Benefits Of Artificial Intelligence Research Articles

Application of Multi-Agent Technology in Decision Supporting

In the study, the development course and present situation of decision support technology is analyzed, and now decision support technology is lack and it is need to solved, it should combine the benefits of artificial intelligence as in the people's way of thinking to solve practical problems. In addition it also needs to have the ability to identify problems, and skills of dealing with distributed collaboration. The Multi-Agent technology in decision support research is introduced, the decision support is based on the Multi-Agent technology, and in order to demonstrate it can meet the specific needs of today's decision support, it analyzes the process of its implementation applying agent modeling theory, the behavior of the agent coordination mechanism and communication mechanism between the agents and so on, and puts forward the corresponding implementation scheme. Finally the effectiveness of the proposed technology and feasibility are analyzed, related results show that it can be applied in the actual decision support. DOI : http://dx.doi.org/10.11591/telkomnika.v12i2.3970

Patient behavior and the benefits of artificial intelligence: The perils of “dangerous” literacy and illusory patient empowerment

ObjectiveArtificial intelligence can provide important support of patient health. However, limits to realized benefits can arise as patients assume an active role in their health decisions. MethodsDistinguishing the concepts of health literacy and patient empowerment, we analyze conditions that bias patient use of the Internet and limit access to and impact of artificial intelligence. ResultsImproving health literacy in the face of the Internet requires significant guidance. Patients must be directed toward the appropriate tools and also provided with key background knowledge enabling them to use the tools and capitalize on the artificial intelligence technology. ConclusionBenefits of tools employing artificial intelligence to promote health cannot be realized without recognizing and addressing the patients’ desires, expectations, and limitations that impact their Internet behavior. In order to benefit from artificial intelligence, patients need a substantial level of background knowledge and skill in information use—i.e., health literacy. Practice implicationsIt is critical that health professionals respond to patient search for information on the Internet, first by guiding their search to relevant, authoritative, and responsive sources, and second by educating patients about how to interpret the information they are likely to encounter.

Efficacious End User Measures—Part 1: Relative Class Size and End User Problem Domains

Biological and medical endeavors are beginning to realize the benefits of artificial intelligence and machine learning. However, classification, prediction, and diagnostic (CPD) errors can cause significant losses, even loss of life. Hence, end users are best served when they have performance information relevant to their needs, this paper’s focus. Relative class size (rCS) is commonly recognized as a confounding factor in CPD evaluation. Unfortunately, rCS-invariant measures are not easily mapped to end user conditions. We determine a cause of rCS invariance, joint probability table (JPT) normalization. JPT normalization means that more end user efficacious measures can be used without sacrificing invariance. An important revelation is that without data normalization, the Matthews correlation coefficient (MCC) and information coefficient (IC) are not relative class size invariants; this is a potential source of confusion, as we found not all reports using MCC or IC normalize their data. We derive MCC rCS-invariant expression. JPT normalization can be extended to allow JPT rCS to be set to any desired value (JPT tuning). This makes sensitivity analysis feasible, a benefit to both applied researchers and practitioners (end users). We apply our findings to two published CPD studies to illustrate how end users benefit.

Four methods for short-term load forecasting using the benefits of artificial intelligence

Four methods are developed for short-term load forecasting and are tested with the actual data from the Turkish Electrical Authority. The method giving the most successful forecasts is a hybrid neural network model which combines off-line and on-line learning and performs real-time forecasts 24-hours in advance. Loads from all day types are predicted with 1.7273% average error for working days, 1.7506% for Saturdays and 2.0605% for Sundays.