Browse Items (16481 total)
Sort by:
-
A COMPUTATIONAL MODEL FOR TEA LEAF PRICE PREDICTION BASED ON QUALITY FACTORS USING HYBRID MACHINE LEARNING TECHNIQUES
This document reflects the effort made to calculate and identify the grade of the tea leaves based on the assessment of the leaves' size and color. The leaves were classified based on their severity with the help of HSV. The leaves were further classified using the k prototypes clustering once their length and width were established. The leaves were then further categorized in line with that. Light, medium, and dark are the three-color categories into which it belongs. The leaves were further sorted according to their quality so that the farmer could sell the produce at a better price. With the machine learning method for the categorization part, we were able to show its values. All of the healthy leaves were considered in a different dataset, and the images were obtained using the feature selection method. The length and width of each individual leaf, along with its color and shape, were then measured using those leaves. We were able to differentiate between the various leaf grades based on the findings. The healthy leaves were separated from the diseased leaves using the textual features. Additionally, we were able to use the other criteria to obtain higher-grade leaves. Little Lion Scientific. -
The Fusion of CNN and MLP Algorithm as High-Performance Classification for Identification of Healthy and Unhealthy Leaves
In this study, it encapsulates the results of the work carried out with the Convolutional Neural Network, Multi-layer Perceptron, and hybrid of CNN and MLP classifier for the recognition of a tea leaf. The leaves are categorized into distinct classes by analysis and identification and recognition, which benefits both the buyer and the farmer by enabling the seller to sell tea leaves based on the quality of the leaf. Nowadays there is more advancement in the field of agriculture. But it is always the latest subject to study in the field of agriculture for the analysis and to identify quality of leaves. Many AI methodologies can be used for identification and recognition and further their fusion with different techniques or methods that can be applied to address the issue and to acquire the better accuracy. In this CNN, MLP and the hybrid of CNN-MLP are employed for determining the accuracy and this can further help in classifying the leaf in different grades like best quality, average quality, and worst quality, as for the future scope. Then the feature selection algorithms are implemented based on the different selection methods such as ANOVA, information gain, feature importance, and the random forest, which will reduce the number of parameters, at the end classification is carried out for identification of the leaf. 2026, Greater Mekong Subregion Academic and Research Network, Asian Institute of Technology. All rights reserved. -
The Middle Class in India Trends and Patterns
The middle class in India is an economically significant group, the composition of which is very diverse. Researchers often use income as an indicator to identify or measure the middle class. This article uses consumption as an indicator based on the purchasing power parity to identify the middle class. Further, it categorises the middle class into different groups based on their economic standing within its class, from the emerging middle class to the higher middle class. 2025 Economic and Political Weekly. All rights reserved. -
Laminating techniques for luxury textiles
In this paper, we delved into the transformative aspects of lamination techniques in luxury textiles. We started by explaining luxury textiles and what makes them premium: craftsmanship, exclusivity, superior ingredients, silk, cashmere, fine wool etc. They presented the lamination procedures that are considered pre-processing steps to improve the functionality, lifespan, and appearance of such textiles. -
Cognitive and Motor profiles of Preterm Infants with Hypoxic Ischemic Encephalopathy (HIE): A Case Report
Hypoxic Ischemic Encephalopathy (HIE) significantly impacts infants' cognitive and motor development, necessitating tailored evaluation tools for early identification and intervention. To address this need, this study aimed to build new normative data for the Bayley Scales of Infant and Toddler DevelopmentTM, Fourth Edition (BayleyTM-4), specific to HIE. A cross-sectional analysis of 54 infants across three age groups (6, 12, and 18 months), consisting of 18 each, revealed significant deficits in the cognitive and motor domains compared with those of matched controls. These findings highlight the need for HIE-specific benchmarks to improve diagnostic accuracy and inform targeted interventions. Establishing these norms can enable clinicians to design personalized strategies to enhance developmental outcomes. 2025 EL-MED-Pub. All rights reserved. -
SHRINKAGE BASED ESTIMATION FOR STRESS STRENGTH RELIABILITY P[Y < X < Z] FOR THE EXPONENTIAL DISTRIBUTION
Estimating stress-strength reliability of the form P(Y < X < Z) is a pivotal concern in reliability analysis, particularly when systems are subjected to both lower and upper stress limits. This paper investigates the reliability measure under the assumption that the stress variables Y and Z, as well as the strength variable X, follow exponential distributions. The analysis is conducted using both complete samples and right-censored samples to reflect realistic data collection scenarios. To improve estimation efficiency, we propose several shrinkage estimators based on distinct strategies: a constant shrinkage weight factor, a modified Thompson-type shrinkage weight, and the formulation introduced by Mehta and Srinivasan (1971). The performance of these estimators is evaluated via extensive Monte Carlo simulations and compared against the conventional maximum likelihood estimator, demonstrating the relative merits and limitations of each approach. ARF India, Gurgaon, India. -
EDGE INCIDENT 2-EDGE COLORING SUM OF GRAPHS
The edge incident 2-edge coloring number, ?ein2(G), of a graph G is the highest coloring number used in an edge coloring of a graph G such that the edges incident to an edge e = uv in G is colored with at most two distinct colors. The edge incident 2-edge coloring sum of a graph G, denoted as (Formula presented.), is the greatest sum among all the edge incident 2-edge coloring of graph G which receives maximum ?ein2(G) colors. The main objective of this paper is to study the edge incident 2-edge coloring sum of graphs and find the exact values of this parameter for some known graphs. I??k University, Department of Mathematics, 2025; all rights reserved. -
STRUCTURAL PROPERTIES OF SIGNED GRAPHS ADMITTING ROMAN DOMINATING FUNCTION
A Roman dominating function(RDF) on a signed graph S = (G, ?) is a function f: V (S) ? {0, 1, 2} such that (i) (Formula presented) for every vertex (Formula presented) and (ii) for any vertex v with f(v) = 0 there exists a vertex (Formula presented) having f(u) = 2. In this article we explore structural properties of signed graphs admitting an RDF. Further, signed graphs with 3-regular graph as their underlying graph are examined and characterisation of one of its subclasses, net-regular signed graphs admitting an RDF is obtained. I??k University, Department of Mathematics, 2025; all rights reserved. -
The DREAMS Outbound Leadership Training (DREAMS OLT) for Psychosocial Empowerment Among Youth and Sustainable Development Goals (SDGs)
DREAMS Intervention Program is a three-year curriculum program for schools and Higher Educational Institutions (HEIs), aimed at developing psycho-social leadership skills through mentoring intervention. Its triangulated model connects Schools (under-served students), Universities (youth mentors), and Community (senior leaders) to transfer knowledge, experiences, and leadership skills as tools for social change. Outbound Leadership Training (OLT) is a key instrument in achieving DREAMS' goals. DREAMS OLT is an experiential program to develop higher leadership skills and build effective teams by mentoring children and teens in various DREAMS chapters. Mentor training is ongoing, developing psychosocial competencies through project execution. DREAMS OLT refines these skills with structured, activitybased experiential learning. Integrating sustainability into education advances a holistic approach to developing professional skills and leadership among youth. Such skills help the youth to deal with complex worldly challenges. Initiatives such as DREAMS OLT enable the transformation of SDG frameworks into meaningful action by nurturing responsibility, innovation, collaboration and community engagement. Education and youth leadership are critical drivers of long-term social transformation. DREAMS OLT supports SDGs: 4 (Quality Education), 9 (Industry, Innovation, and Infrastructure), 17 (Partnership for the Goals), 3 (Good Health and Well-Being), and 11 (Sustainable Cities and Communities). This paper explores how DREAMS OLT applies these SDGs through experiential, mentoring-based leadership development and psycho-social empowerment of youth. 2026 RESTORATIVE JUSTICE FOR ALL. -
Building a sustainable brand in textile industry
The textile industry is at a pivotal moment where integrating sustainability into brand strategies is not merely an ethical obligation but a competitive necessity. This study highlights three key approaches-adoption of circular economy principles, implementation of blockchain technology for supply chain transparency, and the use of innovative, sustainable materials-that are shaping the future of sustainable brand development in the textile sector. -
HEART FAILURE DETECTION USING OPTIMIZATION ALGORITHMS
Heart failure (HF) remains a significant global health challenge, requiring early and precise detection to improve clinical outcomes and reduce mortality rates. Traditional diagnostic approaches often fail to capture the complexity of HF pathophysiology, necessitating advanced computational methods for accurate prediction. In this study, we propose a novel optimized Stacked Support Vector Machine (S-SVM) framework, integrating multiple SVM classifiers with diverse kernel functions to enhance predictive accuracy. A genetic algorithm (GA) is employed to fine-tune hyperparameters, ensuring model robustness and generalizability across patient populations. The model is rigorously evaluated on the UCI Heart Failure Clinical Records Dataset and the Framingham Heart Study Dataset, demonstrating superior performance in accuracy (95.7%), precision (0.90), recall (0.87), and AUC (0.96) compared to conventional machine learning techniques. The proposed system effectively balances computational efficiency with clinical interpretability, making it a promising tool for early-stage HF detection and risk stratification. This research advances the intersection of machine learning and cardiovascular diagnostics, offering a scalable and adaptive solution for real-world healthcare applications. Little Lion Scientific. -
Patriarchal Constraints in Everyday Lives: Gender Roles, Matrilineality, and the Status of Contemporary Khasi Women
The Khasi tribe from Meghalaya in northeast India practices a matrilineal system, which is believed to be more egalitarian than patrilineal systems. The women of the Khasi tribe are often regarded as having a higher status than other women in India. However, despite belonging to a matrilineal society, Khasi women still face challenges in their social lives stemming from patriarchal constructs. This qualitative study examines the social status and subsequent challenges faced by Khasi women in contemporary India. Using in-depth interviews and observations of thirty urban and rural Khasi women in the East Khasi Hills District of Meghalaya, the study reveals how Khasi women experience contradictory and challenging roles, relationship dynamics, and gender stereotypes in their lives. More studies should examine the problems and challenges that Khasi women face in their society despite the benefits of a matrilineal system. 2026 Bridgewater State College. All rights reserved. -
Skin as Script Embodied Archives of Post-headhunting in Longwa, Nagaland
[No abstract available] -
Improper Injective Coloring Parameters of Certain Cycle-Related Graphs
Any vertex coloring of a graph can be viewed as a random experiment of assigning colors to the vertices, whose random variable is defined based on the number of vertices assigned a particular color in that coloring. Based on this, the statistical parameters of mean and variance have been extended to chromatic mean and chromatic variance for various vertex colorings of graphs in the literature. In this article, the ideas of chromatic mean and chromatic variance of cycle-related graphs with respect to their improper injective coloring are investigated. (2025), (Yarmouk University). All rights reserved. -
Enhancing fabric quality with AI-based defect detection systems
In summary, there is a necessity to use AI-based defect detection systems in fabric quality improvement especially in the process of textile production. These sophisticated solutions eliminate the requirement for time-consuming and error-prone traditional manual procedures, and thus not only speed up the inspection but guarantee a higher quality of the products. -
Hegemony of the Visual Question of Disability, Inclusivity, and Justice in Neru
[No abstract available] -
MULTI-REFERENCE SKIP-LOT SAMPLING OF TYPE 3 (MR-SkSP-3)
In the current industrial sector, the rate of defective products present in the lots has been decreasing and most of the products keeps up a good history of quality throughout the production also. Skip-lot sampling plans are the suitable acceptance sampling plan for the situations where the series of products shows a stable and excellent quality. The skip-lot sampling plans are still widely used because of its reduced sampling cost and efforts, because the plan only needs to inspect a fraction of the lots submitted after a continues series of lots with excellent quality. This approach makes the skip-lot plan more cost-effective than the other sampling plans, thus making it an economically important plan. The current study incorporated a modification on the skip-lot sampling of type 3 and designated it as multi-reference skip lot sampling of type 3. The proposed plan has the provision of having multiple reference plans in normal and skipping inspection of a skip-lot sampling plan, unlike the traditional skip-lot plans which has the same reference plan in all phases. The performance measures of the proposed plan are derived using the power series approach. A designing methodology to determine the optimal parameters for the plan using the unity value approach is also described with the help of a numerical illustration. Behaviour of the operating characteristic curves for varying set of parameters are also analysed for the plan. Comparison of the proposed plan is done between the conventional plans using performance measure values and graphical representations. This analysis shows that the new plan is able to effectively optimize the preferences of producer and consumer simultaneously, where the traditional plans fail to. The analysis is supported with the help of graphical representations and tabulated values. 2025, Gnedenko Forum. All rights reserved. -
Social Capital and Income Inequality An Empirical Analysis
The relationship between income inequality and social capital is examined. Using the India Human Development Survey, which includes variables related to formal and informal social capital, income inequality is seen to adversely impact the formation of formal social capital while significantly contributing to the development of informal social capital in India. Further, evidence of a lower level of social capital among low-income individuals is observed. There is substantial inequality in income distribution that amplifies social capital inequality. Traditional income redistributive policies may prove ineffective when inequality becomes deeply ingrained in society. 2025, Economic and Political Weekly. All rights reserved. -
An Intuitionistic Fuzzy-Rough Attribute Selection Using Representative Samples
Selecting relevant features is an important tool for extracting knowledge from datasets with many attributes and objects. The traditional theory of rough set is a fundamental and successful tool for dealing with vagueness and inconsistency. Combining the rough set with the fuzzy set handles the information loss problem arising from the discretisation process. Still, it fails to consider the hesitancy part of any information system. A generalisation of fuzzy set known as an intuitionistic fuzzy (IF) set has more real-world applications to confront uncertainty and ambiguity than the fuzzy set. So, the combination of rough set and IF set not only deals with vagueness but also able to consider the hesitancy available in any real-world data. In this work, we propose an IF rough set model based on representative samples and its application in the area of attribute reduction of high-dimensional datasets. First, we defined the representative sample-based intuitionistic fuzzy rough set and then presented an algorithm to calculate the reduction of a dataset using the degree of dependency method. Mathematical theorems are applied to validate the presented model theoretically. Experimental analysis is also discussed to validate the proposed technique. Finally, we applied our proposed method to improve the prediction of antifungal peptides. 2025 Old City Publishing, Inc.