Browse Items (16488 total)
Sort by:
-
Multi Disease Identification in Tomato Plant using CNN and SVM
Tomato is a major trade crop; it is among the most widely consumed crops in daily life. Crop diseases reduce not only the quality of the crops but also their amount of production, thus, detection and identification of the specific diseases is of great importance. Diseases like the Mosaic virus, Bacterial Spot, and Yellow Leaf Curl Virus infect the tomato plant. The advanced detection and classification techniques are mainly employed in the diagnosis of these diseases. This helps in informing the farmers about the types of diseases that attack their crops. In this study, independent CNN and SVM classifiers built to classify the diseases. The CNN model extracts feature such as color and leaf edges from input images- then, it proceeds to classification. For SVM, PCA is applied for feature reduction in order to enhance performance and accuracy before classification. A dataset sourced from plant village has been utilized to train the network CNN and SVM. The proposed neural network model has been applied to categorize 4 types of tomato leaf conditions: one healthy and three diseased types of tomato leaves. The results show that the SVM approach achieves a classification accuracy of 94.33%, whereas the CNN model has slightly higher accuracy of 95.17%. 2025 IEEE. -
Multi objective energy aware integrated cloud scheduling with a consensus-based security
This research presents a multi-objective, energy-aware workflow scheduling framework for heterogeneous cloudedge environments that addresses both efficiency and data integrity challenges. Conventional encryption-based security mechanisms, although effective in protecting data during task offloading, often introduce significant computational and communication overhead, leading to degraded system performance. To overcome this limitation, this work proposes the consensus security-integrity and quality-aware workflow scheduler (CSIQA-WS), which integrates energy-aware scheduling with a lightweight, consensus-driven security mechanism. The model incorporates automatic service management and an attack prevention module to detect and mitigate malicious behavior during inter-node data transmission while maintaining quality of service (QoS) constraints. A dynamic coordination between edge and cloud resources enables efficient workload distribution and robust resource utilization. Experimental evaluation using scientific workflow benchmarks demonstrates that CSIQA-WS significantly reduces processing time and energy consumption compared to existing approaches. The proposed model achieves up to 92.29% reduction in processing time and consistently improves overall QoS while preserving data integrity in dynamic execution environments. These results indicate that CSIQA-WS provides an effective and scalable solution for secure and energy-efficient workflow scheduling in modern cloudedge systems. 2026 Institute of Advanced Engineering and Science. All rights reserved. -
Multi Parameterized Modified Local Binary Pattern for Lung Cancer Detection by Deep Learning Methods
The research work is focusing on developing a classification model for Lung Cancer detection by integrating the image features with Modified Local Binary Pattern (MLBP), Modified Principal Component Analysis (MPCA), newlinesymptoms and Risk factors using Deep Learning methods and converting the image features into three dimensional (3D) images. The aim of this research is to identify the malignant and normal tumours from the Computer newlineTomography (CT) images with improved accuracy. The 2D CT images of Lung Cancer patients have been preprocessed with Median and Gabor filtering methods and watershed segmentation. The CT images are also newlineprocessed with the Zero Component Analysis (ZCA) whitening and Modified Local Binary Pattern. The processed image is used in the research for classification. The Lung Cancer dataset in the research are collected from newlinevarious medical colleges. The dataset contain CT images with Lung Cancer and without Lung Cancer. The research is conducted by integrating the selected Image features, Risk factor and symptoms of Lung Cancer of the newlinesame patients. The Integration using feature selections is carried out with Modified Principal Component Analysis. The Modified Principal Component Analysis is used in the research to reduce the time complexity. The results are evaluated with Gini coefficient, Confusion Matrix parameters and ROC newlinecurve. Two Dimensional (2D) CT images are converted into a Three Dimensional (3D) image for the clarity and the visibility of Lung Cancer nodules. The conversion from 2D to 3D has been using combining two methods, the orthogonality and visualization of 4D rotation. This enabled to find the location of the Lung Cancer from different angle and with different viewpoints. The 3D image shows the location of the Lung Cancer by Four Dimensional (4D) visualization and 3D rotation, thus giving clarity to the newlineexisting 2D images. -
MULTI REFERENCE SKIP-LOT SAMPLING PLAN
Skip-lot sampling plans have become significant in modern quality control due to rising production volumes and the demand for cost-effective inspection methods that will yield high-quality outputs. When inspecting a submitted lot, a skip-lot plan is economically favourable and guarantees high quality. Thus, this approach benefits both producers and consumers. The skip-lot sampling plan generally utilizes the same sampling plan as the reference plans for both skipping and normal inspection. However, using the same plan in both phase favours either the producer or the consumer in the most essential situations. This article introduces a novel approach, the Multi Reference Skip-Lot Sampling Plan with the provision of having two different reference plans in the normal and skipping phases of the skip-lot plan. The paper explores the efficacy of this approach by deriving performance measures using a power series approach. To evaluate the proposed plan, a comparison is made with existing skip-lot sampling plans that use single sampling plans or double sampling plans as reference plans. This comparison is based on operational characteristics and average sample number values, accompanied by graphical representations. The comparative analysis demonstrates that the new plan effectively balances the satisfaction of both producers and consumers. Additionally, the study offers a strategy for selecting the plan parameters using the unity value approach, supported by a table providing unity values. 2025, Gnedenko Forum. All rights reserved. -
Multi-Agent Deep Reinforcement Learning for Hybrid Motion Planning in Dynamic Environments
This research presents a novel approach to addressing the challenges of gesture forecasting in impenetrable and dynamic atmospheres by integrating a hybrid algorithm within a multi-agent system framework. Traditional methods such as Force-based motion planning (FMP) & deep reinforcement learning (RL) often struggle to handle complex scenarios involving multiple autonomous agents due to their inherent limitations. To overcome these challenges, we propose a hybrid algorithm that seamlessly combines the strengths of RL and FMP while leveraging the coordination capabilities of a multi-agent system. By integrating this hybrid algorithm into a multi-agent framework, we demonstrate its effectiveness in enabling multiple agents to navigate densely populated environments with dynamic obstacles. Through extensive simulation studies, we illustrate the superior performance of our approach compared to traditional methods, achieving higher success rates and improved efficiency in scenarios involving simultaneous motion planning for multiple agents. A hybrid motion planning algorithm is also introduced in this very research. Performance Comparison of Hybrid Algorithm, Deep RL, and FMP are also discussed in the result section. This research paves the way for the development of robust and scalable solutions for motion planning in real-world applications such as collaborative robotics, autonomous vehicle fleets, and intelligent transportation systems. 2024 IEEE. -
Multi-atlas Graph Convolutional Networks and Convolutional Recurrent Neural Networks-Based Ensemble Learning for Classification of Autism Spectrum Disorders
Autism spectrum disorder (ASD) has an influence on social conversation and interaction, as well as encouraging people to engage in repetitive behaviors. The complication begins in childhood and persists through adolescence and maturity. Autism spectrum disorder has become the most common kind of childhood development worldwide. ASD hinders the capacity to interact, socialize, and build connections with individuals of all ages, and thus its early intervention is critical. This paper discusses some of the most recent approaches to diagnostics using convolutional networks and multi-atlas graphs for autism spectrum disorders. Also, several pre-processing approaches are elaborated. Graph convolutional neural networks (GCNs) to diagnose autism spectrum disorder (ASD) because of their remarkable effectiveness in illness prediction using multi-site data. Convolutional neural network (CNN) and recurrent neural networks (RNN) infrastructure studies functional connection patterns between various brain regions to find particular patterns to diagnose ASD. In our research, we implemented the GCN + CRNN ensemble method and achieved 89.01% accuracy based on resting-state data from the fMRI (ABIDE-II), a novel framework for detecting early signs of autism spectrum disorders is presented and discussed. 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. -
Multi-class SVM based network intrusion detection with attribute selection using infinite feature selection technique
An intrusion detection mechanism is a software program or a device that monitors the network and provides information about any suspicious activity. This paper proposes a multi-class support vector machine (SVM) based network intrusion detection using an infinite feature selection technique for identifying suspicious activity. Single and multiple classifiers generally have high complexity. To overcome all the limitations of single and multiple classifiers, we used a multi-class classifier using an infinite feature selection technique, which performed well with multiple classes and gave better results than other classifiers in terms of accuracy, precision, recall, and f_score. Infinite feature selection is a graph-based filtering approach that analyses subsets of features as routes in a graph. We used a standard dataset, namely the UNSW_NB15 data set generated by the IXIA perfect-storm tool in the Australian Centre for Cyber Security. This dataset has a total of nine types of attacks and 49 features. The comparative analysis of the manuscript work is done against eight different techniques, namely, hybrid intrusion detection system (HIDS), C5, one-class support vector machine, and others. The proposed work gave better simulation results using the 2015a Matlab simulator. 2021 Taru Publications. -
Multi-component condensation mediated synthesis of bioactive heterocyclic compounds
Aromatic heterocycles constitute the most diverse family of organic compounds. Moreover, aromatic heterocycles are widely used for the synthesis of dyes and polymeric materials of high value. The development of selective reactions that utilize easily available and abundant precursors for the efficient synthesis of heterocyclic compounds is a long-standing goal of chemical research. Despite the centrality of its role in a number of important research areas, including medicinal chemistry, total synthesis,and materials science, a general, selective, step-economical, and stepefficient synthesis of heterocycles is still needed.Pyrano[2,3-c]pyrazole derivatives have been synthesised by a one-pot multicomponent condensation of different aldehydes, dialdehydes, and ketones with malononitrile, ethyl acetoacetate, hydrazine hydrate (or phenylhydrazine) in the presence of magnetic nano-[CoFe2O4] catalyst under ultrasonic irradiation. The catalyst can be retrieved using an external magnet and used repeatedly. A practical, scalable method for obtaining various pyranopyrazoles has been demonstrated.
-
Multi-component condesation mediated synthesis of bioactive heterocyclic compounds
Aromatic heterocycles constitute the most diverse family of organic compounds. Moreover, aromatic heterocycles are widely used for the synthesis of dyes and polymeric materials of high value. The development of selective reactions that utilize easily available and abundant precursors for the efficient synthesis of heterocyclic compounds is a long-standing goal of chemical research. Despite the centrality of its role in a number of important research areas, including medicinal chemistry, total synthesis, and materials science, a general, selective, step-economical, and step-efficient synthesis of heterocycles is still needed. newlinePyrano[2,3-c]pyrazole derivatives have been synthesised by a one-pot multicomponent condensation of different aldehydes, dialdehydes, and ketones with malononitrile, ethyl acetoacetate, hydrazine hydrate (or phenylhydrazine) in the presence of magnetic nano-[CoFe2O4] catalyst under ultrasonic irradiation. The catalyst can be retrieved using an external magnet and used repeatedly. A practical, scalable method for obtaining various pyranopyrazoles has been demonstrated. The extraordinary catalytic role of the various catalyst has been discovered in the processes, which reveals a possible character of enhancing reaction rates and stabilising the intermediates during the course of the reactions. -
Multi-criteria decision making (MCDM) in diverse domains of education: a comprehensive bibliometric analysis for research directions
Multiple Criteria Decision Making has been one of the powerful and structured approach in solving real world problems in the past. The aim is to determine the best alternative based on multiple criteria. It has shown a remarkable performance in the field of education. In order to gain insights into the existing body of research in this area, a bibliometric analysis was conducted. The study is conducted to provide a comprehensive analysis since 2000 in the field of application of MCDM in the various domains of education. The publication information was accessed from Scopus Database on 1 December 2023 and the bibliometric analysis has been done through Vosviewer, R package bibliometrics and Tableau. Initially 5185 documents were found which were reduced to 1706 after multi layered screening criteria. The analysis is performed to find the relevant documents, most valuable researchers, the major countries where the research in this area is exhaustively conducted. After extensive research it is observed that researchers belonging to China are highly involved in the domain taken for study. Also, research conducted in China is highly cited which shows its quality of work. Further, it is observed that mostly fuzzy analysis techniques are widely used for MCDM. The collaborative work done by Arunodaya Raj Mishra and Rani Pratibha research work is remarkable and highly recommended to conduct the research in the considered domain in the research paper. The conducted bibliometric analysis provides an overview of the scope and global trends of MCDM in shaping the education sector. This would help the researchers to explore the most relevant study, analysis and finding the research gaps as per their research needs. The Author(s) under exclusive licence to The Society for Reliability Engineering, Quality and Operations Management (SREQOM), India and The Division of Operation and Maintenance, Lulea University of Technology, Sweden 2024. -
Multi-Criteria Usability Evaluation of mHealth Applications on Type 2 Diabetes Mellitus Using Two Hybrid MCDM Models: CODAS-FAHP and MOORA-FAHP
People use mHealth applications to help manage and keep track of their health conditions more effectively. With the increase of mHealth applications, it has become more difficult to choose the best applications that are user-friendly and provide user satisfaction. The best techniques for any decision-making challenge are multi-criteria decision-making (MCDM) methodologies. However, traditional MCDM methods cannot provide accurate results in complex situations. Currently, researchers are focusing on the use of hybrid MCDM methods to provide accurate decisions for complex problems. Thus, the authors in this paper proposed two hybrid MCDM methods, CODAS-FAHP and MOORA-FAHP, to assess the usability of the five most familiar mHealth applications that focus on type 2 diabetes mellitus (T2DM), based on ten criteria. The fuzzy Analytic Hierarchy Process (FAHP) is applied for efficient weight estimation by removing the vagueness and ambiguity of expert judgment. The CODAS and MOORA MCDM methods are used to rank the mHealth applications, depending on the usability parameter, and to select the best application. The resulting analysis shows that the ranking from both hybrid models is sufficiently consistent. To assess the proposed frameworks stability and validity, a sensitivity analysis was performed. It showed that the result is consistent with the proposed hybrid model. 2022 by the authors. Licensee MDPI, Basel, Switzerland. -
Multi-dimensional changes in drought patterns across India
Indias hydroclimatic systems are undergoing unprecedented transitions in a warming climate, marked by shifts in temperature extremes, altered precipitation patterns, and increasing drought risk. This study presents a comprehensive assessment of drought trends and hydroclimatic variability across six major geographical zonesWestern, Central, Himalayan, Indo-Gangetic Plain (IGP), Peninsular, and Northeast Indiaduring the period 1971 to 2020. Using a set of advanced climate change metricsStandardized Local Anomalies (SLA), Novel Climate Scores (NCS), and changes in probability of local climate extremes alongside the Standardized Precipitation Evapotranspiration Index (SPEI), we quantify changes in drought conditions and the emergence of non-analogue climates. Changes in climatic extreme are computed using high-resolution daily gridded temperature and rainfall datasets, comparing recent decades against a 19511980 baseline. SLA quantifies deviations from historical variability, highlighting intensified warming over the Indo-Gangetic Plain, western India, and the southern peninsula. NCS reveales the emergence of novel climatescombinations of temperature and precipitation conditions not previously observed, particularly in Southeast India and the Himalayan region. The probability of local climate extremes shows a substantial increase in extreme events across India indicating enhanced climate volatility. These metrics are then integrated with drought analysis using SPEI to incorporate both precipitation and temperature-driven evaporative demand. SPEI trends indicate increasing dryness in Northeast India, the Himalayas, and the Indo-Gangetic Plain, linked to declining monsoonal rainfall and rising temperatures. Meanwhile, Western and Peninsular regions show wetting trends, driven by increased rainfall and convective precipitation events. The rainfall is the dominant drought driver during the monsoon, while high maximum temperatures intensify drought conditions in pre- and post-monsoon seasons by enhancing evaporative demand. Minimum temperature exhibits regional effects, showing a drying influence in the IGP and Himalayas, but a slight moistening signal in Peninsular India. By combining drought indices with climatic extremes metrics, this study offers a comprehensive framework to monitor hydroclimatic shifts and their regional impacts. The findings underscore the need for region-specific adaptation strategies that incorporate early warning systems, sustainable water management, and climate-resilient agriculture to address Indias evolving drought risks. The Author(s), under exclusive licence to Springer Nature B.V. 2025. -
Multi-dynamics and emission tailored fluoroperovskite-based down-conversion phosphors for enhancing the current density and stability of the perovskite solar cells
State-of-the-art and innovative research is being intensively employed on perovskite solar cells (PSCs) to expand their frontiers further. This study is a successful attempt to drive the limit of photocurrent density (Jsc) beyond conventional PSCs (which typically utilize the visible spectrum alone) through a nonlinear optical phenomenon called down-conversion (DC). The use of DC luminescence to harness the UV region from the solar spectrum is explored by utilizing Eu3+ activated RbCaF3, a fluoroperovskite-based phosphor material. It is observed that PSCs, which used RbCaF3:Eu3+ incorporated TiO2 electron transport layer (ETL), enhanced their Jsc and UV stability compared to those with pristine TiO2-oriented ETL. Such improvement in the aforementioned devices is due to the result of converting high-energy UV photons to effectively absorbable low-energy visible photons for perovskite absorbers. Overall, the DC-aided PSC offered a substantial Jsc of 23.54 mA cm?2 (9.2% superior to the conventional PSC) and boosted its power conversion efficiency (PCE) from 11.2% to 13.3%. It is evident that DC-based PSCs show a much better shelf-life when compared to conventional PSCs. This unique approach for boosting the Jsc with enhanced stability can be utilized for the potential applications of PSCs. 2023 The Royal Society of Chemistry. -
Multi-frame twin-channel descriptor for person re-identification in real-time surveillance videos
Automatic re-identification of people entering the camera network is an important and challenging task. Multiple frames of the same person will be easily available in surveillance videos for re-identification. Dealing with pose variations of the person in the image and partial occlusion issues is major challenge in single-frame re-identification process. The use of more frames from the surveillance videos can generate robust descriptor to tackle issues of pose variations and occlusion. In this paper, we have emphasized on using multiple frames from the same video to generate a multi-frame twin-channel descriptor. The work deals with building a spatial-temporal descriptor which takes advantage of the twin paths to extract features of the person image. Mahalanobis distance metric learning algorithms is used for matching and evaluation. Our descriptor is evaluated on two benchmark datasets and found to surpass the performance of the existing methods. 2017, Springer-Verlag London Ltd. -
Multi-functional rechargeable chalk dust collector with recycling unit /
Patent Number: 202041009633, Applicant: Pramod Kandoth Madathil.
A detachable electronic chalk dust collector consisting of a control unit having dust collecting components, a dusting unit with alternative directional suction, inbuilt collection unit and sensors. An attachable recharging and recycling unit with di-suction
unit and multifunctional ports and sensors. -
Multi-Layer Ensemble Deep Reinforcement Learning based DDoS Attack Detection and Mitigation in Cloud-SDN Environment
Cloud computing (CC) remains as a promising environment which offers scalable and cost effectual computing facilities. The combination of the SDN technique with the CC platform simplifies the complexities of cloud networking and considerably enhances the scalability, manageability, programmability, and dynamism of the cloud. This study introduces a novel Multi-Layer Ensemble Deep Reinforcement Learning based DDoS Attack Detection and Mitigation (MEDR-DDoSAD) technique in Cloud-SDN Environment. The major aim of the presented technique lies in the recognition of DDoS attacks from the cloud-SDN platform. The MEDR-DDoSAD technique transforms the input data into images and the features are derived via deep convolutional neural network based Xception model. 2022 IEEE. -
Multi-layer Stacking-based Emotion Recognition using Data Fusion Strategy
Electroencephalography (EEG), or brain waves, is a commonly utilized bio signal in emotion detection because it has been discovered that the data recorded from the brain seems to have a connection between motions and physiological effects. This paper is based on the feature selection strategy by using the data fusion technique from the same source of EEG Brainwave Dataset for Classification. The multi-layer Stacking Classifier with two different layers of machine learning techniques was introduced in this approach to concurrently learn the feature and distinguish the emotion of pure EEG signals states in positive, neutral and negative states. First layer of stacking includes the support vector classifier and Random Forest, and the second layer of stacking includes multilayer perceptron and Nu-support vector classifiers. Features are selected based on a Linear Regression based correlation coefficient (LR-CC) score with a different range like n1, n2,n3,n4 a, for d1 used n1 and n2 dataset,for d2 dataset, combined dataset of n3 and n4 are used and developed a new dataset d3 which is the combination of d1 and d2 by using the feature selection strategy which results in 997 features out of 2548 features of the EEG Brainwave dataset with a classification accuracy of emotion recognition 98.75%, which is comparable to many state-of-the-art techniques. It has been established some scientific groundwork for using data fusion strategy in emotion recognition. 2022. International Journal of Advanced Computer Science and Applications. All Rights Reserved. -
Multi-level Prediction of Financial Distress of Indian Companies Using Machine Learning
Predicting Financial Distress (FD) and shielding companies from reaching that stage is vital, even indispensable for every business. FD, if not attended to on time, ultimately leads to bankruptcy. Prediction variables are essential to forecast the wreckage in the business; however, the prediction is successful when suitable models are used. This study aims to predict FD at three levels: from mild to severe, by applying a machine learning algorithm. The study identifies modern models using the machine learning approach for predicting multi-level FD and summarises the significance of modern models through machine learning technology, to sustain the future development of the economy. The modern models are free from rigid assumptions and have proved to be the best in the prediction of FD. The results show that FD prediction is important at multiple stages. The models performance will be high when the best features are selected using the Pearson Correlation and SFS Feature selection approach. Among the ten models used in the study, LightGBM Classifier shows the highest performance of 80.43% accuracy without feature selection. However, with Pearson Correlation Approach and SFS Feature Selection methods, the accuracy is 82.68% and 86.95% respectively. This study has major implications for the stakeholders of the company to take timely decisions on their investment and for the management as a yardstick to check the performance of the business. The Author(s), under exclusive license to Springer Nature Switzerland AG 2025. -
Multi-level Prediction of Financial Distress of Indian Companies Using Machine Learning
Predicting Financial Distress (FD) and shielding companies from reaching that stage is vital, even indispensable for every business. FD, if not attended to on time, ultimately leads to bankruptcy. Prediction variables are essential to forecast the wreckage in the business; however, the prediction is successful when suitable models are used. This study aims to predict FD at three levels: from mild to severe, by applying a machine learning algorithm. The study identifies modern models using the machine learning approach for predicting multi-level FD and summarises the significance of modern models through machine learning technology, to sustain the future development of the economy. The modern models are free from rigid assumptions and have proved to be the best in the prediction of FD. The results show that FD prediction is important at multiple stages. The models performance will be high when the best features are selected using the Pearson Correlation and SFS Feature selection approach. Among the ten models used in the study, LightGBM Classifier shows the highest performance of 80.43% accuracy without feature selection. However, with Pearson Correlation Approach and SFS Feature Selection methods, the accuracy is 82.68% and 86.95% respectively. This study has major implications for the stakeholders of the company to take timely decisions on their investment and for the management as a yardstick to check the performance of the business. The Author(s), under exclusive license to Springer Nature Switzerland AG 2025. -
Multi-lingual Spam SMS detection using a hybrid deep learning technique
Nowadays, the incremental usage of mobile phones has made spam SMS messages a big concern. Sending malicious links through spam messages harms our mobile devices physically, and the attacker might have a chance to steal sensitive information from our devices. Various state-of-the-art research works have been proposed for SMS spam detection using feature-based, machine, and deep learning techniques. These approaches have specific limitations, such as extracting and selecting signifi-cant and quality features for efficient classification. Very few deep learning techniques are only used for classifying spam detection. Moreover, the benchmark spam datasets written in English are mostly used for evaluation. Very few papers have detected spam messages for other languages. Hence, this paper creates a multilingual SMS spam dataset and proposes a hybrid deep learning technique that combines the Convolutional Neural Network and Long Short-Term Memory (LSTM) model to classify the message dataset. The performance of this proposed hybrid model has been compared with the baseline deep learning models using accuracy, precision, recall, and F1-score metrics. 2022 IEEE.