17 research outputs found
Analysis of Unmanned Four-Wheeled Bot with AI Evaluation Feedback Linearization Method
Get PDFIn this research paperwork, thereis the design and implementation of aBot with the ability to work in four directions of movement forward, backward, left, and right using aself-governingstability system. The bot's resultingbe in command of objective is to follow a path at the required speed, while its primary control purpose is to maintain equilibrium whenever the balance position is unstable owing to a change in the center of gravity. We report our surveys into the concertevaluation of a highly linear four-wheeledmatchingmachine using a PID regulator and a PI-PD regulator. Here I have added advantages with the AI evaluation feedback linearization technique to detect and process with auto error time solutions. The key benefits include cogency in the actual application; switchdevice, enhanced performance, and capacity to overcome uncertainties. Simulated and experimental findings are used to compare and support a performance evaluation of the system. Numerous automatic systems for detecting traffic accidents have been developed by researchers. These techniques frequently make use of many applications such as smartphones, infrared sensors, and mobile applications.All of these techniques fall short when it comes to the instinctiverecognition of traffic accidents. The sifters used in smartphones may make it difficult to detect low-speed collisions. The suggested system does not specify the threshold distances at which an IR sensor will react. It is suggested to use a revolutionary method based on ultrasonic sensors.Using an ultrasonic sensor to identify accidents allows for the ability to do so not only in different street contexts but also in industrial settings, busy intersections, and weather circumstances like clouds, fog weather, rain, and heavy traffic
Machine Learning Techniques to Evaluate the Approximation of Utilization Power in Circuits
Get PDFThe need for products that are more streamlined, more useful, and have longer battery lives is rising in today's culture. More components are being integrated onto smaller, more complex chips in order to do this. The outcome is higher total power consumption as a result of increased power dissipation brought on by dynamic and static currents in integrated circuits (ICs). For effective power planning and the precise application of power pads and strips by floor plan engineers, estimating power dissipation at an early stage is essential. With more information about the design attributes, power estimation accuracy increases. For a variety of applications, including function approximation, regularization, noisy interpolation, classification, and density estimation, they offer a coherent framework. RBFNN training is also quicker than training multi-layer perceptron networks. RBFNN learning typically comprises of a linear supervised phase for computing weights, followed by an unsupervised phase for determining the centers and widths of the Gaussian basis functions. This study investigates several learning techniques for estimating the synaptic weights, widths, and centers of RBFNNs. In this study, RBF networks—a traditional family of supervised learning algorithms—are examined. Using centers found using k-means clustering and the square norm of the network coefficients, respectively, two popular regularization techniques are examined. It is demonstrated that each of these RBF techniques are capable of being rewritten as data-dependent kernels. Due to their adaptability and quicker training time when compared to multi-layer perceptron networks, RBFNNs present a compelling option to conventional neural network models. Along with experimental data, the research offers a theoretical analysis of these techniques, indicating competitive performance and a few advantages over traditional kernel techniques in terms of adaptability (ability to take into account unlabeled data) and computing complexity. The research also discusses current achievements in using soft k-means features for image identification and other tasks
Response of butter beans (Phaseolus lunatus L.) for different combinations of nitrogen and phosphorus on growth, yield and quality characters
Get PDFA field experiment was conducted during June-October (2017) at Horticultural Research Station, Kodaikanal to study the response of butter beans for different combinations of nitrogen and phosphorus on growth, yield and quality characters. A randomized block design was followed with 17 combinations of N (30, 40, 50 and 60 kg/ha), P (37.5, 50, 62.5 and 75 kg/ha) and additional combination of 70: 75:50 kg N P2O5 K2O/ha. K 50 kg/ha was kept constant. The experimental results revealed that all the fertilizer treatments significantly increased the plant height, number of branches per plant, days to 50 % flowering, number of pods per cluster, 100 seed weight, pod weight, pod yield per hectare, protein content and crude fibre content of butter beans. Maximum plant height (220.33 cm), number of branches per plant (4.79), minimum days to 50 % flowering (50) and 100 seed weight were recorded in the combination of 50 kg N, 37.5 kg P2O5 and 50 kg K2O per hectare. Number of pods per cluster (6.78), pod weight (14.00 g) and pod yield per hectare (5.85 t) were maximum in the combination of 60 kg N, 75 kg P2O5 and 50 kg K2O per hectare
Effect of different phosphoms sources and soil amendments on the yield and quality of aswagandh (Withania somnifera Dunal) under acid soils
Get PDFTrials were conducted in acid soil at Yercaud (Tamil Nadu, India) with the objective of identifying the ideal source of phosphorus and soil amendment in aswagandh (Withania somnifera Dunal) in acid soils. Application of 60 kg ha-1 P205 as rock phosphate along with dolamite (5.688 t ha-1) for increasing the yield resulted in the highest dry root yield of 814.5 kg ha-1 in the present study. There was also an improvement in the total withanolides content due to the application of dolomite and rock phosphate.
 
Effect of different phosphoms sources and soil amendments on the yield and quality of aswagandh (Withania somnifera Dunal) under acid soils
Get PDFTrials were conducted in acid soil at Yercaud (Tamil Nadu, India) with the objective of identifying the ideal source of phosphorus and soil amendment in aswagandh (Withania somnifera Dunal) in acid soils. Application of 60 kg ha-1 P205 as rock phosphate along with dolamite (5.688 t ha-1) for increasing the yield resulted in the highest dry root yield of 814.5 kg ha-1 in the present study. There was also an improvement in the total withanolides content due to the application of dolomite and rock phosphate.
 
GIS-Based Soil Mapping of Nagapattinam District, Tamil Nadu, India: A Study on Sulphur Content and Associated Soil Properties
No full textThe importance of sulphur in agriculture is evident because plants require sulphur for the synthesis of essential amino acids, proteins, vitamins, and coenzymes and to activate certain enzymes. Advanced techniques like global positioning systems (GPS), geographic information systems (GIS) and precision agriculture facilitate soil secondary nutrient mapping, providing quantitative support for decision and policy-making to improve agricultural approaches for balanced nutrition. Thus, thematic maps help design appropriate strategies to enhance the productivity of crops. A study was carried out in the Nagapattinam district to assess sulphur status and soil properties, create a data bank, and prepare thematic maps. A total of 1631 geo-referenced surface soil samples covering 11 blocks in Nagapattinam district were collected randomly at 0-15 cm depth and analyzed for various soil properties, such as pH, electrical conductivity (EC), organic carbon (OC), free CaCO3. The overall soil reaction in the Nagapattinam district at different blocks was mainly neutral, with low soil salinity hazards. The data on organic carbon status in the soils was medium. The average free calcium carbonate status in the soils of different blocks revealed moderately calcareous. The average available sulphur was found to be in the range of 54.4 to 153 mg kg-1. Higher availability of sulphur with a combined average of 84.8 mg kg-1 was noticed in the soils of the entire district and could be attributed to the high organic carbon content and heavy texture of the soils
Enhancing digital resilience through GEN-AI driven video content moderation and copyright protection
No full textIn the digital era, ensuring digital resilience in video content moderation and copyright enforcement is crucial due to the vast volume of uploads. Traditional manual review methods are inefficient, necessitating AI-driven automation. This paper presents an AI-powered system integrating computer vision, deep learning, and NLP for real-time video analysis. The system detects inappropriate content using CLIP for visual moderation and Whisper for speech analysis, ensuring high-precision filtering with human oversight. A copyright protection mechanism employs watermarking and fingerprinting to generate unique digital signatures, preventing unauthorized content usage. A React-based UI with Vite framework provides an interactive reviewer experience. By combining automation with human intervention, this approach enhances moderation accuracy, copyright enforcement, and compliance with global content standards, fostering a more secure and resilient digital ecosystem. This system enhances digital resilience and security, making it applicable for defense and national security in protecting sensitive content
Effect of jerky movement of ring rail on quality of ring yarn
No full text248-250A d<span style="color:#070707;
mso-bidi-language:HI">evice <span style="color:black;
mso-bidi-language:HI">h<span style="color:#070707;mso-bidi-language:
HI">as b<span style="color:#070707;
mso-bidi-language:HI">een
design<span style="color:#070707;
mso-bidi-language:HI">ed <span style="color:black;mso-bidi-language:
HI">to measur<span style="color:#070707;
mso-bidi-language:HI">e the <span style="color:black;
mso-bidi-language:HI">j<span style="color:#070707;mso-bidi-language:
HI">erkiness of rin<span style="color:#070707;
mso-bidi-language:HI">g ra<span style="color:black;
mso-bidi-language:HI">il <span style="color:#070707;mso-bidi-language:
HI">of ring <span style="color:black;
mso-bidi-language:HI">fr<span style="color:#070707;mso-bidi-language:
HI">ame a<span style="color:black;
mso-bidi-language:HI">nd th<span style="color:#070707;mso-bidi-language:
HI">e effec<span style="color:black;
mso-bidi-language:HI">t <span style="color:#070707;mso-bidi-language:
HI">of ring <span style="color:black;
mso-bidi-language:HI">r<span style="color:#070707;mso-bidi-language:
HI">ail je<span style="color:black;
mso-bidi-language:HI">r<span style="color:#070707;mso-bidi-language:
HI">ky mo<span style="color:black;
mso-bidi-language:HI">ti<span style="color:#070707;mso-bidi-language:
HI">on o<span style="color:black;
mso-bidi-language:HI">n th<span style="color:#070707;mso-bidi-language:
HI">e quality o<span style="color:black;
mso-bidi-language:HI">f <span style="color:#070707;mso-bidi-language:
HI">yarn s<span style="color:black;
mso-bidi-language:HI">tudi<span style="color:#070707;mso-bidi-language:
HI">ed. <span style="color:black;
mso-bidi-language:HI">Th<span style="color:#070707;mso-bidi-language:
HI">e res<span style="color:black;
mso-bidi-language:HI">ult<span style="color:#070707;mso-bidi-language:
HI">s show <span style="color:black;
mso-bidi-language:HI">an in<span style="color:#070707;mso-bidi-language:
HI">crea<span style="color:#252525;
mso-bidi-language:HI">s<span style="color:#070707;mso-bidi-language:
HI">e in lo<span style="color:black;
mso-bidi-language:HI">n<span style="color:#070707;mso-bidi-language:
HI">g thin fa<span style="color:black;
mso-bidi-language:HI">ult<span style="color:#070707;mso-bidi-language:
HI">s in the ya<span style="color:black;
mso-bidi-language:HI">rn <span style="color:#070707;mso-bidi-language:
HI">due <span style="color:black;
mso-bidi-language:HI">to rin<span style="color:#070707;mso-bidi-language:
HI">g ra<span style="color:black;
mso-bidi-language:HI">il j<span style="color:#070707;mso-bidi-language:
HI">erk.
</span
Detection of Diseases in Flora Through Leaf Image Classification by Convolution Neural Network
Get PDFThe quality of human existence and economic standing are significantly impacted by agriculture. It is the foundation of a nation's economic structure. Therefore, early diagnosis of plant diseases is crucial in both the agricultural sector and in people's daily life. Hunger and starvation are caused by agricultural losses due to plant diseases, especially in less developed nations where access to disease-controlling measures is limited and yearly losses of 30 to 50 percent for main crops are not unusual. Due to inadequate diagnosis of plant diseases, many plants die. Initially, diagnosis of plant disease was performed using MATLAB and machine learning algorithms including SVM. But these diagnoses did not provide accurate results. Also, in previous works website has not been created. To overcome this problem, a CNN model has been proposed that detects plant diseases. This CNN model has been deployed to the website. On this website, the image can be uploaded, and the disease gets predicted according to the image. The detected disease gets displayed on the website. To the CNN model, 15 cases have been fed, including both healthy and unhealthy leaves. The proposed model achieves a greater accuracy of more than 95%. This work offers a major benefit to the farmers by helping them in detecting plant diseases without requiring any special hardware or software
