SNS College of Technology

Difficulties are still present in developing sustainable and biodegradable composites with respect to their mechanical property improvement of natural-fibre-reinforced composites. Some of the limitations that would affect the use of natural fibre-reinforced composites in structural applications have things attached to their poor mechanical properties, high moisture absorption, and non-uniform fibre characteristics. This investigation involved the reinforcement of polylactic acid with pineapple leaf fibre and hemp fibre to produce a biocomposite with improved strength and durability. The composite is fabricated from compression moulding by optimizing the process with an enhanced Taguchi approach. Fine-tuning is made on key parameters like fiber content, moulding temperature, and pressure settings prior to the maximum performance achieved. Mechanical research included tensile test, flexural strength, and impact resistance. Grey relational analysis is used to identify the most significant parameters while principal component analysis helped in reducing the complexity of data for better optimization. Simulation and validation are carried out through MATLAB so that parameters like stress distribution, fiber orientation, and multi-objective optimization could be interpreted. The results showed that with the use of pineapple leaf and hemp fiber reinforced polylactic acid (PALHF-re-PLA) composite, an increase of 73.50

Diabetic retinopathy (DR) is a condition caused by long-term diabetes and clots the retina's blood vessels. Early recognition and categorization of DR are vital for timely diagnosis and preventing vision loss. This paper presents a novel DR-Cinque for detecting and classifying DR in cinque classes from retinal OCT images. Initially, the retinal images are collected from three various publicly available databases and the noisy artifacts are removed by adaptive mean filter. The Otsu segmentation algorithm is applied for segmenting soft and hard exudates from the noise-free retinal images. The proposed DR-Cinque leverages Regularized Network (RegNet) to automatically retrieve appropriate features from the segmented regions. Finally, Artificial Neural Network (ANN) is employed to classify the images into various phases of DR severity ranging from no DR to proliferative DR. The proposed DR-Cinque achieves high accuracy and robustness for outperforming traditional methods in both detection and classification tasks. The efficiency of the proposed DR-Cinque was assessed using the network parameters viz., accuracy, F1 score, sensitivity, accuracy, and specificity. The proposed DR-Cinque framework achieves 99.7

The safe human-level decision-making for expressing the autonomous vehicles and the estimation of the eco vehicles has been proposed for the motion control for the driving behavior. For efficient decision-making, the sensor-based tracking of the autonomous machine for blockchain is to be done. The sensor-based history recording management has to propose, and storing the vehicle’s traveling history must be managed. For security reasons, the blockchain is done. Self-determination theory and energy-efficient mixed-precision neural networks are used in autonomous vehicles’ decision-making, and this technique is used in making moral decisions. The self-determination theory is used in creating the vehicles traveling steps using the innovative signal delivery system of the autonomous vehicles. The energy-efficient mixed-precision neural networks are used in managing the problem that travels the signal to the vehicles using the mixed–precision neural networks. The vehicle network has been made more efficient for storing the data of the mixed precision value and its neural network from autonomous vehicles. Here 80% of the precision value is raised compared to the previous days. In previous days, 20% of the precision has been calculated in autonomous vehicles. Comparing this, 60% of the precision value has been raised in traveling history. According to these variations, 40%–50% of autonomous vehicles’ data transmission that delivers the neural network has been proposed. By improving autonomous vehicles, the efficiency of mixed precision neural networks is the decision-making for efficient precision.

Poly(vinyl alcohol) (PVA) composites reinforced with Cissusquadrangularis short fibers and ultra-porous nutmeg husk biochar were developed to address the dual challenge of structural reinforcement and multifunctional performance. The novelty of this work lies in the use of a hybrid natural fiber-biochar system, combined with silane surface treatment, to simultaneously enhance mechanical, thermal, dielectric, and electromagnetic interference (EMI) shielding properties while reducing water uptake. Both untreated and treated series were fabricated to assess the role of interfacial modification. The treated composites consistently outperformed their untreated counterparts due to improved fiber-matrix adhesion, better filler dispersion, and reduced interfacial resistance. Among them, PTB1 delivered the best mechanical performance with tensile and tear strengths of 145 MPa and 123 MPa, respectively, while PTB2 achieved the highest functional properties, including a thermal conductivity of 0.49 W/mK, dielectric permittivity of 4.8 with a dielectric loss of 0.72, and EMI shielding effectiveness up to 31.91 dB in the J-band. Water absorption was also minimized, confirming improved hydrophobicity. Overall, the results demonstrate that combining porous biochar with chemically modified natural fibers offers a novel, sustainable route to high-performance PVA composites with balanced structural and functional capabilities.

A double slope solar still (DSS) gives more productivity than a single slope solar still (SSS). However, its efficiency remains low and it is strongly dependent on climatic conditions. This study aims to enhance the performance of DSS by using natural fibers (Banana, Sisal, and Palm) as wick materials in combination with an Al2O3 and Glauber Salt (GS) based nano phase change material (nano-PCM). The addition of Nano-PCM composite improves the storage capacity of heat energy, and natural fibers improve the capillary action and spreading of water. Experimental study reveals that the sisal fiber with Nano-PCM composites provides the best productivity of 4.58 l/day, which is 115.02 % higher than the conventional DSS. This improved water productivity of the sisal and Nano-PCM combination is due to its highest evaporative heat transfer coefficient value of 164.24 W/m2K. The average energy efficiency and exergy efficiency are also high for the sisal fiber and NanoPCM combination, which provides 35.34 % and 3.33 %, respectively. The average energy efficiency and exergy efficiency of the sisal fiber and nano PCM combination are 76.2 % and 114.4 % higher than the conventional DSS. Economic study reveals that the water production cost of sisal and nano PCM is just $0.012 per liter, with a payback (PB) period of around 143 days (4.7 months), whereas the production cost of CSS is $0.021, with a PB period of 231 days (7.7 months), respectively.