Digital backpropagation (DBP) loses effectiveness when deployed fiber and transceiver parameters differ from the inverse propagation model, whereas finely discretized DBP incurs substantial computational complexity. This paper proposes a pilot-verified hybridcoherent receiver combining power-adaptive coarse DBP, cross-fitted residual chromatic-dispersion estimation, and bounded phase-equivariant functional-link neural-network (FLNN) correction. Mutually disjoint pilot subsets support acquisition, residual-dispersion estimation, correction verifi cation, and learned-correction gating. Rejected corrections return exactly to the corresponding deterministic fallback, and all deployable decisions use known pilots only. Evaluation employs a hardware-aware five-channel, 32-GBd dual-polarization 16-QAM WDM model over a nominal 10 × 80-km amplified link. The parameter- and sequence-disjointexperiment comprises 24 prespecified operating and mismatch conditions with five independent realizations per condition. Relative to nominal coarse DBP, the proposed receiver provides a condition-balanced mean effective-SNR gain of 3 . 0819 dB, with all 24 condition-level mean gains positive. Across 5 , 880 , 960 evaluated payload bits per method, it reduces pooled BER by 52 . 06%, from 0 . 21451 to 0 . 10284, increases the BER-derived optical Q-factor from -2 . 04 to 2 . 05 dB, and decreases mean EVM by 36 . 65%. Mean NGMI increases from 0 . 44164 to 0 . 63172, raising net GMI throughput by 43 . 04%. The receiver requires 82 . 66% fewer estimated real multiplications than pilot-estimated-dispersion fine DBP and uses 264 learned real coefficients. Across 120 realizations, 115 improve and five reproduce the fallback exactly, with no observed degradation. These floating-point numerical results demonstrate mismatch robustness within the evaluated grid; captured-waveform and fi xed-point hardware validation remain necessary.
Electrocardiogram (ECG) recording is prone to complications, on analysis by physicians, due to noise and artifacts, thus creating ambiguity leading to possible error of diagnosis. Such drawbacks may be overcome with the advent of high resolution Methods, such as Discrete Wavelet Analysis and Digital Signal Processing (DSP) techniques. This ECG signal analysis is implemented in three stages: ECG preprocessing, features extraction and classification with the aim of realizing high resolution ECG diagnosis and improved detection of abnormal conditions in the heart. The preprocessing stage involves removing spurious artifacts (noise), due to such factors as muscle contraction, motion, respiration, etc. ECG features are extracted by applying DSP and suggested sloping method techniques. These measured features represent peak amplitude values and intervals of P, Q, R, S, R', and T waves on ECG, and other features such as ST elevation, QRS width, heart rate, electrical axis, QR and QT intervals. The classification is preformed using these extracted features and the criteria for cardiovascular diseases. The ECG diagnostic system is successfully applied to 12-lead ECG recordings for 12 cases. The system is provided with information to enable it diagnoses 15 different diseases. Physician's and computer's diagnoses are compared with 90% agreement, with respect to physician diagnosis, and the time taken for diagnosis is 2 seconds. All of these operations are programmed in Matlab environment.
29 February 2024 in Journal Européen des Systèmes Automatisés