Christian Omlin

Identifying outlier behavior among sensors and subsystems is essential for discovering faults and facilitating diagnostics in large systems. At the same time, exploring large systems with numerous multivariate data sets is challenging. This study presents a lightweight interconnection and divergence discovery mechanism (LIDD) to identify abnormal behavior in multi-system environments. The approach employs a multivariate analysis technique that first estimates the similarity heatmaps among the sensors for each system and then applies information retrieval algorithms to provide relevant multi-level interconnection and discrepancy details. Our experiment on the readout systems of the Hadron Calorimeter of the Compact Muon Solenoid (CMS) experiment at CERN demonstrates the effectiveness of the proposed method. Our approach clusters readout systems and their sensors consistent with the expected calorimeter interconnection configurations, while capturing unusual behavior in divergent clusters and estimating their root causes.

With the increased penetration of fluctuating renewables and growing population of contemporary loads such as electric vehicles, the uncertainties in the generation and demand in the electric power grids are increasing. This makes the efficient operation and management of these systems challenging. Objective of this study is to propose a real-time management system for EV charging, which maximises the renewable energy utilization. An electric power distribution network with an average and peak demands of 1.51 MW, and 3.6 MW respectively, was chosen for the study. The real time power flow through the network components were analyzed using the OpenDSS model. With a wind power density of 574.51 W/m2 and a solar insolation of 4.14 kWh/m2/day, an optimized renewable energy system consisting of a 2.3 MW wind turbine and 2.61 MWp photovoltaic power plant are proposed for the network. Models …

Abnormal event detection is one of the most challenging tasks in computer vision. Many existing deep anomaly detection models are based on reconstruction errors, where the training phase is performed using only videos of normal events and the model is then capable to estimate frame-level scores for an unknown input. It is assumed that the reconstruction error gap between frames of normal and abnormal scores is high for abnormal events during the testing phase. Yet, this assumption may not always hold due to superior capacity and generalization of deep neural networks. In this paper, we design a generalized framework (rpNet) for proposing a series of deep models by fusing several options of a reconstruction network (rNet) and a prediction network (pNet) to detect anomaly in videos efficiently. In the rNet, either a convolutional autoencoder (ConvAE) or a skip connected ConvAE (AEc) can be used, whereas in the pNet, either a traditional U-Net, a non-local block U-Net, or an attention block U-Net (aUnet) can be applied. The fusion of both rNet and pNet increases the error gap. Our deep models have distinct degree of feature extraction capabilities. One of our models (AEcaUnet) consists of an AEc with our proposed aUnet has capability to confirm better error gap and to extract high quality of features needed for video anomaly detection. Experimental results on UCSD-Ped1, UCSD-Ped2, CUHK-Avenue, ShanghaiTech-Campus, and UMN datasets with rigorous statistical analysis show the effectiveness of our models.

The Compact Muon Solenoid (CMS) experiment is a general-purpose detector for high-energy collision at the Large Hadron Collider (LHC) at CERN. It employs an online data quality monitoring (DQM) system to promptly spot and diagnose particle data acquisition problems to avoid data quality loss. In this study, we present a semi-supervised spatio-temporal anomaly detection (AD) monitoring system for the physics particle reading channels of the Hadron Calorimeter (HCAL) of the CMS using three-dimensional digi-occupancy map data of the DQM. We propose the GraphSTAD system, which employs convolutional and graph neural networks to learn local spatial characteristics induced by particles traversing the detector and the global behavior owing to shared backend circuit connections and housing boxes of the channels, respectively. Recurrent neural networks capture the temporal evolution of the extracted spatial features. We validate the accuracy of the proposed AD system in capturing diverse channel fault types using the LHC collision data sets. The GraphSTAD system achieves production-level accuracy and is being integrated into the CMS core production system for real-time monitoring of the HCAL. We provide a quantitative performance comparison with alternative benchmark models to demonstrate the promising leverage of the presented system.

Artificial virtuous agents are artificial intelligence agents capable of virtuous behavior. Virtues are defined as an excellence in moral character, for example, compassion, honesty, etc. Developing virtues in AI comes under the umbrella of machine ethics research, which aims to embed ethical theories into artificial intelligence systems. We have recently suggested the use of affinity-based reinforcement learning to impart virtuous behavior. Such a technique uses policy regularization on reinforcement learning algorithms, and it has advantages such as interpretability and convergence properties. Hence, we evaluate the efficacy of affinity-based reinforcement learning to design artificial virtuous agents using a stochastic role-playing game environment. Our results show that virtuous behavior can indeed result in our Papers, Please environment, and that algorithmic convergence can be controlled by the relevant …

The past decade has seen significant progress in artificial intelligence (AI), which has resulted in algorithms being adopted for resolving a variety of problems. However, this success has been met by increasing model complexity and employing black-box AI models that lack transparency. In response to this need, Explainable AI (XAI) has been proposed to make AI more transparent and thus advance the adoption of AI in critical domains. Although there are several reviews of XAI topics in the literature that have identified challenges and potential research directions of XAI, these challenges and research directions are scattered. This study, hence, presents a systematic meta-survey of challenges and future research directions in XAI organized in two themes: (1) general challenges and research directions of XAI and (2) challenges and research directions of XAI based on machine learning life cycle’s phases: design …

The compact muon solenoid (CMS) experiment is a general-purpose detector for high-energy collision at the large hadron collider (LHC) at CERN. It employs an online data quality monitoring (DQM) system to promptly spot and diagnose particle data acquisition problems to avoid data quality loss. In this study, we present semi-supervised spatio-temporal anomaly detection (AD) monitoring for the physics particle reading channels of the hadronic calorimeter (HCAL) of the CMS using three-dimensional digi-occupancy map data of the DQM. We propose the GraphSTAD system, which employs convolutional and graph neural networks to learn local spatial characteristics induced by particles traversing the detector, and global behavior owing to shared backend circuit connections and housing boxes of the channels, respectively. Recurrent neural networks capture the temporal evolution of the extracted spatial features. We have validated the accuracy of the proposed AD system in capturing diverse channel fault types using the LHC Run-2 collision data sets. The GraphSTAD system has achieved production-level accuracy and is being integrated into the CMS core production system--for real-time monitoring of the HCAL. We have also provided a quantitative performance comparison with alternative benchmark models to demonstrate the promising leverage of the presented system.

Video anomaly event detection (VAED) is one of the key technologies in computer vision for smart surveillance systems. With the advent of deep learning, contemporary advances in VAED have achieved substantial success. Recently, weakly supervised VAED (WVAED) has become a popular VAED technical route of research. WVAED methods do not depend on a supplementary self-supervised substitute task, yet they can assess anomaly scores straightway. However, the performance of WVAED methods depends on pretrained feature extractors. In this paper, we first address taking advantage of two pretrained feature extractors for CNN (e.g., C3D and I3D) and ViT (e.g., CLIP), for effectively extracting discerning representations. We then consider long-range and short-range temporal dependencies and put forward video snippets of interest by leveraging our proposed temporal self-attention network (TSAN). We design a multiple instance learning (MIL)-based generalized architecture named CNN-ViT-TSAN, by using CNN- and/or ViT-extracted features and TSAN to specify a series of models for the WVAED problem. Experimental results on publicly available popular crowd datasets demonstrated the effectiveness of our CNN-ViT-TSAN.

Retrieval of scenes from traffic videos is an important task in intelligent transportation systems (ITS) for efficient traffic management in AI smart cities. This work proposes natural language-based vehicle retrieval from traffic monitoring videos, emphasizing the significance of temporal information and context. We present contrastive learning as a technique to optimize joint representations of vision and language modalities within a shared latent representation space. The approach involves training contrastive losses to keep similar encodings closer in joint feature representation space by minimizing the distance between positive visual-text pairs and maximizing the distance between negative visual-text pairs. Our study employs state-of-the-art vision models for visual encoding and transformer-based language models for text encoding. We analyze the impact of feature selection from visuals and text on retrieval …

Machine ethics has received increasing attention over the past few years because of the need to ensure safe and reliable artificial intelligence (AI). The two dominantly used theories in machine ethics are deontological and utilitarian ethics. Virtue ethics, on the other hand, has often been mentioned as an alternative ethical theory. While this interesting approach has certain advantages over popular ethical theories, little effort has been put into engineering artificial virtuous agents due to challenges in their formalization, codifiability, and the resolution of ethical dilemmas to train virtuous agents. We propose to bridge this gap by using role-playing games riddled with moral dilemmas. There are several such games in existence, such as Papers, Please and Life is Strange, where the main character encounters situations where they must choose the right course of action by giving up something else dear to them. We …

The field of artificial intelligence (AI) has evolved considerably since the end of the 20th century. While this technology shows great promise and potential to solve daily tasks, the question of fairness of decisions by AI models needs to be addressed. There have been examples of AI models performing unfair and prejudiced decisions which has led to a growing need to be able to know ‘why’ and ‘how’ these models make decisions. This is particularly important in the healthcare field, where the outcomes of AI models play a decisive role in the well-being of patients. In addition, a system for detecting and mitigating biases needs to be developed so that the advantages of AI can be utilized in healthcare. A scoping review was carried out to study the source, nature and impact of biases of AI models. Results showed that bias can be data-driven, algorithmic or introduced by humans. These biases propagate deeply rooted societal inequality, misdiagnose patient groups, and further perpetuate global health inequity. Mitigation of biases is proposed at the various stages of the machine learning pipeline. These strategies use techniques such as scrutinizing the way data is collected, better representation of patient groups, optimal training of the model and evaluating model performance. In conclusion, it must be ascertained that AI decisions are free of unwarranted biases and justly fair. Therefore, in an effort to mitigate bias, AI models should adopt systems that contain techniques in which biases can be predicted, measured, explained and then mitigated.

Extensive research has been conducted on the automatic classification of sleep stages utilizing deep neural networks and other neurophysiological markers. However, for sleep specialists to employ models as an assistive solution, it is necessary to comprehend how the models arrive at a particular outcome, necessitating the explainability of these models. This work proposes an explainable unified CNN-CRF approach (SleepXAI) for multi-class sleep stage classification designed explicitly for univariate time-series signals using modified gradient-weighted class activation mapping (Grad-CAM). The proposed approach significantly increases the overall accuracy of sleep stage classification while demonstrating the explainability of the multi-class labeling of univariate EEG signals, highlighting the parts of the signals emphasized most in predicting sleep stages. We extensively evaluated our approach to the sleep …

The increased complexity of state-of-the-art reinforcement learning (RL) algorithms has resulted in an opacity that inhibits explainability and understanding. This has led to the development of several post hoc explainability methods that aim to extract information from learned policies, thus aiding explainability. These methods rely on empirical observations of the policy, and thus aim to generalize a characterization of agents’ behaviour. In this study, we have instead developed a method to imbue agents’ policies with a characteristic behaviour through regularization of their objective functions. Our method guides the agents’ behaviour during learning, which results in an intrinsic characterization; it connects the learning process with model explanation. We provide a formal argument and empirical evidence for the viability of our method. In future work, we intend to employ it to develop agents that optimize individual financial customers’ investment portfolios based on their spending personalities.

The proliferation of artificial intelligence is increasingly dependent on model understanding. Understanding demands both an interpretation - a human reasoning about a model's behavior - and an explanation - a symbolic representation of the functioning of the model. Notwithstanding the imperative of transparency for safety, trust, and acceptance, the opacity of state-of-the-art reinforcement learning algorithms conceals the rudiments of their learned strategies. We have developed a policy regularization method that asserts the global intrinsic affinities of learned strategies. These affinities provide a means of reasoning about a policy's behavior, thus making it inherently interpretable. We have demonstrated our method in personalized prosperity management where individuals' spending behavior in time dictate their investment strategies, i.e. distinct spending personalities may have dissimilar associations with different investment classes. We now explain our model by reproducing the underlying prototypical policies with discretized Markov models. These global surrogates are symbolic representations of the prototypical policies.

In this paper, we estimate the age-related performance degradation of a wind turbine working under Norwegian environment, based on a deep neural network model. Ten years of high-resolution operational data from a 2 MW wind turbine were used for the analysis. Operational data of the turbine, between cut-in and rated wind velocities, were considered, which were pre-processed to eliminate outliers and noises. Based on the SHapley Additive exPlanations of a preliminary performance model, a benchmark performance model for the turbine was developed with deep neural networks. An efficiency index is proposed to gauge the agerelated performance degradation of the turbine, which compares measured performances of the turbine over the years with corresponding bench marked performance. On an average, the efficiency index of the turbine is found to decline by 0.64 percent annually, which is comparable with the degradation patterns reported under similar studies from the UK and the US.

Predictive maintenance is essential for complex industrial systems to foresee anomalies before major system faults or ultimate breakdown. However, the existing efforts on Industry 4.0 predictive monitoring are directed at semi-supervised anomaly detection with limited robustness for large systems, which are often accompanied by uncleaned and unlabeled data. We address the challenge of predicting anomalies through data-driven end-to-end deep learning models using early warning symptoms on multivariate time series sensor data. We introduce AnoP, a long multi-timestep anomaly prediction system based on unsupervised attention-based causal residual networks, to raise alerts for anomaly prevention. The experimental evaluation on large data sets from detector health monitoring of the Hadron Calorimeter of the CMS Experiment at LHC CERN demonstrates the promising efficacy of the proposed approach. AnoP predicted around 60% of the anomalies up to seven days ahead, and the majority of the missed anomalies are abnormalities with unpredictable noisy-like behavior. Moreover, it has discovered previously unknown anomalies in the calorimeter’s sensors.

Crowd anomaly detection is one of the most popular topics in computer vision in the context of smart cities. A plethora of deep learning methods have been proposed that generally outperform other machine learning solutions. Our review primarily discusses algorithms that were published in mainstream conferences and journals between 2020 and 2022. We present datasets that are typically used for benchmarking, produce a taxonomy of the developed algorithms, and discuss and compare their performances. Our main findings are that the heterogeneities of pre-trained convolutional models have a negligible impact on crowd video anomaly detection performance. We conclude our discussion with fruitful directions for future research.

Personalisation of products and services is fast becoming the driver of success in banking and commerce. Machine learning holds the promise of gaining a deeper understanding of and tailoring to customers’ needs and preferences. Whereas traditional solutions to financial decision problems frequently rely on model assumptions, reinforcement learning is able to exploit large amounts of data to improve customer modelling and decision-making in complex financial environments with fewer assumptions. Model explainability and interpretability present challenges from a regulatory perspective which demands transparency for acceptance; they also offer the opportunity for improved insight into and understanding of customers. Post-hoc approaches are typically used for explaining pretrained reinforcement learning models. Based on our previous modeling of customer spending behaviour, we adapt our recent reinforcement learning algorithm that intrinsically characterizes desirable behaviours and we transition to the problem of prosperity management. We train inherently interpretable reinforcement learning agents to give investment advice that is aligned with prototype financial personality traits which are combined to make a final recommendation. We observe that the trained agents’ advice adheres to their intended characteristics, they learn the value of compound growth, and, without any explicit reference, the notion of risk as well as improved policy convergence.

Micro-segmentation of customers in the finance sector is a nontrivial task and has been an atypical omission from recent scientific literature. Where traditional segmentation classifies customers based on coarse features such as demographics, micro-segmentation depicts more nuanced differences between individuals, bringing forth several advantages including the potential for improved personalization in financial services. AI and representation learning offer a unique opportunity to solve the problem of micro-segmentation. Although ubiquitous in many industries, the proliferation of AI in sensitive industries such as finance has become contingent on the explainability of deep models. We had previously solved the micro-segmentation problem by extracting temporal features from the state space of a recurrent neural network (RNN). However, due to the inherent opacity of RNNs, our solution lacked an explanation. In …

Automatic sleep stage classification can play a vital role when measuring sleep quality and diagnosing different sleep-related ailments. Several automated sleep stage identification algorithms have been proposed using various physiological signals. However, most of these methods use hand-crafted features or multiple Electroencephalography (EEG) signals. This work proposes a one-dimensional convolutional autoencoder (1D-CAE) based on a single-channel EEG signal for sleep stage identification. A total of five 1-D CAEs models are implemented, and each model is trained to reconstructs a specific sleep stage with the lowest reconstruction error, thus enabling the sleep stage identification based on this error. Furthermore, the proposed approach is evaluated on the Sleep EDF expanded datasets and achieved an overall classification accuracy of 87.2% using a single-channel EEG FPz-Cz signal. Also, our …