The increasing demand for high-performance Lithium-Ion Batteries (LIBs) in Electric Vehicles (EVs) underscores the need for high-quality manufacturing. A key challenge is accurately identifying electrodes and measuring anode overhang during the winding process, which directly affects battery performance and safety. Recently, Segment Anything Model (SAM) has been explored to automate data annotation for training small yet specialized segmentation models like Mask R-CNN to infer on the edge. However, SAM struggles to capture sub-pixel boundaries of thin and elongated electrodes due to fixed patch size, lack of high-frequency spatial features, and difficulty of deep fine-tuning. This leads to fragmented masks and irregular boundaries, degrading the annotation quality. On the other hand, existing mask refinement methods, designed primarily for natural images, are not directly applicable for the dense electrodes and low signal-to-noise conditions in industrial X-ray images. To bridge the research gap, a novel local-global two-stage refinement method is proposed in this paper with denoising diffusion steps. The local stage repairs breaks and refines boundary precision at electrode level, while the global stage ensures overall structural consistency across the entire battery cell. Artifact detection and secondary local refinement further improves the mask quality. Experiment results on real-world LIB data collected demonstrate the proposed method outperforms other refinement techniques with visible advancement over coarse masks, enabling more accurate overhang analysis. These findings suggest the potential to reduce manual annotation efforts, paving the way for more scalable and effective LIB manufacturing inspection.

In this paper, we propose an iterative symbol-level detection and decoding scheme for nonbinary low-density parity-check (LDPC) coded generalized two-dimensional (2D) intersymbol interference (ISI) channels. The proposed 2D channel detector consists of two constituent detectors that work iteratively to mitigate downtrack and crosstrack interference. The downtrack detector is based on the nonbinary BCJR algorithm; while the crosstrack detector performs the sum-product algorithm (SPA) over a cycle-free symbol-level factor graph of the crosstrack channel, which can be directly concatenated to the nonbinary LDPC code graph without resorting to bit/symbol log-likelihood ratio (LLR) conversions. Simulation results show that the proposed symbol-level receiver outperforms bit-level schemes and also enables nonbinary LDPC codes to achieve a noticeable performance gain over binary codes when transmitted over severely ISI-distorted 2D channels.

In this paper, we investigate the performance of differentially detected differential phase-shift keying (DPSK) modulation with postdetection maximal ratio combining, in nonselective Rayleigh fading channels with multiple asynchronous cochannel interferers. The approach is based on an analytical technique we have presented earlier in the literature. Exact bit-error probability (BEP) results for binary DPSK and quaternary DPSK are derived. More specifically, we look into the effects of symbol-timing offsets between the interfering signals and the desired signal on the error performance. Our results show that when all the interfering signals are synchronous with the desired signal, the impairment caused by the cochannel interference to the desired user is maximum. On the other hand, when all the interfering signals are half-symbol-duration-delayed with respect to the desired user, they introduce the minimum impairment. Based on these findings, upper and lower bounds on the BEP are derived in simple closed form. Our explicit BEP results also show that the error probabilities of different transmitted symbols of the desired user are affected differently by the interfering signal

We develop in this paper an Alamouti-type space- time (ST) block code that employs orthogonalM-ary FSK (MFSK) modulation. It is demonstrated that every transmitted symbol in the proposed ST-MFSK scheme can be treated as an implicit pilot symbol, and consequently the receiver can attain close to ideal coherent bit-error performance even in the absence of an explicit channel sounding signal. In addition to employing the popular block-wise static fading model for performance evaluation, we also study the implications of a more realistic fading model whereby the fading gains are allowed to vary from one subinterval to another within a ST code block. It was discovered that an iterative channel estimation strategy has to be adopted to mitigate the cross-talk associated with this refined channel model. The iterative channel estimator, in conjunction with a companion minimum mean square error detector, or a companion maximum likelihood detector, enable the receiver to obtain a bit-error performance similar to that obtained under the block-wise static fading model. In comparison with differential ST-MPSK, the two approaches yield similar error performance in a static fading environment. However, the error performance of differential ST-MPSK deteriorates rapidly as the fade rate increases whereas the performance of ST-MFSK is almost independent of the fade rate. In terms of implementation complexity and delay of the receiver, the proposed coherent ST- MFSK scheme and differential ST-MPSK are very similar, as both approaches employ digital filters of similar lengths. The findings in this paper suggest that despite its larger bandwidth requirement, ST-MFSK is a very attractive alternative space-time signaling format.

We investigate in this paper an Alamouti-type space-time block code (STBC) using orthogonal M-ary frequency-shift-keying (MFSK). The signal is coherently detected using the channel estimates derived from the unmodulated (or implicit pilot) component of the orthogonal signal. An exact bit error probability expression for BFSK and tight union bound for MFSK are derived for the proposed coherent ST-FSK receiver. It is observed that the receiver can maintain close to ideal coherent performance even at very fast fading rates. In comparison with differential STBC, the two approaches yield similar error performance in a static fading environment. However, the error performance of differential STBC deteriorates rapidly as the fade rate increases. In terms of implementation complexity and delay, the proposed coherent ST-FSK receiver is similar to differential STBC, as both approaches employ digital filters of similar lengths. The findings in this paper suggest that despite its larger bandwidth requirement, ST-FSK is a very attractive alternative space-time signaling format.