Högskolan i Skövde

To ensure reliable network performance, anomaly detection is an important part of the telecommunication operators’ work. This includes that operators need to timely intervene with the network, should they encounter indications of network performance degradation. In this paper, we describe the results of an initial experiment for anomaly detection with regard to network performance, using topic modeling on base station run-time variable data collected from live Radio Access Networks (RANs). The results show that topic modeling clusters semantically related data in the same way as human experts would and that the anomalies in our test cases could be identified in latent Dirichlet allocation (LDA) topic models. Our experiment further reveals which information provided by the topic model is particularly usable to support human anomaly detection in this application domain.

A Basic Oxygen Furnace (BOF) for steel making is a complex industrial process that is difficult to monitor due to the harsh environment, so the collected production data is very limited given the process complexity. Also, such production data has a low degree of variability. An accurate machine learning (ML) model for predicting production outcome requires both large and varied data, so utilising data from multiple BOFs will allow for more capable ML models, since both the amount and variability of data increases. Data collection setups for different BOFs are different, such that data sets are not compatible to directly join for ML training. Our approach is to let a neural network benefit from these collection differences in a joint training model. We present a neural network-based approach that simultaneously and jointly co-trains on several data sets. Our novelty is that the first network layer finds an internal representation of each individual BOF, while the other layers use this representation to concurrently learn a common BOF model. Our evaluation shows that the prediction accuracy of the common model increases compared to separate models trained on individual furnaces’ data sets. It is clear that multiple data sets can be utilised this way to increase model accuracy for better production prediction performance. For the industry, this means that the amount of available data for model training increases and thereby more capable ML models can be trained when having access to multiple data sets describing the same or similar manufacturing processes. 

The problem of using machine learning (ML) to predict the process endpoint for a Basic Oxygen Furnace (BOF) process used for steelmaking has been largely studied. However, current research often lacks both the usage of a rich dataset and does not address revealing influential factors that explain the process. The process is complex and difficult to control and has a multi-objective target endpoint with a proper range of heat temperature combined with sufficiently low levels of carbon and phosphorus. Reaching this endpoint requires skilled process operators, who are manually controlling the heat throughout the process by using both implicit and explicit control variables in their decisions. Trained ML models can reach good BOF target prediction results, but it is still a challenge to extract the influential factors that are significant to the ML prediction accuracy. Thus, it becomes a challenge to explain and validate an ML prediction model that claims to capture the process well. This paper makes use of a complex and full production dataset to evaluate and compare different approaches for understanding how the data can determine the process target prediction. One approach is based on the collected process data and the other on the ML approach trained on that data to find the influential factors. These complementary approaches aim to explain the BOF process to reveal actionable information on how to improve process control.

Basic oxygen steel making is a complex chemical and physical industrial process that reduces a mix of pig iron and recycled scrap into low-carbon steel. Good understanding of the process and the ability to predict how it will evolve requires long operator experience, but this can be augmented with process target prediction systems. Such systems may use machine learning to learn a model of the process based on a long process history, and have an advantage in that they can make useof vastly more process parameters than operators can comprehend. While it has become less of a challenge to build such prediction systems using machine learning algorithms, actual production implementations are rare. The hidden reasoning of complex prediction model and lack of transparency prevents operator trust, even for models that show high accuracy predictions. To express model behaviour and thereby increasing transparency we develop a reinforcement learning (RL) based agent approach, which task is to generate short polynomials that can explain the model of the process from what it has learnt from process data. The RL agent is rewarded on how well it generates polynomials that can predict the process from a smaller subset of the process parameters. Agent training is done with the REINFORCE algorithm, which enables the sampling of multiple concurrently plausible polynomials. Having multiple polynomials, process developers can evaluate several alternative and plausible explanations, as observed in the historic process data. The presented approach gives both a trained generative model and a set of polynomials that can explain the process. The performance of the polynomials is as good as or better than more complex and less interpretable models. Further, the relative simplicity of the resulting polynomials allows good generalisation to fit new instances of data. The best of the resulting polynomials in our evaluation achieves a better R 2 score on the test set in comparison to the other machine learning models evaluated.

Artificial intelligence (AI) is nowadays included into an increasing number of critical systems. Inclusion of AI in such systems may, however, pose a risk, since it is, still, infeasible to build AI systems that know how to function well in situations that differ greatly from what the AI has seen before. Therefore, it is crucial that future AI systems have the ability to not only function well in known domains, but also understand and show when they are uncertain when facing something unknown. In this paper, we evaluate four different methods that have been proposed to correctly quantifying uncertainty when the AI model is faced with new samples. We investigate the behaviour of these models when they are applied to samples far from what these models have seen before, and if they correctly attribute those samples with high uncertainty. We also examine if incorrectly classified samples are attributed with an higher uncertainty than correctly classified samples. The major finding from this simple experiment is, surprisingly, that the evaluated methods capture the uncertainty differently and the correlation between the quantified uncertainty of the models is low. This inconsistency is something that needs to be further understood and solved before AI can be used in critical applications in a trustworthy and safe manner. © 2020, Springer Nature Switzerland AG.

To ensure that a wireless telecommunication system is reliably functioning at all times, root-causes of potential network failures need to be identified and remedied, ideally before a noticeable network performance degradation occurs. Network operators are today observing a multitude of key performance indicators (KPIs) and are notified of possible network problems through alarms issued by different parts of the network. However, the number of cascading alarms together with the number of observable KPIs are easily overwhelming the operator’s cognitive capacity. In this paper we show how exploratory data analysis and machine learning, in particular topic modelling, can assist the operator when monitoring network performance and identifying anomalous network behaviour as well as supporting the operator’s analysis of the anomaly and identification of its root-cause. 

The steel-making process in a Basic Oxygen Furnace (BOF) must meet a combination of target values such as the final melt temperature and upper limits of the carbon and phosphorus content of the final melt with minimum material loss. An optimal blow end time (cut-off point), where these targets are met, often relies on the experience and skill of the operators who control the process, using both collected sensor readings and an implicit understanding of how the process develops. If the precision of hitting the optimal cut-off point can be improved, this immediately increases productivity as well as material and energy efficiency, thus decreasing environmental impact and cost. We examine the usage of standard machine learning models to predict the end-point targets using a full production dataset. Various causes of prediction uncertainty are explored and isolated using a combination of raw data and engineered features. In this study, we reach robust temperature, carbon, and phosphorus prediction hit rates of 88, 92, and 89 pct, respectively, using a large production dataset. © 2020, The Author(s).

In medicinal chemistry programs it is key to design and make compounds that are efficacious and safe. This is a long, complex, and difficult multiparameter optimization process, often including several properties with orthogonal trends. New methods for the automated design of compounds against profiles of multiple properties are thus of great value. Here we present a fragment-based reinforcement learning approach based on an actor-critic model, for the generation of novel molecules with optimal properties. The actor and the critic are both modeled with bidirectional long short-term memory (LSTM) networks. The AI method learns how to generate new compounds with desired properties by starting from an initial set of lead molecules and then improving these by replacing some of their fragments. A balanced binary tree based on the similarity of fragments is used in the generative process to bias the output toward structurally similar molecules. The method is demonstrated by a case study showing that 93% of the generated molecules are chemically valid and more than a third satisfy the targeted objectives, while there were none in the initial set.

We present a flexible deep convolutional neural network method for the analyse of arbitrary sized graph structures representing molecules. The method makes use of RDKit, an open-source cheminformatics software, allowing the incorporation of any global molecular (such as molecular charge) and local (such as atom type) information. We evaluate the method on the Side Effect Resource (SIDER) v4.1 dataset and show that it significantly outperforms another recently proposed method based on deep convolutional neural networks. We also reflect on how different types of information and input data affect the predictive power of our model. This reflection highlights several open problems that should be solved to further improve the use of deep learning within cheminformatics.

The technology and techniques for bio-sensors are rapidly evolving. Accordingly, there is significant business interest to identify upcoming technologies and new targets for the near future. Text information from internet reflects much of the recent information and public interests that help to understand the trend of a certain field. Thus, we utilize Dirichlet process topic modeling on different media sources containing short text (e.g., blogs, news) which is able to self-adapt the learned topic space to the data. We share the observations from the domain experts on the results derived from topic modeling on wearable biosensors from multiple media sources over more than eight years. We analyze the topics on wearable devices, forecast and market analysis, and bio-sensing techniques found from our method.