Dianzuo Yue

Early in ovo sex identification is important for improving hatchery resource utilization; however, sex-related optical differences are weak during early embryonic development and exhibit clear stage dependence. In this study, longitudinal visible–near-infrared transmission spectra were acquired from 1600 fertilized pink-shelled eggs of Bashang Long-tailed chickens across four independent incubation batches during incubation days 1–7. Before model development, 200 eggs were reserved as a fixed internal hold-out test set, while the remaining 1400 eggs were used for exploratory incubation-day and feature screening, five-fold cross-validation, and model comparison. Among all 21 dual-day combinations, D2 + D5 achieved the highest exploratory validation AUC of 0.951. The selected scheme required separate measurements on D2 and D5, with the final sex classification completed on D5. Further incorporation of the signed difference spectrum ΔS and relative change rate R increased the AUC to 0.965, demonstrating the incremental discriminative value of longitudinal developmental-change information. After the input scheme had been fixed, DSSF-Net achieved the numerically highest performance among the evaluated models under unified egg-level stratified five-fold cross-validation, with an accuracy of 0.915 ± 0.015, an AUC of 0.974 ± 0.012, and an F1-score of 0.915 ± 0.014. The final model achieved an accuracy of 0.915 and an empirical AUC of 0.966 (95% CI: 0.940–0.987) on the fixed internal hold-out test set. Complete four-round leave-one-batch-out validation yielded mean accuracy and AUC values of 0.846 ± 0.014 and 0.926 ± 0.012, respectively, indicating that the longitudinal spectral information from D2 + D5 maintained relatively stable discriminative performance across incubation batches within the investigated population. These results demonstrate the feasibility of longitudinal spectral modeling for early sex identification in fertilized pink-shelled eggs of Bashang Long-tailed chickens. Systematic offline validation was completed under laboratory conditions, including evaluation on the fixed internal hold-out test set and four-round leave-one-batch-out validation, supporting the effectiveness and batch-level stability of D2 + D5 longitudinal developmental spectra. Post hoc wavelength-level interpretation further identified 594–620 nm and 660–675 nm as two candidate spectral regions with relatively high predictive value. Collectively, these findings provide a reliable longitudinal spectral modeling framework for early non-destructive in ovo sex identification and establish an experimental and methodological foundation for wavelength selection, device development, and subsequent engineering validation of multispectral detection systems under hatchery conditions.

Time-delay reservoir computing (RC) systems, particularly those based on semiconductor lasers (SLs), have gained attention due to their low energy consumption, high response rates, and rich nonlinear dynamics. This work investigates the influence of key time parameters—virtual node interval (θ), delay feedback (τ), and data injection period (T) on the performance of SL-based time-delay RC systems. Using the Santa Fe time series prediction task and memory capacity evaluation task, we analyze how these parameters affect prediction accuracy and memory capability. The results reveal that θ = 0.2T_ro (where T_ro is the relaxation oscillation period of the SLs) optimizes prediction performance, while θ = 0.5T_ro maximizes memory capacity. Additionally, feedback delay τ significantly impacts system performance. Shorter τ values (e.g., τ = 0.54T) enhance prediction accuracy, whereas longer τ values (e.g., τ = 1.74T) improve memory capacity. These findings provide valuable insights for optimizing time-delay RC systems, enabling better task-specific performance and stability.

The performance of an optoelectronic reservoir computing (RC) system for recognizing apple leaf diseases is numerically investigated. The disease spot feature extraction and selection methods suitable for time-delay RC are investigated. Two masking methods of sequence extension masking and matrix transformation masking are examined, with appropriate parameters, the optoelectronic RC achieves minimum errors of 0.01 and 0.03 under sequence extension masking and matrix masking methods, respectively. The nonlinear dynamics of the optoelectronic reservoir in the absence of data injection are compared with its recognition performance to establish the relationship between recognition capabilities and the system’s nonlinear dynamics. Additionally, we compared the recognition errors of optoelectronic RC, linear RC, and k-nearest neighbor algorithms. It illustrates that optoelectronic RC, under the nonlinear transformation of the Mach-Zehnder Modulator (MZM) and delayed feedback, can map input information nonlinearly to a high-dimensional state space, enabling effective classification along linear hyperplanes in this high-dimensional space.

Based on a semiconductor laser (SL) under multi-path optical feedback (MPOF) system, a novel post-processing method for fast physical random bit generation has been proposed and demonstrated. The novel post-processing method is called self-circulating exclusive-or (XOR), and through this post-processing method, all bits of samples are used to produce physical random bits which can pass the National Institute of Standard Technology (NIST) statistical tests and triple standard deviation tests. For the chaotic source of a SL under MPOF system, the influences of feedback intensity on time-delay-signature (TDS) and bandwidth of the produced chaotic signal are experimentally analyzed. The experimental results show that a low TDS chaotic signal with 13 GHz bandwidth can be obtained under appropriate operating parameters and 8 × 80 Gb/s statistically passable physical random bits are produced by using the self-circulating XOR method. In addition, the self-circulating XOR method is robust to the number of samples in delay XOR loop and has a great potential to implement by using up-to-date electronic devices.

We numerically investigate the performance of Chinese herbal medicine (CHM) recognition using a time delay reservoir computing (TDRC) system consist of a vertical-cavity surface-emitting laser (VCSEL) subjected to optical feedback. A database of 960 images from 12 CHM categories is used to evaluate the recognition performance, most of which contain many CHM samples and have different backgrounds. The CHM image feature vector is masked and optically injected into the VCSEL, and the VCSEL output in two polarization modes are sampled as the virtual node states for readout. After testing the CHM recognition performance of TDRC under injecting the same information into two polarization modes of the VCSEL, we further test the performance of parallel processing by injecting half of the image information into each of the two polarization modes. By concatenating the virtual node states collected from two modes for readout, the recognition speed is doubled. Meanwhile, the influence of key parameters on recognition performance are investigated and the relationship between system idle state and recognition performance is also examined. The results show that, under parallel processing and orthogonal optical feedback, the TDRC achieves the minimum recognition error of 1.7% at a reservoir processing rate of 2×10 ⁹ images per second.

In this work, the performance of an optoelectronic time-delay reservoir computing system for performing a handwritten digit recognition task is numerically investigated, and a scheme to improve the recognition speed using multiple parallel reservoirs is proposed. By comparing four image injection methods based on a single time-delay reservoir, we find that when injecting the histograms of oriented gradient (HOG) features of the digit image, the accuracy rate (AR) is relatively high and is less affected by the offset phase. To improve the recognition speed, we construct a parallel time-delay reservoir system including multi-reservoirs, where each reservoir processes part of the HOG features of one image. Based on 6 parallel reservoirs with each reservoir possessing 100 virtual nodes, the AR can reach about 97.8%, and the reservoir processing speed can reach about 1 × 10⁶ digits per second. Meanwhile, the parallel reservoir system shows strong robustness to the parameter mismatch between multi-reservoirs.

We experimentally investigate the performances of an optical reservoir computing (RC) system based on two parallel time-delay reservoirs composed of two semiconductor lasers (SLs) subject to optical feedback. In such a system, the information being processed is split into two parts to send into two reservoirs through directly modulating the pump currents of two SLs, and the temporal output of the two SLs are sampled and taken as the virtual node states for training and testing. Via Santa Fe time series prediction task and multi-waveform recognition task, the performances of the proposed RC system are investigated and compared with those of the system based on one reservoir. The results show that the system based on two parallel reservoirs behaves better performance and stronger parameter robustness than that based on one reservoir. Moreover, through analyzing the dependence of the system performances on the number of virtual node states actually used for readout, the potential data processing rate (DPR) of the system is evaluated. For processing a prediction task under guaranteeing the normalized mean square error below 0.1 and a recognition task under guaranteeing the signal error rate below 0.005, the potential DPR of the proposed RC system can achieve 200 MSa/s, which is twice the DPR of the system with only one reservoir.

In this work, we propose and numerically investigate a scheme for reservoir computing (RC) based on two parallel reservoirs under identical electrical message injection, in which two semiconductor lasers (SLs) under optical feedback are utilized as two parallel reservoirs. For simplifying the system, only one mask signal is employed in this scheme. After multiplying with input data, the masked information is injected into two parallel reservoir lasers (SL ₁ and SL ₂ ). The virtual node states can be obtained from the temporal outputs of two SLs. RC can be accomplished by three ways, namely RC ₁ /RC ₂ (the virtual node states originating from SL ₁ /SL ₂ are used for training and testing) and RC _M (the merged virtual node states originating from two SLs are used for training and testing). Via chaotic time series prediction task and memory capacity (MC) test, the performance of the RC system is simulated and assessed. The results show that, for a given data processing rate, better prediction performance and higher MC can be realized by RC _M through setting suitable mismatched parameters between the two SLs. Under satisfying the requirement for achieving a good performance, the highest data processing rate can be doubled for RC _M with respect to that for RC ₁ /RC ₂ .

Polarization switching (PS) and polarization bistability (PB) characteristics of a 1550 nm vertical-cavity surface-emitting laser (VCSEL) subject to orthogonal optical injection (OOI) with time-varying injection power are experimentally investigated for the first time. To implement the optical injection, a Mach-Zehnder modulator (MZM) modulated by a triangular radio wave is adopted, and the influences of some typical parameters on the performances of PS and PB are analyzed. Under suitable operation conditions, PB in the VCSEL subject to OOI with time-varying injection power can be observed only for the input power P0 of MZM locating within a determined range, and the width of hysteresis loop gradually decreases with the increase of P0 from the minimum P0,min to the maximum P0,max. Under different frequency detuning between the injection light and the X polarization mode of the VCSEL, the determined ranges of P0 required for PB are different. With the variation of from a negative value to a positive value, both P0,min and P0,max present a trend of decrease first and then increase. Additionally, with the increase of the modulation frequency, the hysteresis loop width firstly increases rapidly and then gradually tends saturation.