Context-aware auction solution of cooperative fish market monitoring system for intelligent user

Abstract

This study proposes a context-aware auction solution suitable for the intelligent user. The solution informs the most reasonable prices for brokers after considering the size of each species of the catch along with other information and their effects on the fish price. This solution is expected to improve the safety of the catch and increase the competitiveness of auction sites by introducing a digitalized auction system to replace the traditional analog system which could be unsanitary sometimes. The solution’s Unified Modeling Language has been developed with Java Android and the data obtained from the proposed solution is useful in simplifying the bidding process, avoiding over-heated bidding, or stabilizing the fish prices for consumers in the distribution process starting from a broker, distributor and then to consumers. Such a simplified procedure will be able to maintain the freshness of the catch and strengthen the food safety as well as the competitiveness of auction sites, assisting brokers who often experience some difficulties in making a decision on the bidding price due to many variables. This study has focused on the new paradigms, software, middleware and systems for intelligent user. Thus, cost reduction was considered mainly in terms of software engineering. The proposed system is to be supplied with a price 30% less than the existing systems.

Strategy for Development of Fish Auction Place at Cilacap Oceanic Fishing Port, Cilacap Regency, Central Java

“…In the British type of auction, the bidders tend to bid at a higher price than the previous price. According to Seo and Huh (2020), the auction process begins with collecting data and classifying catches based on the type and size to provide convenience for consumers. Subsequently, the auctioneer opens at a predetermined price, and the bidders bid at a higher price.…”

Automotive Vulnerability Analysis for Deep Learning Blockchain Consensus Algorithm

“…Therefore, in this paper, abnormality detection technology has been studied for a long time, and, recently, machine learning and deep learning technologies have developed, showing excellent results in abnormality detection based on time-series data. Therefore, in this study, artificial intelligence-based technologies such as machine learning and deep learning were used to apply them to various fields such as behavior pattern analysis, industrial control systems, and automobile security [12][13][14][15]. Abnormal detection techniques are defined and can be applied differently according to each field, so there are several limitations.…”