Explore the vast range of titles available.

Background Incremental dialysis may preserve residual renal function and improve survival in comparison with full-dose dialysis; however, available evidence is limited. We therefore compared all-cause mortality and residual kidney function (RKF) loss in incremental and full-dose dialysis and time to full-dose dialysis in incremental hemodialysis (IHD) and incremental peritoneal dialysis (IPD). Methods We performed a systematic review and meta-analysis of cohort studies of adults with ESRD starting IHD and IPD. We identified in PubMed and Web of Science database all cohort studies evaluating incremental dialysis evaluating three outcomes: all-cause mortality, RKF loss, time to full dialysis. IPD was defined as < 3 daily dwells in Continuous Ambulatory Peritoneal Dialysis and < 5 sessions per week in Automated Peritoneal Dialysis, while IHD was defined as < 3 HD sessions per week. Results 22 studies (75,292 participants), 15 in HD and 7 in PD, were analyzed. Mean age at dialysis start was 62 and 57 years in IHD and IPD subjects, respectively. When compared to full dose, incremental dialysis (IHD or IPD) had an overall mortality risk of 1.14 [95% CI 0.85–1.52] with high heterogeneity among studies (I 2 86%, P < 0.001), and lower mean RKF loss (− 0.58 ml/min/months, 95% CI 0.16–1.01, P = 0.007). Overall, time to full-dose dialysis was 12.1 months (95% CI 9.8–14.3) with no difference between IHD and IPD (P = 0.217). Conclusions Incremental dialysis allows longer preservation of RKF thus deferring full-dose dialysis, by about 1 year in HD and PD, with no increase in mortality risk. Large and adequate studies are needed to confirm these findings.

This paper explores the development and application of the incremental forming process, an innovative method for manufacturing complex parts with high flexibility and low tooling costs. The review categorizes three key process variants: Single Point Incremental Forming (SPIF), Two Point Incremental Forming (TPIF), and Incremental Forming with Conjugated Active Plate (IFCAP). This study demonstrates the significant effects of these process variants on part accuracy and material behavior, particularly under varying process conditions. This study identifies critical technological parameters such as tool diameter, feed rate, and vertical step size. The findings also demonstrate the role of optimized toolpaths and lubrication in improving process efficiency. Applications of incremental forming across various industries, including automotive, aerospace, medical, and construction, demonstrate its versatility in prototype production and small-series manufacturing. These results contribute to a deeper understanding of incremental forming, offering practical recommendations to enhance precision, scalability, and material formability, and supporting future innovations and broader industrial applications.

PV power production is highly dependent on environmental and weather conditions, such as solar irradiance and ambient temperature. Because of the single control condition and any change in the external environment, the first step response of the converter duty cycle of the traditional MPPT incremental conductance algorithm is not accurate, resulting in misjudgment. To improve the efficiency and economy of PV systems, an improved incremental conductance algorithm of MPPT control strategy is proposed. From the traditional incremental conductance algorithm, this algorithm is simple in structure and can discriminate the instantaneous increment of current, voltage and power when the external environment changes, and so can improve tracking efficiency. MATLAB simulations are carried out under rapidly changing solar radiation level, and the results of the improved and conventional incremental conductance algorithm are compared. The results show that the proposed algorithm can effectively identify the misjudgment and avoid its occurrence. It not only optimizes the system, but also improves the efficiency, response speed and tracking efficiency of the PV system, thus ensuring the stable operation of the power grid.

As a special case of machine learning, incremental learning can acquire useful knowledge from incoming data continuously while it does not need to access the original data. It is expected to have the ability of memorization and it is regarded as one of the ultimate goals of artificial intelligence technology. However, incremental learning remains a long term challenge. Modern deep neural network models achieve outstanding performance on stationary data distributions with batch training. This restriction leads to catastrophic forgetting for incremental learning scenarios since the distribution of incoming data is unknown and has a highly different probability from the old data. Therefore, a model must be both plastic to acquire new knowledge and stable to consolidate existing knowledge. This review aims to draw a systematic review of the state of the art of incremental learning methods. Published reports are selected from Web of Science, IEEEXplore, and DBLP databases up to May 2020. Each paper is reviewed according to the types: architectural strategy, regularization strategy and rehearsal and pseudo-rehearsal strategy. We compare and discuss different methods. Moreover, the development trend and research focus are given. It is concluded that incremental learning is still a hot research area and will be for a long period. More attention should be paid to the exploration of both biological systems and computational models.

Quasi-zero-stiffness (QZS) vibration isolator is widely used in low-frequency vibration isolation due to its high-static-low-dynamic-stiffness (HSLDS) characteristics. The complex nonlinear force of the QZS vibration isolator increases the difficulty of solving it while realizing the HSLDS characteristics. The typical analysis method is to use Taylor expansion to simplify the nonlinear force and make it approximate to polynomial form, which leads to inaccurate analysis results in the case of large excitation and small damping. Therefore, the modified incremental harmonic balance (IHB) method is used to directly analyze the dynamic characteristics of the QZS vibration isolator without simplification in this paper. The classical three-spring QZS vibration isolation model is used as the calculation example. The results are different from the previous approximate equation analysis results in three aspects: (1) There is no unbounded response of the system under displacement excitation; (2) Even harmonics and constant terms also exist in the response of the system and can lead to multiple solution intervals; (3) In the case of small damping and large excitation, both displacement excitation and force excitation have subharmonic resonance, reducing the vibration isolation performance of the system. In addition, the accuracy of the solution obtained by the IHB method is verified by the Runge–Kutta method. The accurate analysis method in this paper provides favorable theoretical support for the design and optimization of vibration isolators.

This paper proposes a novel incremental training mode to address the problem of Deep Reinforcement Learning (DRL) based path planning for a mobile robot. Firstly, we evaluate the related graphic search algorithms and Reinforcement Learning (RL) algorithms in a lightweight 2D environment. Then, we design the algorithm based on DRL, including observation states, reward function, network structure as well as parameters optimization, in a 2D environment to circumvent the time-consuming works for a 3D environment. We transfer the designed algorithm to a simple 3D environment for retraining to obtain the converged network parameters, including the weights and biases of deep neural network (DNN), etc. Using these parameters as initial values, we continue to train the model in a complex 3D environment. To improve the generalization of the model in different scenes, we propose to combine the DRL algorithm Twin Delayed Deep Deterministic policy gradients (TD3) with the traditional global path planning algorithm Probabilistic Roadmap (PRM) as a novel path planner (PRM+TD3). Experimental results show that the incremental training mode can notably improve the development efficiency. Moreover, the PRM+TD3 path planner can effectively improve the generalization of the model.

Based on support vector machine (SVM), incremental SVM was proposed, which has a strong ability to deal with various classification and regression problems. Incremental SVM and incremental learning paradigm are good at handling streaming data, and consequently, they are well suited for solving time series prediction (TSP) problems. In this paper, incremental learning paradigm is combined with incremental SVM, establishing a novel algorithm for TSP, which is the reason why the proposed algorithm is termed double incremental learning (DIL) algorithm. In DIL algorithm, incremental SVM is utilized as the base learner, while incremental learning is implemented by combining the existing base models with the ones generated on the new data. A novel weight update rule is proposed in DIL algorithm, being used to update the weights of the samples in each iteration. Furthermore, a classical method of integrating base models is employed in DIL. Benefited from the advantages of both incremental SVM and incremental learning, the DIL algorithm achieves desirable prediction effect for TSP. Experimental results on six benchmark TSP datasets verify that DIL possesses preferable predictive performance compared with other existing excellent algorithms.

In our ever-evolving world, new data exhibits a long-tailed distribution, such as emerging images in varying amounts. This necessitates continuous model learning imbalanced data without forgetting, addressing the challenge of long-tailed class-incremental learning (LTCIL). Existing methods often rely on retraining linear classifiers with former data, which is impractical in real-world settings. In this paper, we harness the potent representation capabilities of pre-trained models and introduce AdaPtive Adapter RouTing ( Apart ) as an exemplar-free solution for LTCIL. To counteract forgetting, we train inserted adapters with frozen pre-trained weights for deeper adaptation and maintain a pool of adapters for selection during sequential model updates. Additionally, we present an auxiliary adapter pool designed for effective generalization, especially on minority classes. Adaptive instance routing across these pools captures crucial correlations, facilitating a comprehensive representation of all classes. Consequently, Apart tackles the imbalance problem as well as catastrophic forgetting in a unified framework. Extensive benchmark experiments validate the effectiveness of Apart .

This study presents an incremental learning framework to enhance the generalization and robustness of transformer-based deep learning models for segmenting skin cancer and related tissue structures. While deep learning models often perform well on data distributions similar to their training sets, their accuracy typically degrades when exposed to novel scenarios–limiting their clinical utility in skin cancer diagnosis. To address this, we propose a biologically inspired incremental learning strategy tailored for skin cancer classification and segmentation, allowing the model to incorporate new data progressively while reducing catastrophic forgetting. Our approach integrates multiple loss functions to preserve existing knowledge while adapting to additional magnification levels. Experimental results on the in-distribution test set demonstrate consistent performance improvements: achieving 89.05% accuracy with 10 magnification, 92.68% with 10 and 5 combined, and 95.53% when incorporating 10 , 5 , and 2 magnifications. These findings highlight the potential of our method to improve the adaptability and reliability of deep learning systems for empirical generalization in skin cancer classification tasks.

Analyzing the nonlinear characteristics of dual-rotor systems under thermo-mechanical (TM) coupling situations is critical, as operational conditions should be accurately determined, to avoid potential thermally-induced failures. This paper proposes the coupled TM model of a dual-rotor system, which considers multiple nonlinearities and heat generation of four bearings that couple the mechanical and thermal fields. Heat dissipation controlled by lubricant flow rates is introduced into the model to simulate different TM coupling degrees. Nonlinear phenomena and stability evolution are analyzed by the modified incremental harmonic balance method (IHB) at primary resonance regions. An increase in TM coupling degrees can lead to more bifurcation points, resonance regions with lower frequencies, larger vibration responses, and unstable regions. It can also transform resonance hysteresis phenomena into more complex nonlinear phenomena and some saddle-node bifurcation points into Neimark–Sacker bifurcation points. The reason for these transformations is that the effective radial clearance (RC) of bearings changes with rotation speed and thermal expansion. Temperature nonlinearities are induced by the radial bearing loads and the lubricant viscosity, which are investigated by various generalized nonlinear thermal forces. These findings can help further understand nonlinear coupled TM problems of complex dual-rotor systems.