Design of a web-based multiagent system for electronic procurement

The proposed electronic marketplace (EM) is aimed to enhance the procurement process by acting as an intermediary between buyers and suppliers. The proposed EM consists of users (buyers and suppliers), various components and a user interface. As part of the decision engine, a prototype supplier selection system, SupplySelect, is developed and implemented.

Design of a web-based multiagent system for electronic procurement

The proposed electronic marketplace (EM) is aimed to enhance the procurement process by acting as an intermediary between buyers and suppliers. The proposed EM consists of users (buyers and suppliers), various components and a user interface. As part of the decision engine, a prototype supplier selection system, SupplySelect, is developed and implemented.

System anti-jamming technology in the design of intelligent single chip computer constant current source of field strength machine

With the development of the electric power industry, the technical level of automatic testing equipment for the reliability of electrical component circuit breakers in the transmission and distribution network is getting higher and higher. The stability and accuracy of the test power supply are the basis for ensuring the pass rate of the test product. Most of the electrical testing and testing equipment has defects such as inaccurate power supply current regulation, low power, and low level of intelligence, which are difficult to meet the testing requirements. Based on the theory of a closed-loop control system, this paper adopts embedded system design technology to realize a high-current, high-power, high-stability digital constant current source system for line detection. This paper studies the rule-based intelligent anti-jamming decision engine design and system anti-jamming performance analysis of NC-OFDM system. We give the design of an intelligent anti-jamming decision engine based on rule-based decision-making, and focus on two intelligent anti-jamming decision-making algorithms: Adaptive Modulation and Coding (AMC) algorithm based on signal-to-noise ratio difference and packet error rate and Adaptive Sub-Band Selection (ASBS) algorithm. Experimental test results show that the output current range is 200 mA to 2000 mA, the system has realized a microstep adjustment of±5 mA, and the absolute error of current measurement is less than 0.3%+4 mA. The system is stable and reliable, and has high practical value in the field of high precision and low power.

Efficient Access Control Permission Decision Engine Based on Machine Learning

Access control technology is critical to the safe and reliable operation of information systems. However, owing to the massive policy scale and number of access control entities in open distributed information systems, such as big data, the Internet of Things, and cloud computing, existing access control permission decision methods suffer from a performance bottleneck. Consequently, the large access control time overhead affects the normal operation of business services. To overcome the above-mentioned problem, this paper proposes an efficient permission decision engine scheme based on machine learning (EPDE-ML). The proposed scheme converts the attribute-based access control request into a permission decision vector, and the access control permission decision problem is transformed into a binary classification problem that allows or denies access. The random forest algorithm is used to construct a vector decision classifier in order to establish an efficient permission decision engine. Experimental results show that the proposed method can achieve a permission decision accuracy of around 92.6% on a test dataset, and its permission decision efficiency is significantly higher than that of the benchmark method. In addition, its performance improvement becomes more obvious as the scale of policy increases.

Semi-Supervised Machine Learning Enables the Robust Detection of Multireference Character at Low Cost

Multireference (MR) diagnostics are common tools for identifying strongly correlated electronic structure that makes single reference (SR) methods (e.g., density functional theory or DFT) insufficient for accurate property prediction. However, MR diagnostics typically require computationally demanding correlated wavefunction theory (WFT) calculations, and diagnostics often disagree or fail to predict MR effects on properties. To overcome these challenges, we introduce a semi-supervised machine learning (ML) approach with virtual adversarial training (VAT) of an MR classifier using 15 WFT and DFT MR diagnostics as inputs. In semi-supervised learning, only the most extreme SR or MR points are labeled, and the remaining point labels are learned. The resulting VAT model outperforms the alternatives, as quantified by the distinct property distributions of SR- and MR-classified molecules. To reduce the cost of generating inputs to the VAT model, we leverage the VAT model’s robustness to noisy inputs by replacing WFT MR diagnostics with regression predictions in a MR decision engine workflow that preserves excellent performance. We demonstrate the transferability of our approach to larger molecules and those with distinct chemical composition from the training set. This MR decision engine demonstrates promise as a low-cost, high-accuracy approach to the automatic detection of strong correlation for predictive high-throughput screening.

Semi-Supervised Machine Learning Enables the Robust Detection of Multireference Character at Low Cost

Multireference (MR) diagnostics are common tools for identifying strongly correlated electronic structure that makes single reference (SR) methods (e.g., density functional theory or DFT) insufficient for accurate property prediction. However, MR diagnostics typically require computationally demanding correlated wavefunction theory (WFT) calculations, and diagnostics often disagree or fail to predict MR effects on properties. To overcome these challenges, we introduce a semi-supervised machine learning (ML) approach with virtual adversarial training (VAT) of an MR classifier using 15 WFT and DFT MR diagnostics as inputs. In semi-supervised learning, only the most extreme SR or MR points are labeled, and the remaining point labels are learned. The resulting VAT model outperforms the alternatives, as quantified by the distinct property distributions of SR- and MR-classified molecules. To reduce the cost of generating inputs to the VAT model, we leverage the VAT model’s robustness to noisy inputs by replacing WFT MR diagnostics with regression predictions in a MR decision engine workflow that preserves excellent performance. We demonstrate the transferability of our approach to larger molecules and those with distinct chemical composition from the training set. This MR decision engine demonstrates promise as a low-cost, high-accuracy approach to the automatic detection of strong correlation for predictive high-throughput screening.