In the current era of e-commerce, users are overwhelmed with countless products, making it difficult to find relevant items. Recommendation systems generate suggestions based on user preferences, to avoid information overload. Collaborative filtering is a widely used model in modern recommendation systems. Despite its popularity, collaborative filtering has limitations that researchers aim to overcome. In this paper, we enhance the K-nearest neighbor (KNN)-based collaborative filtering algorithm for a recommendation system, by considering the similarity of user cognition. This enhancement aimed to improve the accuracy in grouping users and generating more relevant recommendations for the active user. The experimental results showed that the proposed model outperformed benchmark models, in terms of MAE, RMSE, MAP, and NDCG metrics.

In the grain industry, identifying seed purity is a crucial task because it is an important factor in evaluating seed quality. For rice seeds, this attribute enables the minimization of unexpected influences of other varieties on rice yield, nutrient composition, and price. However, in practice, they are often mixed with seeds from other varieties. This study proposes a novel method for automatically identifying the purity of a specific rice variety using hybrid machine learning algorithms. The core concept involves leveraging deep learning architectures to extract pertinent features from raw data, followed by the application of machine learning algorithms for classification. Several experiments are conducted to evaluate the performance of the proposed model through practical implementation. The results demonstrate that the novel method substantially outperformed the existing methods, demonstrating the potential for effective rice seed purity identification systems.

This paper proposes a multiple-receiver inductive power transfer platform which is capable of controlling the load voltages to satisfy individually rated values and stabilizing the load voltages against the load variations. In the proposed charging platform, multiple transmitting resonators are employed to support a voltage-driven source resonator in manipulating the energy flows toward individual receivers. This structure also helps the voltage source induce constant currents into the transmitting resonators, and therefore, is able to deliver load-independent voltages to the loads. As a result, when the loads are sufficiently large, the load voltage ratio is approximately determined only by the mutual couplings of the coils. This means that the voltage control can be performed by effortlessly adjusting the arrangement of the transmitting resonators inside the charging platform. Electromagnetic simulation and experiment results verify voltage stability and controllability of the proposed system. Although typical constant voltage designs inevitably suffer from efficiency degradation, our scheme can achieve an efficiency of up to 56%, which is acceptable and sufficient for many practical applications.

This paper proposes a design principle for reactance compensation circuit for multiple-input multiple-output (MIMO) inductive power transfer (IPT) where the primary side employs a coil array to send power to a receiving coil array located at the secondary side. Delivering wireless power over multiple streams, MIMO topology is an effective approach to relax strict burdens on system components in high-power IPT applications. An important requirement in MIMO topology is a method to mitigate cross-coupling inside the coil arrays so that load-independent constant-current and constant-voltage can be realized in the same fashion as conventional single-input single-output IPT. Based on transfer matrix analysis, this paper proposes a design principle indicating that passive compensation circuit should implement the negative of the cross-coupling’s reactance matrix to cancel it in the reactance domain. The proposed design is independent of the transmission distance, applicable to MIMO IPT systems at arbitrary scale and does not require the coil arrays to employ any decoupling structure. Full-wave electromagnetic simulations with 3 × 2 MIMO and experiments with 2 × 2 MIMO are provided to verify effectiveness and feasibility of the proposed scheme.