Artificial intelligence (AI) has smoothly penetrated in a number of monitoring and control applications including the agriculture. However, research efforts towards low-power sensing devices with fully-functional AI on board are still fragmented. In this work, we present an embedded system enriched with the AI ensuring the continuous analysis and in-situ prediction of the growth dynamics of plant leaves. The embedded solution is grounded on a low-power embedded sensing system with a Graphics Processing Unit (GPU) and is able to run the neural networks-based AI on board. We use a Recurrent Neural Network (RNN) called the Long-Short Term Memory network (LSTM) as a core of AI in our system. The proposed approach guarantees the system autonomous operation for 180 days using a standard Li-ion battery. We rely on the state-of-the-art mobile graphical chips for ‘smart’ analysis and control of autonomous devices. This pilot study opens up wide vista for a variety of intelligent monitoring applications, especially in the agriculture domain. Also, we share with the research community the Tomato Growth dataset.

Artificial Intelligence (AI) has been recently applied to a number of sensing scenarios for realizing the prediction, control and/or recognition tasks. However, its integration to embedded systems is still limited. We propose a low-power sensing system with the AI on board with a special focus on the application in agriculture. For this reason we designed a Convolutional Neural Network (CNN) which achieves 83% of average Intersection over Union (IoU) score on the test dataset and 97% of seeds recognition accuracy on the validation dataset. The proposed solution is able to perform the seeds recognition, and germination detection through the images processing. For training the CNN we collect a dataset of images of seed germination process at different stages. The entire system is assessed in an industrial facility. The experimental results demonstrate that the proposed system opens up wide vista for smart applications in the context of Internet of Things requiring the intelligent and autonomous operation from ’things’.

Parkinson’s Disease (PD) is a neurodegenerative disease which is among the most spread and growing common neurodegenerative disorders. It significantly limits the physical and social activities of patients if not diagnosed timely. However, diagnostic of PD at an early stage is not a trivial task as a number of neurodegenerative diseases are characterized by similar symptoms. One of the more pressing concerns is the detection of early stages of PD, namely stage 1 and stage 2 for assigning a proper therapy helping to notably reduce the disease progression. In these stages, symptoms might not be as distinguishable and might be more easily confused with other diseases. We report on an approach based on wearable sensors and machine learning to differentiate healthy controls from stage 1 and stage 2 PD patients. For this reason we designed 11 common exercises and collect the data via a wearable commercial off-the-shelf accelerometer, gyroscope and magnetometer sensors. In total, we collected the data from 113 subjects. Data analysis using machine learning methods (feature extraction, dimensionality reduction, classification) helps greatly improve the accuracy of the PD diagnosis at an early stage. Our best results demonstrate f1-micro scores 0.78 and 0.88 for PD stage 1 and stage 2, respectively.

The Hogweed of Sosnowskyi (lat. Heracleum Sosnowskyi) is poisonous for humans, dangerous for farming crops, and local ecosystems. This plant is fast-growing and has already spread all over Eurasia: from Germany to the Siberian part of Russia, and its distribution expands year-by-year. In-situ detection of this harmful plant is a tremendous challenge for many countries. Meanwhile,there are no automatic systems for detection and localization of hogweed. In this work, we report on an approach for fast and accurate detection of hogweed. The approach includes the Unmanned Aerial Vehicle (UAV) with an embedded system on board running various Fully Convolutional Neural Networks (FCNN). We propose the optimal architecture of FCNN for the embedded system relying on the trade-off between the detection quality and frame rate. We propose a model that achieves ROC AUC 0.96 in the hogweed segmentation task, which can process 4K frames at 0.46 FPS on NVIDIA Jetson Nano. The developed system can recognize the hogweed on the scale of individual plants and leaves. This system opens up a wide vista for obtaining comprehensive and relevant data about the spreading of harmful plants allowing for the elimination of their expansion.

Parkinson’s disease (PD) is the second most common neurodegenerative disorder that affects the extrapyramidal motor system. The initial clinical symptoms can appear long before the retirement age, affecting the patients’ ability to continue their work. However, the modern healthcare lacks the apparatus to detect the early signs of the disease, with only selected experts being able to spot the onset. Moreover, even if the disease is detected on time, the current clinical routine has no means of monitoring the progression of the disease, nor the effect of the therapy. In this work, we perform a comparative study of three patient-driven monitoring approaches, including wearable sensors data, video of the routine exercises performed by the patients, and their handwriting – all fine-tuned to detect PD. Aspiring to create an inexpensive clinical workflow, we collect the sensor data using a commercial wearable wireless sensor, and the video and the handwriting data are recorded using a basic smartphone. In the analysis stage, we rely on machine and deep learning methods, using f1 score for gauging the performance of the patient-driven data acquisition approaches. The sensor data analysis demonstrates the best f1 score of 0.93. At the same time, the handwriting and remote video recordings are more comfortable and less time-consuming, offering a sensible trade-off for the patients at the later stages of PD.

Parkinson’s Disease (PD) is a neurodegenerative disease associated with the extrapyramidal motor system disorder currently being the second most common neurodegenerative disorder. The first clinical symptoms can manifest themselves long before the retirement age and inevitably lead to reducing the possibility of continuing work. However, PD is sometimes misdiagnosed. In this article, we discuss the typical misdiagnosed cases and propose a second opinion system based on wearable sensors and artificial intelligence. For this reason, we designed a number of common tasks and recorded the movement data using wearable sensors worn by individuals with PD and other extrapyramidal disorders. PD patients are differentiated against other patients with similar diseases and not against healthy subjects. This allows one to measure the true specificity of wearable technologies with regard to detecting PD. Data analysis and classification of the types of tremor using machine learning methods (feature extraction, dimensionality reduction, classification) helps significantly improve the accuracy of PD diagnosis. Our results show that, when considering bradykinesia and tremor together, the accuracy of distinguishing PD from similar diseases increases (f1 score 0.88). This closed-loop configuration makes it possible to tune exercises to maximize the diagnostic value of the entire routine. We report approbation on 56 patients.