EACMFS Prizes and Awards

This paper describes an approach for model-based feature extraction. It also provides a substantial enhancement of the important characteristics relevant in visual and automatic sleep analysis. A procedure was developed in order to obtain a nonstationary spectrum analysis well suited for EEG signals.

Oesophageal pH-impedance monitoring allows detection of acid and non-acid gastro-oesophageal reflux (GOR) events. Visual analysis of impedance recording requires expertise. Our aim was to evaluate the efficacy of an automated analysis for GOR assessment. Seventy-three patients with suspected GORD underwent 24-h oesophageal pH-impedance monitoring. Recordings analysis was performed visually (V) and automatically using Autoscan function (AS) of Bioview software. A symptom index (SI) > or =50% was considered for a significant association between symptoms and reflux events. AS analysis detected more reflux events, especially non-acid, liquid, pure gas and proximal events. Detection of oesophageal acid exposure and acid reflux events was similar with both analyses. Agreement between V and AS analysis was good (Kendall's coefficient W > 0.750, P < 0.01) for all parameters. During pH-impedance studies, 65 patients reported symptoms. As compared to visual analysis, the sensitivity and specificity of a positive SI determined by AS were respectively 85.7% and 80% for all reflux events, 100% and 98% for acid reflux and 33% and 87.5% for non-acid reflux. Despite good agreement with visual analysis, automatic analysis overestimates the number of non-acid reflux events. Visual analysis remains the gold standard to detect an association between symptoms and non-acid reflux events.

The hypnogram is a schematic representation of sleep dynamics as a sequence of stages along the night. The authors have shown, in previous work, the adequacy of syntactic modeling in automatic sleep analysis. According to this approach, the hypnogram is viewed as expression of a language whose temporal organization is described by stochastic context-free grammars. Here, the authors propose a hybrid model combining syntactic and semantic information, where stage duration is taken into account in terms of attributed grammars. This model enables hypnogram simulation, by means of language generation, and provides improvement in classification accuracy. The method is applied in automatic hypnogram analysis of a control group and a population of dysthymic patients.

Assessment of SOMNOwatch plus EEG for sleep monitoring in healthy individuals

For the classification of sleep stages, international standards based on visual EEG analysis have been established and are in common use, although we are well aware of their limitations. Several authors have suggested different procedures for classifying the stages of vigilance during the waking stages. No universally accepted paradigm, however, has yet been developed. The proposed vigilance classification procedures are based either on visual or automatic analysis procedures. Even though the EEG activity and patterns that reflect vigilance changes have been identified and described as indicators of the state of alertness, opinion is divided on how these should be combined in a vigilance classification rule. Automatic methods, on the other hand, have up to now used only part of the information available, the relationship of which to vigilance indicators has only been partially explored. The COMSTAT (Dept. of Computation and Statistics, AFB-Arzneimittelforschung, Berlin, FRG) rule combines visual and automatic analysis procedures. Different vigilance-dependent EEG patterns, such as the proportion of occipital background rhythm under resting conditions and its replacement by either faster or slower waves, the frequency range of the occipital rhythm and the anteriorization phenomena, have been used as information for a latent class analysis (LCA5) with 5 classes (stages of vigilance). There is a high correlation between the results of the LCA5 with visual classification rules made by experts. Using a robust discriminant analysis function which takes into account prior probabilities of the classes, and with a linear cost function for misclassification, an automatic rule with power spectrum variables was fitted to the results of the LCA5. Reclassification and split-half classification showed a high overlap between LCA5 and automatic classification. The result of this procedure is a new vigilance classification rule that is based on an objective mathematical rationale for the combination of different vigilance-indicative EEG activities and patterns but which can be applied to power-spectral estimators in an automatic EEG analysis procedure.

NCNA: Integrated platform for constructing, visualizing, analyzing and sharing human-mediated nitrogen biogeochemical networks

On-line automatic sleep scoring system involving Bayesian filtering

In this paper, we compare and analyze the results from automatic analysis and visual scoring of nocturnal sleep recordings. The validation is based on a sleep recording set of 60 subjects (33 males and 27 females), consisting of three groups: 20 normal controls subjects, 20 depressed patients and 20 insomniac patients treated with a benzodiazepine. The inter-expert variability estimated from these 60 recordings (61,949 epochs) indicated an average agreement rate of 87.5% between two experts on the basis of 30-second epochs. The automatic scoring system, compared in the same way with one expert, achieved an average agreement rate of 82.3%, without expert supervision. By adding expert supervision for ambiguous and unknown epochs, detected by computation of an uncertainty index and unknown rejection, the automatic/expert agreement grew from 82.3% to 90%, with supervision over only 20% of the night. Bearing in mind the composition and the size of the test sample, the automated sleep staging system achieved a satisfactory performance level and may be considered a useful alternative to visual sleep stage scoring for large-scale investigations of human sleep.

BACKGROUND The traditional monitoring of sleep disorders usually uses polysomnography. However, with the development of medical sensors and deep learning technology in recent years, more and more research has begun to explore the combination of artificial intelligence technology and medical sensors to achieve automatic monitoring, analysis and early warning of sleep, so as to more accurately assess, treat and care for this population. OBJECTIVE In this paper, a deep learning combined with medical sensor is designed to collect patient sleep and physiological data in order to solve the difficulty of patient sleep acquisition and assessment. METHODS A sleep monitoring system for type 2 diabetes in the elderly based on a deep learning model was designed. Sleep data (sleep time, sleep duration, sleep depth, etc.) and physiological parameters (blood glucose level, blood oxygen saturation, heart rate variability, breathing rate, blood pressure) were collected for elderly patients with type 2 diabetes through medical sensors. Deep learning was used to train and analyze the data to identify the type of sleep disorder and predict its severity. RESULTS Results: The research situation is expected to be released in the first quarter of 2026. CONCLUSIONS The sleep monitoring system of deep learning combined with medical sensor data can effectively evaluate sleep disorders in elderly patients with type 2 diabetes.This approach provides an effective and innovative solution for the management of sleep disorders in elderly patients with diabetes.

Digital methods, tools and algorithms are gaining in importance for the analysis of digitized manuscript collections in the arts and humanities. One example is the BMBF-funded research project "eCodicology" which aims to design, evaluate and optimize algorithms for the automatic identification of macro- and micro-structural layout features of medieval manuscripts. The main goal of this research project is to provide better insights into high-dimensional datasets of medieval manuscripts for humanities scholars. The heterogeneous nature and size of the humanities data and the need to create a database of automatically extracted reproducible features for better statistical and visual analysis are the main challenges in designing a workflow for the arts and humanities. This paper presents a concept of a workflow for the automatic tagging of medieval manuscripts. As a starting point, the workflow uses medieval manuscripts digitized within the scope of the project Virtual Scriptorium St. Matthias". Firstly, these digitized manuscripts are ingested into a data repository. Secondly, specific algorithms are adapted or designed for the identification of macro- and micro-structural layout elements like page size, writing space, number of lines etc. And lastly, a statistical analysis and scientific evaluation of the manuscripts groups are performed. The workflow is designed generically to process large amounts of data automatically with any desired algorithm for feature extraction. As a result, a database of objectified and reproducible features is created which helps to analyze and visualize hidden relationships of around 170,000 pages. The workflow shows the potential of automatic image analysis by enabling the processing of a single page in less than a minute. Furthermore, the accuracy tests of the workflow on a small set of manuscripts with respect to features like page size and text areas show that automatic and manual analysis are comparable. The usage of a computer cluster will allow the highly performant processing of large amounts of data. The software framework itself will be integrated as a service into the DARIAH infrastructure to make it adaptable for wider range of communities.

Personalized approach to developing image processing and analysis methods for medical video systems.

Las tecnologías y su dimensión ubicua se hacen presentes en todas las disciplinas y han cambiado la forma de estudiar e investigar, creando campos como las Humanidades Digitales cuyo auge es ya innegable. Los estudios de grado en humanidades no siempre reflejan este giro digital. En este artículo presentamos los resultados de una experiencia docente cuyo objetivo ha sido la mejora de la adquisición de los contenidos de métrica en poesía del grado, así como la adquisición de contenidos transversales en relación a la tecnología y la digitalidad. Para ello se ha combinado la enseñanza de la métrica española con la de las tecnologías computacionales que se aplican a su análisis desde las Humanidades Digitales, buscando una implicación directa de los estudiantes en la investigación universitaria. Con ese fin se organizó una actividad que planeó videoconferencias con expertos internacionales y a una actividad de anotación métrica de sonetos para su procesado computacional. Los resultados, obtenidos por medio de una encuesta de satisfacción y las calificaciones de los estudiantes, muestran una clara mejora en los resultados de la asignatura para los que participaron en esta experiencia y una alta satisfacción con los contenidos referentes a tecnología y la digitalidad aprendidos. Ciertos aspectos como el tamaño de la muestra o la necesidad de otros datos comparativos quedan para la discusión de esta experiencia.

Neural Network Model: Application to Automatic Analysis of Human Sleep

Development of a digital signal processor-based new 12-lead synchronization electrocardiogram automatic analysis system

As part of the advanced launch system technology development effort begun in 1989, the Air Force initiated a program to automate to the extent possible the processing NDE data from the inspection of solid rocket motors during fabrication. The computerized system, called the automated NDE data evaluation system (ANDES), was developed under contract to Martin Marietta. The generic ANDES system has been tailored to support inspection tasks at two Air Logistic Centers in the Air Force. These centers are the Ogden Air Logistic Center at Hill AFB, UT and the San Antonio Air Logistic Center at Kelly AFB, TX. The ANDES systems can be configured to process digital or digitize NDE data from any source. The system will analyze the data for anomalies, classify detected anomalies, and make a recommendation ont he serviceability of the component containing the anomalies base on established criteria. The ANDES systems at Hill AFB is configured to process x-ray computed tomography (CT) images in support of the surveillance activities on the Minuteman III third stage solid rocket motors. The system functions as a supplement to the visual image analysis effort and as an automated report generation and electronic report storage device. The ANDES system installed at Kelly AFB also processes CT images. The components supported are the oil scavenging assembly from the F-100 aircraft engine,t he yoke pivot block casting data images for void content and cracks and a braised joint on the oil scavenge tube for leak paths and total wetted area. The paper will briefly discuss the ANDES development history, the system hardware and software architectures employed at both Hill AFB and Kelly AFB, and a brief description of the performance of the operational systems.