Abstract
In colleges, universities, organizations, schools, and offices, taking attendance is one of the most important tasks that must be done on a daily basis. The majority of the time, it is done manually, such as by calling by name or by roll number. The main goal of this project is to create a Face Recognition-based attendance system that will turn this manual process into an automated one. This project meets the requirements for bringing modernization to the way attendance is handled, as well as the criteria for time management. This device is installed in the classroom, where and student’s information, such as name, roll number, class, sec, and photographs, is trained. The images are extracted using Open CV. Before the start of the corresponding class, the student can approach the machine, which will begin taking pictures and comparing them to the qualified dataset. Logitech C270 web camera and NVIDIA Jetson Nano Developer kit were used in this project as the camera and processing board. The image is processed as follows: first, faces are identified using a Haarcascade classifier, then faces are recognized using the LBPH (Local Binary Pattern Histogram) Algorithm, histogram data is checked against an established dataset, and the device automatically labels attendance. An Excel sheet is developed, and it is updated every hour with the information from the respective class instructor.
Full Paper

Abstract
Diabetic Retinopathy is a condition which occurs most commonly in patient with type 1 or type 2 diabetes. It affects the blood vessels of eye and delay in treatment can cause loss of vision. With the current state of the art deep learning technology, image classification can be performed with an accuracy as high as that of a human being. The idea behind this paper was to develop a highly accurate and reliable multi-class deep learning model which can detect the class of severity of diabetic retinopathy in a patient given an image of retinal fundus. The Aptos 2019 dataset was used for training the deep learning model. The proposed model also considered the high class-imbalance in the used dataset.
Results – Our model achieved 99.18% categorical accuracy in training set and 75.68% categorical accuracy in validation set.
Full Paper

Abstract
Sentiment analysis is a process that discovers the user opinions and views against any service or a product. YouTube is one of the most popular videos sharing platforms obtaining millions of views. These receive several comments, containing valuable information that helps in improving the rating levels of the uploaded content. These comments are utilized by using natural language processing techniques and machine learning techniques. There are many attempts had been proposed scholarly with two (positive or negative), three (two with neutral) or multiple (happy, sad, fear, surprise and anger) classes. However, it is challenging to choose the best accurate model. Therefore, there had been attempts to use sentiment analysis on YouTube comments in identifying the polarity as well. This research paper investigates the sentiment analysis methods and techniques that can be used on the YouTube content. Additionally, it explains and categorizes these approaches which are useful in researches in data mining and sentiment analysis.
Full Paper

Abstract
Credit card fraud detection is presently the most frequently occurring problem in the present world. This is due to the rise in both online transactions and e-commerce platforms. Credit card fraud generally happens when the card was stolen for any of the unauthorized purposes or even when the fraudster uses the credit card information for his use. In the present world, we are facing a lot of credit card problems. To detect the fraudulent activities the credit card fraud detection system was introduced. This project aims to focus mainly on machine learning algorithms. The algorithms used are random forest algorithm, linear regression, XGBoost, KNearest, Support vector classifier, Linear Discriminant Analysis, GaussianNB algorithm. The results of the algorithms are based on accuracy, precision, recall, and F1-score. The ROC curve is plotted based on the confusion matrix. Algorithms are compared and the algorithm that has the greatest accuracy, precision, recall, and F1-score is considered as the best algorithm that is used to detect the fraud.
Full Paper

Abstract
Intelligent Autonomous Systems (IAS) are highly cognitive, reflective, multitask-able, and effective in knowledge discovery. Examples of IAS include software systems that are capable of automatic reconfiguration, autonomous vehicles, network of sensors with reconfigurable sensory platforms, and an unmanned aerial vehicle (UAV) respecting privacy by deciding to turn off its camera when pointing inside a private residence. Research is needed to build systems that can monitor their environment and interactions, learn their capabilities and limitations, and adapt to meet the mission objectives with limited or no human intervention. The systems should be fail-safe and should allow for graceful degradations while continuing to meet the mission objectives. In this paper, we provide an overview of our proposed new methodologies and workflows, and survey the existing approaches and new ones that can advance the science of autonomy in smart systems through enhancements in realtime control, auto-reconfigurability, monitoring, adaptability, and trust. This paper also provides the theoretical framework behind IAS.
Full Paper

Abstract
Having diseases is quite natural in crops due to changing climatic and environmental conditions. Diseases affect the growth and produce of the crops and often difficult to control. To ensure good quality and high production, it is necessary to have accurate disease diagnosis and control actions to prevent them in time. Grape which is widely grown crop in India and it may be affected by different types of diseases on leaf, stem and fruit. Leaf diseases which are the early symptoms caused due to fungi, bacteria and virus. So, there is a need to have an automatic system that can be used to detect the type of diseases and to take appropriate actions. We have proposed an automatic system for detecting the diseases in the grape vines using image processing and machine learning technique. The system segments the leaf (Region of Interest) from the background image using grab cut segmentation method. From the segmented leaf part, the diseased region is further segmented based on two different methods such as global thresholding and using semi-supervised technique. The Features are extracted from the segmented diseased part and it has been classified as healthy, rot, esca, and leaf blight using different machine learning techniques such as Support Vector Machine (SVM), Adaboost and Random Forest tree.
Full Paper

Abstract
Corona virus disease 2019 has become a major health problem. It is spreading very widely due to its contact transparent behavior. So WHO declared to wear mask in crowded areas as a prevention method. Some of the areas the diseases become widely spread out due to improper wearing of facial mask. So to overcome this problem we required an efficient mask monitoring system. By the development of machine learning and image processing analysis introduce methods for mask detection. By using image processing analysis and machine learning method is used for find out mask detection. Face mask detection can be done through various methods. Mainly convolutional neural network method is used rapidly. The accuracy and decision making is very high in CNN compared to others. Here we are discussed about various deep learning techniques used for face mask detection.
Full Paper

Abstract
For the fight against obesity, precise food and energy intake measurement techniques are essential. One of the most important lessons for long-term prevention and effective treatment programmes is the provision of users and patients with practical and intelligent solutions that assist them in measuring their food intake and gathering dietary information. In this article, we suggest a calorie measurement technique to assist patients and medical professionals in their battle against dietrelated illnesses. In this document, we suggest a food identification system that, when given the appropriate quantity of data, can assist a user in keeping track of daily caloric consumption. Calorie estimation for the current method must be done by hand. The proposed model will use a deep learning algorithm to offer a special method of calculating calories. In the world of medicine, calorie calculations for food are crucial. because the calories in this food are beneficial to your health. This measurement is derived from photographs of various foods, including fruits and vegetables. Our suggested solution relies on cell phones, which enable the user to take a picture of the food and instantly calculate the number of calories consumed. We classify food photos for system training using deep convolutional neural networks to reliably identify the food in the system. In this study, we use a convolutional neural network (CNN) to detect and identify images of food. Given the huge range of food types, picture recognition of food products is frequently very difficult. Whatever the case, deep learning has recently been shown to be an incredibly innovative image identification approach, and CNN is the greatest way to use deep learning.
Full Paper

Abstract
A facial recognition system is a computer application for automatically identifying or verifying a person from a digital image or a video frame from a video source. Proposed paper uses face recognition technique for verification in ATM system. For face recognition, there are two types of comparisons. The first is verification, this is where the system compares the given individual with who that individual says they are and gives a yes or no decision. The next one is identification this is where the system compares the given individual to all the other individuals in the database and gives a ranked list of matches. Face recognition technology analyzes the unique shape, pattern and positioning of the facial features. Face recognition is very complex technology and is largely software based using Convolutional Neural network(CNN). Face Recognition is a computer application .It is capable to detect, identify or verify, track human faces from the input captured using a digital camera. This technology facilitates the machine to identify and recognize each and every user uniquely through the face as a key. This completely eliminates the chances of fraud due to theft and duplicity of the ATM cards. The captured face of the user must be matched with the registered face to have the access of the account. On the basis of iris uniqueness and other prerequisites the images of user are differentiated. The main aim or outcome of this project is to provide security to ATM transactions.
Full Paper

Abstract
Cryptocurrency is playing an increasingly important role in reshaping the financial system due to its growing popular appeal and mechant acceptance. While many people are making investments in Cryptocurrency, the dynamical features, uncertainty, the predictability of Cryptocurrency are still mostly unknown, which dramatically risk the investments. It is a matter to try to understand the factors that infiuence the value formation. In this study, we use advanced artificial intelligence frameworks of fully connected Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) Recurrent Neural Network to analyse the price dynamics of Bitcoin, Etherum, and Ripple. We find that ANN tends to rely more on long-term history while LSTM tends to rely more on short-term dynamics, which indicate the efficiency of LSTM to utilise useful information hidden in historical memory is stronger than ANN. However, given enough historical information ANN can achieve a similar accuracy, compared with LSTM. This study provides a unique demonstration that Cryptocurrency.
Full Paper

Abstract
Cryptocurrency is playing an increasingly important role in reshaping the financial system due to its growing popular appeal and mechant acceptance. While many people are making investments in Cryptocurrency, the dynamical features, uncertainty, the predictability of Cryptocurrency are still mostly unknown, which dramatically risk the investments. It is a matter to try to understand the factors that infiuence the value formation. In this study, we use advanced artificial intelligence frameworks of fully connected Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM) Recurrent Neural Network to analyse the price dynamics of Bitcoin, Etherum, and Ripple. We find that ANN tends to rely more on long-term history while LSTM tends to rely more on short-term dynamics, which indicate the efficiency of LSTM to utilise useful information hidden in historical memory is stronger than ANN. However, given enough historical information ANN can achieve a similar accuracy, compared with LSTM. This study provides a unique demonstration that Cryptocurrency.
Full Paper

Abstract
Intrusion Detection Systems are core part of cyber security measures in all organizations. With increasing amount of data available online in digitized form, this has resulted in an ever growing need for stringent cyber security measures against data breaches and malware attacks. Rising number of attacks coupled with new variants of malware being released on a frequent basis require automated intrusion detection systems. With the state of the art performance of the Deep Learning based Models in the field of computer vision, natural language processing and speech recognitionand Deep learning techniques are now being applied to the field of cyber security. Deep Learning has been efficiently implemented in Intrusion Detection Systems.
Full Paper

Abstract
Now-a-days all are using the cloud server to store their data and provides many features suitable for the users or customers. We have cloud servers like Google Cloud Platform, Microsoft Azure etc.For cloud also sometimes there will be storage problem to store the data of the users.We need the security to the data stored in the cloud.For hospitals and some private companies the data should be secure and confidential. So we need both storage and the security to our data stored in the cloud.
Client-Side Authorized Deduplication Here, it is suggested to use CP-ABE, which offers cloud-based security and deduplication. The proposed system offers data security in an encrypted format. In this system, we encrypted user data uploaded to the cloud with the CP-ABE algorithm using the user’s attributes. Additionally, it examines any file duplication on the cloud. When a file is deduplicated, the server forbids uploading an already-existing copy of the file. Deduplication assists in releasing cloud storage. The suggested scheme has benefits over current schemes and satisfies the security criteria. In the cloud context, the suggested permitted deduplication technique offers a good trade-off between storage space efficiency and security, and it is ideal for the hybrid cloud architecture.
Full Paper

Abstract
Cryptocurrency becomes more popular and merchant accept it, it is playing an increasingly vital role in reshaping the financial system. While many people are forming investments in Cryptocurrency, the vital features, distrust, the predictability of Cryptocurrency are quiet basically unknown, which dramatically risk the investments. It’s a business to strain to conclude the procurators that impact the value formation. Here we apply advanced artificial intelligence frameworks of completely connected Artificial Neural Network (ANN) and Long Short Term Memory (LSTM) periodical Neural Network to analyze the price dynamics of Bitcoin, Ethereum, and Ripple.We find that ANN tends to calculate more on long- term chronicle while LSTM tends to calculate more on short- term dynamics, which indicate the effectiveness of LSTM to exploit useful data hidden in literal memory is stronger than ANN. still, given enough historical data ANN can attain an analogous accurateness equated with LSTM. This reverie provides a unique demo that Cryptocurrency market price is predictable. Still, the explanation of the predictability could differ depending on the complexion of the detailed machine- learning model.
Full Paper

Abstract
The modern world is completely reliant on the internet for all aspects of daily life. With each passing day, the amount of time spent in the virtual world is increasing. Everyone in the world has money to spend more time than ever before is spent on the Internet. [7] Consequently, the dangers the number and severity of cyber-threats and -crimes are both rising.
“Cyber” is a phrase used to describe “threat” refers to criminal behaviour that is carried out through the use of the Internet. The methods used by cybercriminals are evolving as a result of passing through the barrier is now possible.
Conventional there is no method that can identify zero-day attacks. Attacks with a high degree of sophistication. [5] There has been a lot of machine learning so far. Detection methods for cybercrimes have been created a fight against cyber attacks. The purpose of this investigation presents an assessment of many commonly used machines. Gaining knowledge of detection methods for some very dangerous risks to cyberspace from cyber attacks. A basic machine learning framework consisting of three components the main focus of the research is on approaches, especially strong religious belief. a network, a decision tree, and an SVM As of right now, we don’t have any examined the effectiveness of these for a brief period of time spam detection, intrusion detection, and other applications of machine learning Based on commonly used and known malware detection and prevention techniques datasets for comparison purposes.
Full Paper

Abstract
Due to of the profound established and intentional damage suffered by polygenic disorder patients, it’s essential to structure cheap methodologies for the peace of mind and treatment of polygenic disorder. In perspective on our expansive assessment, this text bunches those procedures into polygenic disorder one.0 and polygenic disorder two.0, that show insufficiencies regarding frameworks organization and data. we’ll most likely structure a wise, monetarily perceptive, and sharp polygenic disorder assurance game arrange with redid treatment on these lines. During this article, we tend to initially propose the 5G sensible polygenic disorder system, which mixes the line headways, for example, wearable 2.0, AI, and tremendous information to form sweeping recognizing and examination for patients encountering polygenic disorder. By then we tend to gift {the information|theinfo|the information}-sharing half and redid the data examination model for 5G-Smart polygenic disorder. Finally, we tend to build a 5G-Smart polygenic disorder testbed that fuses clever article of clothing, itinerant, and Brobdingnagian information fogs. The take a look at outcomes exhibit that our system will effectively offer altered examination and treatment proposition to patients.
Full Paper

Abstract
Human visual awareness is a hot topic in the machine vision world right now. In applications such as video surveillance, human computer interface, face recognition, and image management, Human face localization and recognition is possible frequently the first step. Identifying and monitoring human faces might be difficult. Although a generic face picture is frequently accessible, face recognition and/or countenance analysis are required. The issue of the study of impartial facial data by computer-based face recognition remains a relatively unexplored field of research. Face recognition is one of the many marvels that AI research has offered to the world. Many techies are interested in this topic because they wish to have a fundamental grasp of how things work. Let’s go into the subject to see how it works. This study describes how deep learning, an essential aspect of the computer science discipline, may be utilized to detect the face utilizing many libraries in OpenCV and Python. This article will include a suggested technology for detecting the human face in real time. This solution may be utilized on a variety of platforms, including machines, cellphones, and software applications. In the face of any image, this strategy is efficient and effective. In addition, the article discusses popular OpenCV applications and classifiers used in these applications, such as image processing, face identification, object detection and facial recognition. Finally, we address various literary assessments applications based on OpenCV in computer vision disciplines such as face detection and recognition, recognition of facial emotions such as grief, rage, and happiness, and recognition of a person’s gender and age.
Full Paper

Abstract
The quick response code (QR) has become most popular barcode because of its larger data capacity and increased damage resistance. Barcode scanners can easily extract information hidden in the QR code when scanning data forms. However, some confidential data stored directly in QR codes are not secure in real world QR apps. To proposed approach to visual secret sharing scheme to encode a secret QR code into distinct shares. In assessment with other techniques, the shares in proposed scheme are valid QR codes that may be decoded with some unique that means of a trendy QR code reader, so that escaping increases suspicious attackers. An existing sharing technique is subjected to loss of security. On this premise, consider the strategy for (k, n) get to structures by using the (k, k) sharing occurrence on each k-member subset dependent on specific relationship. In addition, the secret message is recovered with the aid of XOR-ing the qualified shares. This operation which can effortlessly be achieved the use of smartphones or different QR scanning gadgets. Contribution work is, working on optimal partitioning methods and compare original message with shared message using hashing techniques.
Full Paper

Abstract
The old method of marking attendance involves the lecturer providing an attendance sheet to the students for their signature or the teacher calling out students name individually to mark them present. This old manual method is pretty hectic for teachers and students too. Since, after taking the signed attendance sheet from students, teachers have to manually keep track of every student in the logbook which turned out to a lot of time wastage, missing out studentspresenteeism or students giving proxies for the absentees due to which logbooks can be easily manipulated or prone to errors also, wastage of pen and paper. To avoid this problem, we have developed a system which will monitor the attendance of students by identifying their faces via their facial features. While developing this system we have used a web Camera to capture multiple live images of students for face recognition, Viola-Jones Algorithm to achieve face detection which uses Haar Cascade classifier, Pre- processing which converts the image in greyscale, LBPH algorithm and deep learning algorithms like CNN (Convolutional neural networks) for feature extraction and last but not the least the input faces are then matched with the trained images in the database and once they match, the student will be marked as present and the ones who didn’t match weremarked as absent in the class. Accuracy of 85% and 95% was obtained by testing the model with ten different faces with different facial expressions, angle and lighting conditions for LBPH algorithm and CNN (Convolutional neural networks) respectively.
Full Paper

Abstract
In Wireless Communication Systems (WCSs), the network optimization problems (NOPs) play an important role in maximizing system performance by setting appropriate network configurations. When dealing with NOPs by using conventional optimization methodologies, there exist the following three problems: human intervention, model invalidity, and high computation complexity. As such, in this article we propose an auto-learning framework to achieve intelligent and automatic network optimization by using machine learning (ML) techniques. We review the basic concepts of ML, and propose their rudimentary employment models in WCSs, including automatic model construction, experience replay, efficient trial and error, RL-driven gaming, complexity reduction, and solution recommendation. We hope these proposals can provide new insights and motivation in future research for dealing with NOPs in WCSs by using ML techniques.
Full Paper

Abstract
In the era of internet and online connectedness, where data is the most valuable asset, it is ever important for an organization to protect itself and it’s assets from various security threats. One of these threats is a Distributed Denial of Service (DDoS) attack that can cut off the network service by overwhelming the targeted server or network by flooding it with superfluous requests in an attempt to overload the server to prevent legitimate requests from being fulfilled. DDoS attacks utilize multiple compromised systems as sources of internet traffic to increase their effectiveness. What makes DDoS attacks more lethal is that fighting them requires differentiating legitimate requests from illegitimate ones. A site or service unexpectedly being sluggish or inaccessible is the most obvious symptom of a DDoS attack. But since a number of causes like legitimate spike in network traffic can create similar issues, further investigation is necessary.
Full Paper

Abstract
Cloud computing is a category of network-based computing environment that provides the customers with computing resources as a service over a network on their demand. Load balancing in cloud is the process of distributing the work load among various nodes in a distributed system for better resource utilization and job response time. The load balancer calculates the value in the particular time-span and uses this value to estimate the virtual machine availability for the next time span. Load balancing ensures that all the processor in the system or every node in the network does approximately perform the equal amount of work at any instant of time. It is a process of assigning the total load to the individual nodes of the collective system to make resource utilization effective and to improve the response time of the job, simultaneously removing a condition in which some of the nodes are over loaded while some others are under loaded. It can be observed CPU utilization, throughput etc. will be improvised while balancing the load to virtual machines on the basis of utilization of resources on an instant time. This research work has proposed a novel technique to analyse the performance of optimized load balancer. The offered technique is based on condition which will provide high availability to clients, and estimating the required measures by varying the interval time. In proposed Optimized Load Balancer technique, we tried to avoid the situation of over loading and under loading of virtual machines. The Optimized Load Balancer manages load distribution among various virtual machines and assigns load corresponding to their priority and states. In this way this technique efficiently shares the load of user requests among various virtual machines.
Full Paper

Abstract
In this survey paper we have concentrate on deep learning through brain tumor detection using normal brain image or abnormal by using deep learning. The brain is largest and most complex organ in human body that works with billions of cells. There are three types of tumors as benign, premalignant and malignant. The convolutional neural network algorithm is used to detecting the brain tumor. There are many existing techniques are available for brain tumor segmentation and classification to detect the brain tumor. There are many techniques available presents a study of existing techniques for brain tumor detection and their advantages and limitations. To overcome these limitations, we used Convolution Neural Network (CNN) based classifier. CNN based classifier is used to compare the trained data and test data, from this data get the best result.
Full Paper

Abstract
Cardiovascular diseases are considered due to the fact the most lifestyles-threatening syndromes with the best mortality rate globally. As in step with the distinctive evaluation about eighty-four million human beings in this USA be afflicted by a few shapes of cardiovascular ailment, inflicting approximately 2, two hundred deaths a day, averaging one loss of life every forty seconds. Almost one out of each 3 deaths consequence of cardiovascular ailment. In this task, we’re the use the MaLCaDD framework to get the most accuracy with immoderate precision and the validation of the framework is finished thru three benchmark datasets (i.e. Framingham, Heart Disease, and Cleveland), and the accuracies of 99.1%, 98.0%, and 95.5 % are completed respectively through the use of the KNN and logistic regression method. Finally,the comparative assessment proves that MaLCaDD predictions are greater accurate (with a reduced set of features) in the evaluation of the winning contemporary-day methods.Therefore, MaLCaDD is exceptionally reliable and can be carried out in a real environment for the early analysis of cardiovascular diseases.
Full Paper

Abstract
According to the International Diabetes Federation, there are currently over 470 million individuals diagnosed with diabetes globally, and by 2050, that number might rise to 700 million. There are two types of it: Type 1 and Type 2. Type 1 diabetes is chronic and incurable, however Type 2 diabetes can be cured if caught early. Identification of anomalies in retinal pictures is tough and complex in the medical sector since these signs of diabetes that affect the eyes appear to be very modest. Therefore, a non-invasive technique to uncover these abnormalities was required.
After reviewing a number of research projects and developments, we attempt to highlight and explain the various methodologies used, their benefits and limitations, the general goal of the results, and the significance of a DR detection system. The survey also highlights the significance of early detection and the need to eliminate the factors that obstruct timely discovery.
Full Paper

Abstract
The internet and mobile technology have developed quickly and made it possible for us to freely access various music resources. While the music industry might lean more toward certain genres of music. But there is no particular way by which we can understand what exactly user wants to listen based on current mood or emotion. Music is a great way to express emotions and moods. For example, people like to listen to happy songs when they are feeling good, a soothing song can help us to relax when we’re feeling stressed or exhausted and people tend to listen some sort of sad songs when they are feeling down. So in this project, we are going to develop a system which will capture the real time emotion of user by conversating with user or by other means and based on that emotion related songs will be recommended. We are going to categorize songs into the groups based on the categories like Happy, Sad, Neutral etc. Then according to the captured emotion from the user, the songs related to that emotion will be recommended. In this way, user can listen the songs according to the mood.
Full Paper

Abstract
Cyberbullying or cyber harassment is a form of bullying or harassment using electronic means. Cyberbullying and cyber harassment are also known as online bullying. It has become increasingly common, especially among teenagers, as the digital sphere has expanded and technology has advanced.In this research, we have addressed the problem of cyberbullying detection on Twitter Data Set. Various inbuilt Multiclass Classification Algorithms in Python such as Naive Bayes, Decision tree, Random Forest, K Nearest Neighbor (KNN), Support Vector Machine (SVM), and Natural Language Processing (NLP) techniques are used to classify bullying and non-bullying tweets and performance of these algorithms is compared and model with highest accuracy is selected for the prediction. Bullying tweets will be reported to the nearest Cyber Crime Branch.
Full Paper

Abstract
In Earth there large varities of planet consisting of number of many unknown and known species. Recognizing flora is ability to identify the plant species from the photographers and provide the medicinal information along with the diseases that can be cured by the plants it is an intelligent system .Creating a Tool that Identify the plant by data of certain characteristics features of Leaves. Comparison between standard data and recorded data is done based on predefined parameters. This will also help us to determine the medicinal values that particular plant has in by Classification based on the Characteristics. This identification should be automated as this process was done by human and every person could not identify accurately even if he identify correctly he could not be efficient.So with the help of the expert system can be designed.
Full Paper

Abstract
Expansive soils are always considered as one of the most problematic soil for civil engineers because of their extreme swelling and shrinkage attributes. The nature of swelling and shrinkage properties is due to moisture content change. And because of this, huge settlements and structural damages take place. To understand the cause of failure, the index properties and engineering behavior of the soil should be understood. Many experimental investigations are done in the past concerned over the stabilization of expansive clay soil. In present study, the waste material like rubber powder is selected as the soil stabilizer for modifying soil properties. The soil collected for the study is blended with the varying percentage of stabilizers along with chemical admixtures and laboratory tests were conducted on the blended soil samples to evaluate the effectiveness of stabilizers in stabilization of black cotton soil. Finally, the stability of black cotton Soil is evaluated and optimum dosage of admixture is suggested.
Full Paper

Abstract
Face recognition is one of the mostly used biometrics. It can used for security, authentication, identification, and has got many more advantages. Despite of having low accuracy when compared to iris recognition and fingerprint recognition, it is being widely used due to its contactless and non-invasive process. Furthermore, face recognition system can also be used for attendance marking in schools, colleges, offices, etc. This system aims to build a class attendance system which uses the concept of face recognition as existing manual attendance system is time consuming and cumbersome to maintain. And there may be chances of proxy attendance. Thus, the need for this system increases. This system consists of five phases- database creation, face detection, face recognition, attendance, temperature check and updation.
Full Paper