Recent advances in probabilistic generative modeling have motivated learning Structural Causal Models (SCM) from observational datasets using deep conditional generative models, also known as Deep Structural Causal Model (DSCM). If successful, DSCMs can be utilized for causal estimation tasks, e.g., for answering counterfactual queries (Pawlowski et al. (2020)). In this work, we warn practitioners about non-identifiability of counterfactual inference from observational data, even in the absence of unobserved confounding and assuming known causal structure. We prove counterfactual identifiability of monotonic generation mechanisms with single dimensional exogenous variables. For general generation mechanisms with multi-dimensional exogenous variables, we provide an impossibility result for counterfactual identifiability, motivating the need for parametric assumptions. As a practical approach, we propose a method for estimating worst-case errors of learned DSCMs' counterfactual predictions. The size of this error can be an essential metric for deciding whether or not DSCMs are a viable approach for counterfactual inference in a specific problem setting. In evaluation, our method confirms negligible counterfactual errors for an identifiable Structural Causal Model (SCM) from prior work, and also provides informative error bounds on counterfactual errors for a non-identifiable synthetic SCM.

Developing Hybrid Machine Learning Models to Assign Health Score to Railcar Fleets for Optimal Decision Making Mahyar Ejlali, Ebrahim Arian, Sajjad Taghiyeh, Kristina Chambers, Amir Hossein Sadeghi, Demet Cakdi, Robert B Handfield An expert hybrid predictive fault method is proposed based on fast-DBSCAN and PCA. Inspection data from 1986-2020 of North American Railcar Owner (NARO) is used. The model is able to predict future faults in the railcar fleet accurately. Abstract A large amount of data is generated during the operation of a railcar fleet, which can easily lead to dimensional disaster and reduce the resiliency of the railcar network. To solve these issues and offer predictive maintenance, this research introduces a hybrid fault diagnosis expert system method that combines density-based spatial clustering of applications with noise (DBSCAN) and principal component analysis (PCA). Firstly, the DBSCAN method is used to cluster categorical data that are similar to one another within the same group. Secondly, PCA algorithm is applied to reduce the dimensionality of the data and eliminate redundancy in order to improve the accuracy of fault diagnosis. Finally, we explain the engineered features and evaluate the selected models by using the Gain Chart and Area Under Curve (AUC) metrics. We use the hybrid expert system model to enhance maintenance planning decisions by assigning a health score to the railcar system of the North American Railcar Owner (NARO). According to the experimental results, our expert model can detect 96.4% of failures within 50% of the sample. This suggests that our method is effective at diagnosing failures in railcars fleet. Keywords: Expert system, Predictive maintenance, Railcar maintenance, Machine learning, Maintenance health score 1. Introduction Maintenance consists of activities that ensure the railcar assets continue to operate safely and reliably. These activities include inspection, repair, testing, and replacement of parts.

As a representative of public transportation, the fundamental issue of managing bike-sharing systems is bike flow prediction. Recent methods overemphasize the spatio-temporal correlations in the data, ignoring the effects of contextual conditions on the transportation system and the inter-regional timevarying causality. In addition, due to the disturbance of incomplete observations in the data, random contextual conditions lead to spurious correlations between data and features, making the prediction of the model ineffective in special scenarios. To overcome this issue, we propose a Spatio-temporal Neural Structure Causal Model(STNSCM) from the perspective of causality. First, we build a causal graph to describe the traffic prediction, and further analyze the causal relationship between the input data, contextual conditions, spatiotemporal states, and prediction results. Second, we propose to apply the frontdoor criterion to eliminate confounding biases in the feature extraction process. Finally, we propose a counterfactual representation reasoning module to extrapolate the spatio-temporal state under the factual scenario to future counterfactual scenarios to improve the prediction performance. Experiments on real-world datasets demonstrate the superior performance of our model, especially its resistance to fluctuations caused by the external environment. The source code and data will be released.

Causal models have proven extremely useful in offering formal representations of causal relationships between a set of variables. Yet in many situations we want to study both causal and non-causal relationships between a single set of variables; this cannot be done in a standard causal model. For example, a standard causal model cannot talk simultaneously about the level of high-density lipoprotein cholesterol (H DL), the level of low-density lipoprotein cholesterol (LDL), and the level of total cholesterol (T OT), although this seems quite natural. One can imagine a situation where we only have data regarding the level of total cholesterol, even though our causal model may say that certain health conditions depend on the amount of LDL. The problem is that standard causal models allow simultaneous interventions to all variables in the model. But we cannot intervene to simultaneously setLDL to120 mg/dL,HDL to70, andTOT to 180, for that is logically inconsistent! In this example, the variables have a part-whole relationship, rather than a causal relationship.

Recent years have witnessed significant success in Gradient Boosting Decision Trees (GBDT) for a wide range of machine learning applications. Generally, a consensus about GBDT's training algorithms is gradients and statistics are computed based on high-precision floating points. In this paper, we investigate an essentially important question which has been largely ignored by the previous literature: how many bits are needed for representing gradients in training GBDT? To solve this mystery, we propose to quantize all the high-precision gradients in a very simple yet effective way in the GBDT's training algorithm. Surprisingly, both our theoretical analysis and empirical studies show that the necessary precisions of gradients without hurting any performance can be quite low, e.g., 2 or 3 bits. With low-precision gradients, most arithmetic operations in GBDT training can be replaced by integer operations of 8, 16, or 32 bits. Promisingly, these findings may pave the way for much more efficient training of GBDT from several aspects: (1) speeding up the computation of gradient statistics in histograms; (2) compressing the communication cost of high-precision statistical information during distributed training; (3) the inspiration of utilization and development of hardware architectures which well support low-precision computation for GBDT training. Benchmarked on CPUs, GPUs, and distributed clusters, we observe up to 2$\times$ speedup of our simple quantization strategy compared with SOTA GBDT systems on extensive datasets, demonstrating the effectiveness and potential of the low-precision training of GBDT. The code will be released to the official repository of LightGBM.

The number of rooftop photovoltaic (PV) systems has significantly increased in recent years around the globe, including in Australia. This trend is anticipated to continue in the next few years. Given their high share of generation in power systems, detecting malfunctions and abnormalities in rooftop PV systems is essential for ensuring their high efficiency and safety. In this paper, we present a novel anomaly detection method for a large number of rooftop PV systems installed in a region using big data and a time series complexity measure called weighted permutation entropy (WPE). This efficient method only uses the historical PV generation data in a given region to identify anomalous PV systems and requires no new sensor or smart device. Using a real-world PV generation dataset, we discuss how the hyperparameters of WPE should be tuned for the purpose. The proposed PV anomaly detection method is then tested on rooftop PV generation data from over 100 South Australian households. The results demonstrate that anomalous systems detected by our method have indeed encountered problems and require a close inspection. The detection and resolution of potential faults would result in better rooftop PV systems, longer lifetimes, and higher returns on investment.

Several third-party clients for Twitter are having issues communicating with the social network, leading to issues that prevent users from being able to log in. As TechCrunch reports, Tweetbot and Twitterific have both confirmed that they're having problems and are trying to find the root cause of the issue. "We've reached out to Twitter for more details, but haven't heard back," Tweetbot announced. Fenix has also confirmed that its client for Android is experiencing problems but that its iOS app seems to be unaffected. Matteo Villa, the app's developer, said Fenix for Android was suspended with no communication from the company.

There is growing importance to detecting faults and implementing the best methods in industrial and real-world systems. We are searching for the most trustworthy and practical data-based fault detection methods proposed by artificial intelligence applications. In this paper, we propose a framework for fault detection based on reinforcement learning and a policy known as proximal policy optimization. As a result of the lack of fault data, one of the significant problems with the traditional policy is its weakness in detecting fault classes, which was addressed by changing the cost function. Using modified Proximal Policy Optimization, we can increase performance, overcome data imbalance, and better predict future faults. When our modified policy is implemented, all evaluation metrics will increase by $3\%$ to $4\%$ as compared to the traditional policy in the first benchmark, between $20\%$ and $55\%$ in the second benchmark, and between $6\%$ and $14\%$ in the third benchmark, as well as an improvement in performance and prediction speed compared to previous methods.

Detection of high impedance faults (HIF) has been one of the biggest challenges in the power distribution network. The low current magnitude and diverse characteristics of HIFs make them difficult to be detected by over-current relays. Recently, data-driven methods based on machine learning models are gaining popularity in HIF detection due to their capability to learn complex patterns from data. Most machine learning-based detection methods adopt supervised learning techniques to distinguish HIFs from normal load conditions by performing classifications, which rely on a large amount of data collected during HIF. However, measurements of HIF are difficult to acquire in the real world. As a result, the reliability and generalization of the classification methods are limited when the load profiles and faults are not present in the training data. Consequently, this paper proposes an unsupervised HIF detection framework using the autoencoder and principal component analysis-based monitoring techniques. The proposed fault detection method detects the HIF by monitoring the changes in correlation structure within the current waveforms that are different from the normal loads. The performance of the proposed HIF detection method is tested using real data collected from a 4.16 kV distribution system and compared with results from a commercially available solution for HIF detection. The numerical results demonstrate that the proposed method outperforms the commercially available HIF detection technique while maintaining high security by not falsely detecting during load conditions.

Nowadays, feature selection is frequently used in machine learning when there is a risk of performance degradation due to overfitting or when computational resources are limited. During the feature selection process, the subset of features that are most relevant and least redundant is chosen. In recent years, it has become clear that, in addition to relevance and redundancy, features' complementarity must be considered. Informally, if the features are weak predictors of the target variable separately and strong predictors when combined, then they are complementary. It is demonstrated in this paper that the synergistic effect of complementary features mutually amplifying each other in the construction of two-tier decision trees can be interfered with by another feature, resulting in a decrease in performance. It is demonstrated using cross-validation on both synthetic and real datasets, regression and classification, that removing or eliminating the interfering feature can improve performance by up to 24 times. It has also been discovered that the lesser the domain is learned, the greater the increase in performance. More formally, it is demonstrated that there is a statistically significant negative rank correlation between performance on the dataset prior to the elimination of the interfering feature and performance growth after the elimination of the interfering feature. It is concluded that this broadens the scope of feature selection methods for cases where data and computational resources are sufficient.