Bone Marrow Transplant, a gradational rescue for a wide range of disorders emanating from the bone marrow, is an efficacious surgical treatment. Several risk factors, such as post-transplant illnesses, new malignancies, and even organ damage, can impair long-term survival. Therefore, technologies like Machine Learning are deployed for investigating the survival prediction of BMT receivers along with the influences that limit their resilience. In this study, an efficient survival classification model is presented in a comprehensive manner, incorporating the Chi-squared feature selection method to address the dimensionality problem and Hyper Parameter Optimization (HPO) to increase accuracy. A synthetic dataset is generated by imputing the missing values, transforming the data using dummy variable encoding, and compressing the dataset from 59 features to the 11 most correlated features using Chi-squared feature selection. The dataset was split into train and test sets at a ratio of 80:20, and the hyperparameters were optimized using Grid Search Cross-Validation. Several supervised ML methods were trained in this regard, like Decision Tree, Random Forest, Logistic Regression, K-Nearest Neighbors, Gradient Boosting Classifier, Ada Boost, and XG Boost. The simulations have been performed for both the default and optimized hyperparameters by using the original and reduced synthetic dataset. After ranking the features using the Chi-squared test, it was observed that the top 11 features with HPO, resulted in the same accuracy of prediction (94.73%) as the entire dataset with default parameters. Moreover, this approach requires less time and resources for predicting the survivability of children undergoing BMT. Hence, the proposed approach may aid in the development of a computer-aided diagnostic system with satisfactory accuracy and minimal computation time by utilizing medical data records.

Multinational technology corporation IBM calculated that 72% of business leaders cited fraud as a growing concern in the last year, that $44 billion will be lost worldwide due to fraud by 2024, and that a quarter of e-commerce sales transactions that were declined by artificial intelligence (AI) were false positives. AI has become the leading tool for fighting fraud, but it can still be improved upon. In the past, rule-based engines and simple predictive models were used to computationally identify the majority of fraud attempts. But these methods have not kept up with the increasingly sophisticated nature of fraud attacks today. With a proliferation of digital technologies at criminals' disposal, fraud has grown in both scale and severity over the last few decades. Large criminal organizations and even state-sponsored groups use AI-like machine learning (ML) algorithms to defraud digital businesses for millions of dollars each year.

To fit sparse linear associations, a LASSO sparsity inducing penalty with a single hyperparameter provably allows to recover the important features (needles) with high probability in certain regimes even if the sample size is smaller than the dimension of the input vector (haystack). More recently learners known as artificial neural networks (ANN) have shown great successes in many machine learning tasks, in particular fitting nonlinear associations. Small learning rate, stochastic gradient descent algorithm and large training set help to cope with the explosion in the number of parameters present in deep neural networks. Yet few ANN learners have been developed and studied to find needles in nonlinear haystacks. Driven by a single hyperparameter, our ANN learner, like for sparse linear associations, exhibits a phase transition in the probability of retrieving the needles, which we do not observe with other ANN learners. To select our penalty parameter, we generalize the universal threshold of Donoho and Johnstone (1994) which is a better rule than the conservative (too many false detections) and expensive cross-validation. In the spirit of simulated annealing, we propose a warm-start sparsity inducing algorithm to solve the high-dimensional, non-convex and non-differentiable optimization problem. We perform precise Monte Carlo simulations to show the effectiveness of our approach.

Data can be broadly divided into continuous data, those that can take an infinite number of points within a given range such as distance or time, and categorical/discrete data, which contain a finite number of points or categories within a given group of data such as payment methods or customer complaints. We have already seen examples of applying regression to continuous prediction problems in the form of linear regression where we predicted sales, but in order to predict categorical outputs we can use logistic regression. While we are still using regression to predict outcomes, the main aim of logistic regression is to be able to predict which category and observation belongs to rather than an exact value. Examples of questions which this method can be used for include: "How likely is a person to suffer from a disease (outcome) given their age, sex, smoking status, etc (variables/features)?" "How likely is this email to be spam?" "Will a student pass a test given some predictors of performance?".

To interact with humans, artificial intelligence (AI) systems must understand our social world. Within this world norms play an important role in motivating and guiding agents. However, very few computational theories for learning social norms have been proposed. There also exists a long history of debate on the distinction between what is normal (is) and what is normative (ought). Many have argued that being capable of learning both concepts and recognizing the difference is necessary for all social agents. This paper introduces and demonstrates a computational approach to learning norms from natural language text that accounts for both what is normal and what is normative. It provides a foundation for everyday people to train AI systems about social norms.

Recently, federated learning was used to massively optimize a machine learning model for COVID-19 diagnosis. In December 2021 a paper titled "Advancing COVID-19 diagnosis with privacy-preserving collaboration in artificial intelligence" was released in the peer-reviewed journal Nature Machine Intelligence. This paper presents a considerable improvement for classifying patients as Covid positive or not, by combining the data of multiple geographic locations around the world for the diagnosis of COVID-19. Key findings established how Federated learning massively improved values of sensitivity, specificity, and Area Under the Curve (AUC) for COVID-19 diagnosis. Mainly one of the best achievements of this publication is how Federated learning allowed institutions from China and the United Kingdom (UK) to cooperate together while keeping their data private and protected.

In this paper, we focus on the problem of modeling dynamic geo-human interactions in streams for online POI recommendations. Specifically, we formulate the in-stream geo-human interaction modeling problem into a novel deep interactive reinforcement learning framework, where an agent is a recommender and an action is a next POI to visit. We uniquely model the reinforcement learning environment as a joint and connected composition of users and geospatial contexts (POIs, POI categories, functional zones). An event that a user visits a POI in stream updates the states of both users and geospatial contexts; the agent perceives the updated environment state to make online recommendations. Specifically, we model a mixed-user event stream by unifying all users, visits, and geospatial contexts as a dynamic knowledge graph stream, in order to model human-human, geo-human, geo-geo interactions. We design an exit mechanism to address the expired information challenge, devise a meta-path method to address the recommendation candidate generation challenge, and develop a new deep policy network structure to address the varying action space challenge, and, finally, propose an effective adversarial training method for optimization. Finally, we present extensive experiments to demonstrate the enhanced performance of our method.

Autonomous vehicles are on the horizon and will be transforming transportation safety and comfort. These vehicles will be connected to various external systems and utilize advanced embedded systems to perceive their environment and make intelligent decisions. However, this increased connectivity makes these vehicles vulnerable to various cyber-attacks that can have catastrophic effects. Attacks on automotive systems are already on the rise in today's vehicles and are expected to become more commonplace in future autonomous vehicles. Thus, there is a need to strengthen cybersecurity in future autonomous vehicles. In this article, we discuss major automotive cyber-attacks over the past decade and present state-of-the-art solutions that leverage artificial intelligence (AI). We propose a roadmap towards building secure autonomous vehicles and highlight key open challenges that need to be addressed.

The emergence and dynamics of filamentary structures associated with edge-localized modes (ELMs) inside tokamak plasmas during high-confinement mode is regularly studied using Electron Cyclotron Emission Imaging (ECEI) diagnostic systems. Such diagnostics allow us to infer electron temperature variations, often across a poloidal cross-section. Previously, detailed analysis of these filamentary dynamics and classification of the precursors to edge-localized crashes has been done manually. We present a machine-learning-based model, capable of automatically identifying the position, spatial extend, and amplitude of ELM filaments. The model is a deep convolutional neural network that has been trained and optimized on an extensive set of manually labeled ECEI data from the KSTAR tokamak. Once trained, the model achieves a $93.7\%$ precision and allows us to robustly identify plasma filaments in unseen ECEI data. The trained model is used to characterize ELM filament dynamics in a single H-mode plasma discharge. We identify quasi-periodic oscillations of the filaments size, total heat content, and radial velocity. The detailed dynamics of these quantities appear strongly correlated with each other and appear qualitatively different during the pre-crash and ELM crash phases.

We establish a high-dimensional statistical learning framework for individualized asset allocation. Our proposed methodology addresses continuous-action decision-making with a large number of characteristics. We develop a discretization approach to model the effect from continuous actions and allow the discretization level to be large and diverge with the number of observations. The value function of continuous-action is estimated using penalized regression with generalized penalties that are imposed on linear transformations of the model coefficients. We show that our estimators using generalized folded concave penalties enjoy desirable theoretical properties and allow for statistical inference of the optimal value associated with optimal decision-making. Empirically, the proposed framework is exercised with the Health and Retirement Study data in finding individualized optimal asset allocation. The results show that our individualized optimal strategy improves individual financial well-being and surpasses benchmark strategies.