Explore the vast range of titles available.

With the rapid advancement of intelligent driving technology, multi-source information fusion has become a vital topic in the field of environmental perception. To address the fusion deviation resulting from changes in sensor performance due to environmental variations, this paper proposes a multi-source information fusion algorithm based on the improved Sage-Husa adaptive extended Kalman filtering (SHAEKF) algorithm. First, a multi-source information fusion system is constructed based on the vehicle kinematic model and the sensor measurement model. Then, the Sage-Husa adaptive fading extended Kalman filtering (SHAFEKF) algorithm is constructed by introducing a fading factor into the SHAEKF algorithm to enhance the influence of newly incoming data. Finally, the experimental results indicate that the positional average errors of the algorithm in the two scenarios are 0.137 and 0.071. When compared to the SHAEKF algorithm, the positional average errors have been reduced by 2.8% and 13.4%, while the mean squared errors have decreased by 64% and 72%. This demonstrates that the SHAFEKF algorithm offers high accuracy and low fluctuation, enhancing its adaptability in multi-source information fusion systems.

In this paper, electro-hydraulic braking (EHB) force allocation for electric vehicles (EVs) is modeled as a constrained nonlinear optimization problem (NOP). Recurrent neural networks (RNNs) are advantageous in many folds for solving NOPs, yet existing RNNs’ convergence usually requires convexity with calculation of second-order partial derivatives. In this paper, a recurrent neural network-based NOP solver (RNN-NOPS) is developed. It is seen that the RNN-NOPS is designed to drive all state variables to asymptotically converge to the feasible region, with loose requirement on the NOP’s first-order partial derivative. In addition, the RNN-NOPS’s equilibria are proved to meet Karush–Kuhn–Tucker (KKT) conditions, and the RNN-NOPS behaves with a strong robustness against the violation of the constraints. The comparative studies are conducted to show RNN-NOPS’s advantages for solving the EHB force allocation problem, it is reported that the overall regenerative energy of RNN-NOPS is 15.39% more than that of the method for comparison under SC03 cycle.

In this paper, the car-following model based on drivers' psychological characteristics is proposed for developing drivers' explicit behavior decision under complicated driving environment. The nature of driving behavior in different driving mode is discussed based on the concept of decision-making system, using the drivers' psychological individuality combined with universality of vehicle kinetics. Especially, the perceived distance and expected safety distance are considered rather than the traditional space headway. The genetic algorithm and NGSIM (New Generation Simulation) data are used to calibrate parameters in car-following model. It is shown in the calibration results that the drivers have different concerns in different driving mode, and it is logical for the drivers' psychological characteristics. The effectiveness and accuracy of proposed model have been verified compared to the GM and FVD model in simulation results.

The covariance matrix of measurement noise is fixed in the Kalman filter algorithm. However, in the process of battery operation, the measurement noise is affected by different charging and discharging conditions and the external environment. Consequently, obtaining the noise statistical characteristics is difficult, which affects the accuracy of the Kalman filter algorithm. In order to improve the estimation accuracy of the state of charge (SOC) of lithium-ion batteries under actual working conditions, a fuzzy fractional-order unscented Kalman filter (FFUKF) is proposed. The algorithm combines fuzzy inference with fractional-order unscented Kalman filter (FUKF) to infer the measurement noise in real time and take advantage of fractional calculus in describing the dynamic behavior of the lithium batteries. The accuracy of the SOC estimation under different working conditions at three different temperatures is verified. The results show that the accuracy of the proposed algorithm is superior to those of the FUKF and extended Kalman filter (EKF) algorithms.

Semantic segmentation is crucial to the autonomous driving, as an accurate recognition and location of the surrounding scenes can be provided for the street scenes understanding task. Many existing segmentation networks usually fuse high‐level and low‐level features to boost segmentation performance. However, the simple fusion may impose a limited performance improvement because of the gap between high‐level and low‐level features. To alleviate this limitation, we respectively propose spatial aggregation and channel fusion to bridge the gap. Our implementation, inspired by the attention mechanism, consists of two steps: (1) Spatial aggregation relies on the proposed pyramid spatial context aggregation module to capture spatial similarities to enhance the spatial representation of high‐level features, which is more effective for the latter fusion. (2) Channel fusion relies on the proposed attention‐based channel fusion module to weight channel maps on different levels to enhance the fusion. In addition, the complete network with U‐shape structure is constructed. A series of ablation experiments are conducted to demonstrate the effectiveness of our designs, and the network achieves mIoU score of 81.4% on Cityscapes test dataset and 84.6% on PASCALVOC 2012 test dataset.

To evaluate the efficacy and safety of transarterial chemoembolization (TACE) plus regorafenib and PD-1 inhibitor (T-R-P) versus regorafenib plus PD-1 inhibitor (R-P) as the second-line treatment for unresectable hepatocellular carcinoma (uHCC). In this retrospective, single-center cohort study, 130 uHCC patients who received second-line therapy between February 2020 and July 2024 were enrolled. Among the 130 enrolled patients, 69 received T-R-P and 61 received R-P. Propensity score matching (PSM) and inverse probability treatment weighting (IPTW) were used to minimize confounding factors. Outcomes included overall survival (OS), progression-free survival (PFS), objective response rate (ORR) and disease control rate (DCR). Multivariate Cox regression analysis was used to identify prognostic factors. Subgroup analyses were conducted to assess the treatment benefits in specific patient populations. After PSM, the T-R-P regimen showed significantly improved OS (14.3 vs 8.1 months) and PFS (8.4 vs 4.3 months) compared to the R-P regimen (P < 0.001). According to mRECIST, ORR (56.5% vs 15.2%) and DCR (69.6% vs 37.0%) were also significantly higher with the T-R-P regimen. Multivariate Cox regression analysis identified the T-R-P regimen as an independent protective factor for both OS (hazard ratio [HR] = 0.33, P < 0.001) and PFS (HR = 0.39, P < 0.001). These consistent survival benefits in the T-R-P regimen were maintained in both the unmatched cohort and after IPTW. Subgroup analyses further confirmed the consistent survival benefits of the T-R-P regimen across the most predefined patient subgroups. No treatment-related deaths occurred during the study period. After PSM, the T-R-P regimen continued to demonstrate statistically significant and clinically meaningful improvements in both OS and PFS, coupled with a manageable safety profile, compared to the R-P regimen in patients with uHCC. These findings provide a rationale for considering the T-R-P regimen as a potential second-line treatment option.

BackgroundAlthough transjugular intrahepatic portosystemic shunt (TIPS) is recommended for secondary prophylaxis of variceal bleeding if standard therapy fails and for patients with high risk of recurrent bleeding, no guidelines for the treatment of symptomatic portal hypertension in HCC patients are available. This study aimed to compare the efficacy and safety of TIPS with endoscopic + β-blocker for prevention of the rebleeding in such patients.Methods106 consecutive advanced HCC patients receiving tyrosine kinase inhibitor (TKI) who had been treated with vasoactive drugs plus endoscopic therapy for variceal bleeding were randomly assigned to receive either TIPS (n = 52) or endoscopic + β-blocker therapy (n = 54) for the prevention of rebleeding. The primary endpoint was variceal rebleeding after randomization.ResultsDuring a median follow-up of 16 months, rebleeding occurred in 14 patients in the endoscopic + β-blocker group and 3 patients in the TIPS group (p < 0.001). Forty-nine patients died (38 in endoscopic + β-blocker group and 11 in TIPS group, p < 0.001). The 6-, 12-, and 18-month overall survival rates were 95, 81, and 73% for TIPS group and 35, 21, and 15% for endoscopic + β-blocker group, respectively (p < 0.001). Eight patients in endoscopic + β-blocker group received TIPS as rescue therapy, but two died. TKIs was discontinued in 32 patients, including 24 in the endoscopic + β-blocker group and 8 in the TIPS group (p < 0.001). No significant differences were observed between the two groups with respect to serious adverse events.ConclusionsIn advanced HCC patients receiving TKIs and presented with variceal bleeding, the use of TIPS was associated with significant reduction in rebleeding, improved a higher adherence to TKIs therapy, and prolonged survival.

We explore the dose-efficacy relationship of lenvatinib plus anti-PD-1 in patients with unresectable hepatocellular carcinoma (u-HCC) infected with hepatitis B virus (HBV) in real-world practice. Furthermore, we identify the population sensitive to lenvatinib plus anti-PD-1 treatments. This retrospective study included 70 patients treated with lenvatinib plus at least 3 cycles of anti-PD-1 and 140 with lenvatinib alone. Stabilized inverse probability of treatment weighting (SIPTW) was used to balance clinical features between the two groups. The overall survival (OS), progression-free survival (PFS), objective response rate (ORR), disease control rate (DCR), and adverse events (AEs) were analyzed. Subpopulation treatment effect pattern plot (STEPP) estimated treatment-effect differences between the two groups. The median age was 54 years, and 189 (90%) cases were male. A total of 180 (85%) patients were infected with HBV. A slowly increasing 12-month survival rate was with the cycles of anti-PD-1, and 5 cycles and more of anti-PD-1 appeared the most beneficial and stable survival rate. The lenvatinib plus at least 3 cycles anti-PD-1 group had better OS (21.4 vs 14 months, p = 0.041), PFS (8.0 vs 6.3 months, p = 0.015) than the lenvatinib alone group in unadjusted cohorts, and the SIPTW adjusted cohorts had confirmed it. For patients with portal vein trunk invasion (PVTI) or extrahepatic spread (EHS) combined with Child-Pugh class B (CPB), lenvatinib plus anti-PD-1 made the 12-month survival rate increase by 38%, while, in the other population, it did only 18%. The two groups had similar AEs (p ≥ 0.05). The lenvatinib combined with at least 3 cycles of anti-PD-1 was efficacy and safe for u-HCC patients infected with HBV. Especially, patients with PVTI or EHS combined with CPB may benefit most from the combination therapy.

This paper proposes a new generalized adaptive gain sliding mode observer (GAGSMO) for estimating the unavailable states of a class of multi-input multi-output uncertain nonlinear systems. To further improve the estimation performance of conventional sliding mode observer, the observer gains of GAGSMO are designed for the first time as the generalized bounded positive functions of the available output errors and the upper bounds of disturbance terms. Due to the features of the designed observer gains, the GAGSMO has stronger robustness than the conventional sliding mode observer in the presence of system uncertainties and nonlinearities. The finite-time error convergence of GAGSMO is proved by the Lyapunov stability theorem in conjunction with the introduced mapping functions. Then, by catching sight of the inherent feature of sliding motion, a recursive mechanism based only on available estimation information is formulated to update the designed observer gains online in the sliding mode stage. With the recursive mechanism, the chattering level of GAGSMO is minimized, and the estimation accuracy of GAGSMO is further improved. The effectiveness and excellent performance of the proposed GAGSMO are illustrated with two numerical examples.

Abstract Background To investigate the outcomes of combined lenvatinib plus immune checkpoint inhibitors (ICIs) in patients with unresectable, recurrent, or metastatic hepatocellular carcinoma (HCC) in a real-world setting. Material and methods This retrospective study included patients with unresectable, recurrent, or metastatic HCC who received lenvatinib combined with ICIs at the Fifth Medical Center of the Chinese PLA General Hospital between May 2018 and November 2022. The study outcomes were overall survival (OS), progression-free survival (PFS), and treatment response. Results This study included 117 patients. The objective response rate (comprising both complete and partial responses) was 53.2%. Among those with first-line lenvatinib plus ICI (n = 109), the disease control rate (complete response, partial response, and stable disease) was 89.9%. In all patients, the median OS and PFS were 26.0 (95% CI, 22.0-30.4) and 15.3 (95% CI, 13.2-17.5) months, respectively. In first-line patients, the median OS and PFS were 27.6 (95% CI, 23.4-34.6) and 15.4 (95% CI, 13.4-18.2) months, respectively. Among the 117 patients, treatment was discontinued in 58 (50%) because of AE (n = 9, 16%), PD (n = 43, 74%), or an unknown reason (n = 6, 10%). Among the 117 patients, treatment was interrupted in 26 (22%), and the dose was adjusted in 24 (21%). Conclusion This real-world study supports the possibility of using lenvatinib combined with ICI for the management of patients with unresectable, recurrent, or metastatic HCC, including first-line treatment. Confirmation through a formal clinical trial would provide firmer conclusions.