Tetsuya Shimamura

Distributed estimation in wireless sensor networks (WSNs) has attracted considerable attention across various scientific and engineering disciplines. Traditionally, most studies have focused on estimating the unknown parameter of interest in noisy environments under the assumption that the training signal or the desired signal is known in advance at the receiver. However, in many practical applications, it is often difficult or even impossible to obtain the prior information of the training signal or the desired signal. Consequently, distributed blind equalization, which seeks to recover the transmitted data signal without requiring prior knowledge of the training signal, has emerged as an important research topic. Nevertheless, the performance of the distributed blind equalization is highly sensitive to transmission channel conditions, particularly under ill-conditioned channels where severe noise or distortion may occur. In order to address this challenge, we propose a block-combination weight strategy designed to mitigate the adverse effects of the ill-conditioned channel, thereby improving the accuracy of source signal estimation. A theoretical analysis of the proposed method is presented in terms of the mean-square error (MSE). Furthermore, the effectiveness of the proposed method is validated through computer simulations and compared with conventional methods using both MSE and symbol error rate (SER) as performance metrics. The simulation results demonstrate that the proposed approach consistently outperforms existing approaches in terms of both MSE and SER.

Spectrum sensing (SS) using machine learning (ML) or deep learning (DL) in an intelligent way is a current trend in cognitive radio networks (CRNs). The primary objective of any SS method is to enhance the detection probability of a primary user (PU) in low signal-to-noise ratio (SNR) environments. This paper proposes a multi-branch concatenate neural approach (MBCNA), designed as an aggregated neural network framework for SS in CRNs to improve PU detection capabilities. Additionally, we introduce a method for generating a dataset to serve as a training, validation, and testing data source for the proposed approach by utilizing the standard deviation of the real and imaginary parts, as well as the maximum and median values of the fast Fourier transform (FFT) of the received signals. This work considers quadrature amplitude modulation (QAM) over a Rayleigh fading channel with additive white Gaussian noise (AWGN). The effectiveness of the proposed method is evaluated with performance metrics such as accuracy, precision, recall, F1-score, confusion matrix, probability of detection, and false alarm rate. Simulation results demonstrate the validity of the proposed approach, and comparative analysis shows that it outperforms state-of-the-art DL methods. Specifically, the proposed method achieves 100.00% PU detection ability at an SNR of -10 dB.

The temperature at the base of the ear is highly correlated with the core body temperature of sheep and responds sensitively to febrile conditions, making it a valuable indicator of sheep health. In northern China, the closed housing environment during winter increases the incidence of seasonal diseases such as upper respiratory infections and pneumonia, which severely affect the economic efficiency of sheep farming. To address this issue, this study proposes an early-warning method for winter diseases in sheep based on ear-base temperature. Ear temperature, body weight, and environmental data were collected, and Random Forest was employed for feature selection. Bayesian optimization was used to fine-tune the hyperparameters of a one-dimensional convolutional neural network to construct a predictive model of ear-base temperature using data from healthy sheep. Based on the predicted normal range, an early-warning strategy was established to detect abnormal temperature patterns associated with disease onset. Experimental results demonstrated that the proposed method achieved a high detection rate for common winter diseases while maintaining a low false positive rate, and validation experiments confirmed its effectiveness under practical farming conditions. Combined with low-cost temperature-sensing ear tags, the proposed approach enables real-time health monitoring and provides timely early warnings for winter diseases in large-scale sheep farming, thereby improving management efficiency and economic performance.

Spectrum sensing is boosting the research to find more techniques to improve reliable spectrum utilization in cognitive radio networks. Machine learning can significantly contribute to developing the future of wireless networks by enabling flexible, efficient, and intelligent communication systems. On the other hand, multiple antenna systems at the transmitter and/or receiver are one of the most popular technologies in modern high-speed wireless communication to enhance performance. In this paper, we propose a machine learning technique in spectrum sensing for cognitive radio of users with multiple antennas, considering the non-cooperative approach to improve the spectrum sensing performance. Initially, we propose a synthetic dataset preparation method based on multiple antenna-assisted spectrum sensing for cognitive radio. After that, the popular linear classifiers, such as support vector machine (SVM) and logistic regression (LR) are used as supervised learning algorithms on the generated dataset for machine learning-based spectrum sensing. In the simulation, binary phase-shift keying (BPSK) modulation schemes over the Rayleigh fading channel with additive white Gaussian noise (AWGN) are studied. The significance and effectiveness of the proposed method are validated through simulation in terms of confusion matrix, accuracy, precision, recall, F1-score, probabilities of detection, miss detection, and false alarm. The simulation findings indicate that the proposed method provides better results compared to traditional and state-of-the-art methods. In particular, the proposed method provides the probability of detection (Pd) of 97.49% at a signal-to-noise ratio (SNR) of -25 dB with 4 antennas, and maintains the probability of false alarm (Pf) of 0.01.