Average Matching Rate Research Articles

IJADE web-miner: an intelligent agent framework for internet shopping

There is growing interest in using intelligent software agents for a variety of tasks, including navigating and retrieving information from the Internet and from databases, online shopping activities, user authentication, negotiation for resources, and decision making. We propose an integrated framework for information retrieval and information filtering in the context of Internet shopping. We focus on applying agent technology, together with Web mining technology, to automate a series of product search and selection activities. It is based on a multiagent development platform, namely, iJADE (intelligent Java agent development environment), which supports various e-commerce applications. The framework comprises an automatic facial authentication utility and six other modules, namely, customer requirements definition, a requirement-fuzzification scheme, a fuzzy agents-negotiation scheme, a fuzzy product-selection scheme, a product-defuzzification scheme, and a product-evaluation scheme. A series of experiments were carried out and favorable results were produced in executing the framework. From an experimental point of view, we used a database of 1,020 facial images that were obtained under various conditions of facial expression, viewing perspective and size. An overall correct recognition rate of over 85 percent was attained. For the product selection test of our fuzzy shopper system, an average matching rate of more than 81 percent was achieved.

Comparative proteomics analysis of human lung squamous carcinoma

Two-dimensional polyacrylamide gel electrophoresis (2-DE) profiles of human lung squamous carcinoma tissue and paired surrounding normal bronchial epithelial tissue were compared. Selected differential protein-spots were identified with peptide mass fingerprinting based on matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF-MS) and database searching. Well-resolved and reproducible 2-DE patterns of both the tumor and the normal tissues were acquired. The average deviations of spot position were 0.873 ± 0.125 mm in IEF direction and 1.025 ± 0.213 mm in SDS–PAGE direction, respectively. For the tumor tissues, a total of 1349 ± 67 spots were detected and 1235 ± 48 spots were matched with an average matching rate of 91.5%. For the corresponding normal tissues, a total of 1297 ± 73 spots were detected and 1183 ± 56 spots were matched with an average matching rate of 91.2%. A total of 1069 ± 45 spots were matched between the tumor and the normal tissues. Forty differential proteins between tumor and normal tissues were characterized. Some proteins were the products of oncogenes and others were involved in the regulation of cell cycle and signal transduction. These data are valuable for mass identification of differentially expressed proteins involved in lung carcinogenesis, establishing human lung cancer proteome database and screening molecular marker to further study human lung squamous carcinoma.

Proteomic Comparison of Two-Dimensional Gel Electrophoresis Profiles from Human Lung Squamous Carcinoma and Normal Bronchial Epithelial Tissues

Differential proteome profiles of human lung squamous carcinoma tissue compared to paired tumor-adjacent normal bronchial epithelial tissue were established and analyzed by means of immobilized pH gradient-based two-dimensional polyacrylamide gel electrophoresis (2-D PAGE) and matrix-assisted laser desorption/ionization time of flight mass spectrometry (MALDI-TOF-MS). The results showed that well-resolved, reproducible 2-DE patterns of human lung squamous carcinoma and adjacent normal bronchial epithelial tissues were obtained under the condition of 0.75-mg protein-load. The average deviation of spot position was 0.733±0.101 mm in IEF direction, and 0.925±0.207 mm in SDS-PAGE direction. For tumor tissue, a total of 1241±88 spots were detected, 987±65 spots were matched with an average matching rate of 79.5%. For control, a total of 1190±72 spots were detected, and 875±48 spots were matched with an average matching rate of 73.5%. A total of 864±34 spots were matched between tumors and controls. Forty-three differential proteins were characterized: some proteins were related to oncogenes, and others involved in the regulation of cell cycle and signal transduction. It is suggested that the differential proteomic approach is valuable for mass identification of differentially expressed proteins involved in lung carcinogenesis. These data will be used to establish human lung cancer proteome database to further study human lung squamous carcinoma.

Multistage word recognizer based on reliably detected phoneme similarity regions

The multistage word recognizer uses a word reference representation based on reliably detected peaks of phoneme similarity values. The word reference representation captures the basic features of the words by targets that describe the location and shape of stable peaks of phoneme similarity values. The first stage of the word hypothesizer represents each reference word with statistical information on the number of high similarity regions over a predefined number of time intervals. The second stage represents each word by a prototype that consists of a series of phoneme targets and global statistics, namely the average word duration and average match rate. These represent the degree of fit of the word prototype to its training data. Word recognition scores generated in the two stages are converted to dimensionless normalized values and combined by averaging for use in selecting the most probable word candidates.