Earticle

Due to the radical changing of the global economy, a more precise stock valuation helps providing important judgment principles to decision-makers and investors. With the advent of the third-generation (3G) or future forth-generation (4G) Internet, the mobile commerce (MCommerce) will become increasingly important. In addition, the mobile stock investment decision support system attracts great interests for professionals, such as stockholders, bondholders, financial analysts, governmental officials, and even the general public, recently. This study introduces a Mobile Agent-based Stock Intermediary Services System (MASISS) framework based on the mobile agent perspective to provide ubiquitous and seamless transaction activities for financial institutions. It also helps customers to make a more precise decision in the current intense commercial competition environment. For building distributed enterprise systems, The MASISS framework is developed in an integration of J2ME and J2EE environment with cross-platform portability, a huge server-side and client-side deployment base, and coverage for most W3C standards..

This study proposes design concepts for a comprehensive home financial learning environment that individual investors can use as a reference in establishing web-based learning and investment platforms. This study also introduces a hybrid approach that demonstrates a data mining function of the financial learning environment. Known as Fuzzy BPN, this approach is comprised of backpropagation neural network (BPN) and fuzzy membership function. This membership function takes advantage of the nonlinear features of artificial neural networks (ANNs) and the interval values as a means of overcoming the inadequacy of single-point estimation of ANNs. Based from these characteristics, a dynamic and intelligent time-series forecasting system will be developed for practical financial predictions. In addition to this, the experimental processing can demonstrate the feasibility of applying the hybrid model-Fuzzy BPN. The empirical results of the study show that Fuzzy BPN provides an alternative data mining tool for financial learning environment to investment forecasting.

The paper summarizes research findings related to SmartResource project (2004-2007) funded by Tekes and industrial companies. The main objectives was research and development of the large-scale distributed environment for integration of smart devices, web services and humans based on combination of Semantic Web, agent technologies and serviceoriented architecture. A prototype platform for self-maintained smart resources in smart spaces has been designed and implemented for particular tasks of industrial partners. In this paper we will present the summary of research results obtained during the project period and related industrial case study. Several lessons have been learned during the project in addition to published results, which we are going to share with scientific community. We also present a vision how to utilize project results to design various complex smart spaces taking into account such issues as interoperability, coordination, self-manageability, reputation and trust in future generation smart space environments.

In this paper, we propose an intelligent system, called “Mobile Fashion Advisor”, aimed to create a virtual fashion assistant to give suggestions on the usage of clothing and help users avoid buying clothes that are never worn. Many different computer theories and techniques are exploited in the system. Digital image processing techniques, such as edge detection and color histogram, are employed to obtain the essential data of garments. Fuzzy theories are applied for gathering fashion matching rules. Users can simply use a smart phone to take a photo of the garment when shopping and submit it to the clothes server through ubiquitous network.Then Attire Scheme Harmony Evaluator follows match rules to search whether there are clothes in her personal garment database that matches the new one. The results of matching and grades of whether to buy are sent back and shown on the phone. The work is to provide such a user-centric services system that functions as a personal fashion advisor for clothes shopping.

Decision Making is one of the most important activities of the human being. Nowadays decisions imply to consider many different points of view, so decisions are commonly taken by formal or informal groups of persons. Groups exchange ideas or engage in a process of argumentation and counter-argumentation, negotiate, cooperate, collaborate or even discuss techniques and/or methodologies for problem solving. Group Decision Making is a social activity in which the discussion and results consider a combination of rational and emotional aspects. In this paper we will present a Smart Decision Room, LAID (Laboratory of Ambient Intelligence for Decision Making). In LAID environment it is provided the support to meeting room participants in the argumentation and decision making processes, combining rational and emotional aspects.

This paper reports some experiments which assess the potential use of a footstep biometric verification system for a smart home environment. We present a semi-automatic capture system and report results on a database with independent development and evaluation datasets comprised of more than 3500 footsteps collected from 55 persons. We present an optimisation of geometric and holistic feature extraction approaches. An equal error rate of 13% is obtained with holistic features classified with a support vector machine. The database is freely available to the research community.

Recently, wireless sensor networks have been proposed for assisted living and residential monitoring. In such networks, physiological sensors are used to monitor vital signs e.g. heartbeats, pulse rates, oxygen saturation of senior citizens. Sensor data is sent periodically via wireless links to a personal computer that analyzes the data. In this paper, we first describe the architecture of a sensor-based medical information system that we are developing. Then, we describe how we deal with security issues in our system. Next, we describe an ECG anomaly detection scheme that we proposed. Our approach is based on time series analysis that will allow the computer to determine whether a stream of real-time sensor data contains any abnormal heartbeats. If anomaly exists, that time series segment will be transmitted via the network to a physician so that he/she can further diagnose the problem and take appropriate actions. When tested against the heartbeat data readings stored at the MIT database, our ECG anomaly scheme is shown to have better performance than another scheme that has been recently proposed. Our scheme enjoys an accuracy rate that varies from 70-90% while the other scheme has an accuracy that varies from 40-70%.

This paper presents a smart home system prototype which employs an indoor positioning system called the III Beacon Match (I3BM) positioning method to intelligently trigger the appropriately services for the home members. To overcome the ninja problem in the I3BM method, the signal filtering, adjustment and smooth procedures are proposed. The proposed system prototype employs the Zigbee module to implement the prototypes of the components for the I3BM positioning method, and the prototypes had passed the ZigBee Compliant Platform (ZCP) certification test. The proposed system prototype which intelligently controls the air condition and light system for smart home applications is also verifying in our demo room and in the smart house in National Taiwan University.

With the popularity of sensor networks, solving the knapsack problem has become important in selecting the best combination of sensor nodes. Many methods have been proposed to solve the Knapsack problem, but few of them have used the genetic algorithm, especially in unbounded Knapsack problems. In this paper, we use the genetic algorithm to solve the unbounded Knapsack problem. We combine an elite strategy and a self adapting system into the genetic algorithm. Using the elite strategy overcomes the problem of the slow convergence rate of the general genetic algorithm. The elite strategy retains good chromosomes and ensures that they are not eliminated through the mechanism of crossover and mutation, ensuring that the features of the offspring chromosomes are at least as good as their parents. The system automatically adapts the number of the initial population of chromosomes and the number of runs to be executed in the genetic algorithm. It will obtain the best value from the chromosomes of each run executed, and retain the values in an elite group. The optimal value is then taken from the elite group and adopted as the real solution. Experimental results have shown that our method rapidly discovers the best solution of the problem.