Explainable t-SNE for single-cell RNA-seq data analysis

Single-cell RNA (scRNA-seq) sequencing technologies trigger the study of individual cell gene expression and reveal the diversity within cell populations. To measure cell-to-cell similarity based on their transcription and gene expression, many dimension reduction methods are employed to retrieve the corresponding low-dimensional embeddings of input scRNA-seq data to conduct clustering. However, the methods lack explainability and may not perform well with scRNA-seq data because they are often migrated from other fields and not customized for high-dimensional sparse scRNA-seq data. In this study, we propose an explainable t-SNE: cell-driven t-SNE (c-TSNE) that fuses the cell differences reflected from biologically meaningful distance metrics for input scRNA-seq data. Our study shows that the proposed method not only enhances the interpretation of the original t-SNE visualization for scRNA-seq data but also demonstrates favorable single cell segregation performance on benchmark datasets compared to the state-of-the-art peers. The robustness analysis shows that the proposed cell-driven t-SNE demonstrates robustness to dropout and noise in dimension reduction and clustering. It provides a novel and practical way to investigate the interpretability of t-SNE in scRNA-seq data analysis. Unlike the general assumption that the explainanbility of a machine learning method needs to compromise with the learning efficiency, the proposed explainable t-SNE improves both clustering efficiency and explainanbility in scRNA-seq analysis. More importantly, our work suggests that widely used t-SNE can be easily misused in the existing scRNA-seq analysis, because its default Euclidean distance can bring biases or meaningless results in cell difference evaluation for high-dimensional sparse scRNA-seq data. To the best of our knowledge, it is the first explainable t-SNE proposed in scRNA-seq analysis and will inspire other explainable machine learning method development in the field.

Discrete indirect adaptive sliding mode control for uncertain Hammerstein nonlinear systems

The robustness issue of uncertain nonlinear systems’ control has attracted the attention of numerous researchers. In this paper, we propose three techniques to deal with the uncertain Hammerstein nonlinear model. First, a discrete sliding mode control (SMC) is developed, which is based on converting the original nonlinear system into a linearized one in the vicinity of the operating region using Taylor series expansion. However, the presence of relatively high nonlinearities and parameter variations leads to the deterioration of the desired performances. In order to overcome these problems and to improve the performance of classical SMC, we propose two solutions. The first one is based on the synthesis of a discrete SMC, taking into account the presence of nonlinearity. The second solution is a new discrete adaptive SMC for input–output Hammerstein model. In order to show the effectiveness of the proposed controllers, a detailed robustness analysis is clearly developed. Simulation examples are reported at the end of the paper.

Design and robustness analysis of fuzzy PID controller for automatic voltage regulator system using genetic algorithm

In this paper, a Fuzzy proportional–integral–derivative (Fuzzy PID) controller design is presented to improve the automatic voltage regulator (AVR) transient characteristics and increase the robustness of the AVR. Fuzzy PID controller parameters are determined by a genetic algorithm (GA)-based optimization method using a novel multi-objective function. The multi-objective function, which is important for tuning the controller parameters, obtains the optimal solution using the Integrated Time multiplied Absolute Error (ITAE) criterion and the peak value of the output response. The proposed method is tested on two AVR models with different parameters and compared with studies in the literature. It is observed that the proposed method improves the AVR transient response properties and is also robust to parameter changes.

Application hybrid GSAPSO Technique for AGC in Inter Connected Power System with Generation Rate Constant

An attempt has been taken in this work to effectively implement the combination of GSA and PSO (hGSA-PSO) technique towards AGC in two-area inter-connected power systems with generation rate constraint (GRC) is considered. For the design and analysis, a initial attempt has been taken to optimize parameters of proportional-integral-derivative (PID) controller in two area non-reheat thermal power system employing GSA and hGSA-PSO algorithm with ITAE objective function. A sensitivity studies carried out for the robustness of the system by changing the operating condition and variation of the parameter and generation rate constant (GRC= ±0.05 and ±0.025) is considered. The performances of the proposed controller has been evaluated with those of some previously published optimization techniques such as GA and BOFA based optimized controller parameters for the same power system. This study of the present work is extended to two area multi sources power system to test the robustness analysis of the system by comparing the hGSA-PSO optimized to PI controller with same structure of system by selecting with and without GRC for showing the dynamic performance analysis of the system in term of settling time and overshoot.

Electro-Thermal Model-Based Design of Bidirectional On-Board Chargers in Hybrid and Full Electric Vehicles

In this paper, a model-based approach for the design of a bidirectional onboard charger (OBC) device for modern hybrid and fully electrified vehicles is proposed. The main objective and contribution of our study is to incorporate in the same simulation environment both modelling of electrical and thermal behaviour of switching devices. This is because most (if not all) of the studies in the literature present analyses of thermal behaviour based on the use of FEM (Finite Element Method) SWs, which in fact require the definition of complicated models based on partial derivative equations. The simulation of such accurate models is computationally expensive and, therefore, cannot be incorporated into the same virtual environment in which the circuit equations are solved. This requires long waiting times and also means that electrical and thermal models do not interact with each other, limiting the completeness of the analysis in the design phase. As a case study, we take as reference the architecture of a modular bidirectional single-phase OBC, consisting of a Totem Pole-type AC/DC converter with Power Factor Correction (PFC) followed by a Dual Active Bridge (DAB) type DC/DC converter. Specifically, we consider a 7 kW OBC, for which its modules consist of switching devices made with modern 900 V GaN (Gallium Nitrade) and 1200 V SiC (Silicon Carbide) technologies, to achieve maximum performance and efficiency. We present a procedure for sizing and selecting electronic devices based on the analysis of behaviour through circuit models of the Totem Pole PFC and DAB converter in order to perform validation by using simulations that are as realistic as possible. The developed models are tested under various operating conditions of practical interest in order to validate the robustness of the implemented control algorithms under varying operating conditions. The validation of the models and control loops is also enhanced by an exhaustive robustness analysis of the parametric variations of the model with respect to the nominal case. All simulations obtained respect the operating limits of the selected devices and components, for which its characteristics are reported in data sheets both in terms of electrical and thermal behaviour.

What Can Explain Momentum? Evidence from Decomposition

This study comprehensively evaluates and ranks a large number of competing explanations for the momentum anomaly. As a benchmark for evaluation, firm fundamentals are found to be the most promising among well-known explanations of momentum, followed by prospect theory and mental accounting, and anchoring effect. Collectively, all explanations capture 31% of momentum, whereas 69% of momentum remains unexplained. This study thoroughly examines what fractions of the momentum anomaly emerge from the interaction effects between past returns and various firm characteristics. It is further found that strategies based on firm characteristics and residual momentum can significantly alleviate the severity of momentum crashes. Finally, robustness analysis is provided for choosing different formation and holding periods, excluding January observations, and analyze at the level of portfolio rather than individual stock. This paper was accepted by David Simchi-Levi, finance.

Network Robustness Analysis Based on Maximum Flow

Network robustness is the ability of a network to maintain a certain level of structural integrity and its original functions after being attacked, and it is the key to whether the damaged network can continue to operate normally. We define two types of robustness evaluation indicators based on network maximum flow: flow capacity robustness, which assesses the ability of the network to resist attack, and flow recovery robustness, which assesses the ability to rebuild the network after an attack on the network. To verify the effectiveness of the robustness indicators proposed in this study, we simulate four typical networks and analyze their robustness, and the results show that a high-density random network is stronger than a low-density network in terms of connectivity and resilience; the growth rate parameter of scale-free network does not have a significant impact on robustness changes in most cases; the greater the average degree of a regular network, the greater the robustness; the robustness of small-world network increases with the increase in the average degree. In addition, there is a critical damage rate (when the node damage rate is less than this critical value, the damaged nodes and edges can almost be completely recovered) when examining flow recovery robustness, and the critical damage rate is around 20%. Flow capacity robustness and flow recovery robustness enrich the network structure indicator system and more comprehensively describe the structural stability of real networks.