Policy Compression for Intelligent Continuous Control on Low-Power Edge Devices.

Interest in deploying deep reinforcement learning (DRL) models on low-power edge devices, such as Autonomous Mobile Robots (AMRs) and Internet of Things (IoT) devices, has seen a significant rise due to the potential of performing real-time inference by eliminating the latency and reliability issues incurred from wireless communication and the privacy benefits of processing data locally. Deploying such energy-intensive models on power-constrained devices is not always feasible, however, which has led to the development of model compression techniques that can reduce the size and computational complexity of DRL policies. Policy distillation, the most popular of these methods, can be used to first lower the number of network parameters by transferring the behavior of a large teacher network to a smaller student model before deploying these students at the edge.

An encoding framework for binarized images using hyperdimensional computing.

Introduction: Hyperdimensional Computing (HDC) is a brain-inspired and lightweight machine learning method. It has received significant attention in the literature as a candidate to be applied in the wearable Internet of Things, near-sensor artificial intelligence applications, and on-device processing. HDC is computationally less complex than traditional deep learning algorithms and typically achieves moderate to good classification performance.

EmoWear: Wearable Physiological and Motion Dataset for Emotion Recognition and Context Awareness.

The EmoWear dataset provides a bridge to explore Emotion Recognition (ER) via Seismocardiography (SCG), the measurement of small cardio-respiratory induced vibrations on the chest wall through Inertial Measurement Units (IMUs). We recorded Accelerometer (ACC), Gyroscope (GYRO), Electrocardiography (ECG), Blood Volume Pulse (BVP), Respiration (RSP), Electrodermal Activity (EDA), and Skin Temperature (SKT) data from 49 participants who watched validated emotionally stimulating video clips. They self-assessed their emotional valence, arousal, and dominance, as well as extra questions about the video clips.

Missing Value Imputation of Wireless Sensor Data for Environmental Monitoring.

Over the past few years, the scale of sensor networks has greatly expanded. This generates extended spatiotemporal datasets, which form a crucial information resource in numerous fields, ranging from sports and healthcare to environmental science and surveillance. Unfortunately, these datasets often contain missing values due to systematic or inadvertent sensor misoperation.

Classification of Targets and Distractors in an Audiovisual Attention Task Based on Electroencephalography.

Within the broader context of improving interactions between artificial intelligence and humans, the question has arisen regarding whether auditory and rhythmic support could increase attention for visual stimuli that do not stand out clearly from an information stream. To this end, we designed an experiment inspired by pip-and-pop but more appropriate for eliciting attention and P3a-event-related potentials (ERPs). In this study, the aim was to distinguish between targets and distractors based on the subject's electroencephalography (EEG) data.

Design and Construction of an Experimental Setup to Enhance Mineral Weathering through the Activity of Soil Organisms.

Enhanced weathering (EW) is an emerging carbon dioxide (CO2) removal technology that can contribute to climate change mitigation. This technology relies on accelerating the natural process of mineral weathering in soils by manipulating the abiotic variables that govern this process, in particular mineral grain size and exposure to acids dissolved in water. EW mainly aims at reducing atmospheric CO2 concentrations by enhancing inorganic carbon sequestration.

Semantic segmentation of plant roots from RGB (mini-) rhizotron images-generalisation potential and false positives of established methods and advanced deep-learning models.

Background: Manual analysis of (mini-)rhizotron (MR) images is tedious. Several methods have been proposed for semantic root segmentation based on homogeneous, single-source MR datasets. Recent advances in deep learning (DL) have enabled automated feature extraction, but comparisons of segmentation accuracy, false positives and transferability are virtually lacking.

Training a Hyperdimensional Computing Classifier Using a Threshold on Its Confidence.

Hyperdimensional computing (HDC) has become popular for light-weight and energy-efficient machine learning, suitable for wearable Internet-of-Things devices and near-sensor or on-device processing. HDC is computationally less complex than traditional deep learning algorithms and achieves moderate to good classification performance. This letter proposes to extend the training procedure in HDC by taking into account not only wrongly classified samples but also samples that are correctly classified by the HDC model but with low confidence.

Monitoring Kikuletwa river levels in northern Tanzania: A data set unlocking insights for effective flood early warning systems.

Floods are a recurring natural disaster that pose significant risks to communities and infrastructure. The lack of reliable and accurate data on river systems in developing countries has hindered the development of effective flood early warning systems. This paper presents a data set collected using ultrasonic distance sensors installed at two locations along the Kikuletwa River in the Pangani River Basin, Northern Tanzania.

Age of peak performance in professional road cycling.

In this study, we investigated the relationship between age and performance in professional road cycling. We considered 1864 male riders present in the yearly top 500 ranking of ProCyclingStats (PCS) since 1993 until 2021 with more than 700 PCS Points. We applied a data-driven approach for finding natural clusters of the rider's speciality (General Classification, One Day, Sprinter or All-Rounder).

A Multi-Modal Wireless Sensor System for River Monitoring: A Case for Kikuletwa River Floods in Tanzania.

Reliable and accurate flood prediction in poorly gauged basins is challenging due to data scarcity, especially in developing countries where many rivers remain insufficiently monitored. This hinders the design and development of advanced flood prediction models and early warning systems. This paper introduces a multi-modal, sensor-based, near-real-time river monitoring system that produces a multi-feature data set for the Kikuletwa River in Northern Tanzania, an area frequently affected by floods.

Modeling Match Performance in Elite Volleyball Players: Importance of Jump Load and Strength Training Characteristics.

In this study, we investigated the relationships between training load, perceived wellness and match performance in professional volleyball by applying the machine learning techniques XGBoost, random forest regression and subgroup discovery. Physical load data were obtained by manually logging all physical activities and using wearable sensors. Daily wellness of players was monitored using questionnaires.

Battery-Less Environment Sensor Using Thermoelectric Energy Harvesting from Soil-Ambient Air Temperature Differences.

Energy harvesting is an effective technique for prolonging the lifetime of Internet of Things devices and Wireless Sensor Networks. In applications such as environmental sensing, which demands a deploy-and-forget architecture, energy harvesting is an unavoidable technology. Thermal energy is one of the most widely used sources for energy harvesting.

Downlink Performance Modeling and Evaluation of Batteryless Low Power BLE Node.

Deploying low maintenance and long-life systems is an important requirement of emerging commercial Internet of Things (IoT) solutions. Such systems can be envisioned in which the connected devices are powered by energy harvested from ambient sources and stored in long-lifetime capacitors rather than short-lived and polluting batteries. However, due to the unpredictable nature of ambient energy harvesting, such batteryless IoT devices might not always have enough energy to initiate communication.

Leveraging Artificial Intelligence and Fleet Sensor Data towards a Higher Resolution Road Weather Model.

Road weather conditions such as ice, snow, or heavy rain can have a significant impact on driver safety. In this paper, we present an approach to continuously monitor the road conditions in real time by equipping a fleet of vehicles with sensors. Based on the observed conditions, a physical road weather model is used to forecast the conditions for the following hours.

Lessons Learned from a Distributed RF-EMF Sensor Network.

In an increasingly wireless world, spatiotemporal monitoring of the exposure to environmental radiofrequency (RF) electromagnetic fields (EMF) is crucial to appease public uncertainty and anxiety about RF-EMF. However, although the advent of smart city infrastructures allows for dense networks of distributed sensors, the costs of accurate RF sensors remain high, and dedicated RF monitoring networks remain rare. This paper describes a comprehensive study comprising the design of a low-cost RF-EMF sensor node capable of monitoring four frequency bands used by wireless telecommunications with an unparalleled temporal resolution, its application in a small-scale distributed sensor network consisting of both fixed (on building façades) and mobile sensor nodes (on postal vans), and the subsequent analysis of over a year of data between January 2019 and May 2020, during which slightly less than 10 million samples were collected.

Joint Communication and Sensing: A Proof of Concept and Datasets for Greenhouse Monitoring Using LoRaWAN.

In recent years, greenhouse-based precision agriculture (PA) has been strengthened by utilization of Internet of Things applications and low-power wide area network communication. The advancements in multidisciplinary technologies such as artificial intelligence (AI) have created opportunities to assist farmers further in detecting disease and poor nutrition of plants. Neural networks and other AI techniques need an initial set of measurement campaigns along with extensive datasets as a training set to baseline and evolve different applications.

Network control by a constrained external agent as a continuous optimization problem.

Social science studies dealing with control in networks typically resort to heuristics or solely describing the control distribution. Optimal policies, however, require interventions that optimize control over a socioeconomic network subject to real-world constraints. We integrate optimisation tools from deep-learning with network science into a framework that is able to optimize such interventions in real-world networks.

A Learn-to-Rank Approach for Predicting Road Cycling Race Outcomes.

Professional road cycling is a very competitive sport, and many factors influence the outcome of the race. These factors can be internal (e.g.

Noise robustness of persistent homology on greyscale images, across filtrations and signatures.

Topological data analysis is a recent and fast growing field that approaches the analysis of datasets using techniques from (algebraic) topology. Its main tool, persistent homology (PH), has seen a notable increase in applications in the last decade. Often cited as the most favourable property of PH and the main reason for practical success are the stability theorems that give theoretical results about noise robustness, since real data is typically contaminated with noise or measurement errors.

Parent and PHY Selection in Slot Bonding IEEE 802.15.4e TSCH Networks.

While IEEE 802.15.4e Time-Slotted Channel Hopping (TSCH) networks should be equipped to deal with the hard wireless challenges of industrial environments, the sensor networks are often still limited by the characteristics of the used physical (PHY) layer.

ATARI: A Graph Convolutional Neural Network Approach for Performance Prediction in Next-Generation WLANs.

IEEE 802.11 (Wi-Fi) is one of the technologies that provides high performance with a high density of connected devices to support emerging demanding services, such as virtual and augmented reality. However, in highly dense deployments, Wi-Fi performance is severely affected by interference.

Chest-Worn Inertial Sensors: A Survey of Applications and Methods.

Inertial Measurement Units (IMUs) are frequently implemented in wearable devices. Thanks to advances in signal processing and machine learning, applications of IMUs are not limited to those explicitly addressing body movements such as Activity Recognition (AR). On the other hand, wearing IMUs on the chest offers a few advantages over other body positions.

Field application of a novel active-passive sampling technique for the simultaneous measurement of a wide range of contaminants in water.

A first test of the field capabilities of a novel in situ sampling technique combining active and passive sampling (APS) was conducted in the sea. The proof-of-concept device uses a pump to draw water into a diffusion cell where dissolved target substances are accumulated onto sorbents which are selective for different classes of contaminants (i.e.

Comparing Localization Performance of IEEE 802.11p and LTE-V V2I Communications.

The future of transportation systems is going towards autonomous and assisted driving, aiming to reach full automation. There is huge focus on communication technologies expected to offer vehicular application services, of which most are location-based services. This paper provides a study on localization accuracy limits using vehicle-to-infrastructure communication channels provided by IEEE 802.