Learning other agents' preferences in multi-agent negotiation using the bayesian classifier

In multi-agent systems, most of the time, an agent does not have complete information about the preferences and decision making processes of other agents. This prevents even the cooperative agents from making coordinated choices, purely due to their ignorance of what others want. To overcome this problem, traditional coordination methods rely heavily on inter-agent communication, and thus become very inefficient when communication is costly or simply not desirable (e.g. to preserve privacy). In this paper, we propose the use of learning to complement communication in acquiring knowledge about other agents. We augment the communication-intensive negotiating agent architecture with a learning module, implemented as a Bayesian classifier. This allows our agents to incrementally update models of other agents' preferences from past negotiations with them. Based on these models, the agents can make sound predictions about others' preferences, thus reducing the need for communication in their future interactions.

Effect of selenium-saturated bovine lactoferrin (Se-bLF) on antioxidant enzyme activities in human gut epithelial cells under oxidative stress

Cancer and many chronic inflammatory diseases are associated with increased amounts of reactive oxygen species (ROS). The potential cellular and tissue damage created by ROS has significant impact on many disease and cancer states and natural therapeutics are becoming essential in regulating altered redox states. We have shown recently that iron content is a critical determinant in the antitumour activity of bovine milk lactoferrin (bLF). We found that 100% iron-saturated bLF (Fe-bLF) acts as a potent natural adjuvant and fortifying agent for augmenting cancer chemotherapy and thus has a broad utility in the treatment of cancer. Furthermore, we also studied the effects of iron saturated bLF's ability as an antioxidant in the human epithelial colon cancer cell line HT29, giving insights into the potential of bLF in its different states. Thus, metal saturated bLF could be implemented as anti-cancer neutraceutical. In this regard, we have recently been able to prepare a selenium (Se) saturated form of bLF, being up to 98% saturated. Therefore, the objectives of this study were to determine how oxidative stress induced by hydrogen peroxide (H₂O₂) alters antioxidant enzyme activity within HT29 epithelial colon cancer cells, and observe changes in this activity by treatments with different antioxidants ascorbic acid (AA), Apo (iron free)-bLF and selenium (Se)-bLF. The states of all antioxidant enzymes (glutathione peroxidase (GPx), glutathione reductase (GR), glutathione-s-transferase (GsT), catalase and superoxide dismutase (SOD)) demonstrated high levels within untreated HT29 cells compared to the majority of other treatments being used, even prior to H₂O₂ exposure. All enzymes showed significant alterations in activity when cells were treated with antioxidants AA, Apo-bLF or Se-bLF, with and/or without H₂O₂ exposure. Obvious indications that the Se content of the bLF potentially interacted with the glutathione (GSH)/GPx/GR/GsT associated redox system could be observed immediately, showing capability of Se-bLF being highly beneficial in helping to maintain a balance between the oxidant/antioxidant systems within cells and tissues, especially in selenium deficient systems. In conclusion, the antioxidative defence activity of Se-bLf, investigated in this study for the first time, shows dynamic adaptations that may allow for essential protection from the imbalanced oxidative conditions. Because of its lack of toxicity and the availability of both selenium and bLF in whole milk, Se-bLF offers a promise for a prospective natural dietary supplement, in addition to being an immune system enhancement, or a potential chemopreventive agent for cancers.

A multi-agent incremental negotiation scheme for meetings scheduling

We present an agent-oriented approach to the meeting scheduling problem and propose an incremental negotiation scheme that makes use of a hierarchical structure of an individual agent's working knowledge. First, we formalise the meeting scheduling problem in a multi-agent context, then elaborate on the design of a common agent architecture of all agents in the system. As a result, each agent becomes a modularised computing unit yet possesses high autonomy and robust interface with other agents. The system reserves the meeting participants' privacy since there are no agents with dominant roles, and agents can communicate at an abstract level in their hierarchical structures

A neural network-based multi-agent classifier system with a Bayesian formalism for trust measurement

In this paper, a neural network (NN)-based multi-agent classifier system (MACS) utilising the trust-negotiation-communication (TNC) reasoning model is proposed. A novel trust measurement method, based on the combination of Bayesian belief functions, is incorporated into the TNC model. The Fuzzy Min-Max (FMM) NN is used as learning agents in the MACS, and useful modifications of FMM are proposed so that it can be adopted for trust measurement. Besides, an auctioning procedure, based on the sealed bid method, is applied for the negotiation phase of the TNC model. Two benchmark data sets are used to evaluate the effectiveness of the proposed MACS. The results obtained compare favourably with those from a number of machine learning methods. The applicability of the proposed MACS to two industrial sensor data fusion and classification tasks is also demonstrated, with the implications analysed and discussed.