Search Results (12)

By transferring external information between the equalizer and the decoder iteratively, the performance of turbo equalization is close to the channel capacity. Conventional turbo equalization (CTE) relies on channel coding, while the transmission of external information is a problem in an uncoded system, and turbo equalization without channel coding (TECC) remains unexplored. Therefore, this paper introduces a TECC framework with a virtual decoder constructed by bidirectional processing. The main innovation is that the existence of the virtual decoder enables the transmission of external information. Under this new framework, we implement it with a minimum mean square error decision feedback equalizer (MMSE-DFE) and evaluate its performance across stationary channels and multipath fading channels. Simulation results demonstrate significant communication performance enhancement after three to four iterations, surpassing both conventional bidirectional and unidirectional equalization. In addition, the proposed TECC is verified through underwater acoustic communication in a sea trial. The results also demonstrate that the TECC achieves better bit error performance. Full article

Cattle face segmentation and recognition in complex scenarios pose significant challenges due to insufficient fine-grained feature representation in segmentation networks and limited modeling of salient regions and local–global feature interactions in recognition models. To address these issues, DBCA-Net, a dual-branch context-aware algorithm for cattle face segmentation and recognition, is proposed. The method integrates an improved TransUNet-based segmentation network with a novel Fusion-Augmented Channel Attention (FACA) mechanism in the hybrid encoder, enhancing channel attention and fine-grained feature representation to improve segmentation performance in complex environments. The decoder incorporates an Adaptive Multi-Scale Attention Gate (AMAG) module, which mitigates interference from complex backgrounds through adaptive multi-scale feature fusion. Additionally, FACA and AMAG establish a dynamic feedback mechanism that enables iterative optimization of feature representation and parameter updates. For recognition, the GeLU-enhanced Partial Class Activation Attention (G-PCAA) module is introduced after Patch Partition, strengthening salient region modeling and enhancing local–global feature interaction. Experimental results demonstrate that DBCA-Net achieves superior performance, with 95.48% mIoU and 97.61% mDSC in segmentation tasks and 95.34% accuracy and 93.14% F1-score in recognition tasks. These findings underscore the effectiveness of DBCA-Net in addressing segmentation and recognition challenges in complex scenarios, offering significant improvements over existing methods. Full article

Large language models (LLMs) are widely integrated into autonomous driving systems to enhance their operational intelligence and responsiveness and improve self-driving vehicles’ overall performance. Despite these advances, LLMs still struggle between hallucinations—when models either misinterpret the environment or generate imaginary parts for downstream use cases—and taxing computational overhead that relegates their performance to strictly non-real-time operations. These are essential problems to solve to make autonomous driving as safe and efficient as possible. This work is thus focused on symmetrical trade-offs between the reduction of hallucination and optimization, leading to a framework for these two combined and at least specifically motivated by these limitations. This framework intends to generate a symmetry of mapping between real and virtual worlds. It helps in minimizing hallucinations and optimizing computational resource consumption reasonably. In autonomous driving tasks, we use multimodal LLMs that combine an image-encoding Visual Transformer (ViT) and a decoding GPT-2 with responses generated by the powerful new sequence generator from OpenAI known as GPT4. Our hallucination reduction and optimization framework leverages iterative refinement loops, RLHF—reinforcement learning from human feedback (RLHF)—along with symmetric performance metrics, e.g., BLEU, ROUGE, and CIDEr similarity scores between machine-generated answers specific to other human reference answers. This ensures that improvements in model accuracy are not overused to the detriment of increased computational overhead. Experimental results show a twofold improvement in decision-maker error rate and processing efficiency, resulting in an overall decrease of 30% for the model and a 25% improvement in processing efficiency across diverse driving scenarios. Not only does this symmetrical approach reduce hallucination, but it also better aligns the virtual and real-world representations. Full article

Orthogonal Time–Frequency Space (OTFS) is an innovative modulation method that ensures efficient and secure communication over a time-varying channel. This characteristic inspired us to integrate OTFS technology with underwater acoustic (UWA) communications to counteract the time-varying and overspread characteristics of UWA channels. However, implementing OTFS in UWA communications presents challenges related to overspread channels. To handle these challenges, we introduce a specialized OTFS system and offer frame design recommendations for UWA communications in this article. We propose a Doppler compensation method and a dual-domain joint channel estimation method to address the issues caused by severe Doppler effects in UWA communication. Additionally, we propose an OTFS system detection approach. This approach incorporates an iterative detection process which facilitates soft information exchange between a message passing (MP) detector and a low-density parity check (LDPC) decoder. By conducting simulations, we demonstrate that the proposed UWA OTFS system significantly outperforms Orthogonal Frequency-Division Multiplexing (OFDM), Initial Estimate Iterative Decoding Feedback (IE-IDF-MRC), and two-dimensional Passive Time Reversal Decision Feedback Equalization (2D-PTR-DFE) in UWA channels. Full article

Magnetic Resonance Imaging (MRI) reconstruction and segmentation are crucial for medical diagnostics and treatment planning. Despite advances, achieving high performance in both tasks remains challenging, especially in the context of accelerated MRI acquisition. Motivated by this challenge, the objective of this study is to develop an integrated approach for MRI image reconstruction and segmentation specifically tailored for accelerated acquisition scenarios. The proposed method unifies these tasks by incorporating segmentation feedback into an iterative reconstruction algorithm and using a transformer-based encoder–decoder architecture. This architecture consists of a shared encoder and task-specific decoders, and employs a feature distillation process between the decoders. The proposed model is evaluated on the Stanford Knee MRI with Multi-Task Evaluation (SKM-TEA) dataset against established methods such as SegNetMRI and IDSLR-Seg. The results show improvements in the PSNR, SSIM, Dice, and Hausdorff distance metrics. An ablation study confirms the contribution of feature distillation and segmentation feedback to the performance gains. The advancements demonstrated in this study have the potential to impact clinical practice by facilitating more accurate diagnosis and better-informed treatment plans. Full article

In recent years, emotional dialogue generation garnered widespread attention and made significant progress in the English-speaking domain. However, research on emotional dialogue generation in Chinese still faces two critical issues: firstly, the lack of high-quality datasets with emotional characteristics makes it difficult for models to fully utilize emotional information for emotional intervention; secondly, there is a lack of effective neural network models for extracting and integrating inherent logical information in the context to fully understand dialogues. To address these issues, this paper presented a Chinese dialogue dataset called LifeDialog, which was annotated with sentiment features. Additionally, it proposed DialogCIN, a contextual inference network that aims to understand dialogues based on a cognitive perspective. Firstly, the proposed model acquired contextual representations at both the global and speaker levels. Secondly, different levels of contextual vectors were separately inputted into the understanding unit, which consists of multiple inference modules. These modules iteratively performed reasoning and retrieval to delve into the inherent logical information of the dialogue context. Subsequently, appropriate emotions were predicted for feedback. Finally, an emotion-aware decoder was employed to generate a response. Experimental results on our manually annotated dataset, LifeDialog, demonstrated that DialogCIN can effectively simulate human cognitive inference processes, enabling a better understanding of dialogue context and improving the quality of generated dialogues. Full article

This paper proposes using direct adaptation (DA)-based turbo equalization in multiple-input-multiple-output (MIMO) filtered multitone (FMT) time reversal (TR) acoustic communications to jointly suppress noise, residual co-channel interference (CCI) and intersymbol interference (ISI) after the TR process. Soft information-based adaptive decision feedback equalization (ADFE) adjusted according to the recursive expected least squares (RELS) algorithm, including interference cancellation and decoding, is used to construct the DA-based turbo equalization. In the proposed method, soft information is exchanged between soft symbols with soft decisions of decoding iteratively, and interference suppression is proceeded successively and iteratively until the performance is stable. The principle of the proposed method is analyzed, and based on the acoustic channel responses measured in a real experiment, the performance is assessed in relation to that of anther two methods. Compared with the MIMO-FMT TR underwater acoustic communication using interference suppression without error control coding (ECC), the proposed method performs better, benefitting from the ECC included in turbo equalization. Additionally, compared with the MIMO-FMT TR underwater acoustic communication using interference suppression based on hard decision equalization and decoding, the proposed method exhibits superior performance by exploiting soft information. Full article

This paper studies the secrecy coding analysis achieved by the self-jamming technique in the presence of an eavesdropper by considering a short-packet Full-Duplex (FD) transmission developed based on iterative blind or semi-blind channel estimation and advanced decoding algorithms. Indeed, the legitimate receiver and eavesdropper can simultaneously receive the intended signal from the transmitter and broadcast a self-jamming or jamming signal to the others. Unlike other conventional techniques without feedback, the blind or semi-blind algorithm applied at the legitimate receiver can simultaneously estimate, firstly, the Self-Interference (SI) channel to cancel the SI component and, secondly, estimate the propagation channel, then decode the intended messages by using 5G Quasi-Cyclic Low-Density Parity Check (QC-LDPC) codes. Taking into account the passive eavesdropper case, the blind channel estimation with a feedback scheme is applied, where the temporary estimation of the intended channel and the decoded message are fed back to improve both the channel estimation and the decoding processes. Only the blind algorithm needs to be implemented in the case of a passive eavesdropper because it achieves sufficient performances and does not require adding pilot symbols as the semi-blind algorithm. In the case of an active eavesdropper, based on its robustness in the low region of the Signal-to-Noise Ratio (SNR), the semi-blind algorithm is considered by trading four pilot symbols and only requiring the feedback for channel estimation processes in order to overcome the increase in noise in the legitimate receiver. The results show that the blind or semi-blind algorithms outperform the conventional algorithm in terms of Mean Square Error (MSE), Bit Error Rate (BER) and security gap ($S_g$). In addition, it has been shown that the blind or semi-blind algorithms are less sensitive to high SI and self-jamming interference power levels imposed by secured FD transmission than the conventional algorithms without feedback. Full article

In a wiretap channel system model, the jammer node adopts the energy-harvesting signal as artificial noise (jamming signal) against the cooperative eavesdroppers. There are two eavesdroppers in the wiretap channel: eavesdropper E1 is located near the transmitter and eavesdropper E2 is located near the jammer. The eavesdroppers are equipped with multiple antennas and employ the iterative block decision feedback equalization decoder to estimate the received signal, i.e., information signal at E1 and jamming signal at E2. It is assumed that E1 has the channel state information (CSI) of the channel between transmitter and E1, and similarly, E2 has the CSI of channel between jammer and E2. The eavesdroppers establish communication link between them and cooperate with each other to reduce the information signal interference at E2 and jamming signal interference at E1. The performance of decoders depends on the signal to interference plus noise ratio (SINR) of the received signal. The power of information signal is fixed and the power of the jamming signal is adjusted to improve the SINR of the received signal. This research work is solely focused on optimizing the jamming signal power to degrade the performance of cooperative eavesdroppers. The jamming signal power is optimized for the given operating SINR with the support of simulated results. The jamming signal power optimization leads to better energy conservation and degrades the performance of eavesdroppers. Full article

In this paper, a non-binary low-density parity-check (NB-LDPC) coded high-order continuous phase modulation (CPM) system is designed and optimized to improve power and iterative efficiencies. Firstly, the minimum squared normalized Euclidean distance and the 99% double-sided power bandwidth are introduced to design a competitive CPM, improving its power efficiency under a given code rate and spectral efficiency. Secondly, a three-step method based on extrinsic information transfer (EXIT) and entropy theory is used to design NB-LDPC codes, which reduces the convergence threshold approximately 0.42 and 0.58 dB compared with the candidate schemes. Thirdly, an extrinsic information operation is proposed to address the positive feedback issue in iterative detection and decoding and the value of bit error rate (BER) can approximately be reduced by $5\times {10}^{-3}$. Finally, iteration optimization employing the EXIT chart and mutual information between demodulation and decoding is performed to achieve a suitable tradeoff for the communication reliability and iterative decoding delay. Simulation results show that the resulting scheme provides an approximately 3.95 dB coding gain compared to the uncoded CPM and achieves approximately 0.5 and 0.7 dB advantages compared with the candidate schemes. The resulting NB-LDPC-coded high-order CPM for a given code rate and spectral efficiency converges earlier into a turbo cliff region compared with other competitors and significantly improves power and iterative efficiencies. Full article

Multiple Input Multiple Output Orthogonal Frequency Division Multiplexing (MIMO-OFDM) proves to be a better choice for high speed underwater acoustic (UWA) communication as it increases the data rate and solves the bandwidth limitation issue; however, at the same time, it increases the design challenges and complexity of the receivers. Inter-Symbol Interference (ISI) and Inter-Carrier Interference (ICI) are introduced in the received signal by the extended multipath and Doppler shifts along with different types of noises due to the noisy acoustic channel. Here we propose two iterative receivers: one is ICI unaware iterative MIMO-OFDM receiver, which uses a novel cost function threshold based soft information decision feedback method. The second one is ICI aware progressive iterative MIMO-OFDM receiver, which adapts and increases the progressions according to the level of ICI present in the received signal, while fully utilizing the soft information from the previous iterations, therefore reducing the complexity. Orthogonal Matching pursuit (OMP) channel estimation, low density parity check (LDPC) decoding and minimum mean square error (MMSE) equalization schemes are exploited by both the receivers. The proposed receivers are analyzed and compared with the standard Alamouti MIMO receiver as a reference and also compared with the non-iterative, basic turbo iterative and non-progressive iterative MIMO receivers. Simulations and experimental results prove the efficiency and effectiveness of the proposed receivers. Full article

An iterative QR-based soft feedback segment interference cancellation (QRSFSIC) detection and decoder algorithm for a Reed–Muller (RM) space-time turbo system is proposed in this paper. It forms the sufficient statistic for the minimum-mean-square error (MMSE) estimate according to QR decomposition-based soft feedback successive interference cancellation, stemmed from the a priori log-likelihood ratio (LLR) of encoded bits. Then, the signal originating from the symbols of the reliable segment, the symbol reliability metric, in terms of an a posteriori LLR of encoded bits which is larger than a certain threshold, is iteratively cancelled with the QRSFSIC in order to further obtain the residual signal for evaluating the symbols in the unreliable segment. This is done until the unreliable segment is empty, resulting in the extrinsic information for a RM turbo-coded bit with the greatest likelihood. Bridged by de-multiplexing and multiplexing, an iterative QRSFSIC detection is concatenated with an iterative trellis-based maximum a posteriori probability RM turbo decoder as if a principal Turbo detection and decoder is embedded with an iterative subordinate QRSFSIC detection and a RM turbo decoder, exchanging each other’s detection and decoding soft-decision information iteratively. These three stages let the proposed algorithm approach the upper bound of the diversity. The simulation results also show that the proposed scheme outperforms the other suboptimum detectors considered in this paper. Full article