Browsing by Author "Ahmadian, Ali"

Now showing 1 - 20 of 28

Citation Count: 0
An adaptive algorithm for numerically solving fractional partial differential equations using Hermite wavelet artificial neural networks
(Elsevier, 2024) Ali, Amina; Senu, Norazak; Wahi, Nadihah; Almakayeel, Naif; Ahmadian, Ali
This study aims to develop a new strategy for solving partial differential equations with fractional derivatives (FPDEs) using artificial neural networks (ANNs). Numerical solutions to FPDEs are obtained through the Hermite wavelet neural network (HWNN) model. The Caputo fractional derivative is consistently applied throughout the research to address fractional -order partial differential problems. To enhance computational efficiency and expand the input pattern, the hidden layer is removed. A neural network (NN) model featuring a feed -forward architecture and error -back propagation without supervision is employed to optimize network parameters and minimize errors. Numerical illustrations are presented to demonstrate the effectiveness of this approach in preserving computational efficiency while solving FPDEs.
Citation Count: 0
An advanced scheme based on artificial intelligence technique for solving nonlinear riccati systems
(Springer Heidelberg, 2024) Admon, Mohd Rashid; Senu, Norazak; Ahmadian, Ali; Majid, Zanariah Abdul
Recently, one artificial intelligence technique, known as artificial neural network (ANN), has brought advanced development to the arena of mathematical research. It competes effectively with other traditional methods in providing accurate solutions for fractional differential equations (FDEs). This work aims to implement a feedforward ANN with two hidden layers to solve nonlinear systems based on the fractional Riccati differential equation (FRDE). The network parameters are trained using the Adam optimization method with the aid of automatic differentiation. A vectorization algorithm is designated for the selected step to make the computation process more efficient. Two different initial value problems in integer-order derivatives and fractional-order derivatives are discussed. Numerical results demonstrate that the proposed method not only closely matches the exact solutions and reference solutions but also is more accurate than other existing methods.
Citation Count: 0
AI-based visual speech recognition towards realistic avatars and lip-reading applications in the metaverse
(Elsevier, 2024) Li, Ying; Hashim, Ahmad Sobri; Lin, Yun; Nohuddin, Puteri N. E.; Venkatachalam, K.; Ahmadian, Ali
The metaverse, a virtually shared digital world where individuals interact, create, and explore, has witnessed rapid evolution and widespread adoption. Communication between avatars is crucial to their actions in the metaverse. Advances in natural language processing have allowed for significant progress in producing spoken conversations. Within this digital landscape, the integration of Visual Speech Recognition (VSR) powered by deep learning emerges as a transformative application. This research delves into the concept and implications of VSR in the metaverse. This study focuses on developing realistic avatars and a lip-reading application within the metaverse, utilizing Artificial Intelligence (AI) techniques for visual speech recognition. Visual Speech Recognition in the metaverse refers to using deep learning techniques to comprehend and respond to spoken language, relying on the visual cues provided by users' avatars. This multidisciplinary approach combines computer vision and natural language processing, enabling avatars to understand spoken words by analyzing the movements of their lips and facial expressions. Key components encompass the collection of extensive video datasets, the employment of 3D Convolutional Neural Networks (3D CNNs) combined with ShuffleNet and Densely Connected Temporal Convolutional Neural Networks (DC-TCN) called (CFS-DCTCN) to model visual and temporal features, and the integration of contextual understanding mechanisms. The two datasets Wild (LRW) dataset and the GRID Corpus datasets are utilized to validate the proposed model. As the metaverse continues its prominence, integrating Visual Speech Recognition through deep learning represents a pivotal step towards forging immersive and dynamic virtual worlds where communication transcends physical boundaries. This paper contributes to the foundation of technology-driven metaverse development and fosters a future where digital interactions mirror the complexities of human communication. The proposed model achieves 99.5 % on LRW and 98.8 % on the GRID dataset.
Citation Count: 0
An appropriate artificial intelligence technique for plastic materials recycling using bipolar dual hesitant fuzzy set
(Nature Portfolio, 2024) Ramya, Lakshmanaraj; Thilagasree, Chakkarapani Sumathi; Jayakumar, Thippan; Peter, Antony Kishore; Akhir, Emelia Akashah P.; Ferrara, Massimiliano; Ahmadian, Ali
Plastic recycling has become more important than ever as the globe struggles with growing environmental issues. This research explores the significant environmental impact of recycling plastic and its growing relevance. The pervasive material known as plastic presents a complex risk to both human health and ecosystems in contemporary life. It exacerbates problems including marine pollution, habitat damage, and wildlife entanglement because of its persistence in landfills and seas, which leads to serious ecological deterioration. In addition, producing plastic uses a lot of energy and produces a lot of greenhouse gas emissions, which exacerbate climate change. Through the use of multi-criteria decision making (MCDM), this study emphasizes how vital it is to support recycling activities in order to protect the environment and promote a sustainable future. The elimination and choice ex-pressing reality (ELECTRE) approach is used to rank the alternatives in this proposed research study that employs bipolar dual hesitant fuzzy sets (BDHFs). The most efficient and versatile outranking method for making decisions is the BDHF-ELECTRE approach. The weights of environment, economic, social, technical, and finally safety is computed using the entropy distance metric. The economic factor received the highest score of 0.2945 among the other factors since economic considerations are crucial in choosing the most efficient plastic recycling method, as they ensure sustainability, cost-effectiveness, resource allocation, and overall feasibility in managing plastic waste. The decision-makers determined that the mechanical recycling approach ought to be prioritized over all others for the efficient recycling of plastic waste. The robustness of the system is examined in the sensitive and comparative analyses. The proposed MCDM technique thus presents a viable solution, mitigating the adverse effects of plastic waste by conserving resources, reducing energy consumption, and curbing pollution.
Citation Count: 1
Assessing performance and satisfaction of micro-mobility in smart cities for sustainable clean energy transportation using novel APPRESAL method
(Elsevier Sci Ltd, 2024) Manirathinam, Thangaraj; Narayanamoorthy, Samayan; Geetha, Selvaraj; Ahmadian, Ali; Ferrara, Massimiliano; Kang, Daekook
South Korea signed the Global Methane Pledge to reduce methane emissions by 30% by 2030, updated its Nationally Determined Contribution (NDC) to target a 40% reduction in GHGs (Green House Gas) from 2018 levels by 2030. In addition, South Korea submitted its Long -Term Strategy (LTS) to achieve carbon neutrality by 2050. Nowadays, to mitigate the GHG emission every country explicitly planning to reduce non-renewable energy resource vehicles. The electric vehicle (EV) markets growing rapidly with various technologies, strategies and innovations to support decarbonization. In 2022, by the transportation CO2 (Carbon dioxide) emission report of International Energy Agency (IEA), the cars and vans contributes 48% in the over all CO2 emissions. Increasing the electric micro -mobility service would be one of the best effective approach in accordance to reduce CO2 emission. This research study support to reduce the GHG emission by increasing the clean energy vehicle. A case study conducted to analyze firm -wise e -scooter sharing service performance and its satisfaction in smart cities of South Korea. Lacking in the consistent good quality and performance affects the number of electric vehicle users. Hence, electric vehicle firm should focus into their product better performance and quality. This research supports to analyze the e -scooter based on the various criteria from the user's perspective. This research study helps to firms to identify their lacking criteria and improve their quality and performance. We considered the performance, accessibility, tangibility, reliability and responsiveness factors which affects user's perspective in e -scooter sharing services. A survey was conducted over sixty user's for different e -scooter services with twenty four factors. Generally, MCDM (Multi -Criteria Decision -Making) techniques holds two phases to determine the weight of the criteria and another phase to ranking the alternatives. The existing MCDM techniques lacks to handle the user' satisfaction index analysis and not considering the influence grade of each factors in the analysis. To overcome this draw back and analyze the micro -mobility services based over the user's point of view, we introduced a novel fuzzy based MCDM method name as Approach for Preference, Performance and Ranking Evaluation with SAtisfaction Level (APPRESAL) approach. The findings show that Lime, a micro -mobility firm, outperformed other firms with high -quality service and user satisfaction, followed by Wind, XingXing, Alpaca, and Beam. The influences of defected factors from the accessibility, reliability, responsiveness, and assurance dimensions had an adverse effect on quality of firm's micro -mobility service with unsatisfactory performance.
Citation Count: 0
An augmented fuzzy decision support system to analyse compatible cosmetic face masks for various complexions
(Wiley, 2024) Brainy, Joseph Raj Vikilal Joice; Narayanamoorthy, Samayan; Kalaiselvan, Samayan; Saraswathy, Ranganathan; Ahmadian, Ali; Senu, Norazak; Jeon, Jeonghwan
Beauty face masks (BFM) are becoming increasingly popular among both men and women since they provide quick refreshment and nurture the skin. Given the wide range of skin types and the chemicals used in their formulation, it can be difficult to find a product that not only complements the skin type but is also free of potentially harmful ingredients that could endanger the consumer's health. When dealing with ambiguous situations, the multi-attribute decision making (MADM) approach combined with fuzzy set theory is more effective. Type-2 fuzzy sets (T2FS) provide greater flexibility in dealing with uncertainty in real-world issues since they are characterised by a main and secondary membership function. In this research, we present the innovative idea of type-2 linear diophantine fuzzy set (T2LDFS) as an intriguing tool for capturing expert reluctance about an issue. For analysing the discussed problem, a hybrid fuzzy VIKOR enhanced with the proposed fuzzy logic is suggested. A sensitivity and comparative analysis is carried out to establish the validity of the recommended approach.
Citation Count: 1
A bipolar intuitionistic fuzzy decision-making model for selection of effective diagnosis method of tuberculosis
(Elsevier, 2024) Natarajan, Ezhilarasan; Salahshour, Soheıl; Saraswathy, Ranganathan; Narayanamoorthy, Samayan; Salahshour, Soheil; Ahmadian, Ali; Kang, Daekook
Objectives: Tuberculosis (TB) is a contagious illness caused by Mycobacterium tuberculosis. The initial symptoms of TB are similar to other respiratory illnesses, posing diagnostic challenges. Therefore, the primary goal of this study is to design a novel decision-support system under a bipolar intuitionistic fuzzy environment to examine an effective TB diagnosing method. Methods: To achieve the aim, a novel fuzzy decision support system is derived by integrating PROMETHEE and ARAS techniques. This technique evaluates TB diagnostic methods under the bipolar intuitionistic fuzzy context. Moreover, the defuzzification algorithm is proposed to convert the bipolar intuitionistic fuzzy score into crisp score. Results: The proposed method found that the sputum test (T3) is the most accurate in diagnosing TB. Additionally, comparative and sensitivity analyses are derived to show the proposed method's efficiency. Conclusion: The proposed bipolar intuitionistic fuzzy sets, combined with the PROMETHEE-ARAS techniques, proved to be a valuable tool for assessing effective TB diagnosing methods.
Citation Count: 0
Centroid and Graded Mean Ranking Methods for Intuitionistic Trapezoidal Dense Fuzzy Set to Solve MCDM Problems of Robot Selection
(Springer Heidelberg, 2024) Sampathkumar, Swethaa; Augustin, Felix; Narayanamoorthy, Samayan; Ahmadian, Ali; Ferrara, Massimiliano; Kang, Daekook
Fuzzy ranking plays a vital role in decision-making problems and various fuzzy applications. There are plenty of ranking methods that are used to rank fuzzy numbers. However, they fail to give satisfactory results in certain situations due to the complexity of the problem. In this present study, an attempt has been made to introduce four types of ranking methods in the field of intuitionistic dense fuzzy (IDF) depending on centroid and graded mean ranking. Also, arithmetic operations based on lambda 1,lambda 2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda _1, \lambda _2$$\end{document}-cuts, fuzzy numbers, and extension principles are defined for IDF environment. A model is framed to rank MCDM problems, which are aggregated using a weighted aggregation operator and ordered using the proposed and extended ranking methods. To illustrate the proposed MCDM model under the field of IDF, the problem of robot selection is taken for war fighter robots and exoskeleton robots to help and replace humans in war and help assistive walking patients with spinal cord injuries. The result reveals that the Ripsaw and Rewalk emerge as preferable options for substituting humans in the contexts of war fighters and exoskeleton robots, respectively. To analyze the effectiveness of the ranking results, comparative and sensitivity analyses are examined. Thus, the results provide a satisfactory output.
Citation Count: 0
Deep prediction on financial market sequence for enhancing economic policies
(Springer int Publ Ag, 2024) Salahshour, Soheıl; Salimi, Mehdi; Tehranian, Kian; Erfanibehrouz, Niloufar; Ferrara, Massimiliano; Ahmadian, Ali
Numerous sectors are significantly impacted by the quick advancement of image and video processing technologies. Investors can kind knowledgeable savings choices based on the examination and projection of financial bazaar income, and the government can create accurate policies for various forms of economic control. This study uses an artificial rabbits optimization algorithm in image processing technology to examine and forecast the returns on financial markets and multiple indexes using a deep-learning LSTM network. This research uses the time series technique to record the regional correlation properties of financial market data. Convolution pooling in LSTM is then used to gather significant details concealed in the time sequence information, generate the data's tendency bend, and incorporate the structures using technology for image processing to ultimately arrive at the forecast of the economic sector's moment series earnings index. A popular artificial neural network used in time series examination is the long short-term memory (LSTM) network. It can accurately forecast financial marketplace values by processing information with numerous input and output timesteps. The correctness of financial market predictions can be increased by optimizing the hyperparameters of an LSTM model using metaheuristic procedures like the Artificial Rabbits Optimization Algorithm (ARO). This research presents the development of an enhanced deep LSTM network with the ARO method (LSTM-ARO) for stock price prediction. According to the findings, the research's deep learning system for financial market series prediction is efficient and precise. Data analysis and image processing technologies offer practical approaches and significantly advance finance studies.
Citation Count: 0
A dimensionally reduction approach to study kink soliton and its fission and fusion process of (3+1)-dimensional KdV-CDG equation
(Wiley, 2024) Rahman, Mati Ur; Sun, Mei; Salimi, Mehdi; Ahmadian, Ali
The Hirota bilinear (HB) is a powerful and widely used technique to find various types of solitons of integrable systems. In this manuscript, we implement HB technique to find bilinear form of a dimensionally reduced (3+1)-dimensional KdV-Calogero-Bogoyavlenskii-Schiff (KdV-CBS) equation at z = x, z = y, and z = t. We present various results for distinct auxiliary function to study kink solitons and its fission and fusion dynamics. The MATLAB-2020 is used to display all the results via 3D and line 2D graphs for appropriate values of parameters. These findings provide a strong new insight into the nonlinear features of the model and lay the foundation for future studies in soliton dynamics and nonlinear events in related systems.
Citation Count: 0
The effects of bioconvection, non-Fourier heat flux, and thermal radiations on Williamson nanofluids and Maxwell nanofluids transportation with prescribed thermal conditions
(Wiley-v C H verlag Gmbh, 2024) Afzal, Saima; Siddique, Imran; Abdal, Sohaib; Hussain, Sajjad; Salimi, Mehdi; Ahmadian, Ali
The utilization of nanoentities in common fluids has opened new opportunities in the area of heat transportation. The rising requirements to enhance the efficiency of compact heat exchangers can be achieved by using various nanofluids. In this article, the thermal output of Maxwell and Williamson nanofluids transport over a prolonging sheet with bioconvection of self-motivated organisms is scrutinized. A magnetic flux and the porous effects of a medium influence the flow of fluids. The fundamental principles for conservation of mass, concentration, momentum, and energy yield a nonlinear set of partial differential equations that can then be altered into ordinary differential form. A heat transfer flux is presented along with temperature boundary conditions, PST, and PHF (prescribed surface temperature and prescribed heat flux). The numerical results are acquired by executing the Runge-Kutta method with a shooting procedure in MATLAB coding. By fluctuating the inputs of influential variables of the dependent functions, a precise overview of the scheme is acquired. It can be seen that velocity decreases with the rising values of buoyancy ratio, magnetic force, Raleigh number, and porosity. Also, the temperature of the fluids begins to rise directly with the rising values of thermophoresis and Brownian motion parameters. The present study addresses bioconvection, non-Fourier heat flow, and thermal radiations while combining the special properties of Williamson and Maxwell nanofluids. The field of biomedical engineering may benefit from this study, particularly with regard to therapies for hyperthermia and drug delivery systems. This study can be useful in cutting-edge cooling systems, bioengineering, solar energy conversion and biotechnology.
Citation Count: 0
Efficient scheme for a category of variable-order optimal control problems based on the sixth-kind Chebyshev polynomials
(de Gruyter Poland Sp Z O O, 2024) Salahshour, Soheıl; Hosseini, Kamyar; Salahshour, Soheil; Baleanu, Dumitru; Ahmadian, Ali; Park, Choonkil
The main goal of the present study is to introduce an operational collocation scheme based on sixth-kind Chebyshev polynomials (SCPs) to solve a category of optimal control problems involving a variable-order dynamical system (VODS). To achieve this goal, the collocation method based on SCPs, the pseudo-operational matrix for the fractional integral operator, and the dual operational matrix are adopted. More precisely, an algebraic equation is obtained instead of the objective function and a system of algebraic equation is derived instead of the VODS. The constrained equations obtained from joining the objective function to the VODS are ultimately optimized using the method of the Lagrange multipliers. Detailed convergence analysis of the suggested method is given as well. Four illustrative examples along with several tables and figures are formally provided to support the efficiency and preciseness of the numerical scheme.
Citation Count: 0
An emerging network for COVID-19 CT-scan classification using an ensemble deep transfer learning model
(Elsevier, 2024) Yousefpanah, Kolsoum; Ebadi, M. J.; Sabzekar, Sina; Zakaria, Nor Hidayati; Osman, Nurul Aida; Ahmadian, Ali
Over the past few years, the widespread outbreak of COVID-19 has caused the death of millions of people worldwide. Early diagnosis of the virus is essential to control its spread and provide timely treatment. Artificial intelligence methods are often used as powerful tools to reach a COVID-19 diagnosis via computed tomography (CT) samples. In this paper, artificial intelligence-based methods are introduced to diagnose COVID-19. At first, a network called CT6-CNN is designed, and then two ensemble deep transfer learning models are developed based on Xception, ResNet-101, DenseNet-169, and CT6-CNN to reach a COVID-19 diagnosis by CT samples. The publicly available SARS-CoV-2 CT dataset is utilized for our implementation, including 2481 CT scans. The dataset is separated into 2108, 248, and 125 images for training, validation, and testing, respectively. Based on experimental results, the CT6-CNN model achieved 94.66% accuracy, 94.67% precision, 94.67% sensitivity, and 94.65% F1-score rate. Moreover, the ensemble learning models reached 99.2% accuracy. Experimental results affirm the effectiveness of designed models, especially the ensemble deep learning models, to reach a diagnosis of COVID-19.
Citation Count: 1
Enabling business sustainability for stock market data using machine learning and deep learning approaches
(Springer, 2024) Divyashree, S.; Joshua, Christy Jackson; Md, Abdul Quadir; Mohan, Senthilkumar; Abdullah, A. Sheik; Mohamad, Ummul Hanan; Ahmadian, Ali
This paper introduces AlphaVision, an innovative decision support model designed for stock price prediction by seamlessly integrating real-time news updates and Return on Investment (ROI) values, utilizing various machine learning and deep learning approaches. The research investigates the application of these techniques to enhance the effectiveness of stock trading and investment decisions by accurately anticipating stock prices and providing valuable insights to investors and businesses. The study begins by analyzing the complexities and challenges of stock market analysis, considering factors like political, macroeconomic, and legal issues that contribute to market volatility. To address these challenges, we proposed the methodology called AlphaVision, which incorporates various machine learning algorithms, including Decision Trees, Random Forest, Na & iuml;ve Bayes, Boosting, K-Nearest Neighbors, and Support Vector Machine, alongside deep learning models such as Multi-layer Perceptron (MLP), Artificial Neural Networks, and Recurrent Neural Networks. The effectiveness of each model is evaluated based on their accuracy in predicting stock prices. Experimental results revealed that the MLP model achieved the highest accuracy of approximately 92%, outperforming other deep learning models. The Random Forest algorithm also demonstrated promising results with an accuracy of around 84.6%. These findings indicate the potential of machine learning and deep learning techniques in improving stock market analysis and prediction. The AlphaVision methodology presented in this research empowers investors and businesses with valuable tools to make informed investment decisions and navigate the complexities of the stock market. By accurately forecasting stock prices based on news updates and ROI values, the model contributes to better financial management and business sustainability. The integration of machine learning and deep learning approaches offers a promising solution for enhancing stock market analysis and prediction. Future research will focus on extracting more relevant financial features to further improve the model's accuracy. By advancing decision support models for stock price prediction, researchers and practitioners can foster better investment strategies and foster economic growth. The proposed model holds potential to revolutionize stock trading and investment practices, enabling more informed and profitable decision-making in the financial sector.
Citation Count: 0
Enabling business sustainability for stock market data using machine learning and deep learning approaches (AUG, 10.1007/s10479-024-06118-x, 2024 )
(Springer, 2024) Divyashree, S.; Joshua, Christy Jackson; Quadir, Md Abdul; Mohan, Senthilkumar; Abdullah, A. Sheik; Mohamad, Ummul Hanan; Ahmadian, Ali
[No Abstract Available]
Citation Count: 0
An end-to-end categorizing strategy for green energy sources: Picture q-rung orthopair fuzzy EXPROM-II: MADA approach
(Elsevier, 2024) Parthasarathy, Thirumalai Nallasivan; Narayanamoorthy, Samayan; Sulaiman, Riza; Elamir, Amir Mohamed; Ahmadian, Ali; Kang, Daekook
In today's world, people's need for sustainable energy is crucial. In India, people utilizing 73% of electricity from fossil fuels is the biggest hazard to the environment. In order to partly gratify the nation, policymakers have decided to invest in sustainability renewable energy sources rather than non-renewable resources for the production of energy. There five distinct kinds of green energy sources. The research key contribution is selecting the best renewable energy sources among the five different categories. Therefore, here we form a mathematical fuzzy model to identify the decision received from hesitating knowledge in the form of an Picture Q -rung orthopair fuzzy set (PQROFS) is engaged to handle the uncertain data in decision makers' thoughts. A gathering of relevant judgment Multi -Attribute Decision Analysis (MADA) is employed. Attributes play a prominent role in DM for ranking the alternatives. Here we have twelve attributes and five alternatives. An objective CRiteria Importance Through Intercriteria Correlation (CRITIC) method is employed for attributes priority determination and EXtension of the PROMethee-II (EXPROM-II) method an method is determining the alternative from the preference between each alternative and novel methodology. Ultimately, to validate the proposed results, compared the proposed results with other existing MCDA method results.
Citation Count: 0
An enhanced fuzzy IDOCRIW-COCOSO multi-attribute decision making algorithm for decisive electric vehicle battery recycling method
(Elsevier, 2024) Parthasarathy, Thirumalai Nallasivan; Salahshour, Soheıl; Thilagasree, Chakkarapani Sumathi; Marimuthu, Palanivel Rubavathi; Salahshour, Soheil; Ferrara, Massimiliano; Ahmadian, Ali
An adaptation to electric mobility quickens waste management tasks for recyclers to end-to-end processing of marketed electric vehicle batteries. Especially lithium-ion batteries play a prominent role in electrifying the world for e-transport technology innovation. This research offers a multi-attribute decision-making (MADM) structure for finding the best performance e-vehicle recycling techniques. The structured algorithm combines an advanced stratified MADM strategy with e-transportation recycling techniques. The optimal algorithm evaluates the results of qualitative attributes and alternatives using a weighted-ranking MADM approach. The importance of attributes is calculated using a blending of dual objective-weighted approaches: entropy and CILOS methods, viz., the aggregated IDOCRIW approach. The ranking of alternatives is determined through the COCOSO method in a hesitation environment. The q-rung orthopair picture fuzzy set (q-ROPFS) is used to cope with uncertainty and vagueness in decision analysis. The feasibility and robustness of the suggested algorithm were validated through different MADM methods and by altering crucial ranking-dependent parameters in the problem.
Citation Count: 0
Evolutionary game theoretical approach for reducing carbon emissions in a complex supply chain organization
(Emerald Group Publishing Ltd, 2024) Bao, Zongke; Wang, Chengfang; Innab, Nisreen; Mouldi, Abir; Ciano, Tiziana; Ahmadian, Ali
PurposeOur research explores the intricate behavior of low-carbon supply chain organizations in an ever-evolving landscape, emphasizing the profound implications of government-mandated low-carbon policies and the growing low-carbon market. Central to our exploration is applying a combined game theory model, merging Evolutionary Game Theory (EGT) with the Shapley Value Cooperative Game Theory Approach (SVCGTA).Design/methodology/approachWe establish a two-tier supply chain featuring retailers and manufacturers within this novel framework. We leverage an integrated approach, combining strategic Evolutionary Game Theory and Cooperative Game Theory, to conduct an in-depth analysis of four distinct low-carbon strategy combinations for retailers and manufacturers.FindingsThe implications of our findings transcend theoretical boundaries and resonate with a trinity of economic, environmental and societal interests. Our research goes beyond theoretical constructs to consider real-world impacts, including the influence of changes in government low-carbon policies, the dynamics of consumer sensitivities and the strategic calibration of retailer carbon financing incentives and subsidies on the identified ESS. Notably, our work highlights that governments can effectively incentivize organizations to reduce carbon emissions by adopting a more flexible approach, such as regulating carbon prices, rather than imposing rigid carbon caps.Originality/valueOur comprehensive analysis reveals the emergence of an Evolutionary Stability Strategy (ESS) that evolves in sync with the phases of low-carbon technology development. During the initial stages, our research suggests that manufacturers or retailers adopt low-carbon behavior as the optimal approach.
Citation Count: 0
An identification of optimal waste disposal method for dumpsite remediation using the Fermatean fuzzy multi-criteria decision-making method
(Springer Heidelberg, 2024) Jeon, Jeonghwan; Manirathinam, Thangaraj; Geetha, Selvaraj; Narayanamoorthy, Samayan; Salimi, Mehdi; Ahmadian, Ali
Improperly managed wastes that have been dumped in landfills over the years pose various challenges, but they also offer potential benefits. The feasibility of recycling such waste depends on the type of wastes, the condition of dumpsites, and the technology implemented for disposal. The selection of an alternative waste disposal method from the many available options for dumpsite remediation is a complex decision-making process among experts. The primary aim of this study is to assist in an extended multi-criteria decision-making (MCDM) method to reduce complexity in the proposed dumpsite remediation problem influenced by multiple criteria and to identify the optimal waste disposal method. Data uncertainties are managed with the proposed Fermatean fuzzy preference scale, and the importance of all socio-economic criteria is assessed using the full consistency method (FUCOM). The final ranking results of the weighted aggregated sum product assessment (WASPAS) method identify that the Waste-to-Energy (WtE) process could play a significant role in the disposal of land-filled unprocessed wastes, promoting sustainable waste management. Meanwhile, the methodology explores the idea that financial and logistical constraints may limit the feasibility of large-scale recycling efforts. This combination of environmental science and decision science addresses real-world challenges, helping municipal solid waste management authorities implement sustainable waste management practices.
Citation Count: 0
Intelligent cardiovascular disease diagnosis using deep learning enhanced neural network with ant colony optimization
(Nature Portfolio, 2024) Xia, Biao; Innab, Nisreen; Kandasamy, Venkatachalam; Ahmadian, Ali; Ferrara, Massimiliano
To identify patterns in big medical datasets and use Deep Learning and Machine Learning (ML) to reliably diagnose Cardio Vascular Disease (CVD), researchers are currently delving deeply into these fields. Training on large datasets and producing highly accurate validation results is exceedingly difficult. Furthermore, early and precise diagnosis is necessary due to the increased global prevalence of cardiovascular disease (CVD). However, the increasing complexity of healthcare datasets makes it challenging to detect feature connections and produce precise predictions. To address these issues, the Intelligent Cardiovascular Disease Diagnosis based on Ant Colony Optimisation with Enhanced Deep Learning (ICVD-ACOEDL) model was developed. This model employs feature selection (FS) and hyperparameter optimization to diagnose CVD. Applying a min-max scaler, medical data is first consistently prepared. The key feature that sets ICVD-ACOEDL apart is the use of Ant Colony Optimisation (ACO) to select an optimal feature subset, which in turn helps to upgrade the performance of the ensuring deep learning enhanced neural network (DLENN) classifier. The model reforms the hyperparameters of DLENN for CVD classification using Bayesian optimization. Comprehensive evaluations on benchmark medical datasets show that ICVD-ACOEDL exceeds existing techniques, indicating that it could have a significant impact on CVD diagnosis. The model furnishes a workable way to increase CVD classification efficiency and accuracy in real-world medical situations by incorporating ACO for feature selection, min-max scaling for data pre-processing, and Bayesian optimization for hyperparameter tweaking.