results taking into the % clay-sized particles. Based on Modified Chinese criteria, the soils ranging from 10-20 ft, 25-30 ft and 30-35 ft were found explicitly non-susceptible, whereas soil ranging from 0-10 ft and 20-25 ft requires further study on non-plastic clay-sized grains as per the criteria. The paper delves into slope stability analysis using PLAXIS2D and GEOSLOPE software to determine the optimal earthworks layout for a embankment excavation based on Eurocode 7. Upon numerical modelling, various trials were carried out considering various factors of safety across different earthworks layouts and the one with satisfying factor of safety is considered safest, ensuring safety and cost-effectiveness of embankment cut besides the road.
Free
Scientific article
The depletion of fossil fuel is driving the world towards the application of renewable energy sources. However, their intermittent nature, in addition to load variation and transmission line sag-tension change due to temperature, is a great deal of problems for reliable power delivery. Without a reliable power delivery, power generation is just a waste of resources. A reliable power delivery can be achieved when the best and the worst case steady state information of a power system network is known to plan and control accordingly. If a system is affected by the presence of uncertainty, a deterministic load flow analysis fails to provide the worst-case load flow result in a single analysis. As a result, a load flow analysis considering the presence of uncertainty is mandatory. On this paper, a novel complex affine arithmetic (AA) based load flow analysis in the presence of generation and load uncertainties is proposed. The proposed approach is tested on an IEEE bus systems and compared with Monte Carlo approach. The proposed approach convergence faster than the Monte Carlo based method and it is slightly conservative.
Free
Load test of induction motors based on PWM technique using genetic algorithm
Scientific article
Genetic algorithms(GA) is optimization technique used in the equivalent load test of the induction motors to select the values of the factors(modulation indicators) that effect on the performance properties in terms of the values of the currents and the total loss within the machine. One way to choose these parameters is by trial and error while this paper based on GA method to improve the parameters selection. A model is designed to simulate the loading of the induction motor and obtain its own results by the MATLAB program 2017a. There are different methods used to achieve this task such as PWM inverter with different modulation techniques, Constant Voltage Variable Frequency (CVVF) method, Variable Voltage Constant Frequency (VVCF) method and Variable Voltage Variable Frequency (VVVF) method.
Free
Local Reweighted Kernel Regression
Scientific article
Estimating the irregular function with multiscale structure is a hard problem. The results achieved by the traditional kernel learning are often unsatisfactory, since underfitting and overfitting cannot be simultaneously avoided, and the performance relative to boundary is often unsatisfactory. In this paper, we investigate the data-based localized reweighted regression model under kernel trick and propose an iterative method to solve the kernel regression problem. The new framework of kernel learning approach includes two parts. First, an improved Nadaraya-Watson estimator based on blockwised approach is constructed; second, an iterative kernel learning method is introduced in a series decreased active set to choose kernels. Experiments on simulated and real data sets demonstrate that the proposed method can avoid underfitting and overfitting simultaneously and improve the performance relative to the boundary effect.
Free
Scientific article
Vehicular adhoc networks (VANETs) are relegated as a subgroup of Mobile adhoc networks (MANETs), with the incorporation of its principles. In VANET the moving nodes are vehicles which are self-administrated, not bounded and are free to move and organize themselves in the network. VANET possess the potential of improving safety on roads by broadcasting information associated with the road conditions. This results in generation of the redundant information been disseminated by vehicles. Thus bandwidth issue becomes a major concern. In this paper, Location based data aggregation technique is been proposed for aggregating congestion related data from the road areas through which vehicles travelled. It also takes into account scheduling mechanism at the road side units (RSUs) for treating individual vehicles arriving in its range on the basis of first-cum-first order. The basic idea behind this work is to effectually disseminate the aggregation information related to congestion to RSUs as well as to the vehicles in the network. The Simulation results show that the proposed technique performs well with the network load evaluation parameters.
Free
MA-Helformer: A Sentiment-Aware Adaptive Framework for Multi-Horizon Crypto Forecasting
Scientific article
The cryptocurrency market is highly non-linear, non-stationary and driven by sentiment volatility, which poses fundamental challenges for price prediction. The recently proposed Helformer model couples a Transformer-based architecture with Holt-Winters exponential smoothing and shows excellent performance for univariate forecasting. However, the model relies only on closing price data and does not incorporate external sentiment sources, and uses static decomposition parameters without taking into account market conditions. Finally, the Helformer model has only been evaluated on a single asset. To systematically address these limitations, this paper proposes the Multivariate Adaptive Helformer (MA-Helformer), an improved deep learning framework with three main contributions. First, the input feature space is enriched with a complete multivariate set of 13 technical indicators, six on-chain metrics, seven macroeconomic variables, and three sentiment scores from FinBERT. Second, an adaptive market regime detection module based on Hidden Markov Models (HMM) dynamically conditions Holt-Winters decomposition parameters on detected market state (Bull, Bear, Sideways). Third, a multi-horizon forecasting head is trained jointly to produce price forecasts for 1-day, 7-day, and 30-day horizons simultaneously. We experiment on Bitcoin (BTC), Ethereum (ETH) and Solana (SOL) using daily data from January 2017 to December 2024. MA-Helformer reduces next-day RMSE by 49.2% relative to the baseline Helformer, achieves a Sharpe Ratio of 2.34 in a realistic trading simulation that accounts for variable transaction costs and slippage, and shows particularly strong improvements in Bear market regimes. All reported performance gains are statistically significant ("p<0.01" ) according to the Diebold-Mariano test. Experimental results demonstrate that MA-Helformer consistently outperforms the baseline Helformer and several competitive forecasting models across multiple evaluation metrics and forecast horizons, while achieving statistically significant improvements under the adopted experimental protocol. Although the proposed framework demonstrates promising predictive performance, its evaluation is based on historical market data and simulated trading conditions; therefore, further validation using real-time deployment and additional financial assets remains future work.
Free
Machine Learning-based Renewable Energy Adaptation: Case study Bangladesh
Scientific article
For environmental sustainability and energy security, renewable sources must be incorporated into sustainable energy solutions. Machine learning (ML) techniques are explored in this study to optimize the adoption of renewable energy sources in Bangladesh. Specifically, it proposes a three-phase methodology: (1) forecasting demand for nonrenewable energy, (2) predicting renewable energy availability and costs, and (3) analyzing potential savings and environmental benefits. Utilizing decision trees and random forests, this study presents a comparative analysis of energy demand and cost predictions, contributing to a data-driven framework for energy transition. The results indicate that strategic adoption of renewable energy can mitigate Bangladesh’s electricity shortages while reducing dependency on fossil fuels. Machine learning plays a crucial role in energy optimization by accurately forecasting energy demand and availability, allowing for better resource allocation. It helps identify patterns and trends in energy consumption, enabling more efficient integration of renewable sources. By using techniques like decision trees and random forests, machine learning models can optimize energy production and distribution, ultimately leading to more sustainable and cost-effective energy systems.The findings provide policymakers and energy planners with insights to enhance sustainability efforts.
Free
Machine learning approaches for cancer detection
Scientific article
Accurate prediction of cancer can play a crucial role in its treatment. The procedure of cancer detection is incumbent upon the doctor, which at times can be subjected to human error and therefore leading to erroneous decisions. Using machine learning techniques for the same can prove to be beneficial. Many classification algorithms such as Support Vector Machines (SVM) and Artificial Neural Networks (ANN) are proven to produce good classification accuracies. The following study models data sets for breast, liver, ovarian and prostate cancer using the aforementioned algorithms and compares them. The study covers data from condition of organs, which is called standard data and from gene expression data as well. This research has shown that SVM classifier can obtain better performance for classification in comparison to the ANN classifier.
Free
Man-made Object Detection Based on Texture Visual Perception
Scientific article
Based on human visual attention mechanism and texture visual perception, this paper proposes a method for man-made object detection by extracting texture and geometry structure features. Followed by clustering the texture feature, geometry structure feature is obtained to realize final detection. Then a man-made object detection scheme is designed, by which typical man-made objects in complex natural background, including airplanes, tanks and vehicles can be detected. The experiments sustain that the proposed method is effective and rational.
Free
Manufacturer's Pricing Strategy for Supply Chain with Service Level-Dependent Demand
Scientific article
This article considers the pricing strategies of a manufacturer in a two-echelon supply chain with service level-dependent demand. This chain consists of one manufacturer and two retailers. The manufacturer decides the wholesale prices as a Stackelberg leader, and the retailers determine their service levels as the Stackelberg followers. We discuss the segmented and unified pricing strategies of the manufacturer. We also compute the optimal service levels and profits of the retailers, as well as the optimal wholesale prices and profits of the manufacturer associated with different pricing strategies. We conclude that the segmented pricing strategy benefits the manufacturer, whereas it cannot benefit the two retailers simultaneously. Furthermore, it is disadvantageous to the profit of the entire supply chain. Moreover, the increase in service cost coefficient adversely affects the earnings of the customers, the retailers, the manufacturer, and the entire supply chain. However, an increase in diffusion intensity benefits the customers, the manufacturer, and the supply chain.
Free
Scientific article
Sabkha is an Arabic word for a salt-flat area found mainly along arid area coastlines and inlands within sand dunes areas. The sabkha that form within the sand are relatively flat and very saline areas of sand or silt that forms just above the water-table where the sand is cemented together by evaporite salts from seasonal ponds. Such shallow water is normally highly saline. Here the crust is rich in gypsum and halite veins where the underline thin layer is made of sand and silt. Such sabkha have an average thickness of a meter or slightly less. On the other hand, marine sabkha represent transitional environments between the land and the sea. The UAE is home to some of the largest concentrations of sabkha both coastal and inland. The coastal areas of Abu Dhabi include several small shoals, islands, protected lagoons, channels and deltas, an inner zone of intertidal flats with algal mats and broad areas of supratidal sabkha salt flats. Identifying sabkha habitats from remotely sensed data is a challenging process. Traditional classification techniques of multispectral data alone, usually fail to properly identify sabkha pixels or provide lower rates of mapping accuracy for sabkha habitats. The primary objective of this research is to develop a much more accurate methodology for properly mapping and identifying sabkha areas from remotely sensed data. Properly mapping sabkha habitats from remotely sensed data is the first steps towards studying the ecological changes within such habitats using earth observation techniques. Furthermore, sabkha habitats can in certain situations be a geotechnical hazard due to its highly salinity and with adverse effects on concrete, asphalt, steel and other structures, in addition to their sporadic heaves and collapses. As the UAE continue to build major infrastructure and development projects identifying the location of such habitats is vitally important. In this research a new technique that combines the multispectral information of Landsat 8, principal component analysis and spectral soil salinity detection is developed. The study area is located in the western part of the UAE along the border with the Kingdom of Saudi Arabia, an area known to include large tracks of inland and coastal sabkha. Landsat 8 data from path 161 and row 43 was acquired for the study. A multi-source classification approach was followed that utilizes the multispectral data of Landsat 8 along with components from the principal components analysis and the spectral salinity index maps. The preliminary results confirmed by field observations show that the combined data improved the classification accuracy to almost 90% in comparison to multispectral data alone of 78%.
Free
Mask-Aware Localized Inpainting Method for CPU-Based Inference
Scientific article
Image generation methods, including inpainting, are evolving rapidly; however, high memory requirements continue to limit their practical deployment. As a result, the efficient utilization of Latent Diffusion Models on edge devices has become increasingly important. This work explores techniques for reducing memory usage in Latent Diffusion Models while preserving their generative capabilities. We propose a resource-efficient inpainting method optimized for CPU-based inference, based on a combination of VAE tiling, attention slicing, and dynamic region-of-interest slicing. Experimental results demonstrate that the model's memory footprint can be significantly reduced while maintaining output quality, without substantial increases in computation time, enabling execution on systems with as little as 4 GB of memory and only two processing cores. While the introduced optimizations, particularly those based on localized image processing, introduce an inherent trade-off between memory usage and computational cost, resulting in longer inference times compared to GPU-accelerated solutions, they demonstrate strong potential for deployment in memory-limited environments. Additionally, we provide analysis of key deployment bottlenecks, including model compilation for cold-start overhead mitigation, proper runtime configuration and scheduler selection. These findings confirm the feasibility of effectively deploying Latent Diffusion Models for inpainting tasks on CPU-only, resource-constrained platforms, thereby broadening their applicability to edge computing scenarios.
Free
Mathematical Model of Subpopulation Dynamics in Case of Different Niches for Subpopulations
Scientific article
The article presents a model of dynamic processes occurring in non-isolated populations that differ in their habitat and mode of nutrition. The results of theoretical studies carried out on the basis of this model show the decisive influence of the ratio of the coefficients of inter-subpopulation competition on qualitative changes in the behavior of the system and individual subpopulations. This ratio is also the main factor influencing the formation of the dominant subpopulation in the system. It has been shown that the system-wide dynamics of subpopulation processes significantly depends on the reproductive potential of all subpopulations and on the mass fraction of individuals that, according to their phenotypic properties, are related to the parents. In this case, the mass fractions of individuals (transition coefficients) must correspond to the condition of closed system and be in specified intervals. It has been established that subpopulations in real life can exchange descendants, which, in turn, can significantly affect the numerical and qualitative aspects of the dynamics. Using the example of a two-dimensional system, the relationship between the sum of the main elements of the transition coefficient matrix and the mutual dependence of subpopulations, as well as their transition to qualitatively different levels, is shown. The bifurcation properties of the model of subpopulation dynamics with a Lotka–Voltaire type function in basic quality have been studied. An approximate justification of possible bifurcations of the system allows us to evaluate the factors that qualitatively influence the dynamics of the system and develop a number of recommendations to prevent the occurrence of catastrophes and collapses in the system.
Free
Medical Image Synthesis Using Variational Autoencoder and Generative Adversarial Networks
Scientific article
Nowadays, image synthesis has become essential in the medical field for lever- aging deep learning technique to improve decision- making. Our proposed research work combines Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) to synthesize medical im- ages, enhancing diagnostics, medical training, and image analysis. The model presented combines a Discriminator, and a Variational Autoencoder to capitalize on the strengths of both VAEs and GANs. The Decoder is tasked with generating synthetic medical images, the Discriminator evaluates their distinguishing factor, and the VAE learns a probabilistic mapping from input to latent space, ensuring a structured representation of underlying medical features. The training process involves a decoder creating realistic medical images, a discriminator distinguishing real from synthetic ones, and a VAE capturing meaningful data variations in the latent space. Verified on the dataset sourced from the Kaggle. The model refines its parameters iteratively using a training loop, resulting in enhanced quality and variety of generated medical images. The proposed VAE- GAN model demonstrates its efficacy by generating diverse and realistic medical images. The structured latent space contributes to interpretability, making the images suitable for purposes like data augmentation, anomaly detection, and machine learning model training.
Free
