IJSRET Volume 6 Issue 6, Nov-Dec-2020



Face Expression Recognition: A Review
Authors:- M.Tech. Student Palak Jain, Assistant professor Anamika Pyasi

Abstract:- Recognition of outward appearances assumes a significant job in many mechanized framework applications like mechanical technology, instruction, man-made brainpower, and security. Perceiving outward appearances precisely is testing. Approaches for explaining FERi(Facial Expression Recognition) issue can be ordered into 1) Static single pictures and 2) Image successions. Customarily, various procedures like Multi-layer Perceptron Model, k-Nearest Neighbors, Support Vector Machines were utilized by scientists for fathoming FER. These techniques removed highlights like Local Binary Patterns, Eigenfaces, Face-milestone highlights, and Texture highlights. Among every one of these techniques, Neural Networks have increased especially ubiquity and they are broadly utilized for FER. As of late, CNNsi(Convolutional Neural Networks) have picked up notoriety in field of profound learning in view of their easygoing engineering and capacity to give great outcomes without prerequisite of manual component extraction from crude picture information. This paper centers around review of different face demeanor acknowledgment methods dependent on CNN. It incorporates cutting edge techniques proposed by various scientists. The paper additionally shows steps required for utilization of CNN for FER. This paper additionally incorporates examination of CNN based methodologies and issues requiring consideration while picking CNN for unraveling FER.

Income Analysis of Census Database Using Pyspark
Authors:- Abhishek R., Pavan Dutt, Sahana S. R., Assistant Professor Dr.M.Sujithra M.C.A,M.Phil,Ph.D, Assistant Professor Dr.P.Velvadivu M.C.A.,M.Phil.,Ph.D.

Abstract:-The data set contains information about every individual’s age, education level and various other features from the census along with the income . The income feature is a categorical feature with two classes i.e., less than 50k dollars or greater than 50k dollars. The problem is to build a machine learning model that could effectively predict the income of people given the input features. Considering the size of the data and the dimension of the data, the model is built using Big Data Techniques.

Review of Machine Learning Algorithm on Cancer DataSet
Authors:- M. Tech. Scholar Animesh Urgiriye, Assistant Professor Rupali Bhartiya

Abstract:-Cancer is a basic disease from numerous years. This prompts demise in the event that it isn’t analyzed at beginning phase. It is a subject of concern on the grounds that genuine treatment of this infection isn’t found till date. Patients having this sickness must be spared if and just in the event that it is found in beginning phase (I and II). On the off chance that it is recognized in last stage (III and IV) at that point possibility of endurance is extremely less. AI and information mining strategy is exceptionally useful method to deal with this issue. AI is exhibiting the guarantee of creating reliably precise appraisals. AI framework successfully “realizes” how to assess from preparing dataset of finished activities. There are different procedures accessible in Machine Learning to foresee the Cancer based on gathered standard datasets. The datasets may have been recorded by web-based media, medical care sites and some different vaults. We have to apply a few classifiers of Machine Learning Techniques on these dataset to recognize the disease in a human. The primary point of the audit is to help the exploration on exact assessment, for example to ease different specialists for pertinent right assessment examines utilizing AI procedures. Our survey recommends that these procedures are serious with conventional assessors on datasets and furthermore show that these strategies are touchy to the information on which they are prepared.

Application of the Analytical Hierarchy Process (AHP) for Geo-Hazards Susceptibility Mapping:Urban Settlement Marquez De León, La Paz.,Mexico.
Authors:-Joel Hirales-Rochin

Abstract:- Geology as a tool to identify areas of geological risk is useful to determine the close relationship between thegeological Space and the sustain able urban development ofacity. Atthenational, regional and local level where the study are a is located, there is a growing need to create new urban areas, but these are not linked to an adequate analys is of the geological environment and the knowledge of the main factors that control risk conditions. The methodology was based on a characterization of the geological, hydro geological and geo mechanical conditions of one of the main urban settlements of the city of La Paz, capital of the state of Baja California Sur., Mexico. Therefore, using the Analytic Hierarchy Process (AHP) methodology it was generateda risk susceptibility map-related in local areas to flood events and landslides. The results represent the first stage of a larger scale project and with this; it is possible to contribute new knowledgeto be used in the most precisezoning of geographic risks, which will allow the state capital a sustainable growth of the population of the city. The improvement of current constructionst and ards and the corresponding zoning to anticipate their development in anorderlymanner.Finally, it is considered that this research´s type (urban settlementscale) provides ananalysis of the risk conditions where the citizen can locate in their community and know their conditions of civil protection, all the opposite of most risk studies that offer large- scale results and only offer a broaderview.

Website Development of Mudis Cooling
Authors:-Professor Jadhav P.D, Akshay Gade, Piyush Pipriye, Pranav Bansod,
Soham Badjate, Mohammed Mustafa

Abstract:- A website or web site is a collection of related network web resources, such as web pages, multimedia content, which are typically identified with a common domain name, and published on at least one web server. Notable examples are wikipedia.org, google.com, and amazon.com. Websites can have many functions and can be used in various fashions; a website can be a personal website, a corporate website for a company, a government website, an organization website, etc. A static website is one that has web pages stored on the server in the format that is sent to a client web browser. It is primarily coded in Hypertext Markup Language (HTML); Cascading Style Sheets (CSS) are used to control appearance beyond basic HTML. Images are commonly used to effect the desired appearance and as part of the main content. Audio or video might also be considered “static” content if it plays automatically or is generally non-interactive. A dynamic website is one that changes or customizes itself frequently and automatically. Server-side dynamic pages are generated “on the fly” by computer code that produces the HTML (CSS are responsible for appearance and thus, are static files). There are a wide range of software systems, such as CGI, Java Servlets and Java Server Pages (JSP), Active Server Pages and ColdFusion (CFML) that are available to generate dynamic web systems and dynamic sites The objective of this project is to prepare the static web site for Modi’s cooling, a dealer of cooling electronic appliances such as Air conditioning units, deep freezer, fruit freezer etc. The function of a web site to provide online information to the customer about the product available, the prices address and contact number of the dealer. For design of this web page HTML is used whereas for database and uploading SQL, MYSQL

Seismic Response Study of Multi-Storied Reinforced Concrete Building With Accordion Mass Dampers
Authors:-Mr. P. G. Kadwade, Prof. Zubair Shaikh, Dr G. R. Gandhe

Abstract:- Damping plays important role in design of earthquake resistant structures, which reduces the response of the structure when they are susceptible to lateral loads. There are many different types of dampers in use. In the present study accordion mass dampers (AMD) are used to evaluate the response of RCC buildings. The main task of a structure is to bear the lateral loads and transfer them to the foundation. In order to have earthquake resistant structures, accordion mass dampers (AMD) have been used. The building is modeled in ETAB 2018 and modeled with different location of AMD. After the study results show building having AMD on outer side shows better performance than building having other location of accordion mass damper.

Development of a Healthy Noodles Enriched with the Flavors of Coleus Aromaticus, Mentha, Erythrina Indica
Authors:- Suruthi B., Amutha A.

Abstract:- Noodles have been the staple foods for Asian countries since ancient time. They can be made from wheat, rice and other raw materials such as buckwheat and starches derived from potato, sweet potato and pulses. Normally, wheat noodles is enriched with protein, carbohydrates and fibre content. This study was conducted to add additional nutrients content to the wheat noodles by incorporating the powders of Coleus amboinicus (Omavalli leaves), Mentha (mint leaves) and Erythrina Indica (Kalyana murungai leaves). Omavalli leaves is used in curing cough, cold, stomach problems, indigestion etc. Mint leaves is used for easing queasy stomach, calming stress and anxiety etc. Kalyana murungai leaves is useful for treating cough, cold and is very good for women as it treats many ailments that women regularly face. People use to crush these leaves and eat in the normal mouth or boiled these leaves in the water and from cold, cough or fever. But not everyone like to have this. As we know, noodles is a food, with zero haters. So we have incorporated these flavours in noodles. This noodles is prepared with the composition of 55% wheat flour, 15% omavalli powder, 15% mint powder and 15% kalyana murugai powder.

Upfc Power Compensation with Power Generation Smart Grid
Authors:- Suresh Waskle, Mr. Lavkesh Patidar

Abstract:- The problem of power system to face many problem like as power quality, THD and stabailuty.in modern technology to use of FACT Devices, The FACT Device are many types these paper are present of UPFC power stability device oriented. For recent used many technique to improvement of UPFC performance and reduction of THD. We proposed Machine learning technique like as Fuzzy logic and shunt filter with transformer work as controller to controlling of power transient conditions.

A Review: Air Pollution Analysis System Using IOT
Authors:- KulprakashSingh , Avatarsingh, Mistry, Balaji Khansole Sir

Abstract:- In this paper we are getting to make an IOT Based pollution Monitoring System during which we’ll monitor the Air Quality over a webserver using internet and can display on webpage when the air quality goes down beyond a particular level, means when there are sufficient amount of harmful gases are present within the air like CO2, smoke, alcohol, benzene and NH3. It will show the air quality on webpage so that we can monitor it very easily. The main reason for increasing of pollution level are crop’s remaining burning, emission from the automobile, open defecation of smoke in atmosphere from the industries and burning of garbage openly. Internet of Things (IoT) based pollution system is employed to detect the present level of hazardous gases in the atmosphere. The IoT based pollution system will help us to fetch the info from any location where device is installed. By using the concept of IoT we can use multiple pollution devices at different locations and fetch the data to the web server.

Design and Analysis Of A Upqc Power Flow Control Using Distribution Transformer
Authors:- Bhavsingh Ajnare, Mr. Deepak Bhataniya

Abstract:- Unified power quality conditioners (UPQCs) allow the mitigation of voltage and current disturbances that could affect sensitive electrical loads while compensating the load reactive power. Diverse control techniques have been proposed to evaluate the instantaneous output voltage of the series active power filter of the UPQC but, in most cases, these controllers only can compensate a kind of voltage disturbance.

Construction of Runways by Soil Stabilisation/Recycling Technology Gmr Airport Hyderabad
Authors:- K.Hima Vamsi, K.V Prabhakar Rao

Abstract:- Rajiv Gandhi international airport servers as a important international Airport in south India.The RITES has done a comprehensive study of the Existing Pavement and identified the weak areas. Stabilization has been taken up in those areas. The total area of stabilization work is 7 Lakh Sqm which includes main runway, secondary runway and taxiway. Out of this 7 Lakhs Sqm Approximately 33(2,30,000 Sqm) Approximately 67% (4.70,000 Sqm) for relaying works.

Credit Card Fraud Detection using Autoencoders
Authors:- Saatwik Bisaria, Aryan Aditya Singh, Sarita Yadav

Abstract:- There are certain characteristics of fraudulent transactions that differentiate them from legitimate ones. Machine Learning algorithms recognize patterns in the data points which allow them to detect fraud transactions from legitimate ones, based on thousands of pieces of information, that sometimes may seem completely unrelated to a human being. In Machine Learning, problems like fraud detection are usually framed as classification problems —predicting a discrete class label output given a data observation. Autoencoders are special type of neural network architectures in which the output is same as the input. Autoencoders are trained in an unsupervised manner in order to learn the extremely low-level representations of the input data. These low-level features are then deformed back to project the actual data. An autoencoder is a regression task where the network is asked to predict its input (in other words, model the identity function). These networks have a tight bottleneck of a few neurons in the middle, forcing them to create effective representations that compress the input into a low-dimensional code that can be used by the decoder to reproduce the original input.

Leave a Reply

Your email address will not be published. Required fields are marked *