This paper presents a new study based on artificial neural network, which is a typical technique for processing big data, for the prediction of systolic blood pressure by correlated factors (gender, serum cholesterol, fasting blood sugar and electrocardiography signal). Two neural network algorithms, back-propagation neural network and radial basis function network, are used to construct and validate the bio-medical prediction system. The database of raw data is divided into two parts: 80% for training the neural network and the remaining 20% for testing the performance. The experimental result shows that artificial neural networks are suitable for modeling and predicting systolic blood pressure. This novel method of predicting systolic blood pressure contributes to giving early warnings to adults who may not take regular blood pressure measurements. Also, as it is known that an isolated blood pressure measurement is sometimes not very accurate due to the daily fluctuation, our predictor can provide another reference value to the medical staff.
In this paper, a battery swapping station (BSS) model is proposed as an economic and convenient way to provide energy for the batteries of the electric vehicles (EVs). This method would overcome some drawbacks to the use of electric vehicles like long charging time and insufficient running distance. On the economic concern of a battery swapping station, the station would optimize the availability of the batteries in stock, and at the same time determine the best strategy for recharging the batteries on hand. By optimizing the charging method of the batteries, an optimization model of BSS with the maximum number of batteries in stock has been developed for the bus terminal at the Hong Kong International Airport. The secondary objective would be to minimize a cost on the batteries due to the use of different charging schemes. The genetic algorithm (GA) has been used to implement the optimization model, and simulation results are shown.
The nickel metal hydride technology for battery application is relatively immature even though this technology was made widely known by Philips' scientists as long ago as 1970. Recently, because of the international environmental regulatory pressures being placed on cadmium in the workplace and in disposal practices, battery companies have initiated extensive development programs to make this technology a viable commercial operation. These hydrides do not pose a toxilogical threat as does cadmium. Also, they provide a higher energy density and specific energy when compared to the other nickel based battery technologies. For these reasons, the nickel metal hydride electrochemisty is being evaluated as the next power source for varied applications such as laptop computers, cellular telephones, electric vehicles, and satellites. A parallel development effort is under way to look at aerospace applications for nickel metal hydride cells. This effort is focused on life testing of small wound cells of the commercial type to validate design options and development of prismatic design cells for aerospace applications.
In this paper, a new study based on machine learning technique, specifically artificial neural network, is investigated to predict the systolic blood pressure by correlated variables (BMI, age, exercise, alcohol, smoke level etc.). The raw data are split into two parts, 80% for training the machine and the remaining 20% for testing the performance. Two neural network algorithms, back-propagation neural network and radial basis function network, are used to construct and validate the prediction system. Based on a database with 498 people, the probabilities of the absolute difference between the measured and predicted value of systolic blood pressure under 10mm Hg are 51.9% for men and 52.5% for women using the back-propagation neural network With the same input variables and network status, the corresponding results based on the radial basis function network are 51.8% and 49.9% for men and women respectively. This novel method of predicting systolic blood pressure contributes to giving early warnings to young and middle-aged people who may not take regular blood pressure measurements. Also, as it is known an isolated blood pressure measurement is sometimes not very accurate due to the daily fluctuation, our predictor can provide another reference value to the medical staff. Our experimental result shows that artificial neural networks are suitable for modeling and predicting systolic blood pressure.
An online web application called Student-Trade has been developed. It is a state-of-the-art platform for direct consumer-to-consumer trading in the Internet. The platform is targeted for direct consumer-to-consumer trading among university students. The items for trading include books, household items, electronics, housing rental, sports equipment and tutoring services. This paper is on the design intelligence of the Student-Trade web application. One objective is to help the user to decide on the selling price of his item when the item is being posted in the web application. The system integrates a hybrid neighborhood search algorithm for determining the price of sale item when it is placed for trading in the Internet. Data mining techniques are explored for efficient processing of a vast amount of information in the database tables. In addition, the trading system would also have the intelligence of recommending items or products to a potential buyer given the previous purchase patterns. The aim is to provide a pleasant trading experience for the user.
This paper describes a decision support system that integrates a hybrid neighborhood search algorithm for determining the price of sale item when it is placed for trading in the Internet. The seller would provide the condition and number of years of usage of the used item, and the intelligent system would provide real-time search on related items in the marketplace and suggest a price for trading. Data mining techniques are explored for efficient processing of a vast amount of information in the database tables. In addition, the trading system would also have the intelligence of recommending items or products to a potential buyer given the previous purchase patterns. Related items to a recently purchased item would also be suggested with an aim of providing friendly reminders and recommendations so that the user of the website would obtain a pleasant trading experience.
'/%3e%3cuse xlink:href='%23a' transform='rotate(144 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(216 450 300)'/%3e%3cuse xlink:href='%23a' transform='rotate(288 450 300)'/%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)
