Search

In this modem age, the use of biometrics is an important aspect in the lives of people in all areas. Iris recognition is now a trustworthy method of personal recognition due to the outstanding requirements for security and reliable types of identification in biometric systems. It is a main and challenging field of study because of its advantages of high precision and non-contact recognition technology. In automatic identification, iris recognition technology plays a vital role. This paper introduces a new concept of optimal security where the proposed system is trained using Convolutional Neural Networks (CNN) incorporated with softmax classifier. The model is trained on a dataset for iris recognition where only a small number of images were trained for each set and showed an enhancement in the results over earlier methods. It focuses on a systematic approach for iris recognition, even when the images have noise, obstructions and various levels of illuminations. Experiments with standard datasets have shown that the put forward approach can attain high performance than competing with other deep learning-based methods. The efficiency gained from iris recognition based on performance evaluation is accurate, achieving a total of 99%. [ABSTRACT FROM AUTHOR]

Here, the efficiency, pollution attributes of a typical DI Diesel power train working on Diesel fuel, B20, and the combination of B20 with MgO and TiO2 in the aforementioned proportions(B20NA25, B20NA50, B20NA75, and B20NA100), were examined. The experiment was conducted with a Mono-cylinder Diesel engine runs at 1500 rpm speed at steady-state circumstances. Throughout the testing, the engine output, fuel consumption, and exhaust pollutants are noted. Methyl ester of Papaya and Diesel fuel was shown to create much less Smoke, HCand COpollution. However, when equated to diesel fuel, it exhibited a less BTE and a 3.2% higher BSFC. However, when the cylinder's internal temperature increased, so did the NOX emission. [ABSTRACT FROM AUTHOR]

The main ideal of this document is to Analyze and Design of a Multi storey structure applying a Software usually known as STAAD Pro and its cost prediction using a AI technique called Machine Learning. In this we are designing a multi storey building of G+12 which involves load calculations, sesmic load conditions and analysing of building by STAAD pro and also analyzing the building erect for chancing the bending moments, shear forces, deflections and also underpinning details for the structural members of structure(similar as shafts, columns & crossbeams) for developing the provident and sustainable design. For this design process we used Indian standard code books of IS 456-2000, IS 875 (Part 1,2,3,5). AUTOCAD software is used for development of plans and the plan is imported to staad pro and designed. The total height of the building is 39m and the area of the building is around 8000sq.ft consisting of 12 floors. This paper also introduces machine learning (ML) technology to optimize design costs. In our project we used linear regression algorithm. Linear regression relationships are modelled using a linear prediction function that estimates unknown model parameters from data. Data is given in form of datasets that comprises of attributes such as essential building materials and their cost according to the area, so that the future cost is predicted accordingly. The result obtained in trained model and the manual estimation is accurate. In this project we are calculating and comparing the cost of high rise, mid rise and dwarf buildings through machine learning as well as through manual estimation of the building. [ABSTRACT FROM AUTHOR]

Video Surveillance assumes a vital part in the present world. The innovations have been progressed an excessive amount of when man-made brainpower, AI and profound learning pitched into the framework. Utilizing above mixes, unique frameworks are set up which assists with separating different dubious practices in live following of recordings. The greatest unusual thing is human conduct and is undeniably challenging to discover whether it is dubious or ordinary. Profound learning approach is utilized to distinguish dubious or ordinary movement in a scholastic climate, and which sends an alarm message to the comparing authority, if there should arise an occurrence of anticipating a dubious movement. Observing is frequently performed through successive outlines are extricated in video. The whole system is partitioned into two sections. At initial segment, highlights are registered in video outlines and in other part, in view of the got highlights classifier foresee dubious or ordinary. [ABSTRACT FROM AUTHOR]

There are very few automobiles in developing countries because two wheelers have always been the uppermost mode of transport. Motorcycle crashes have been on the rise in the last few years. A number of people who are involved in traffic collisions include motorcyclists who do not wear reflective helmets, since they do not believe they provide sufficient protection. Once the traffic police spot those driving Motorcycles on a whole-or Motorcycles in junctions-without helmets, they also use video from CCTV to take control of the drivers of those vehicles and penal those who are riding without one. However, it can only be achieved through human action and commitment. Again they classifies moving vehicles as motorcycle or nonmotorcycle. for example, when referring to the head component, in the case of a motorcyclists, it is graded as either full face or non-full face. An excellent image analysis of the motorcycle number is then used to extract the characters that were missed by the identification software and/ Finally, the character count of the motorcycle is found, and from the motorcycle is examined using OCR software. The algorithm detects Objects to discover faces from still photos or videos. In their study "Rapid Object Detection using a Boosted Cascade of Simple Characteristics," Viola and Jones presented edge or line detection features, which are used by the technique. A deep learning algorithm called a convolutional neural network may analyse a picture as input and rank its significance. to separate elements/objects in the picture and be able to tell one from the other. Because of its great accuracy, CNNs are utilized for picture categorization and recognition. With the use of a hierarchical model, the CNN creates a network in the form of a funnel that eventually yields a fully connected layer in which all of the neurons are interconnected and the output is processed. [ABSTRACT FROM AUTHOR]

The aim of this research work is to improve the accuracy of currency more efficiently using Region based Image segmentation compared with Edge based segmentation. Materials and Methods:The accuracy and sensitivity of Region based image segmentation (n=20) was compared with accuracy and sensitivity of Edge based segmentation(n=20) with p value 0.8 by varying different currency images in Matlab simulation tool. The extraction rate is to be improved in terms of accuracy and sensitivity using Region based image segmentation and it is compared with Edge based segmentation for different currency images. Result : According to results obtained Region based image segmentation method has accuracy 96.91% and edge based segmentation accuracy 89.33% and the sensitivity of Region based image segmentation is 96.37% and also sensitivity of edge based segmentation is 89.09%. Region based image segmentation has results significantly 0.00 compared with Edge based segmentation 0.00. Conclusion :Within the limits of study, the accuracy and sensitivity of currency images using Region based Image segmentation provides significant results. [ABSTRACT FROM AUTHOR]

There is a plethora of tools available in the literature for analysis and prediction. Some of them are built on top of JAVA scripts for Matlab, Minitab, SPSS, R, Ky plot, etc., while others are based on C programming. The article makes use of the WEKA programme, which stands for Waikato Environment for Knowledge Analysis. We use atmospheric data such as visibility, wind speed, minimum and maximum temperatures, and local weighted learning (LWL) and regression by discretization (R2D) techniques based on M5P trees. After calculating the RMSE and SMAPE for each of the three trees, we can then pick the optimal one. [ABSTRACT FROM AUTHOR]

This paper aims at measurement of hydrodynamic parameters of cold model of Pressurized Fluidized Bed Gasifier (PFBG) and develops hydrodynamic similarity with the existing hot model PFBG of an IGCC Power plant. In the present experimental work, pilot scale hot model data of PFBG of 168 TPD had been verified by constructing hydrodynamically similar cold model of 2/3rd scale semi-circular. Also pressure measurements at four different heights have been taken for recording pressure fluctuations. Bed hydrodynamics are reflected in the amplitude of pressure variations, which is shown to be proportional to bubble size. Variable distributor setups with apex angles of 1500 and 1800 have been tested. Which were designed, fabricated and tested in a cold model and the optimised distributor configuration arrived. Various materials, including REFRACTORY (with mean particle sizes-0.8mm) and BOTTOM ASH (with mean particle sizes-0.8mm), were tested at varying static bed heights (D, 1.5D, 2D) using distributors with apex angles of 150° and 180°. We have shown the variation of distributor pressure drop (ΔPd) and Bed pressure drop (ΔPbe) over time as a function of surface velocity (Uo) have been recorded and formatted into a graph of ΔPbedVsUo. The Umfs for the aforementioned materials at the aforementioned static bed heights for the aforementioned distributors are then calculated. Minimum fluidization velocities (Umf) were found to be decreasing with the increase in static bed heights when air flow was raised from zero to its maximum (D, 1.5D, 2D). The Umf values are found to be increasing with increase in distributor apex angle (α) from 150° to 180°. [ABSTRACT FROM AUTHOR]

In this paper, our aim is to reduce sensors and measure pulse and temperature to monitor in rapid speed. A total of 25 samples are collected from one person by using Sensors. These samples are divided into training dataset (n=70%) and test dataset(n=30%). Time period values are calculated to quantify the performance of the Arduino based system. By using Arduino to monitor specific functions like pulse and temperature in 30 sec i.e quicker than previous conventional system which takes at least 1 minute. Arduino uno reduces measuring time by reducing more number of sensors when compared with conventional systems which have more sensors that take more time to monitor. [ABSTRACT FROM AUTHOR]

Rainfall plays an important role for cultivation and drinking purpose. If rains are high human beings face problems like floods and rains are low human beings again face another problems like droughts. In this paper, annual rainfall data from 1988 to 2017 is used for estimation of outliers using control limits and specification limits. After eliminating outliers for modified data of Rayalaseema, Coastal Andhra Pradesh and Telangana regions, we are fitting general linear model, Holt's linear exponential smoothing model and Brown's linear exponential smoothing model. Best among these three models is estimated using R2 criteria. [ABSTRACT FROM AUTHOR]

With the increase in the population density, portability and industrial pursuit maintain at a stimulating rate, in the recent years, air pollution has acquired the surveillance of policy makers in both the urban and metropolitan areas. There is a frequent review in highly polluted cities concerning the growing mortality correlated with acute diseases whose consequences may be incensed owing to exposure to air contaminants. Forecasting environmental pollution is contemplated as an indispensable lead for timely warning and control management of environmental pollution, specifically in emergency circumstances, where large proportions of pollutants are immediately liberated in the air, bringing about substantial destructions. Predicting environmental pollution in such circumstances is distinctly demanding owing to numerous spatial aspects influencing environmental pollution. In this study, we propose a method called Bivariate Gibbs and Spatial Correlated Deep Prediction (BG-SCDP). The proposed BG-SCDC based on Bivariate Gibbs Aggregated Feature Selection algorithm and Spatial Correlated Deep Prediction for highly dynamic environmental prediction mining. First, meteorological big data dataset is provided as input to the Bivariate Gibbs Aggregated Feature Selection model. Here, data points that include missing value are eliminated therefore obtaining computationally efficient features for further reference. Furthermore, if uncertain spatial big data analytic estimates of prediction make the forecasting more reliable, a Convoluted Long and Short-Term Memory for highly dynamic environment quality prediction is designed that allows in mining spatial data features in a precise and accurate manner. We conduct extensive experimental evaluations using meteorological dataset. The results demonstrate the efficiency of our proposed BG-SCDC method in comparison to state-of-the-art methods in terms of execution time, true positive rate and prediction accuracy. [ABSTRACT FROM AUTHOR]

MD simulation is used to study the interaction between the molecules at atomic as well as molecular level. In this simulation study, Carbon nanotube has been dispersed in water base solution to measure the interactions between the carbon-carbon, carbon-hydrogen, carbon-oxygen, hydrogen-oxygen molecules. Lennard-Jones (LJ) potential is used to determine the interfacial properties between the CNTs and water molecules. Study depicts that viscosity of the nanofluid increases as the concentration of particle increases at fixed temperature 308K and vice versa. Investigation concluded that at fixed temperature 308K, viscosity of nanofluid is 373.69mPa-ses. [ABSTRACT FROM AUTHOR]

Civil engineering has grown in numerous aspects as a result of technological advancements and evolution. Previously, the study and sustainability of civil structures were done using paper-based calculations, which resulted in insufficient precision and changeable elements causing the structure's demise through inevitable events. However, with the help of the integration of various engineering fields, this determination of various characteristic changes, deformation, or failure caused by hidden factors that are left out in real-time and manual calculations, i.e., paper-basedcalculations, has converted and led this system to a whole new level. Currently, Various software are being developedfor the analysis, computing, and management of a very precise RCC Entrance Arch. This study explains how to use and benefit from the software STAAD Proficient in the field of building and in the examination of concrete structures. [ABSTRACT FROM AUTHOR]