Journal of Applied Research and Technology

Enhanced approach for artificial neural network-based optical fiber channel modeling: Geometric constellation shaping WDM system as a case study

A. M. Abbass, R. S. Fyath — Wed, 11 Dec 2024 00:00:00 -0600

Recently, there has been increasing interest in applying machine learning (ML) approaches to enhance the performance of optical communication systems. This paper applies some of these approaches to design advanced wavelength-division multiplexed (WDM)-coherent optical fiber communication (OFC) systems assisted by the constellation shaping technique. A theoretical design and performance investigation are reported assuming end-to-end deep learning (E2EDL) autoencoder (AE)-assisted system configuration. A flexible artificial neural network (ANNs)-based optical fiber channel modeling approach suitable for different multi-span transmission links in OFCs is presented. This approach is applied to E2EDL-based geometric constellation shaping WDM systems and the results reveal that using a bi-directional gated recurrent unit (Bi-GRU)-neural network (NN) gives the best modeling that tracks the numerical nonlinear interference noise fiber model with much less computation time(~7%). This work is implemented using the Python programming language and utilizing the TensorFlow framework to develop the simulation models.

Comparative analysis of machine learning models to predict rectangular patch antenna dimensions

R. Degachi, S. Ghendir — Wed, 11 Dec 2024 00:00:00 -0600

The non-linear relationship between antenna characteristics and their electromagnetic responses made the design and optimization process difficult, in the face of these difficulties, antenna engineers used several techniques, including machine learning, as it has great capabilities that make it a very useful tool that can help researchers in this field. In this paper, four machine learning algorithms: ANN, Random Forest, Decision Tree and SVR are used to predict the dimensions of a rectangular patch antenna, through the utilization of a dataset comprising 3111 simulated samples collected using HFSS Simulation software. The results showed that random forest with 100 estimators exhibited an outstanding performance concerning prediction accuracy, with a mean square error (MSE) of 0.52.

Proposed theoretical approaches for cellular base station radiation level estimation in urban environments

S. K. AL-jaff, Rusul Musadaq, A. M. Khodayer, A. H. Sallomi — Wed, 11 Dec 2024 00:00:00 -0600

Increasing demand for cellular communication service forced service providers to improve their quality of service by increasing the number of base stations inside or in the proximity of populated areas. Consequently, the level of electromagnetic pollution is increased resulting in great concern about the probable health risk due to exposure to the base station radiations.

In order to estimate the possible health impact due to population exposure to cellular base station radiations, this paper presents two mathematical approaches suggested to evaluate the base station radiation level in terms of power density induced at the exposed objects. The first approach depends on the superposition theorem that considers radiations from all base stations surrounding the exposed object. The second approach uses a fluid model to study and estimate the power density received by the objects exposed to the cellular base station radiations in urban areas. Once the induced power density in the exposed human body is obtained, it is possible to evaluate the health effects, and the safety exposure limits can be set.

Ball mill energy efficiency optimization: A lifter face angle optimization approach

L. Maregedze, K. Chiteka, R. Masike, T. Kanyowa — Wed, 11 Dec 2024 00:00:00 -0600

On average, approximately 40% of the total energy consumed by grinding comminution industries is attributed to industrial ball mills, underscoring the urgent necessity to address this energy consumption challenge. This study investigates the influence of lifter face angle variations on the performance of ball mills in comminution processes. Through a combination of Discrete Element Method (DEM) simulations and experimental design, the study explores the effects of lifter face angle on energy efficiency, wear rates, and comminution effectiveness. Findings reveal that smaller lifter face angles result in increased scattering of ore particles within the mill, while larger angles lead to reduced wear and improved grindability of materials. The optimal lifter face angle is identified as approximately 24.8°, falling within the typical range used by industrial ball mill accessories manufacturers. An overall energy saving of 5.89% is achieved by using the optimum ball mill lifter face angle of 24.8°. Recommendations for future research include further exploration of optimal parameters, experimental validation of findings, and the development of advanced modelling techniques. By implementing these recommendations, the study aims to contribute to enhanced efficiency, durability, and sustainability in ball mill operations.

Obstacle arrangements effect on the mixed convection in an enclosure with movable top surface

A. M. Shaker, N. J. Yasin, H. A. Ameen, A. S. Abedalh — Wed, 11 Dec 2024 00:00:00 -0600

The flow finds extensive application in coating, drying, and mixing processes. The temperature and velocity distribution inside a rectangular enclosure that is driven by a lid were examined using a finite volume numerical method. Five adiabatic cylindrical obstacles were mounted within the cage measures 25 cm in width and 30 cm in length. The right and left walls enclosure is each fully insulated, the top wall was cooled isothermally at T_c and moved at variable speed of U, and the bottom wall was kept at T_h using water as a working fluid. Three types of an obstacle with equal area were utilized in this study they were, circle triangle and square. The results showed that the average Nusselt number increases by 10.4%,12%, 16%, and 19% compared with that of without the obstacle for radius values (r=0.5,1,1.5 and 2 cm) respectively. The results indicate that obstacles can be very useful in achieving a higher rate of heat transfer compared to the enclosure without obstacles. Also, as opposed to a situation without barriers, the results demonstrate that the existence of obstructions causes an increase in the average Nusselt number. When compared to triangular and square shapes, the obstacle with a circular shape has a larger average Nusselt number. Furthermore, the enhancement percentage of Nusselt number was calculated to be 16, 13, 11 % for obstacle models of circle have a radius of 1 cm, triangle and square of 1 cm (major dimension) respectively comparing with that of no obstacles.

Development and implementation of a microstrip antenna for autonomous vehicles and IoT in 5G communication systems

N. Q. Ali, A. J. Mohammed, H. T. S. ALRikabi, A. K. Aliwy, H. F. Khazaal — Wed, 11 Dec 2024 00:00:00 -0600

This research paper shows the design and implementation of a 5.8 GHz microstrip patch antenna (MPA). Experimental investigations have concluded that employing a 0.8 mm high Rogers Rt-duroid substrate along with an inset feeding technique produces optimal outcomes to fulfill the demands of 5G applications. The designed antenna demonstrates 8.09 dBi directivity, a 7.38 dB gain, and -20 dB return loss at its resonant frequency. To further verify the performance of antenna, it was fabricated and evaluated using the CST Microwave Studio program, a 3D simulation tool specifically designed for antenna design and parameter calculation

Influence of flow field and gas diffusion layer on polymer electrolyte membrane fuel cell performance

I. P. Sahu, M. K. Das, M. K. Soni, N. Agrawal, R. L. Himte, T. Ananat — Wed, 11 Dec 2024 00:00:00 -0600

In the present study, the flow field in the bi-polar plate and Gas diffusion layer (GDL) of 1.2 kW Nexa fuel cell (FC) training system having a serpentine flow field has been examined. The channel dimension and shape in the flow field of the bipolar/end plates have been examined. Pressure drop with hydrogen flow rate and channel length. For enormous hydrogen inputs, The optimal measurement is around 1.5, 1.5,, and 0.5 mm for the values of channel width, channel depth, and width of land, corresponding Research on the effect of channel designs revealed that semi-circular, rectangle and triangular-shaped and found The land width for triangular and semicircular-shaped are almost zero millimeters which increase the water vapor accumulation, due to which the losses increase. However there are very few losses in the polarization curve seen in the square cross-section because there is very l water vapor buildup. A GDL is an essential component of an FC. The three-dimensional model of the GDL is simulated using COMSOL metaphysics 4.2 and observed that increased porosity facilitated the entry of more reactants into the reaction side, resulting in increased current density. Low membrane thickness resulted from excessive current density in the membrane. Thicker GDL provides reactant species that raise the rate of consumption at the point where the catalytic layer and GDL interface. The outcomes of the simulation are contrasted with experimental data found in published works. The comparison demonstrates that the modeling outcomes and the experimental data agree quite well.

Diagnose eyes diseases using deep learning algorithms

Z. N. Abed, A. M. Al-Bakry — Wed, 11 Dec 2024 00:00:00 -0600

Early diagnosis of eye illnesses is the only way to avoid blindness and to guarantee prompt treatment. A crucial part of early eye disease screening is using fundus images. However, as deep learning (DL) offers a precise classification for medical images, using these methods for fundus images makes sense. Recently, DL architectures were applied extensively to image recognition applications. In the presented study, we use DL models, like Convolutional Neural Networks (CNNs), to identify eye diseases in humans. Due to the development of DL methods, investigations on the detection of eye diseases have produced some fascinating results; nevertheless, most of them are restricted to a particular disease. Ocular Disease Intelligent Recognition dataset is used to assess the suggested approach. This has five thousand images representing eight distinct fundus classes. Those classes correspond to various eye diseases. This work will provide an illustration of the five-step recommended system for diagnosing eye problems. The first step of the model is to collect data sets. The second step is to divide the data sets into 70% for training and 30% for testing. The third step is pre-processing to enhance prediction (converting color images into gray-scale, Histogram Equalization, BLUR and resizing process). The fourth step is to use a variety of the feature extraction algorithms (SIFT and GLCM algorithms) are performed to remove redundant information and extract features from the original data, where features are extracted before they are fed into the classifier for the purpose of accelerating the classification process. In the fourth phase, this study created a CNN-based diagnostic system. Next, it features a model for the prediction of presence or absence of diseases in the patient. The findings demonstrated that the classifiers reached highest accuracy of 99.9%. In addition, we see that our best-performing model outperforms several state-of-art techniques in producing competitive outcomes.

Intrusion detection system with an ensemble DAE and BiLSTM in the fog layer of IoT networks

G. F. Edakulathur, S. Sheeja, A. John, J. Joseph — Wed, 11 Dec 2024 00:00:00 -0600

The world is rapidly arriving at the period of the IoT, which connects all types of technology to digital services and provides us with great ease. As the quantity of IoT-connected equipment increases rapidly, there may be a rise in network vulnerabilities, leading to an increase in network threats. Fog computing seems to be a distinctive paradigm that includes the cloud's network's edge, including practical computation and vital infrastructure. As a result of easy access to resources, the fog layer renders the system susceptible to several threats. Tackling these challenges entails detecting intrusions and tracing the route leading to the source of the threat. The objective of this study is to offer a security mechanism and demonstrate how an intrusion detection system can guarantee the integrity of IoT networks. Based on deep learning (DL) approaches, several promising intrusion detection systems (IDSs) have been presented, however, they need time-consuming parameter adjustment in various situations. To address this issue, this study suggests a hybrid Deep Auto Encoder (DAE) and BiLSTM for item installation in the fog due to the need to safeguard essential infrastructure against prompt and efficient identification of malicious threats. Further sparrow search optimization algorithm is proposed for parameter tuning. Utilizing IoT-based data, we assess the effectiveness of our suggested model. The outcome of the experiment obtained by analyzing the suggested IDS utilizing CICIDS2017 and Bot-Iot datasets attested to their supremacy over modern systems that are currently available in terms of precision, accuracy, false alarm rate, and detection rate. To learn more about how well our model works, we added two additional metrics: Cohen's Kappa coefficients and Mathew correlation. The outcomes of our experiments and simulations showed that the suggested approach was stable and reliable across a variety of performance criteria. The experimental outcomes show that the proposed system can effectively describe normal activity inside fog nodes and identify various kinds of attacks.

Deep-learning framework for state of charge (SoC) estimation of electric vehicle batteries using a Pynq board

V. S. Vijaya Krishna V., N. Pappa, S. P. Joy Vasantha Rani — Wed, 11 Dec 2024 00:00:00 -0600

In recent years, carbon emissions are increasing worldwide due to excessive usage fossil fuels. To overcome these emissions, lithium-ion (Li-ion) batteries have become more prominent alternative. Li-ion batteries are used as primary component of energy storage systems for sustainable energy in response to rising global carbon gases. Battery Management System (BMS) in Electric Vehicles (EVs) is an important aspect and is indicated by two parameters called State of Charge (SoC) and State of Health (SoH). Of these two, SoC value is related to energy distribution, charging and discharging of batteries. Hence Estimating SoC value is of high important in BMS for optimum usage of batteries. Recent trends in Artificial Intelligence and Deep Learning provides a way for new developments in algorithms for estimating SoC. At the same time, the use of programmable devices like Field Programmable Gate Arrays (FPGAs) for data processing applications provides acceleration in time and optimal use of hardware. Pynq boards which are Zynq dependent and one variant of FPGAs are capable of executing python programs directly on hardware. This paper focuses on developing different DNN architectures for estimating SoC of a Li-ion battery of an EV and realizing on Pynq Z2 board.

Utilizing advanced machine learning techniques for accurate prediction of oxygen quantity in gas-fired boiler combustion to enhance environmental pollution control

K. Ganpati, S. Bhusnur — Wed, 11 Dec 2024 00:00:00 -0600

PyTorch, an open-source machine learning framework built on the Torch library, is used in this application to apply deep learning to image classification in a boiler section and to design an entity algorithm for predicting the amount of oxygen available in the furnace section. The physical features of this flame are viewable using pictures obtained from a Charge Coupled Device (CCD). By removing the nonlinear elements, a multilayer CNN forecasts the amount of oxygen in the flue gas from a boiler. From the results of experiments conducted on-site in a real-time combustion system, images of boilers under various settings, including temperatures, air pressures, and gas conditions, have been obtained. Classification models are then applied. The precise quantity of oxygen content is calculated with these photos as input and comparing the outcomes with the test data set. More insightful information about the flame's physical features can be defined using a Convolutional Neural Network (CNN) model and a multilayer representation of the flame images. The flame images captured on-site from an actual combustion system are utilized to illustrate this notion. The oxygen content is predicted using a multilevel-based, unsupervised, and semi-supervised deep entity algorithm by taking 12 classes and training 4,203,592 images each flame image in the tests has a resolution of 24 bits per pixel and a size of 658*492 pixels. After training the model, the loss is as low as 3%, and the attained accuracy is 97%.

Characterization of urban mobility in Bogotá: A spatial autocorrelation analysis

J. Pantoja, O. Melo, D. J. Rodríguez — Wed, 11 Dec 2024 00:00:00 -0600

This paper studies the variables influencing urban mobility in Bogotá's Urban Planning Zones (UPZs) through spatial autocorrelation analysis. Initially, data from various databases were compiled, covering 13 variables across 111 UPZs. A descriptive analysis identified significant variables, revealing a positive skewness trend. Higher social strata (4, 5, and 6) correlated with better mobility indices and more automobiles per family. The Moran Index showed strong spatial autocorrelation in mobility indices, indicating that nearby UPZs have similar mobility patterns. Areas like Suba and Usaquén, with better infrastructure, showed higher mobility indices, while Ciudad Bolívar and Usme had poor infrastructure and low mobility. The study highlights the correlation between mobility and factors like social strata, automobile numbers, and infrastructure, providing a foundation for future transport and urban planning policies.

Technologies for safety and health management in large companies in Ecuador: A worker-centric exploration from technology adoption attitudes

Y. González-Cañizalez, J. Silva-Barreto, R. Manrique-Suárez, B. Rodríguez — Wed, 11 Dec 2024 00:00:00 -0600

Implementing I4.0 technologies to promote a safe work environment is essential to safeguard worker safety and health (OSH). An analysis based on the Unified Theory of Acceptance and Use of Technology (UTAUT) and the adapted Technology Organization and Environment (TOE) model led the association between applications based on the Industrial Internet of Things (IIoT) and workers’ attitude toward these ap- plications in large Ecuadorian companies. Service & Commerce business companies gathering most workers, predominantly between 18 and 43 years old (63.86%), shows a positive and significant correlation between operation and supervision responsibilities, educational level, and the use of portable devices, especially in OSH (78.31%). A positive correlation is depicted between perceived ease of use (EU), perceived usefulness (PU), and risk perception (RP). The use of portable devices for work activities, combined with the detection of issues in the workflow, is positively correlated with sharing data to identify risks, bridging collective and individual OSH. Monitoring activities, data collection, and training concentrate the key technological applications in large companies in Ecuador.

Social media advertisement for public disease prevention framework as an innovative tool: An approach using EFA and PLS-SEM

J. Mejía-Trejo — Wed, 11 Dec 2024 00:00:00 -0600

The article discusses Social Media Advertisement (SMA) as an innovative tool for Public Disease Prevention (PDP), emphasizing its cost-effectiveness and accessibility to small organizations. The study aims to highlight the importance of SMA platforms in emerging countries like Mexico and explores their potential as tools for PDP, addressing eight factors. The research follows a four-step methodology involving qualitative and quantitative approaches, leading to the development of a validated questionnaire. The study's theoretical framework integrates qualitative and quantitative methods, offering insights for strategic digital marketing planning, especially benefiting Mexican university students. The research fills a gap in studies related to Mexico and establishes a conceptual framework validated through PLS-SEM, contributing to both theory and practice in SMA for PDP. Future studies are encouraged to explore cross-cultural adaptation and advanced data analytics for a deeper understanding.

Application of metal oxide/metal nanoparticle-based antimicrobial films in food packaging: Potential use, risk factors, safety assessments and regulatory matters

T. Vats, G. Arora, P. Tiwari — Wed, 11 Dec 2024 00:00:00 -0600

Packaging is an important feature of our everyday life and it has a vital role to play in food industry. A lot of work is being done for diversifying the role of packaging including use of packaging for increasing the storage time of food items. In this review, we have discussed the role of commonly used metals and metal oxide nanoparticles based antimicrobial agents as a component of packaging material. Though “nano” is a magic word used these days, in this article the potential health hazards on the probable leaching of packaging nanomaterial into food have been discussed. Besides, the safety regulations of various economies have also been covered.