Jawaharlal Nehru Government Engineering College

Alterations in land usage and land cover are two of the most substantial forces influencing landscape change. Land use activities have a long-standing and spatially variable effect on the land cover. The current study focuses on the LULC deviations in the Mandi district of Himachal Pradesh (India) using multi-temporal remotely detected data from 2004 to 2024. The Support Vector Machine (SVM) administered classification technique extracted statistics from satellite records. The post-classification modification discovery method was employed to identify monitor land use/cover change. While agricultural land and thickly vegetated land showed a significant decline in the study area between 2004 and 2024, built-up land, bare land, water bodies, and grasslands increased. The overall correctness of land cover change maps generated from Landsat data alternated between 80 and 85

Land-use/land-cover (LULC) change affects the balance between settlements, agricultural land, and natural ecosystems, making its assessment important for land-use planning in mountainous regions. This study integrates Random Forest (RF) classification and Cellular Automata–Artificial Neural Network (CA-ANN) modeling to assess historical LULC change in Sarkaghat Tehsil, Himachal Pradesh, and generate baseline projections for 2031 and 2046. Landsat imagery from 2016, 2021, and 2026 was classified into six classes: Forest Land (FL), Agricultural Land (AL), Built-up Land (BUL), Barren Land (BL), Water Body (WB), and Grass Land (GL). Overall classification accuracy was 95%, 96%, and 93%, respectively, with Kappa coefficients of 0.91, 0.94, and 0.89. The 2026 map had the lowest accuracy; the lower agreement was particularly evident for Grass Land, which had a user’s accuracy of 0.83. Historical comparisons from 2016 to 2026 showed increases in BUL (0.46%), BL (0.04%), and GL (0.16%), and decreases in AL (0.45%) and FL (0.21%); WB changed negligibly. The CA–ANN simulation of 2026, evaluated against the independently classified 2026 map, achieved an overall accuracy of 97.898% and a Kappa coefficient of 0.965. Relative to 2016, the 2031 baseline projection indicates changes of FL 0.00%, AL −0.37%, BUL +0.27%, BL −0.03%, WB 0.00%, and GL +0.13%. For 2046, the corresponding changes are FL −0.01%, AL −0.37%, BUL +0.27%, BL −0.03%, WB 0.00%, and GL +0.14%. The projections are conditional on stable historical transition relationships and should be interpreted as baseline scenarios rather than certain forecasts. The integrated workflow provides a locally evaluated basis for assessing land transitions and informing land-use planning in Sarkaghat Tehsil.

ABSTRACT The design and development of sportswear fabrics require optimized yarns with improved moisture management properties, leading to optimum comfort. This study is performed with an aim to rank various structurally modified doubled polyester/cotton blended yarns for sportswear by using the VIKOR multi-criteria decision-making method. Using a Box–Behnken three-factor experimental approach, fifteen distinct polyester/cotton blended yarn samples were produced by systematically varying the percentage of cotton fiber, yarn linear density (Ne), and twist multiplier (TM). This statistical factorial method was utilized to examine the effect of process parameters on the structural and performance characteristics of the produced yarns. Dissolution of cotton component was done to create additional pores in the yarn structure to improve moisture management and hence the comfort properties of the fabric produced from it. Various yarn characteristics, such as strength, compressibility, packing density, irregularity, hairiness and immediate elastic recovery, were assessed before and after treatment. To ascertain the weights, the triangular fuzzy AHP technique which combines triangular fuzzy numbers with absolute priority scales to effectively handle uncertainty and subjectivity in the evaluation process was used to determine the weights. A pairwise comparison matrix was created using the absolute numbers of priority levels for the aforementioned yarn properties to determine their relative weights. The optimum rank is achieved for treated double yarn (YS6) produced from a 95/5 polyester/cotton blend and 40s Ne single yarn having a 4.5 TM. The results of the best-selected yarn revealed reduction in hairiness, unevenness, packing fraction, and strength, whereas an improvement in compressibility and immediate elastic recovery is observed in comparison to the untreated yarn.

Hardware security has emerged as a major concern in modern digital integrated circuits due to globalization of semiconductor manufacturing, increasing complexity of IC design, and widespread deployment of IoT devices. Modern hardware systems are vulnerable to attacks such as hardware Trojans, side-channel attacks, reverse engineering, counterfeit IC insertion, and intellectual property piracy. Researchers have proposed several defense mechanisms including logic locking, physically unclonable functions (PUFs), secure boot architectures, hardware obfuscation, and side-channel resistant design techniques. This review paper discusses major hardware security threats, analyzes recent research developments from 2016 onward, compares existing protection methods, and highlights future challenges in secure digital IC design.

State-of-the-art deep learning techniques for the detection of cattle infected by lumpy skin disease are presented in this chapter. This is a viral infection caused by poxvirus lumpy skin disease virus (LSDV), which is a dangerous threat to cattle health and the agricultural economy. So, early detection and diagnosis play a significant role for efficient disease prevention, management, and control. In this study, we utilized various deep learning models, such as CNN, MobileNet, ResNet50, EfficientNetB0, and VGG16, respectively, on a specific image dataset to classify the cases of lumpy skin disease into lumpy or normal skin. Every model was trained for 100 epochs followed by a strict assessment that made accuracy the focus of evaluation. In our experiments, we discovered that the VGG16 followed by the EfficientNetB0 model is superior to others in terms of metrics like accuracy and balanced F1-score in detecting the disease. VGG16 and EfficientNetB0 show 91.42