Mass Spectrometry (MS) and Nuclear Magnetic Resonance Spectroscopy (NMR) are critical components of every industrial chemical process as they provide information on the concentrations of individual compounds and by-products. These processes are carried out manually and by a specialist, which takes a substantial amount of time and prevents their utilization for real-time closed-loop process control. This paper presents recent advances from two projects that use Artificial Neural Networks (ANNs) to address the challenges of automation and performance-efficient realizations of MS and NMR. In the first part, a complete toolchain has been developed to develop simulated spectra and train ANNs to identify compounds in MS. In the second part, a limited number of experimental NMR spectra have been augmented by simulated spectra to train an ANN with better prediction performance and speed than state-of-the-art analysis. These results suggest that, in the context of the digital transformation of the process industry, we are now on the threshold of a possible strongly simplified use of MS and MRS and the accompanying data evaluation by machine-supported procedures, and can utilize both methods much wider for reaction and process monitoring or quality control.

The paradigm change towards the Industrial Internet of Things carries considerations related to the implementation and quality of processes already established inside the industries. If we also consider the essential roles that Cyber-Physical systems play in modern industries, we cannot avoid recognizing that devices are obtaining more responsibility. Thus, their safety functioning has to be guaranteed, even if their batteries are running low. The correct scheduling of tasks can provide a functional safety execution, and additionally save energy to ensure that the safety-critical tasks are allowed to run. We present in this paper a novel algorithm named TIRUB, specially designed for the industrial scenario so that devices are compliant with safety standards as the IEC-61508.

The ongoing megatrends in industry and academia like the Internet ofThings (IoT), the Industrial Internet of Things (IIoT) and Cyber-Physical Systems(CPS) present the developers of modern computer architectures with variouschallenges. A novel class of processors which provide more data throughputwith a simultaneously tremendously reduced energy consumption are required asa backbone for these “Things”. Additionally, the requirements of CPS like realtime, reliability, dependability, safety, and security are gaining in importance inthese applications. This paper shows a brief overview of novel processor architecturesproviding high flexibility to adapt during design- and runtime to changingrequirements of the application and the internal and external system status.

Electrocardiogram (ECG) signals convey a substantial amount of information that can be used for detecting and predicting the occurrence of several diseases and conditions. Approaches to ECG analysis were traditionally based on Signal Processing (SP), but several recent work have managed to substantially increase the quality of the analyses by using Machine Learning (ML) techniques. Still, while ML offers the potential to extract a substantially more information and predict diseases with better accuracy, it is also intrinsically more computationally expensive. Given the importance of this field and recent advances, we present a survey on ML approaches to ECG processing, focusing on particular diseases and conditions that can be detected and the different algorithms used for that. Moreover, we also discuss recent implementations of such algorithms on low-power wearable devices. We identify an opportunity for the development of novel embedded architectures that could enable the continuous monitoring of ECG signals and identify emerging technologies that could help in paving the way towards that.

Cache memories are an essential component of modern processors and consume a large percentage of their power consumption. Its efficacy depends heavily on the memory demands of the software. Thus, finding the optimal cache for a particular program is not a trivial task and usually involves exhaustive simulation. In this article, we propose a machine learning–based methodology that predicts the optimal cache reconfiguration for any given application, based on its dynamic instructions. Our evaluation shows that our methodology reaches 91.1% accuracy. Moreover, an additional experiment shows that only a small portion of the dynamic instructions (10%) suffices to reach 89.71% accuracy.

One of the newest criteria that companies have in mind when innovating their processes, is to acquire devices which have the ability to establish a wireless connection to other surrounding devices, enabling the interconnection of processes. The Internet of Things defines this capability. Elements designed for basic tasks, such as an assembly line can be enhanced by obtaining information on the particularities that single products should have. Although very useful for modern industries, this connectivity has intrinsic risks that might not be getting the attention they should. Security and safety problems, added to a high energy consumption, the need to reduce wires and the short life of sensor-batteries, will become a major problem in the days to come. This work analyses the requirements for an application layer protocol to be defined as a safe protocol, and the missing elements of modern protocols to be used on a safety environment for an industrial application. This work aims to raise awareness on the safety characteristics a system should accomplish, without neglecting energy requirements. We selected three of the most used application layer protocols, AMQP, CoAP and MQTT. Next we set the safety standards IEC-61508 and IEC-61784, including the standardized OpenSafety protocol, as baseline to analyze the requirements that a wireless protocol needs to accomplish in order to be considered Safety compliant.

Deep Neural Networks (DNNs) are widely used for complex applications, such as image and voice processing. Two varieties of DNNs, namely Convolutional Neuronal Networks (CNNs) and Recurrent Neuronal Networks (RNNs), are particularly popular regarding recent success for industrial applications. While CNNs are typically used for computer vision applications like object recognition, RNNs are well suited for time variant problems due to their recursive structure. Even though CNNs and RNNs belong to the family of DNNs, their implementation shows substantial differences. Besides more common Central Processing Unit (CPU) and Graphic processing Unit (GPU) implementations, Field Programmable Gate Array (FPGA) implementations offer great potential. Recent evaluations have shown significant benefits of FPGA implementations of DNNs over CPUs and GPUs. In this paper, we compare current FPGA implementations of CNNs and RNNs and analyze their optimizations. With this, we provide insights regarding the specific benefits and drawbacks of recent FPGA implementations of DNNs.

Cache memories are an important component of modern processors and consume a large percentage of the processor's power consumption. The quality of service of this cache memories relies heavily on the memory demands of the software, what means that a certain program might benefit more from a certain cache configuration which is highly inefficient for another program. Moreover, finding the optimal cache configuration for a certain program is not a trivial task and usually, involves exhaustive simulation. In this paper, we propose a machine learning-based methodology that, given an unknown application as input, it outputs a prediction of the optimal cache reconfiguration for that application, regarding energy consumption and performance. We evaluated our methodology using a large benchmark suite, and our results show a 99.8% precision at predicting the optimal cache configuration for a program. Furthermore, further analysis of the results indicates that 85% of the mispredictions produce only up to a 10% increase in energy consumption in comparison to the optimal energy consumption.