The purpose of this paper is t o develop an automated system which gives reply to user query on behalf of human for education system. It can give answer to each and every query asked by end user. Existing Chabot such as Facebook chat bot, WeChat, Natasha from Hike, Operator, etc. were giving reply from its local database. But our approach is to focus on local database as well as web database and also to make system scalable, user friendly, highly interactive. Various techniques such as neural network (RNN), NLP, pattern matching data mining algorithms are used in this paper to enhance the performance of the system

Cloud computing systems have graced the internet world in a way that no other technology has ever done before. They bring in a sense of comfort and a superiority that has enriched the lives of people who have benifited from it. Many giant companies like Google, Amazon and Microsoft has taken this technology to the next level by providing Google Cloud platform, Amazon Web Services and Microsoft Azure respectively. The problem comes in with the amount of data that is being uploaded to the cloud. The amount of data is directly proportional to the storage hardware devices and backup media used. The simplification that the businesses and enterprises enjoy comes at a cost. A technology called data deduplication can severely reduce the amount of data that is being stored on the cloud. Most of the data on the internet is redundant. Storing the replicated data on the cloud only increases the cost for the enterprise. Data deduplication is a technology that most of the enterprises use to get rid of the redundant data. Data deduplication aims at allowing only a single copy of a particular file to be stored on the cloud while discarding the replicated copies of the same file. This paper shows the implementation of deduplication. Alongside deduplication this paper also asserts at the security of data in cloud environment. SecCloud and SecCloud+ are the systems that help us achieve both deduplication and data integrity

Nowadays, we have seen many files which come along with intrusion present in it. Every application has a motive to reduce this intrusion so that the system does not get affected. Humans nowadays has created many applications to detect these intrusions and to keep the files or systems secure. NIDS is one of the outstanding system for security. It helps to keep the system free from attacks and thus enhancing its use. NIDS not only helps to reduce the attacks but gives the name of the specific attack present in the file or the system. Thus enhancing the dynamic use. Many systems have been developed for the same but NIDS proves to be better with its confidence factor to detect the attack. IDS is a champion around those all the sections of security. The majority key section to security establishments to association conditions, what’s more may be comprehensively utilized as a only distinguishing, recognizing and further more emulating those gatecrashers that is progressive and also sensible.

In this paper, we have implemented our idea to help blind individuals with their daily struggle. We have used Google’s TensorFlow library in our project. TensorFlow is an open source, fast and scalable open source machine learning library. TesnsorFlow is used by many internal Google products including: Gmail, translate, YouTube, and Play.

In the era of online shopping with the online shopping giants like Flipkart, Amazon dominating the shopping world, people are ignoring the local vendors who also provide us with the same quality goods. And so, in an attempt to provide global platform to the local vendors and to acquaint the people with the shops available in their locality, we are designing an online shopping application for local vendors in Pune.

Quick Response (QR) codes are now extremely popular due to the widespread uses of smart phones. Almost all the areas have had the QR codes to overtake the traditional one-dimensional bar codes, due to the increased capacity and quick data retrieval. QR codes offer a myriad of specifications like small space, durability against damage due to soil, better data capacity and higher language support, which make them much better than bar codes. Further, this Project is attempting expand the size of the QR codes further by making use of Color QR codes. Blowfish algorithm is efficient. This has been proved due by measuring the time required for its execution as well as its throughput. Due to the use of large key size, the efficiency of the algorithm may be affected. Further, the data which is considered is encrypted using Blowfish Algorithm, which makes the data secure and tamper-proof. Blowfish Algorithm belongs to the class of the algorithms which have a symmetric block cipher. The block cipher has a size of 64 bits and the key is variable, having a key length which can range from 32 bits until 448 bits at the maximum. This algorithm is a very fast and a useful scheme. It consists of a sub-key, an S-box phase and the actual encryption phase.

A Virtual Dressing Room for Low-End Smartphones is presented here. The proposed system uses Euclidean distance measurement algorithm. It involves capturing image of the subject or the person who wishes to try out the apparel. Systems similar to this have are in use in the West. They involve the use of Augmented Reality. They are available in for countries like US, UK, France, etc. But considering the PPP, GDP, etc. pricing factors of India, it is more expensive to deploy similar systems here. Hence to overcome this problem we came up with the solution that will enable everyone who owns at least a smartphone to benefit from the system. Basic idea is user will take their own photograph. Give the measurement of the reference object and place the points on their shoulder/height in image taken by smart phone camera. Our system will calculate the appropriate length and suggest garments accordingly which the users want to try out. Users can place an order at the same time via the following system.

People use internet to communicate with one another. Without internet, it would be both more expensive and slower to maintain personal and professional relationships. Many people use internet to enjoy themselves and to engage in personal interests. However, there are many security threats people come across which may be viruses, worms, file inclusion etc. So, to provide security to web applications and preventing root shell access and admin passwords is the main challenge. In previous survey, we have studied on security threats such as remote file inclusion and local file inclusion. Also, we have mentioned different prevention techniques such as Digital Signature, File size verification, Sanitization of input and Dynamic allocation to prevent website attacks. In this paper we have implemented these techniques by using methods such as MD5, SHA256. The expected outcome will be achieved by using these methods, providing security to the websites from RFI and LFI attacks.

In today’s world, millions of cases of dengue are reported ever year. The number of cases has increased, afflicting many individuals. For prediction of dengue clinical methodology comprises of antigens and anti-bodies tests. The tests are conducted on the blood samples collected from the patients. In our proposed system we are stratifying dengue into Dengue Fever (DF), Dengue Hemorrhagic Fever (DHF) and healthy patients. The dataset [GDS5093] being referred in this proposed model are of acute dengue patients. Existing work uses PSO approach which achieved the accuracy of 90.91%, in order to achieve high accuracy we are using optimization algorithms like Spider Monkey Optimization (SMO) and Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) and to increase the optimality of the model, we have also used Probabilistic Neural Network (PNN). PNN uses feedforward technique for classification.

In the recent years, social networking websites are not much in used for taking benefits for e-commerce websites. Many e-commerce related or product purchase websites uses the concept of login with social networking sites. In e-commerce there is a webpage called microblogs in which e-commerce’s users add the purchase products.in this paper, the purchase system gives solution to the newly login user on e-commerce which does not having any microblog related information at all. Such users or problem called as cross-site cold start product recommendation problem.in our purpose system, the product recommendation is given as per the user’s interest.to do this ,their is need to extract such a knowledge from social networking site which gives you knowledge about interest of the user’s such as profile information, demographic information, their network related information and many more. And this knowledge is used to give relevant recommendation to newly login users. This propose system also having one more feature is that ,to link the users from e-commerce & social networking websites as bridge between them, to map users feature to another feature representation..

Even though world is focusing on being digital still large amount of information or the data is represented by the papers only and that may also contain critical data. Now a days official documents are strongly secured with modern techniques such as artwork or printed pattern, but still paper documents suffer from a lack of security it means that with the high availability of cheap scanning and printing hardware, non-experts also can easily create fake documents. For the many organizations prevention of fraud has become a major concern. The industry understood the problem and is just now starting to act by innovation of new techniques for fraud detection. But as always said prevention is better than cure, we will focus on prevention of frauds, it is the best way to reduce frauds, fraudsters are adaptive and will usually find ways to break the security and circumvent such measures. So, for that purpose we have to make prevention system more and more stronger. In this paper, we present convenient and much more efficient approach for fraud prevention. In our approach, we use the smart card (can be RFID, magnetic tape based etc.). In this smart card, all the educational details can be linked so that the details can be obtained on the go, and hence there is no worries related to carrying your documents all the time with you. So, the issues related to the forgery or alteration of original documents will be reduced (or you can say fully eliminated!)

In today’s era almost in every hospital, we see a large amount of people waiting in queue to take treatment from doctors for different types of illness. In this scenario people get fed up to stand in queue for a long time waiting for their turn for treatment, leaving all their usual important work and job. To help them out and to avoid their stress to stand in the queue and wastage of their important time, we have developed system that gives queue waiting time to patients through the web application which updates in real time. We developed a Parallel Patient Time Prediction Algorithm which will give the patient waiting time for their treatment .So that they can attain the hospital according to the time predicted to them. Also we developed the Hospital Queuing Recommendation (HQR) System, which suggests the treatment to the patient according to waiting time of treatment. The treatment with short queue among other is first recommended to the patient.

India being an agricultural country, its economy predominantly depends on agriculture yield growth and allied agro industry products. In India, agriculture is largely influenced by rainwater which is highly unpredictable. Agriculture growth also depends on diverse soil parameters, namely Nitrogen, Phosphorus, Potassium, Crop rotation, Soil moisture, pH, surface temperature and weather aspects like temperature, rainfall, etc. India now is rapidly progressing towards technical development. Thus, technology will prove to be beneficial to agriculture which will increase crop productivity resulting in better yields to the farmer. The proposed project provides a solution for Smart Agriculture by monitoring the agricultural field which can assist the farmers in increasing productivity to a great extent. Weather forecast data obtained from IMD (Indian Metrological Department) such as temperature and rainfall and soil parameters repository gives insight into which crops are suitable to be cultivated in a particular area. This work presents a system, in form of an android based application and a website, which uses Machine Learning techniques in order to predict the most profitable crop in the current weather and soil conditions. The proposed system will integrate the data obtained from repository, weather department and by applying machine learning algorithm: Multiple Linear Regression, a prediction of most suitable crops according to current environmental conditions is made. This provides a farmer with variety of options of crops that can be cultivated. Thus, the project develops a system by integrating data from various sources, data analytics, prediction analysis which can improve crop yield productivity and increase the profit margins of farmer helping them over a longer run.