A novel perspective on the selection of an effective approach to reduce road traffic accidents under Fermatean fuzzy settings.

Road traffic accidents (RTAs) pose a significant hazard to the security of the general public, especially in developing nations. A daily average of more than three thousand fatalities is recorded worldwide, rating it as the second most prevalent cause of death among people aged 5-29. Precise and reliable decisionmaking techniques are essential for identifying the most effective approach to mitigate road traffic incidents. This research endeavors to investigate this specific concern. The Fermatean fuzzy set (FFS) is a strong and efficient method for addressing ambiguity, particularly when the concept of Pythagorean fuzzy set fails to provide a solution. This research presents two innovative aggregation operators: the Fermatean fuzzy ordered weighted averaging (FFOWA) operator and the Fermatean fuzzy dynamic ordered weighted geometric (FFOWG) operator. The salient characteristics of these operators are discussed and important exceptional scenarios are thoroughly delineated. Furthermore, by implementing the suggested operators, we develop a systematic approach to handle multiple attribute decisionmaking (MADM) scenarios that involve Fermatean fuzzy (FF) data. In order to show the viability of the developed method, we provide a numerical illustration encompassing the determination of the most effective approach to alleviate road traffic accidents. Lastly, we conduct a comparative evaluation of the proposed approach in relation to a number of established methodologies.

Integrating fuzzy-AHP and GIS for solid waste disposal site selection in Kenitra province, NW Morocco.

Selecting an optimal solid waste disposal site is one of the decisive waste management issues because unsuitable sites cause serious environmental and public health problems. In Kenitra province, northwest Morocco, sustainable disposal sites have become a major challenge due to rapid urbanization and population growth. In addition, the existing disposal sites are traditional and inappropriate. The objective of this study is to suggest potential suitable disposal sites using fuzzy logic and analytical hierarchy process (fuzzy-AHP) method integrated with geographic information system (GIS) techniques. For this purpose, thirteen factors affecting the selection process were involved. The results showed that 5% of the studied area is considered extremely suitable and scattered in the central-eastern parts, while 9% is considered almost unsuitable and distributed in the northern and southern parts. Thereafter, these results were validated using the area under the curve (AUC) of the receiver operating characteristics (ROC). The AUC found was 57.1%, which is a moderate prediction's accuracy because the existing sites used in the validation's process were randomly selected. These results can assist relevant authorities and stakeholders for setting new solid waste disposal sites in Kenitra province.

Detecting emotions through EEG signals based on modified convolutional fuzzy neural network.

Emotion is a human sense that can influence an individual's life quality in both positive and negative ways. The ability to distinguish different types of emotion can lead researchers to estimate the current situation of patients or the probability of future disease. Recognizing emotions from images have problems concealing their feeling by modifying their facial expressions. This led researchers to consider Electroencephalography (EEG) signals for more accurate emotion detection. However, the complexity of EEG recordings and data analysis using conventional machine learning algorithms caused inconsistent emotion recognition. Therefore, utilizing hybrid deep learning models and other techniques has become common due to their ability to analyze complicated data and achieve higher performance by integrating diverse features of the models. However, researchers prioritize models with fewer parameters to achieve the highest average accuracy. This study improves the Convolutional Fuzzy Neural Network (CFNN) for emotion recognition using EEG signals to achieve a reliable detection system. Initially, the pre-processing and feature extraction phases are implemented to obtain noiseless and informative data. Then, the CFNN with modified architecture is trained to classify emotions. Several parametric and comparative experiments are performed. The proposed model achieved reliable performance for emotion recognition with an average accuracy of 98.21% and 98.08% for valence (pleasantness) and arousal (intensity), respectively, and outperformed state-of-the-art methods.

Evaluating modern intrusion detection methods in the face of Gen V multi-vector attacks with fuzzy AHP-TOPSIS.

The persistent evolution of cyber threats has given rise to Gen V Multi-Vector Attacks, complex and sophisticated strategies that challenge traditional security measures. This research provides a complete investigation of recent intrusion detection systems designed to mitigate the consequences of Gen V Multi-Vector Attacks. Using the Fuzzy Analytic Hierarchy Process (AHP) and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), we evaluate the efficacy of several different intrusion detection techniques in adjusting to the dynamic nature of sophisticated cyber threats. The study offers an integrated analysis, taking into account criteria such as detection accuracy, adaptability, scalability, resource effect, response time, and automation. Fuzzy AHP is employed to establish priority weights for each factor, reflecting the nuanced nature of security assessments. Subsequently, TOPSIS is employed to rank the intrusion detection methods based on their overall performance. Our findings highlight the importance of behavioral analysis, threat intelligence integration, and dynamic threat modeling in enhancing detection accuracy and adaptability. Furthermore, considerations of resource impact, scalability, and efficient response mechanisms are crucial for sustaining effective defense against Gen V Multi-Vector Attacks. The integrated approach of Fuzzy AHP and TOPSIS presents a strong and adaptable strategy for decision-makers to manage the difficulties of evaluating intrusion detection techniques. This study adds to the ongoing discussion about cybersecurity by providing insights on the positive and negative aspects of existing intrusion detection systems in the context of developing cyber threats. The findings help organizations choose and execute intrusion detection technologies that are not only effective against existing attacks, but also adaptive to future concerns provided by Gen V Multi-Vector Attacks.

Maize leaf disease recognition using PRF-SVM integration: a breakthrough technique.

The difficulty of collecting maize leaf lesion characteristics in an environment that undergoes frequent changes, suffers varying illumination from lighting sources, and is influenced by a variety of other factors makes detecting diseases in maize leaves difficult. It is critical to monitor and identify plant leaf diseases during the initial growing period to take suitable preventative measures. In this work, we propose an automated maize leaf disease recognition system constructed using the PRF-SVM model. The PRFSVM model was constructed by combining three powerful components: PSPNet, ResNet50, and Fuzzy Support Vector Machine (Fuzzy SVM). The combination of PSPNet and ResNet50 not only assures that the model can capture delicate visual features but also allows for end-to-end training for smooth integration. Fuzzy SVM is included as a final classification layer to accommodate the inherent fuzziness and uncertainty in real-world image data. Five different maize crop diseases (common rust, southern rust, grey leaf spot, maydis leaf blight, and turcicum leaf blight along with healthy leaves) are selected from the Plant Village dataset for the algorithm's evaluation. The average accuracy achieved using the proposed method is approximately 96.67%. The PRFSVM model achieves an average accuracy rating of 96.67% and a mAP value of 0.81, demonstrating the efficacy of our approach for detecting and classifying various forms of maize leaf diseases.

A novel MCGDM technique based on correlation coefficients under probabilistic hesitant fuzzy environment and its application in clinical comprehensive evaluation of orphan drugs.

Probabilistic hesitant fuzzy sets (PHFSs) are superior to hesitant fuzzy sets (HFSs) in avoiding the problem of preference information loss among decision makers (DMs). Owing to this benefit, PHFSs have been extensively investigated. In probabilistic hesitant fuzzy environments, the correlation coefficients have become a focal point of research. As research progresses, we discovered that there are still a few unresolved issues concerning the correlation coefficients of PHFSs. To overcome the limitations of existing correlation coefficients for PHFSs, we propose new correlation coefficients in this study. In addition, we present a multi-criteria group decision-making (MCGDM) method under unknown weights based on the newly proposed correlation coefficients. In addition, considering the limitations of DMs' propensity to use language variables for expression in the evaluation process, we propose a method for transforming the evaluation information of the DMs' linguistic variables into probabilistic hesitant fuzzy information in the newly proposed MCGDM method. To demonstrate the applicability of the proposed correlation coefficients and MCGDM method, we applied them to a comprehensive clinical evaluation of orphan drugs. Finally, the reliability, feasibility and efficacy of the newly proposed correlation coefficients and MCGDM method were validated.

Optimization of ship hull forms by changing CM and CB coefficients to obtain optimal seakeeping performance.

Ship design involves optimizing the hull in order to enhance safety, economic efficiency, and technical efficiency. Despite the long-term research on this problem and a number of significant conclusions, some of its content still needs to be improved. In this study, block and midship coefficients are incorporated to optimize the ship's hull. The considered ship was a patrol vessel. The seakeeping analysis was performed employing strip theory. The hull form was generated using a fuzzy model. Though the body lines generated by the midship coefficient (CM) and block coefficient (CB) varied indecently, the other geometric parameters remained the same. Multi-objective optimization was used to optimize CB and CM. According to the results of this study, these coefficients have a significant impact on the pitch motion of the patrol vessel as well as the motion sickness index. Heave and roll motions, as well as the added resistance, were not significantly influenced by the coefficients of CM and CB. However, increasing the hull form parameters increases the maximum Response Amplitude Operator (RAO) of heave and roll motions. The frequency of occurrence of the maximum roll RAO was in direct relation with CB and CM. These coefficients, however, had no meaningful impact on the occurrence frequency of other motion indices. In the end, the CB and CM coefficients were selected based on the vessel's seakeeping performance. These findings might be used by shipbuilders to construct the vessel with more efficient seakeeping performance.

Survival estimation of oral cancer using fuzzy deep learning.

BACKGROUND: Oral cancer is a deadly disease and a major cause of morbidity and mortality worldwide. The purpose of this study was to develop a fuzzy deep learning (FDL)-based model to estimate the survival time based on clinicopathologic data of oral cancer. METHODS: Electronic medical records of 581 oral squamous cell carcinoma (OSCC) patients, treated with surgery with or without radiochemotherapy, were collected retrospectively from the Oral and Maxillofacial Surgery Clinic and the Regional Cancer Center from 2011 to 2019. The deep learning (DL) model was trained to classify survival time classes based on clinicopathologic data. Fuzzy logic was integrated into the DL model and trained to create FDL-based models to estimate the survival time classes. RESULTS: The performance of the models was evaluated on a test dataset. The performance of the DL and FDL models for estimation of survival time achieved an accuracy of 0.74 and 0.97 and an area under the receiver operating characteristic (AUC) curve of 0.84 to 1.00 and 1.00, respectively. CONCLUSIONS: The integration of fuzzy logic into DL models could improve the accuracy to estimate survival time based on clinicopathologic data of oral cancer.

Key determinants to supply chain resilience to face pandemic disruption: An interpretive triple helix framework.

Today, supply chain (SC) networks are facing more disruptions compared to the past. While disruptions are rare, they can have catastrophic long-term economic or societal repercussions, and the recovery processes can be lengthy. These can tremendously affect the SC and make it vulnerable, as observed during the COVID-19 pandemic. The identification of these concerns has prompted the demand for improved disruption management by developing resilient, agile, and adaptive SC. The aim of this study is to introduce an assessment framework for prioritizing and evaluating the determinants to supply chain resilience (SCR). To analyze the empirical data, fuzzy criteria importance through intercriteria correlation (fuzzy CRITIC) and fuzzy technique for order of preference by similarity to ideal solution (fuzzy TOPSIS) have been incorporated. Fuzzy CRITIC method was used to identify the critical determinants and fuzzy TOPSIS method was applied for determining relative ranking of some real-world companies. Finally, by developing propositions an interpretive triple helix framework was proposed to achieve SCR. This research stands out for its originality in both methodology and implications. By introducing the novel combination of Fuzzy CRITIC and Fuzzy TOPSIS in the assessment of determinants to SCR and applying these determinants with the help of interpretive triple helix framework to establish a resilient SC, this study offers a unique and valuable contribution to the field of SCR. The key findings suggest that 'Responsiveness' followed by 'Managerial coordination and information integration' are the most significant determinant to achieve SCR. The outcome of this work can assist the managers to achieve SCR with improved agility and adaptivity.

Ankylosing spondylitis prediction using fuzzy K-nearest neighbor classifier assisted by modified JAYA optimizer.

The diagnosis of ankylosing spondylitis (AS) can be complex, necessitating a comprehensive assessment of medical history, clinical symptoms, and radiological evidence. This multidimensional approach can exacerbate the clinical burden and increase the likelihood of diagnostic inaccuracies, which may result in delayed or overlooked cases. Consequently, supplementary diagnostic techniques for AS have become a focal point in clinical research. This study introduces an enhanced optimization algorithm, SCJAYA, which incorporates salp swarm foraging behavior with cooperative predation strategies into the JAYA algorithm framework, noted for its robust optimization capabilities that emulate the evolutionary dynamics of biological organisms. The integration of salp swarm behavior is aimed at accelerating the convergence speed and enhancing the quality of solutions of the classical JAYA algorithm while the cooperative predation strategy is incorporated to mitigate the risk of convergence on local optima. SCJAYA has been evaluated across 30 benchmark functions from the CEC2014 suite against 9 conventional meta-heuristic algorithms as well as 9 state-of-the-art meta-heuristic counterparts. The comparative analyses indicate that SCJAYA surpasses these algorithms in terms of convergence speed and solution precision. Furthermore, we proposed the bSCJAYA-FKNN classifier: an advanced model applying the binary version of SCJAYA for feature selection, with the aim of improving the accuracy in diagnosing and prognosticating AS. The efficacy of the bSCJAYA-FKNN model was substantiated through validation on 11 UCI public datasets in addition to an AS-specific dataset. The model exhibited superior performance metrics-achieving an accuracy rate, specificity, Matthews correlation coefficient (MCC), F-measure, and computational time of 99.23 %, 99.52 %, 0.9906, 99.41 %, and 7.2800 s, respectively. These results not only underscore its profound capability in classification but also its substantial promise for the efficient diagnosis and prognosis of AS.

Enhancing gastric cancer early detection: A multi-verse optimized feature selection model with crossover-information feedback.

Gastric cancer (GC), an acknowledged malignant neoplasm, threatens life and digestive system functionality if not detected and addressed promptly in its nascent stages. The indispensability of early detection for GC to augment treatment efficacy and survival prospects forms the crux of this investigation. Our study introduces an innovative wrapper-based feature selection methodology, referred to as bCIFMVO-FKNN-FS, which integrates a crossover-information feedback multi-verse optimizer (CIFMVO) with the fuzzy k-nearest neighbors (FKNN) classifier. The primary goal of this initiative is to develop an advanced screening model designed to accelerate the identification of patients with early-stage GC. Initially, the capability of CIFMVO is validated through its application to the IEEE CEC benchmark functions, during which its optimization efficiency is measured against eleven cutting-edge algorithms across various dimensionalities-10, 30, 50, and 100. Subsequent application of the bCIFMVO-FKNN-FS model to the clinical data of 1632 individuals from Wenzhou Central Hospital-diagnosed with either early-stage GC or chronic gastritis-demonstrates the model's formidable predictive accuracy (83.395%) and sensitivity (87.538%). Concurrently, this investigation delineates age, gender, serum gastrin-17, serum pepsinogen I, and the serum pepsinogen I to serum pepsinogen II ratio as parameters significantly associated with early-stage GC. These insights not only validate the efficacy of our proposed model in the early screening of GC but also contribute substantively to the corpus of knowledge facilitating early diagnosis.

Exploring the Potential of Artificial Intelligence as a Facilitating Tool for Formulation Development in Fluidized Bed Processor: a Comprehensive Review.

This in-depth study looks into how artificial intelligence (AI) could be used to make formulation development easier in fluidized bed processes (FBP). FBP is complex and involves numerous variables, making optimization challenging. Various AI techniques have addressed this challenge, including machine learning, neural networks, genetic algorithms, and fuzzy logic. By integrating AI with experimental design, process modeling, and optimization strategies, intelligent systems for FBP can be developed. The advantages of AI in this context include improved process understanding, reduced time and cost, enhanced product quality, and robust formulation optimization. However, data availability, model interpretability, and regulatory compliance challenges must be addressed. Case studies demonstrate successful applications of AI in decision-making, process outcome prediction, and scale-up. AI can improve efficiency, quality, and cost-effectiveness in significant ways. Still, it is important to think carefully about data quality, how easy it is to understand, and how to follow the rules. Future research should focus on fully harnessing the potential of AI to advance formulation development in FBP.

A new multi-criteria decision making method for the selection of construction contractors using interval valued fuzzy set.

OBJECTIVE: This article introduces a novel approach called Digital Weighted Multi Criteria Decision Making (DWMCDM) that employs interval valued fuzzy sets to select the best contractor for building projects. The contractor is chosen based on the pre-qualification and bid evaluation phases. In the first phase, the distance between the actual and required skills of the significant criteria is determined, and it is then converted into digital weighted distances to identify the maximum number of criteria related to the specific project of each contractor. The second step ranks the best contractor based on the bid price and digital weighted distances. RESULTS: The suggested technique integrates the pre-qualification and bid review phases to address project award delays and other restrictions. Finally, a real-world application is addressed to demonstrate the applicability of the proposed approach to any type of interval valued fuzzy inputs.

The effect of retirement on physical and mental health in China: a nonparametric fuzzy regression discontinuity study.

BACKGROUND: With the rapid aging of the domestic population, China has a strong incentive to increase the statutory retirement age. How retirement affects the health of the elderly is crucial to this policymaking. The health consequences of retirement have been debated greatly. This study aims to investigate the effects of retirement on physical and mental health among Chinese elderly people. METHODS: The data we use in this study comes from four waves (2011, 2013, 2015, and 2018) of the Harmonized China Health and Retirement Longitudinal Study (Harmonized CHARLS), a prospective cohort. We use the nonparametric fuzzy regression discontinuity design to estimate the effects of retirement on physical and mental health. We test the robustness of our results with respect to different bandwidths, kernel functions, and polynomial orders. We also explore the heterogeneity across gender and education. RESULTS: Results show that retirement has an insignificant effect on a series of physical and mental health outcomes, with and without adjusting several sociodemographic variables. Heterogeneity exists regarding gender and education. Although stratified analyses indicate that the transition from working to retirement leaves minimal effects on males and females, the effects go in the opposite direction. This finding holds for low-educated and high-educated groups for health outcomes including depression and cognitive function. Most of the results are stable with respect to different bandwidths, kernel functions, and polynomial orders. CONCLUSIONS: Our results suggest that it is possible to delay the statutory retirement age in China as retirement has insignificant effects on physical and mental health. However, further research is needed to assess the long-term effect of retirement on health.

Fuzzy machine learning logic utilization on hormonal imbalance dataset.

In this research work, a novel fuzzy data transformation technique has been proposed and applied to the hormonal imbalance dataset. Hormonal imbalance is ubiquitously found principally in females of reproductive age which ultimately leads to numerous related medical conditions. Polycystic Ovary Syndrome (PCOS) is one of them. Treatment along with adopting a healthy lifestyle is advised to mitigate its consequences on the quality of life. The biological dataset of hormonal imbalance "PCOS" provides limited results that is whether the syndrome is present or not. Also, there are input variables that contain binary responses only, to deal with this conundrum, a novel fuzzy data transformation technique has been developed and applied to them thus leading to their fuzzy transformation which provides a broader spectrum to diagnose PCOS. Due to this, the output variable has also been transformed. Hence, a novel fuzzy transformation technique has been employed due to the limitation of the dataset leading to the transition of binary classification output into three classes. An adaptive fuzzy machine learning logic model is developed in which the inference of the transformed biological dataset is performed by the machine learning techniques that provide the fuzzy output. Machine learning techniques have also been applied to the untransformed biological dataset. Both implementations have been compared by computation of the relevant metrics. Machine learning employment on untransformed biological dataset provides limited results whether the syndrome is present or absent however machine learning on fuzzy transformed biological dataset provides a broader spectrum of diagnosis consisting of a third class depicting that PCOS might be present which would ultimately alert a patient to take preventive measures to minimize the chances of syndrome development in future.

Prioritization of control measures in leakage scenario using Hendershot theory and FBWM-TOPSIS.

Currently, there is increasing concern about the safety and leakage of process industries. Therefore, the present study aims to prioritize control measures before and after the leakage scenario by using the Hendershot theory and MCDM techniques. In this study, two proactive and reactive layers were selected before and after leakage of tanks, respectively. Then, criteria and alternatives were selected to perform fuzzy TOPSIS (FTOPSIS) and find the best alternative based on the literature review and Hendershot approach. The linear model of the fuzzy Best-Worst method (FBWM) was constructed and resolved using Lingo 17 software. Subsequently, criteria were assigned weights based on thorough calculations of the inconsistency rate. The weight of study experts was equal to 0.25. The results of FBWM showed that the reliability index with a weight of 0.3727 was ranked first and the inconsistency rate ([Formula: see text]) was calculated to be equal to 0.040. Inherent Safety Design (ISD) (0.899) and passive safety (0.767) also ranked first before and after tank leaks, respectively. Using the FBWM method leads to fewer pairwise comparisons and at the same time more stability. Although ISD and passive strategies are more valid and strict, elements of all strategies are necessary for a comprehensive process safety management program.

A novel decision support system for proactive risk management in healthcare based on fuzzy inference, neural network and support vector machine.

BACKGROUND: The nature of activities practiced in healthcare organizations makes risk management the most crucial issue for decision-makers, especially in developing countries. New technologies provide effective solutions to support engineers in managing risks. PURPOSE: This study aims to develop a Decision Support System (DSS) adapted to the healthcare constraints of developing countries that enables the provision of decisions about risk tolerance classes and prioritizations of risk treatment. METHODS: Failure Modes and Effects Analysis (FMEA) is a popular method for risk assessment and quality improvement. Fuzzy logic theory is combined with this method to provide a robust tool for risk evaluation. The fuzzy FMEA provides fuzzy Risk Priority Number (RPN) values. The artificial neural network is a powerful algorithm used in this study to classify identified risk tolerances. The risk treatment process is taken into consideration in this study by improving FMEA. A new factor is added to evaluate the feasibility of correcting the intolerable risks, named the control factor, to prioritize these risks and start with the easiest. The new factor is combined with the fuzzy RPN to obtain intolerable risk prioritization. This prioritization is classified using the support vector machine. FINDINGS: Results prove that our DSS is effective according to these reasons: (1) The fuzzy-FMEA surmounts classical FMEA drawbacks. (2) The accuracy of the risk tolerance classification is higher than 98%. (3) The second fuzzy inference system developed (the control factor for intolerable risks with the fuzzy RPN) is useful because of the imprecise situation. (4) The accuracy of the fuzzy-priority results is 74% (mean of testing and training data). CONCLUSIONS: Despite the advantages, our DSS also has limitations: There is a need to generalize this support to other healthcare departments rather than one case study (the sterilization unit) in order to confirm its applicability and efficiency in developing countries.

Resilience evaluation of low-carbon supply chain based on improved matter-element extension model.

How to evaluate the resilience level and change trend of supply chain is an important research direction in current supply chain management practice. This paper proposes a new method of supply chain resilience assessment based on hesitant fuzzy linguistic term set (HFLTS) and matter element extension theory. Firstly, based on the research status quo at home and abroad, a low-carbon enterprise supply chain resilience assessment index system is established, which includes six first-level indicators and corresponding 21 second-level indicators of product supply resilience, resource resilience, partner resilience, information response resilience, financial resilience and knowledge resilience. Secondly, HFLTS was used to collect expert opinions and Ordered Weighted Arithmetic (OWA) to calculate the expert composite language, by which the fuzzy evaluation matrix of supply chain resilience assessment indicators was obtained. Once again, the resilience indicator weights are determined based on a game-theoretic portfolio assignment method combining the best-worst method (BWM) and the CRITIC method. Finally, the nearness degree function is combined with the extension comprehensive evaluation method to improve the matter element extension model, and the supply chain resilience assessment model of low-carbon enterprises based on the game theory combination assignment-improved matter element extension is established. Taking X low-carbon enterprise as an example, the evaluation results show that the supply chain resilience level of this enterprise is II, and the eigenvalue of the grade variable is 2.69, and the supply chain resilience is shifting to III, and the supply chain resilience is shifting to III, which indicates that the supply chain resilience of this enterprise is being enhanced. Therefore, the improved matter element extension not only ensures the accuracy of the evaluation results, but also has higher prediction accuracy.

Dynamic analysis of a fuzzy Bobwhite quail population model under g-division law.

This paper is concerned with a kind of Bobwhite quail population model x n + 1 = A + B x n + x n x n - 1 x n - 2 , n = 0 , 1 , ⋯ , where the parameters and initial values are positive parabolic fuzzy numbers. According to g-division of fuzzy sets and based on the symmetrical parabolic fuzzy numbers, the conditional stability of this model is proved. Besides the existence, boundedness and persistence of its unique positive fuzzy solution. When some fuzzy stability conditions are satisfied, the model evolution exhibits oscillations with return to a fixed fuzzy equilibrium no matter what the initial value is. This phenomena provided a vivid counterexample to Allee effect in density-dependent populations of organisms. As a supplement, two numerical examples with data-table are interspersed to illustrate the effectiveness. Our findings have been verified precise with collected northern bobwhite data in Texas, and will help to form some efficient density estimates for wildlife populations of universal applications.

Wavelet scattering transform and entropy features in fluorescence spectral signal analysis for cervical cancer diagnosis.

Cervical cancer is a prevalent malignant tumor within the female reproductive system and is regarded as a prominent cause of female mortality on a global scale. Timely and precise detection of various phases of cervical cancer holds the potential to substantially enhance both the rate of successful treatment and the duration of patient survival. Fluorescence spectroscopy is a highly sensitive method for detecting the biochemical changes that arise during cancer progression. In our study, fluorescence spectral data is collected from a diverse group of 110 subjects. The potential of the scattering transform technique for the purpose of cancer detection is explored. The processed signal undergoes an initial decomposition into scattering coefficients using the wavelet scattering transform (WST). Subsequently, the scattering coefficients are subjected to computation for fuzzy entropy, dispersion entropy, phase entropy, and spectral entropy, for effectively characterizing the fluorescence spectral signals. These combined features generated through the proposed approach are then fed to 1D convolutional neural network (CNN) classifier to classify them into normal, pre-cancerous, and cancerous categories, thereby evaluating the effectiveness of the proposed methodology. We obtained mean classification accuracy of 97% using 5-fold cross-validation. This demonstrates the potential of combining WST and entropic features for analyzing fluorescence spectroscopy signals using 1D CNN classifier that enables early cancer detection in contrast to prevailing diagnostic methods.