Medication Plan for Patient Data using Block chain Technology
Authors- M.Tech. Scholar Harsha Gupta, Asst. Prof. Shailendra Tiwari, Tanmay Jain
Abstract- – This paper helps to prospect the block chain technology and smart contracts to build private ness and aware of applications. The main focus is on a medication plan containing prescriptions, built on a block chain system of smart contracts. First the problem is presented, why medication plans are in need of digit allocation and why block chain technology is a fitting technology for implementing such an application. Thereafter, a design is proposed for solving the problem. A system of smart contracts was built to prove how such an application can be built and suggested guidelines for how a block chain system should be designed to achieve the requirements that were defined. it is a permission block chain, and because the smart contracts contains logic which is independent from the block chain layer .a block of Doctor’s prescription by the name of patient which will be visible to doctor as well as Pharmacy portal. The name of GUI is the medical smart contract demo .the blocks in block chain are secure because all blocks have their unique hash value .the hash value is used as a security purpose. And the hash value is result of solving the hashing algorithm and the hashing algorithm is used in this thesis is MD5 and SHA256.
A Review on Integrated Control and Protection System for Photovoltaic Microgrids
Authors- M.Tech. Scholar Aditi Agarwal, Asst. Prof. Rajni Kori, Prof. Rachna Dubey
Abstract- – Availability of the huge amount of unstructured data accessible online today, there is much to be picked up from the mining frameworks that can effectively sort out and order this information, so it can be utilized by clients. Sentiment investigation has attracted awesome attention for many researches for blog entries, film and eatery surveys, and so forth. So these papers solve issues of sentiment identification by using particle swarm optimization algorithm. Identification of sentiment was done by using pattern feature of text mining. So based on clustered patterns obtain from generic algorithm sentiment identification was done. Experiment was done on real dataset and results shows that proposed work has improved the various evaluation parameters of sentiment analysis.
Curve Smoothing in a Local Polynomial: Local Weighted Error Sum of Squares (Lowess)
Authors- Raymond Manna Bangura, Sahr Milton John Bull
Abstract- – The objective of this paper is to provide a summary approach to curve fitting in a local polynomial; local weighted error sum of squares. We proposed a fit diagnostics for the value Y and also compared quadratic and linear interpolation method in a local polynomial of second order degree. Again, we re-established the fact that curve fits better than line interpolations of a given set of points.
A Survey: E-Mail Spam Classification using Machine Learning Techniques
Authors- M.E. Scholar Shripriya Dongre, Prof. Kamlesh Patidar
Abstract- -E-mail is one of the most secure medium for online communication and transferring data or messages through the web. An overgrowing increase in popularity, the number of unsolicited data has also increased rapidly. To filtering data, different approaches exist which automatically detect and remove these untenable messages. There are several numbers of email spam filtering technique such as Knowledge-based technique, Clustering techniques, Learning-based technique, Heuristic processes and so on. This paper illustrates a survey of different existing email spam filtering system regarding Machine Learning Technique (MLT) such as Naive Bayes, SVM, K-Nearest Neighbor, Bayes Additive Regression, KNN Tree, and rules. However, here we present the classification, evaluation and comparison of different email spam filtering system and summarize the overall scenario regarding accuracy rate of different existing approaches.
Forecasting Crude Oil Price using Polynomial Regression and Autoregressive Integrated Moving Average (Arima) Model
Authors- Erros Josephus M. Gutierrez , Karen C. De Pablo
Abstract- The researchers aim to formulate a model to forecast the crude oil price using polynomial regression and Autoregressive Integrated Moving Average (ARIMA) model. The researchers used an equally weigh price between Brent Crude Oil Price and the West Texas Intermediate (WTI) from January 2001 to December 2018 with a total of 216 observations. The Crude Oil Price has undergone logarithmic transformation in formulating the model. Statistical tests are conducted within the study to be able to come up with the best polynomial regression model and ARIMA model. In polynomial regression, quadratic regression turned out to be the best regression model with a mean absolute percentage error of 7.8203. On the other hand, ARIMA (6,1,6) turned out to be the best ARIMA model with a mean absolute percentage error of 7.1210. By Testing the forecasting accuracy of both polynomial regression of 2nd degree and ARIMA (6,1,6), in terms of Mean Square Error (MSE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE), ARIMA (6,1,6) outperformed the regression model with Mean Square Error of 0.0913, Root Mean Square Error of 0.3021 and Mean Absolute Percentage Error of 7.1210. The analysis shows that ARIMA (6,1,6) has the best forecasting power to forecast the crude oil price. This study can help the government in reviewing and implementing policies with regards to crude oil prices in the Philippines.
Iris Image Watermarking by DWT and Neural Network Model
Authors- Arzoo Singh, Prof. Abhishek Sharma
Abstract- In recent years image data embedding schemes techniques have been widely studied. This data watermarking schemes allow us to embed a secret message into an image. So this work focuses on image watermarking in a image. Here DWT low frequency band was used for embedding watermark information. Binary water mark information was hiding in the image and this hided vectors are utilized to robust by chaotic shuffling function. Extraction of watermark was done at receiver end from rounded chaotic function. Use of this kind of embedding combination of frequency and LSB techniques increase robustness of the hided data against various types of attacks. Experiment was done on real image dataset and compared on various evaluation parameters. Results shows that proposed work has improved the PSNR, MSE, values as compared to other previous approaches.
A Survey on Intrusion Detection System Techniques and Features for Identification
Authors- Ph.D Scholar Raj Kumar Pandey, Dr. Shiv Shakti Shrivastava
Abstract- The intrusion detection systems (IDSs) are essential elements when it comes to the protection of an ICT infrastructure. Intrusion detection systems (IDSs) are widespread systems able to passively or actively control intrusive activities in a defined host and network perimeter. Recently, different IDSs have been proposed by integrating various detection techniques, generic or adapted to a specific domain and to the nature of attacks operating on. In this paper survey was done on the various techniques of intrusion detection system where some of supervised and unsupervised intrusion detection techniques are discussed. Here methodology of various researchers is explained with their steps of working. Different types of attacks done by the intruders were also discussed.
A Survey on Techniques and Features of Document Classification
Authors- Ph.D Scholar Vinod Sharma, Dr. Shiv Shakti Shrivastava
Abstract- Traditional information retrieval methods become inadequate for increasing vast amount of data. Without knowing what could be in the documents; it is difficult to formulate effective queries for analyzing and extracting useful information from the data. This survey focused on some of the present strategies used for filtering documents. Starting with different types of text features this paper has discussed about recent developments in the field of classification of text documents. This paper gives a concise study of methods proposed by different researchers. Here various pre-processing steps were also discussed with a comprehensive and comparative understanding of existing literature.
A Survey on Different Techniques of Static and Dynamic Load Balancing
Authors- Ph.D Scholar Vinod Patidar, Dr. Shiv Shakti Shrivastava
Abstract- As cloud computing have number of issues related to security, bandwidth efficiency, large information handling, load balancing, etc. Load balancing implies distribution of the workload to node or servers or assets with the goal that one can accomplish maximum utilization of resources, reduce execution time, increase system throughput and so on. This paper gives a concise study of cloud based service balancing methods proposed by different researchers. Here various features of service are detailed for the load balancing and planning. Different sorts of requirement of load balancing was additionally talked with their significance and limitations. So according to the module as well as steps used in techniques classification of load balancing algorithms are done with a comprehensive and comparative understanding of existing literature.
Soft Fusion Combining For Cooperative Spectrum Sensing Using Artificial Neural Network
Authors- M.Tech Scholar Arun Kumar, Prof. Suresh S Gawande
Abstract- Cognitive radio (CR) technology is an emerging technology that overcomes the scarcity and poor utilization of spectrum resources. Under the constraint of system energy, this paper puts forward a cooperative spectrum sensing algorithm to minimize the sensing.
A Survey on various Features and Techniques of Social Bot Detection
Authors- M.Tech. Scholar Roshani Singh, Prof. Sumit Sharma
Abstract- This paper presents the study of various methods for detection of fake profiles. In this paper a study of various papers is done, and in the reviewed paper we explain the algorithm and methods for detecting fake profiles for security purpose. The main part of this paper covers the security assessment of security on social networking sites. This paper give a brief survey of social bot detection challenges. Here features of fake profiles are collect. Hence paper reveals the potential hazards of malicious social bots, reviews the detection techniques within a methodological categorization and proposes avenues for future research.