Enhanced Wetland Classification using Deep Learning based Fusion Approach on Multi-Source Remote Sensing Images

Bahromjon; Maha

doi:https://doi.org/10.54216/IJAACI.060102

International Journal of Neutrosophic Science | 2025

Evaluation of the Use of Whey in the Production of Aromatized Beverages by Neutrosophic Multicriteria Analysis

In this study, a thorough evaluation of the impact of whey use in the production of flavored beverages was carried out, using the neutrosophic analysis of variance method as the central research tool· The research focused on analyzing how whey, a byproduct of cheese production, could be used effectively in the production of flavored beverages, exploring its possible benefits and challenges from a comprehensive and multidisciplinary perspective· Through a series of experiments and exhaustive analyses, different variants of flavored beverages were examined, evaluating both their sensory quality and physical-chemical stability, and compared with beverages made without whey, revealing valuable insights about their viability and potential in the beverage industry· food and drinks· The findings of this study not only offer a deeper understanding of the role of whey in the production of flavored beverages, but also highlight the importance of the variance neutrosophic approach in evaluating this complex relationship· By integrating sensory analyzes with physicochemical measurements and stability considerations, a holistic and accurate picture of the effects of whey on the quality and characteristics of beverages could be obtained· These results not only have practical implications for the food industry, but also contribute to the advancement of research in multidimensional analysis methods and their application in the evaluation of innovative and sustainable food products. 

groups

Zoila Eliana Zambrano Ochoa mail -

Gabriela Beatriz Arias Palma mail -

Carmen Amelia Cando Condorcana mail -

Jhony Daniel Lema Ramos mail

link https://doi.org/10.54216/IJNS.250131

Volume & Issue

Vol. Volume 25 / Iss. Issue 1

Details open_in_new

Journal of International Economics Research | 2026

Evaluating the Effectiveness of the Paris Agreement and Challenges to International Climate Cooperation: A Political, Economic, and Justice-Based Analysis

The Paris Agreement (2015) marked a significant change in international climate regulation, as it does not have binding targets and instead contains a flexible, bottom-up system of nationally determined contributions (NDCs). Although this construction ensured almost universal participation, its use of voluntary commitments and lax implementation schemes has constrained its capacity to achieve the profound, fair cuts in emissions to curb warming to 1.5C. This study critically analyzes the effectiveness of the Agreement, its institutional structure, the dynamics of ambition, transparency framework, Article 6 market mechanism and finance. Basing his analysis on the prominent scholarly works, global climatic evaluation, and documentation undertaken by the UN, the analysis recognizes political self-interest, economic inequalities, unresolved differentiation, and finance gaps as key obstacles to real international collaboration. These structural vices are more impactful in developing countries. By examining Uzbekistan, a climate-vulnerable, and lower-middle-income Central Asian nation engaged in Article 6, this paper shows how the global challenges are being reflected at national levels, such as conditional NDCs, MRV capacity limitations, and reliance on outside assistance. The results highlight that in the absence of enhanced accountability, scaled and predictable climate finance, operationalized equity under CBDRRC, and hybrid governance, the Paris framework may stay aspirational, as opposed to transformative. The policy recommendations aim to achieve convergence in Article 6, improve domestic surveillance, and apply the principles of just transition to bridge the ambition and equity gap.

groups

Freshta qauomy mail -

Salimova Sevara mail

link https://doi.org/10.54216/JIER.040203

Volume & Issue

Vol. Volume 4 / Iss. Issue 2

Details open_in_new

International Journal of Neutrosophic Science | 2025

Exploring Intuitionistic Fuzzy-Valued Neutrosophic Multiset Technique for High-Dimensional Financial Data Classification in Complex Systems

In decision-making, neutrosophic set allows for the information representation with three membership functions: truth (T), indeterminacy (I), and false (F). Each component in a neutrosophic set has membership, non-membership, and indeterminacy degrees that are independent and range from 0 to 1. This makes neutrosophic set especially suitable in complex decision-making scenarios where information is contradictory, incomplete, or ambiguous, which enables robust and more nuanced analysis and solutions. A large portion of finance companies experience problems handling vast amounts of data. These data are often left unstructured and unorganized. Therefore, it is necessary to classify them to exploit it. Data classification also simplifies to use, locating, and retrieval of information. It becomes vital while handling risk management, legal discovery, data security, and compliance. Therefore, this manuscript presents an Intuitionistic Fuzzy-Valued Neutrosophic Multiset based Financial Data Classification (IFVNMS-FDC) technique in Complex Systems. The main aim of the IFVNMS-FDC technique is to recognize and categorize the financial data into respective classes. To do so, the IFVNMS-FDC technique initially uses min-max scalar as a pre-processing step. Besides, the high-dimensional financial data can be handled by the design of whale optimization algorithm (WOA) based feature selection. Finally, the IFVNMS-FDC technique derives IFVNMS technique for the identification of various classes related to the financial data. A wide-ranging experiments were involved in exhibiting the performance of the IFVNMS-FDC technique. The experimental values depicted that the IFVNMS-FDC method obtains reasonable performance on financial data recognition.

groups

Hafis Hajiyev mail -

Emil Hajiyev mail -

Zarnigor Ilkhamova mail -

Elena Klochko mail -

E. Laxmi Lydia mail

link https://doi.org/10.54216/IJNS.250134

Volume & Issue

Vol. Volume 25 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

Harnessing Single-Valued Linguistic Complex Neutrosophic Set based Arabic Sentiment Classification on Natural Language Processing

Neutrosophic logic (NL) goes further by introducing a third component: indeterminacy. Each logical proposition in NL belongs to three degrees: truth (T), indeterminacy (I), and false (F), each taking value within the range of zero and one. This allows the processing and representation of uncertain, incomplete, and inconsistent data in a superior way. NL finds it beneficial in partially contradictory, partially known, and partially unknown scenarios, it becomes an effective instrument for applications in fields such as information fusion, artificial intelligence, and data analysis, where logical framework might be unsuccessful in handling the nuances and complexities of real-time data. Recently, Arabic sentiment analysis has become a hot research topic, which mainly intends to recognize sentiments that exist in Arabic social media. Therefore, this study introduces a Single-Valued Linguistic Complex Neutrosophic Set based Arabic Sentiment Classification (SVLCNS-ASC) technique on NLP applications. The presented SVLCNS-ASC technique undergoes Arabic data pre-processing and Glove word embedding process. For sentiment recognition, the SVLCNS-ASC technique applies the SVLCNS model, which enables to identification of various kinds of sentiments. At last, the performance of the SVLCNS model can be boosted by the use of artificial bee colony (ABC) based parameter-tuning approach. The results of the SVLCNS-ASC system has been studied on Arabic database. The experimental values indicate the supremacy of the SVLCNS-ASC approach compared to recent models.

groups

Aigul Sushkova mail -

Alfiya Yarullina mail -

Leysan Akhmetova mail -

Barno Shamuratova mail -

E. Laxmi Lydia mail

link https://doi.org/10.54216/IJNS.250135

Volume & Issue

Vol. Volume 25 / Iss. Issue 1

Details open_in_new

International Journal of Neutrosophic Science | 2025

Integrating Transfer Learning with Neutrosophic Weighted Extreme Learning Machine for Violence Detection in Smart Cities

Neutrosophic logic extends conventional and fuzzy logic (FL) by integrating the concepts of indeterminacy, truth, and falsity, enabling for a further extensive management of uncertainty. In classical binary logic, a statement can be either true or false. FL extends this by adding degree of truth, where a statement is partially true or false. The smart city technology shown to be an effective solution to the problems regarding improved urbanization. The practical applications of a smart city technology to video surveillance relies on the ability of processing and gathering large quantities of live urban data. Violence detection is considered as a major challenge in smart city monitoring.  The required computational power is substantial due to the large volume of video data gathered from the extensive camera network. As a result, the algorithm based on handcrafted features utilizing video and image processing fails to provide a promising solution. Deep Learning (DL) and Deep Neural Networks (DNNs) models are more reliable to handle these data. In this study, we introduce a Transfer Learning with Neutrosophic Weighted Extreme Learning Machine for Violence Detection (TL-NWELMVD) technique in smart cities. The TL-NWELMVD technique aims to recognize the presence of the violence in the smart city environment. In the TL-NWELMVD technique, the features can be extracted using SE-RegNet model. To enhance the performance of the TL-NWELMVD technique, a hyperparameter optimizer using monarch butterfly optimization (MBO) is involved. Finally, the NWELM classifier is applied for the identification of violence in the smart city environment. To investigate the accomplishment of the TL-NWELMVD technique, a widespread investigational outcome is involved. The simulation results portrayed that the TL-NWELMVD technique gains better performance compared to other models.

groups

Nigora Khaytboeva mail -

Sergey Bakhvalov mail -

Veronika Denisovich mail -

Rafina Zakieva mail

link https://doi.org/10.54216/IJNS.250136

Volume & Issue

Vol. Volume 25 / Iss. Issue 1

Details open_in_new

International Journal of Advances in Applied Computational Intelligence | 2024

Enhancing Healthcare Data Classification: Leveraging Machine Learning on ChatGPT-Generated Datasets

With the large-scale language methods namely ChatGPT, there is a chance to explore the use of machine learning (ML) methods on ChatGPT-generated data for classifying healthcare data.  Healthcare data classification gains more significance in extracting and organizing useful insights from the huge volume of medical data available. The ChatGPT-generated data has realistic and different healthcare-based text datasets that can be applied to training classification methods. ML approaches include supervised learning methods as support vector machines (SVMs), and random forests (RF), which can be implemented for classifying the healthcare data. The methods were trained on the ChatGPT-generated data that can be carefully validated and labelled with suitable classes related to the healthcare field. With this motivation, this article presents an automated healthcare data classification-using barnacles mating optimizer with a pyramid neural network (AHDC-BMOPNN) technique. The presented AHDC-BMOPNN technique examines the healthcare data effectually using an ML model with a feature selection process. Primarily, the AHDC-BMOPNN technique exploits min-max data normalization for scaling the input dataset. In addition, the butterfly optimization algorithm-based feature selection (BOA-FS) method is deployed for the selection of optimum feature subset. In this work, the PNN algorithm was utilized for the classification of medical data. Ultimately, the BMO-based hyperparameter tuning process takes place to boost the overall classifier results of the PNN technique. The empirical findings of the AHDC-BMOPNN approach was validated on ChatGPT generated dataset. The simulation values highlight that the AHDC-BMOPNN method and the diverse healthcare text data generated by ChatGPT enhance the ability to extract valuable insights and organize medical information effectively.

groups

Basheer Abd Al Rida Sadiq mail -

Murhaf Obaidi mail

link https://doi.org/10.54216/IJAACI.050203

Volume & Issue

Vol. Volume 5 / Iss. Issue 2

Details open_in_new

International Journal of Advances in Applied Computational Intelligence | 2024

Quantum Sparrow Swarm Optimization with Deep Learning Enabled Deception Detection on Facial Micro Expressions

Deception detection means finding whether an individual is lying or being deceptive depending on cognitive cues, and various behavioural, or physiological. It is a significant domain of research with applications in social psychology, law enforcement, and security. Deception detection relevant to microexpressions includes examining these subtle facial cues for determining whether an individual is being deceptive or lying. Microexpressions can deliver significant cues to detect deception. Deep learning (DL) and Machine learning (ML) models were utilized for finding micro-expressions and are trained for differentiating deceptive statements from genuine ones. Still, it necessitates a diverse and large dataset of video recordings in addition to careful tuning and pre-processing of the DL approach. So, this article presents an Automated Deception Detection on Facial Microexpressions using Improved Sparrow Swarm Optimization with Deep Learning (ADDFM-ISSODL) method. The proposed ADDFM-ISSODL algorithm examines facial micro-expressions effectively for detection of deceptive behaviour. To complete this, developed ADDFM-ISSODL model uses a Gaussian filtering (GF) approach for pre-processing. Besides, ADDFM-ISSODL technique employs MobileNetv3 model for feature extraction and the hyper parameter tuning procedure performed using ISSO algorithm. The ISSO approach was designed by the integration of the standard SSO approach with the quantum evolutionary algorithm (QEA). For deception detection, a probabilistic neural network (PNN) classifier was employed. At last, grasshopper optimization algorithm (GOA) was implemented for parameter tuning of PNN method. The performance validation of ADDFM-ISSODL system tested utilizing facial expression dataset. The simulation outcome stated the greater results of ADDFM-ISSODL algorithm over other methodologies.

groups

Khadija Ben Othman mail

link https://doi.org/10.54216/IJAACI.050204

Volume & Issue

Vol. Volume 5 / Iss. Issue 2

Details open_in_new

International Journal of Advances in Applied Computational Intelligence | 2024

Gorilla Troops Optimizer with Deep Learning-based Multi-Criteria Decision Making for Traffic Analysis in V2X Networks

Multi-criteria decision-making (MCDM) is employed for analyzing traffic in a Vehicle-to-Everything (V2X) network. V2X suggests communication among vehicles and other entities, containing pedestrians, infrastructure, and other vehicles. Traffic analysis and management in V2X networks need effectual decision-making approaches, which assume several conditions. MCDM contains estimating and choosing alternatives depending on several conditions or objectives. In the context of traffic analysis in V2X networks, MCDM algorithms are employed for decision-making concerning traffic flow optimizer, resource allocation, route planning, and congestion management. Deep learning (DL) approaches are trained to analyze massive counts of data gathered from several sources from the V2X network. These sources contain traffic sensors, GPS data, vehicle-to-infrastructure (V2I) communication, and historical traffic designs. By processing this data, DL approaches extract useful insights and create informed decisions depending on various conditions. Therefore, this article proposes a gorilla troops optimizer with deep learning-based MCDM for traffic analysis (GTODL-MCDMTA) technique in the V2X network. The purpose of the GTODL-MCDMTA algorithm is to identify the traffic flow prediction for improving route planning and resource allocation with the consideration of various factors into account. In the presented GTODL-MCDMTA technique, the input data is pre-processed to remove noise and normalize it for analysis. Next, the GTO algorithm is used for the feature selection process. Besides, the deep extreme learning machine (DELM) model is used for the forecast of traffic movement. Finally, the seeker optimization algorithm (SOA) has been utilized for the parameter tuning of the DELM technique. A brief set of simulation outcomes can be applied to emphasize the promising outcomes of the GTODL-MCDMTA technique. The experimental outcome demonstrates the efficiency and efficiency of the GTODL-MCDMTA approach in handling the complexity and dynamic nature of V2X network traffic analysis.

groups

Djamal Lhiani mail -

Othman Al-basheer mail

link https://doi.org/10.54216/IJAACI.050205

Volume & Issue

Vol. Volume 5 / Iss. Issue 2

Details open_in_new

International Journal of Advances in Applied Computational Intelligence | 2024

Optimal Deep Learning-Based Image Classification for IoT-Enabled UAVs in Remote Sensing Applications

Unmanned Aerial Vehicles (UAVs), together with Internet of Things (IoT) technology, have emerged as robust tools for remote sensing (RS) and data collection in different sectors, including environmental monitoring, agriculture, and disaster management. The incorporation of data from UAVs with IoT sensors on the ground can provide a holistic view of the environment, improving the quality of input for image classification. Deep learning (DL) models-based image classification is a key component of IoT-assisted UAVs, transforming them from data collection tools into intelligent decision-making platforms. Especially, Convolutional Neural Networks (CNNs) can automatically recognize objects, patterns, and anomalies in images captured by UAVs. Therefore, the study presents an automated image classification with the Tyrannosaurus optimization algorithm using deep learning (AIR-TROADL) method on the IoT-aided UAV network. The AIR-TROADL technique aims to examine the UAV images for the identification and classification of images into distinct categories. In the projected AIR-TROADL method, an enhanced ShuffleNet model is exploited for feature extraction. Besides, the hyperparameter tuning of enhanced ShuffleNet model can be performed by using TROA, which in turn boosts the classification performance. Finally, the classification of images takes place using the attention-based gated recurrent unit (AGRU) model. A series of simulations have been conducted to exhibit the promising outcome of the AIR-TROADL technique. The comparative outcomes highlighted that the AIR-TROADL method reaches high efficiency over its recent approaches in terms of distinct measures.

groups

Sanjar Mirzaliev mail -

Samandarboy Sulaym mail

link https://doi.org/10.54216/IJAACI.060101

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new

International Journal of Advances in Applied Computational Intelligence | 2024

Enhanced Wetland Classification using Deep Learning based Fusion Approach on Multi-Source Remote Sensing Images

Accurate remote sensing (RS) monitoring of wetland ground objects is an enormous importance for ecological preservation. Wetland classification on multi-source remote sensing images (MS-RSI) includes leveraging data from different sensors for accurately describing and categorizing wetland regions. This method normally incorporates data from infrared, radar, and optical sensors to take a wide-ranging view of wetland features. Advanced image processing methodologies, comprising machine learning (ML) approaches are often implemented for analyzing these multi-source images as well as recognizing spectral and spatial patterns indicative of wetland characteristics. The interaction of various RS data increases the accuracy and robustness of wetland classification models, allowing a more complex analysis of wetland ecosystems and aiding environmental observation, conservation, and control measures. To accomplish effective training for wetland mapping through the RS, it is essential for a significant training data that comprises a numerous array of class variants. In this article, we propose an Enhanced Wetland Classification using a Deep Learning based Fusion Approach (EWC-DLFA) on MS-RSI. The proposed EWC-DLFA technique examines the MS-RSI for wetland classification using the DL model which can be used for other land cover classification types. To accomplish this, the EWC-DLFA technique utilizes the data from multiple sources such as Sentinel-1 (SAR), Landsat-8, Sentinel2 (multi-spectral), and digital elevation model (DEM). In the presented EWC-DLFA technique, a deep convolutional neural network-based EfficientNetB-5 model can be applied for the extraction of features from the multi-source images. For increasing the performance of the EfficientNet-B5 model, the marine predators algorithm (MPA) based hyper parameter tuning process can be applied. Finally, an ensemble of three ML classifiers such as extreme learning machine (ELM), multilayer perceptron (MLP), and gradient boosting machine (GBM) are used to classify the wetland into different types such as fen, bog, marsh, swamps, and upland. The performance of the EWC-DLFA technique can be validated using a large set of simulations. The resultant values pointed out that the EWC-DLFA technique reaches better performance over other models on wetland classification.

groups

Bahromjon Urmanov mail -

Maha Ibrahim mail

link https://doi.org/10.54216/IJAACI.060102

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new