Split Ratio Research Articles

Impact Assessment of Nematode Infestation on Soybean Crop Production Using Aerial Multispectral Imagery and Machine Learning

Accurate and prompt estimation of geospatial soybean yield (SY) is critical for the producers to determine key factors influencing crop growth for improved precision management decisions. This study aims to quantify the impacts of soybean cyst nematode (SCN) infestation on soybean production and the yield of susceptible and resistant seed varieties. Susceptible varieties showed lower yield and crop vigor recovery, and high SCN population (20 to 1080) compared to resistant varieties (SCN populations: 0 to 340). High-resolution (1.3 cm/pixel) aerial multispectral imagery showed the blue band reflectance (r = 0.58) and Green Normalized Difference Vegetation Index (GNDVI, r = −0.6) have the best correlation with the SCN populations. While GDNVI, Green Chlorophyll Index (GCI), and Normalized Difference Red Edge Index (NDRE) were the best differentiators of plant vigor and had the highest correlation with SY (r = 0.59–0.75). Reflectance (REF) and VIs were then used for SY estimation using two statistical and four machine learning (ML) models at 10 different train–test data split ratios (50:50–95:5). The ML models and train–test data split ratio had significant impacts on SY estimation accuracy. Random forest (RF) was the best and consistently performing model (r: 0.84–0.97, rRMSE: 8.72–20%), while a higher train–test split ratio lowered the performances of the ML models. The 95:5 train–test ratio showed the best performance across all the models, which may be a suitable ratio for modeling over smaller or medium-sized datasets. Such insights derived using high spatial resolution data can be utilized to implement precision crop protective operations for enhanced soybean yield and productivity.

Flexibility analysis on absorption-based carbon capture integrated with energy storage

Post-combustion carbon capture in power plants is essential in reducing greenhouse gas emission. As the available heat in the plant is instable in time, it becomes a challenge to maintain the efficient operation of capture system. The lean/rich solvent storage proves to be a potential way for the capture system to keep high CO2 capture rate. However, the performance of the integrated system under different operating conditions is not fully evaluated, especially for the match criterion of lean/rich solvent process. The impact factors of single and coupled operating conditions of solvent storage still remain unclear. In this work, system performance during peak/off-peak period is first evaluated. Results indicates that heat duty, split ratio, solution concentration and absorption solvent flow rate are key factors for CO2 capture rate. Then, system performance under continuous operation is explored at the global CO2 capture rate from 0.918 to 0.978. It demonstrates that maintaining a relatively equal CO2 capture rate during peak/off-peak period efficiently improves the global CO2 capture rate, which can be achieved by adjusting flow rate and split ratio of solvent. Finally, volume and cost of integrated CO2 capture with solvent storage are compared with that of CO2 capture with heat storage. The volume of solvent storage decreases by over 69% and the cost of solvent storage decreases by over 84%, which indicates a promising application in terms of technical and economic aspects.

Preserving authenticity: transfer learning methods for detecting and verifying facial image manipulation

Facial retouching in supporting documents can have adverse effects, undermining the credibility and authenticity of the information presented. This paper presents a comprehensive investigation into the classification of retouched face images using a fine-tuned pre-trained VGG16 model. We explore the impact of different train-test split strategies on the performance of the model and also evaluate the effectiveness of two distinct optimizers. The proposed fine-tuned VGG16 model with “ImageNet” weight achieves a training accuracy of 99.34 % and a validation accuracy of 97.91 % over 30 epochs on the ND-IIITD retouched faces dataset. The VGG16_Adam model gives a maximum classification accuracy of 96.34 % for retouched faces and an overall accuracy of 98.08 %. The experimental results show that the 50 % - 25 % train-test split ratio outperforms other split ratios mentioned in the paper. The demonstrated work shows that using a Transfer Learning approach reduces computational complexity and training time, with a max. training duration of 39.34 min for the proposed model.

Infrared all-dielectric bifocal metasurface beam splitter based on the transflective structure

Based on the design concept of a transflective double-ended response structured metasurface and the Pancharatnam-Berry (PB) phase modulation mechanism, we have designed and numerically demonstrated a bifocal all-dielectric metasurface beam splitter. This device is constructed by arranging silicon nanocolumns on SiO2 substrates. The bifocal metasurface beam splitter developed in this study achieves double-ended deflected focusing beam splitting at a wavelength of 1.55 μm. The focusing efficiency at both ends exceeds 50%, the equivalent numerical aperture at both ends is greater than 0.85, and the beam splitting ratio is approximately 1.4:1. Furthermore, compared to most current single-ended response bifocal metasurfaces, the transflective bifocal metasurface beam splitter, with equal phase modulation at both ends, is anticipated to be integrated into compact optical systems that require real-time signal feedback.

LGG-25. ADVANCING RESPONSE ASSESSMENT OF LOW-GRADE GLIOMAS: IDENTIFYING VOLUME CORRELATIONS OF BI-PERPENDICULAR DIAMETER CHANGES WITH MACHINE LEARNING

Abstract BACKGROUND Assessing brain tumor response is key for effective management and clinical trial benchmarks. Traditionally, bi-perpendicular diameter (BPD) measurements have been used to estimate tumor size. However, recent studies suggest volumetric assessment yields a more accurate measure of response and estimate of tumor burden. Advances in technology enable rapid volume assessments. Integrating volumetric analysis into clinical settings is challenged by the absence of volume-based standards aligned with traditional RAPNO bi-dimensional criteria. Our goal was to correlate volume change percentages with bi-perpendicular diameter changes using machine learning. METHODS In this project, we compared 2 machine learning models to establish a correlation between percentage change of sum of products of BPD and percent change in volume using a generalized linear model (GLM) and an artificial neural network (ANN). We analyzed 49 patients with low grade glioma, treated with focal irradiation (NCT04065776) (n=27) or mirdametinib (NCT04923126) (n=22). We trained and validated the models at train-test split ratios of 80/20, 75/25, and 70/30, incorporating a proportionate split of tumors from each group. The models were compared on the validation data set using mean-squared error (MSE). RESULTS At percentage changes of +25%, -25%, -50%, and -75% in the sum of BPDs, the GLM predicts changes in volume to be +33%, -31%, -59%, and -83%, respectively. For the ANN, the predicted changes are +20%, -29%, -53%, and -78%. The ANN demonstrated a lower MSE compared to the GLM. The two models showed higher concordance in their volume predictions at negative percentage changes in the sum of BPDs: -25% (p=0.15), -50% (p=0.03), and 75% (p=.08) CONCLUSION We identified volume percentage changes matching BPD changes per RAPNO criteria using two machine learning methods, both agreeing on negative values. Further testing with a larger dataset is needed to reliably correlate percentage changes.

Hydrodynamic characteristics analysis of series hydraulic cyclone separators for pond aquaculture wastewater purification

This study introduces a series of hydraulic cyclone separators designed to efficiently remove sediments and other high-density particulate matter from pond aquaculture wastewater. A three-dimensional two-phase model of these hydraulic cyclone separators was developed using the discrete phase model (DPM) and Reynolds stress turbulence model (RSM) based on numerical simulation theory. The computational fluid dynamics (CFD) method was validated by comparing it with experimental data, and an analysis of the hydrodynamic characteristics of the hydraulic cyclone separators was conducted. Furthermore, the relationships between structural parameters and separation efficiency were examined using Pearson's correlation coefficient. The findings reveal that the length of the first-stage cyclone column significantly influences the tangential velocity distribution within the second-stage cyclone, while the length of the second-stage cyclone column predominantly affects the pressure distribution of the first-stage cyclone. Increasing the column length enhances the overall particulate separation efficiency of the system. Moreover, adjustments in the split ratio of the first-stage cyclone have a notable impact on the tangential velocity and pressure distribution within the second-stage cyclone. Increasing the split ratio proves beneficial in improving the separation efficiency of particulate matter. This study provides valuable insights into the design and optimization of hydraulic cyclone separators, offering a dependable computational model for predicting and understanding their flow behavior and separation performance effectively.

Gastric Emptying Scintigraphy Protocol Optimization Using Machine Learning for the Detection of Delayed Gastric Emptying.

The purpose of this study is to examine the feasibility of a machine learning (ML) system for optimizing a gastric emptying scintigraphy (GES) protocol for the detection of delayed gastric emptying (GE), which is considered a primary indication for the diagnosis of gastroparesis. An ML model was developed using the JADBio AutoML artificial intelligence (AI) platform. This model employs the percent GE at various imaging time points following the ingestion of a standardized radiolabeled meal to predict normal versus delayed GE at the conclusion of the 4 h GES study. The model was trained and tested on a cohort of 1002 patients who underwent GES using a 70/30 stratified split ratio for training vs. testing. The ML software automated the generation of optimal predictive models by employing a combination of data preprocessing, appropriate feature selection, and predictive modeling analysis algorithms. The area under the curve (AUC) of the receiver operating characteristic (ROC) curve was employed to evaluate the predictive modeling performance. Several models were developed using different combinations of imaging time points as input features and methodologies to achieve optimal output. By using GE values at time points 0.5 h, 1 h, 1.5 h, 2 h, and 2.5 h as input predictors of the 4 h outcome, the analysis produced an AUC of 90.7% and a balanced accuracy (BA) of 80.0% on the test set. This performance was comparable to the training set results (AUC = 91.5%, BA = 84.7%) within the 95% confidence interval (CI), demonstrating a robust predictive capability. Through feature selection, it was discovered that the 2.5 h GE value alone was statistically significant enough to predict the 4 h outcome independently, with a slightly increased test set performance (AUC = 92.4%, BA = 83.3%), thus emphasizing its dominance as the primary predictor for delayed GE. ROC analysis was also performed for single time imaging points at 1 h and 2 h to assess their independent predictiveness of the 4 h outcome. Furthermore, the ML model was tested for its ability to predict "flipping" cases with normal GE at 1 h and 2 h that became abnormal with delayed GE at 4 h. An AI/ML model was designed and trained for predicting delayed GE using a limited number of imaging time points in a 4 h GES clinical protocol. This study demonstrates the feasibility of employing ML for GES optimization in the detection of delayed GE and potentially shortening the protocol's time length without compromising diagnostic power.

Pressurized oxy-fuel combustion with sCO2 cycle and ORC for power production and carbon capture

The pressurization of oxy-fuel combustion presents the opportunity to recuperate more latent heat from the flue gas within the boiler. This study proposed a coal-fired pressurized oxy-fuel combustion plant coupled with the sCO2 Brayton cycle for simultaneous power production and carbon capture. Two configurations, i.e., sCO2 recuperator split and sCO2 bottom cycle, are conceived to fully exploit the flue gas heat from the boiler. Waste heat from various sources, including the air separation unit, the CO2 compression and purification unit and the sCO2 cycle, are recuperated by the organic Rankine cycle (ORC) to augment the net power efficiency. Sensitive analyses, including the turbine parameters, the recuperator split ratio, and the ORC parameters, are conducted to optimize the design and operation conditions of the plant. The plant net power efficiency ranges between 39.4 % and 42.9 %, inclusive of CO2 compression. The levelized cost of electricity (LCOE) is calculated, and the LCOE results are in the range of 101.60 $/MWh and 106.07 $/MWh for different configurations. These findings suggest the system's viability for future coal-fired plant with carbon capture.

Sentiment analysis of the Hamas-Israel war on YouTube comments using deep learning

Sentiment analysis aims to classify text based on the opinion or mentality expressed in a situation, which can be positive, negative, or neutral. Therefore, in the world, a lot of opinions are available on various social media sites, which must be gathered and analyzed to assess the general public’s opinion. Finding and monitoring comments, as well as manually extracting the information contained in them, is a difficult task due to the vast diversity of ideas on YouTube. Identifying public opinion on war topics is crucial for offering insights to opposing sides based on popular opinion and emotions about the ongoing war. To address the gap, we build a model on YouTube comment sentiment analysis of the Hamas-Israel war to determine public opinion. In this study, we address the gaps by developing a deep learning-based approach for sentiment analysis. We have collected 24,360 comments from popular YouTube News Channels including BBC, WION, Aljazeera, and others about the Hamas-Israel War using YouTube API and Google spreadsheet and labeled them by linguistic experts into three classes: positive, negative, and neutral. Then, textual comments were preprocessed using natural language processing (NLP) techniques, and features were extracted using Word2vec, FastText, and GloVe. Moreover, we have used the SMOTE data balancing technique and used different data splits, but the 80/20 train-test split ratio has the highest accuracy. For classification model building, commonly used classification algorithms LSTM, Bi-LSTM, GRU, and Hybrid of CNN and Bi-LSTM were applied, and their performance is compared. As a result, the Hybrid of CNN and Bi-LSTM with Word2vec achieved the highest performance with 95.73% accuracy for comments classifications.

A non-linear and interaction effect analysis of various risk factors influencing mobile phone use while driving among long-haul truck drivers travelling across India

Mobile phone use while driving (MPWD) is one of the most critical behaviours contributing to distraction related fatalities and injuries. However, MPWD is not well understood among long-haul truck drivers (LHTDs) especially in developing countries like India. The present study aims to develop a prediction model for MPWD and attempts to identify the underlying factors and patterns affecting MPWD among LHTDs travelling across India. A total of 756 valid samples were collected utilising a questionnaire in Salem city, Tamil Nadu, India. Machine learning algorithms including Decision tree, Random Forest, Adaptive Boosting, and Extreme gradient boosting were employed to model MPWD. A split ratio of 70:30 was adopted for training and testing purposes. A 10-fold cross validation procedure was carried out during model development. The analysis results showed that XGBoost demonstrated superior performance than other models (accuracy = 0.82, F1 score =0.8, and AUROC = 0.82). In addition, SHapley Additive explanations (SHAP) were implemented to reveal the importance of predictors contributing to MPWD. The findings of the study showed that type of commodity, pressured delivery, calls received during driving, smoking habits, educational level, and continuous driving duration as major factors contributing to MPWD among LHTDs. SHAP values were also utilised to investigate hidden patterns and interaction effects for major factors affecting MPWD. Parcel and food items coupled with frequent pressured delivery and middle aged LHTDs driving continuously for 5–6 h are some of the interactive risk factors enhancing MPWD. These findings are useful for road safety authorities and truck companies to draft suitable policies and help to introduce effective interventions for reducing MPWD among LHTDs.

Design and validation of a miniaturized reconfigurable power divider with arbitrary power split ratio and flexible output phase difference

This study introduces a microstrip line (ML) based reconfigurable 5-port power divider (PD) capable of manipulating power ratios at four output ports. The proposed PD offers two operational modes: unidirectional and bidirectional. In unidirectional transmission mode, the entire source power is directed to a particular output port, while in bidirectional transmission mode, the source power is equally distributed between two output ports. The selection of different transmission modes is accomplished by configuring six adaptive loads that are coupled to the PD structure, and the corresponding S-parameters of the proposed PD are derived by even–odd mode modeling. The resulting data is subsequently optimized by a numerical approach to identify the required design parameters that would ensure optimal performance. The proposed PD resonates at 1.06GHz and covers a frequency range spanning 0.9GHz to 1.2GHz, making it an excellent option for supplying regulated power to multi-port antennas or multiple input multiple output (MIMO) antennas proposed for aircraft navigation applications. The prototype has been developed to validate the notion of reconfigurable reactive loads utilizing varactor diodes and the recorded result is evaluated with the simulated results. The findings confirm excellent performance with regards to insertion loss (with a difference of <-2dB from the optimal values), reflection coefficient (≥-20dB), and isolation (≥-40dB) between the transmitting (input port) and non-transmitting or the remaining ports.

High-performance electro-optic switches with compact multimode interference and Bezier S-bend waveguides

High-speed and energy-efficient electro-optic (EO) switches are crucial for next-generation data communication systems. This paper presents a novel EO switch utilizing a multimode interference (MMI) coupler-based approach on a lithium-niobate (LiNbO3) platform. The switch is designed with Bezier S-bend waveguides, leading to a significant reduction in bending loss to 0.18 dB. This Bezier-bend EO switch shows an excess loss of 0.33 dB and crosstalk of −20.44 dB for the bar port switching, while the cross port switching exhibits an excess loss of 0.64 dB and crosstalk of −13.66 dB. Applying a 3.27 V voltage achieves a balanced splitting ratio of 29:29:29 between the three outputs. The length of this EO switch is 4.09 mm, which requires 4.1 V to create a phase shift, showing a voltage efficiency of 1.68 V.cm. This paper presents a promising pathway for a novel EO switch design and introduces improved signal management for next-generation computing systems.

Microfluidic flow tuning via asymmetric flow of nematic liquid crystal under temperature gradient

In this work, efficient microfluidic flow rate tuning based on the asymmetric flow of nematic liquid crystal 5CB under a horizontal temperature gradient is studied. Rectangular microchannels with the width of 100 μm are fabricated through soft lithography and treated with homeotropic surface anchoring conditions. Polarized optical microscopy is applied to explore the unique optical anisotropic characteristics of the nematic liquid crystal. The asymmetric velocity profiles in the microchannel are obtained by particle tracking velocimetry. The effects of temperature, flow rate, and aspect ratio on the velocity profile and split ratio of the asymmetric flow are quantitatively studied for the first time, while the mechanism of the flow asymmetry of the nematic liquid crystal is discussed. The results show that the asymmetric flow of the nematic liquid crystal occurs after the horizontal temperature gradient is applied, with the velocity in the heated region markedly higher than its counterpart. The split ratio of the asymmetric flow increases with the increase in the temperature gradient and the decrease in the flow rate. The aspect ratio influences the asymmetric flow through approaches of average velocity and surface anchoring strength, while the former is more distinct. The impacts of temperature gradient, flow rate, and aspect ratio on the flow asymmetry of nematic liquid crystals are caused by the coupling between physical properties, velocity field, and director field. Microchannels based on the asymmetric flow characteristics of nematic liquid crystals can act as a novel kind of temperature-controlled microvalve to achieve efficient microfluidic flow tuning.

Microscopic spray characteristics of diethyl ether–diesel blends under single and split injection strategies

The phase doppler interferometry technique was used to thoroughly investigate microscopic spray characteristics of single and split injection strategies. The diethyl ether blending with diesel resulted in smaller and uniform droplet formation. Diethyl ether–diesel blend spray exhibited a lower droplet axial velocity distribution than baseline diesel, which can be improved by split injection strategies. At atmospheric pressure, the maximum axial velocity for diesel and diethyl ether–diesel blends was almost identical under single and split injection strategies. However, split injection improved the spray droplet's axial velocity at higher ambient pressures compared to single injection. The chances of coalescence and having coarse droplets were higher at elevated ambient pressure, especially for lower fuel injection pressures. Therefore, increasing the fuel injection pressure is more suitable to avoid droplet coalescence. Unlike the split ratio, dwell time strongly influenced fuel spray atomization. The droplet diameter distribution exhibited a higher probability of finer droplets for a longer dwell time of 0.45 ms than a shorter dwell time of 0.15 ms. A major finding of this study is that diethyl ether–diesel blend spray with a longer dwell time exhibited superior spray characteristics.

Deep learning based fault detection of automobile dry clutch system using spectrogram plots

Dry friction clutches are extremely important in the context of power transmission systems. Continuous exposure to extreme heat and loading makes clutch extremely susceptible to various faults. The timely detection and diagnosis of such faults are of utmost importance to prevent any damage to internal components and also helps in avoiding transmission system failures. In this research study, a novel approach that leverages the power of transfer learning (a famous deep learning technique) is proposed to diagnose multiple types of clutch faults including, worn release fingers, fractured pressure plates, deteriorated pressure plates, loss of friction material and distorted tangential strips using spectrogram plots. To train and validate the diagnostic system, vibration readings were taken from a specially designed test rig with the help of piezoelectric accelerometer while the clutch system was operated under different load conditions of 0 (no load), 5 and 10 kg This procedure of data collection was then repeated to acquire the vibration data for all of the fault conditions by replacing the good with fault components individually. These vibration signals were further processed and transformed into spectrogram plots that serves as the input data for the deep learning models considered. Fine-tuning techniques were applied on pretrained networks to maximise the prediction accuracy of the models to effectively determine and diagnose faults in the clutch system. For this study 12 pre-trained networks were chosen namely, Xception, InceptionResNet, DenseNet, AlexNet, VGG16, GoogLeNet, VGG19, ResNet101, ResNet50, InceptionV3, MobileNetV2 and ShuffleNet. To optimize the performance of deep learning models, a systematic adjustment of hyperparameters such as the train-test split ratio, learning rate, optimizer and batch size for each network model was carried out. Through careful experimentation and analysis, significant improvements in fault classification accuracy were achieved thereby enhancing the reliability and effectiveness of the diagnostic system. From the results it was noted that 100% classification accuracy was displayed by AlexNet (for the no load condition and the 10 kg load condition) and GoogLeNet (for 5 kg load condition) with extremely low computation times.

Two-stage injection of polymer and microsand during ballasted flocculation for treating kaolin waters with or without humic acid: Floc evolutional characteristics, performance and mechanisms

Ballasted flocculation is regarded as a most promising water treatment technology in aspects of retrofit and high-rate applications. To deep understand the incorporation behaviors of ballasting agent into ballasted floc growth, two distinct injection modes (namely a two-stage injection of polyacrylamide (PAM) alone, and a two-stage injection of both PAM and microsand) were developed in this study. Then, ballasted flocculation tests of kaolin and kaolin-HA (humic acid) waters were conducted at varying split ratios for fixed total dosages of both PAM and microsand. The experimental results showed that for either two-stage injection mode, the higher the second percentage of each split ratio, the greater the average size of maturated flocs at the second sub-stage of maturation. Meanwhile, the turbidity and UV254 values of settled water became lower at 30 and 180 s of sedimentation, suggesting that varying split ratios significantly affected the kinetics of ballasted floc growth. Moreover, it was suggested that the selection of either two-stage injection mode or corresponding split ratios played a more pronounced role in the HA removal than the total dosage of PAM. This suggestion was supported by SEM, FTIR and XPS analyses for surface morphological details, functional groups and chemical states of maturated flocs eventually formed in the kaolin-HA water through both two-stage injection modes. Accordingly, newly-established conceptual models of ballasted floc growth were proposed to explore the potential influencing mechanisms of varying split ratios on the ballasted flocculation performance. At each sub-stage of maturation, an appropriate dosage ratio between PAM and microsand was of great importance to effectively incorporate microsand particles into ballasted floc formation, besides the hydrolyzed produces of AS coagulant formed at the coagulation stage of ballasted flocculation. This study is expected to provide valuable insights for making ballasted flocculation more effective, economical and sustainable in water treatment engineering.

Splitting long‐term and short‐term financial ratios for improved financial distress prediction: Evidence from Taiwanese public companies

AbstractFinancial distress occurs when a company cannot meet its financial obligations within a specified timeframe, often owing to prolonged poor operational performance. While studies on financial distress prediction (FDP) use financial ratios (FRs) to forecast distress, they neglect to differentiate long‐term (LT) attributes from FRs. To address this gap, our study introduces a novel model that distinguishes between LT and short‐term (ST) accounting attributes in FRs. Using data from Taiwanese public companies (1991–2018), our proposed model employs a stacking ensemble classifier to split LT and ST Altman's ratios. This study addresses three key questions: (1) Do models involving split of LT and ST ratios outperform those that combine them? (2) How reliable and robust are these proposed models? (3) What is the proposed model's impact on distress prediction? The results show a significant outperformance of the existing solution, with higher accuracy, lower Type I and Type II errors, and reduced misclassification costs. These models are reliable in handling imbalanced data, proving suitable for real‐market investigations. Diverse FR contexts from previous Taiwanese studies validate the distinction between LT and ST features, representing robust performance. This model identifies characteristics of correctly and incorrectly predicted distress in companies, providing nuanced insights into complex distress attributes. This study introduces a pioneering model demonstrating superior predictive accuracy, reliability, and robustness by considering the split between LT and ST accounting attributes. It lays a foundation for future studies to extend and refine the proposed model, offering valuable insights into the complex dynamics of FDP.

Study the effect of ANN splitting ratios and training functions on the prediction of corroded steel-to-concrete bond strength

Study the effect of ANN splitting ratios and training functions on the prediction of corroded steel-to-concrete bond strength

Reverse design of multifunctional cascade devices based on the adjoint method

In this paper, a 1×4 ultra-compact wavelength division multiplexing cascaded device(DMC) with an arbitrary splitting ratio based on adjoint topology optimization reverse design is proposed, which is approximately two orders of magnitude smaller than that of conventional waveguide devices. It can simultaneously perform wavelength demultiplexing, mode conversion, and arbitrary ratio power splitting. The DMC separates 1310 nm and 1550 nm wavelengths, converts the input light from fundamental transverse mode (TE0) to first-order transverse mode (TE1) and second-order transverse modes (TE2), and performs arbitrarily proportional power splitting of the converted higher-order light source.

A comparative study of machine learning models for identifying noxious gases through thermal fingerprint measurements and MOS sensors

Recently, there has been a notable surge of interest in developing swift and precise gas detection and categorization tools through artificial intelligence. This work specifically focuses on designing a simple sensor array configuration and empirically compares various machine-learning models for identifying multiple gases. The study employs eight metal oxide semiconductor sensors, each operating independently based on the thermal fingerprint principle. These sensors are utilized to gather data on responses to different toxic gases, and a range of traditional machine learning classifiers are trained and assessed using this dataset. The classifiers undergo investigation across various train/test dataset split ratios and different principal component analysis dimensionalities. Average accuracy metrics are employed over the entire testing dataset to evaluate model performance. The results demonstrated the challenge of selectively detecting each gas type solely through conventional analyses with the gas response data of the proposed sensor array. Nevertheless, the utilization of machine learning models has exhibited promising outcomes in augmenting gas identification and classification. The findings reveal a consistent improvement in testing accuracy for the Gradient Boosting model, which achieves an outstanding accuracy rate, with instances of reaching 100% accuracy in the training dataset when three or more principal components are considered. This study highlights the potential of the proposed straightforward sensor array and presents effective recognition algorithms applicable to creating electronic noses for gas-sensing applications.