No abstract

Problems in the medical supply chain are neither new nor uncommon: These products can travel through global supply chains in which documentation is often manual and paper-based, increasing at each handoff and border crossing. As a result, theft and quality control issues are common, and regulators and distributors struggle to locate substandard products that have entered the system. As both the technology and the industry’s processes for working together matures, blockchains could help us get better and faster at getting medicines and vaccines to where we have the most urgency. With more granular visibility, stakeholders could better zero in on clogs in supply chains, more quickly locate and remove expired, damaged, or fraudulent products.

In Today's world data is collected at an unpredictable scale from various application areas. Prior to the arrival of Big Data, all the data that was generated was handled manually. With data being produced in the range of terabytes today, that is impossible. To make the situation worse, almost 80% of the data generated by organizations is unstructured. This means that it cannot be understood in its avail-able format. It is very difficult and risky to make decisions just based on such crude data. In order to make quick, yet correct decisions, the generated data has to be optimized. This Paper discusses to create an end-to-end system to optimize approximately 6 million records of unstructured data provided as .txt files, which is in the form of strings and numbers into understandable or structured data. The next step is to analyse the structured data in order to make calculations on the given dataset. Finally, the analysed data will be represented in the form of dashboards, which are tabular reports or charts. In this Paper, unstructured data in the form of .txt files will be transformed into structured data in the form of tables through the SQL stored procedures in SQL Server Management Studio (SSMS). Along with the data, four other tables called dimensions will be created and then all five tables will then be integrated using SQL Server Integrated Ser-vices. Then an Online Analytical Processing (OLAP) cube is built over this data with product, customer, currency and time as its dimen-sions using the SQL Server Analysis Services (SSAS). At last this analysed data is then reported through dashboards through SQL Server Reporting Services (SSRS).The results of the analysed data is viewed in the form of reports and charts. These reports are customizable and a variety of operations can be performed on them as required by an organization. Since these reports are short and informative, they will be easy to understand and will provide for easier and correct decision making.

This paper aims to develop an innovative neural network approach to achieve better stock market predictions. Data were obtained from the live stock market for real-time and off-line analysis and results of visualizations and analytics to demonstrate Internet of Multimedia of Things for stock analysis. To study the influence of market characteristics on stock prices, traditional neural network algorithms may incorrectly predict the stock market, since the initial weight of the random selection problem can be easily prone to incorrect predictions. Based on the development of word vector in deep learning, we demonstrate the concept of “stock vector.” The input is no longer a single index or single stock index, but multi-stock high-dimensional historical data. We propose the deep long short-term memory neural network (LSTM) with embedded layer and the long short-term memory neural network with automatic encoder to predict the stock market. In these two models, we use the embedded layer and the automatic encoder, respectively, to vectorize the data, in a bid to forecast the stock via long short-term memory neural network. The experimental results show that the deep LSTM with embedded layer is better.

No abstract