RESUMO
Vibrations are a common issue in the machining and metal-cutting sector, in which the spindle vibration is primarily responsible for the poor surface quality of workpieces. The consequences range from the need to manually finish the metal surfaces, resulting in time-consuming and costly operations, to high scrap rates, with the corresponding waste of time and resources. The main problem of conventional solutions is that they address the suppression of machine vibrations separately from the quality control process. In this novel proposed framework, we combine advanced vibration-monitoring methods with the AI-driven prediction of the quality indicators to address this problem, increasing the quality, productivity, and efficiency of the process. The evaluation shows that the number of rejected parts, time devoted to reworking and manual finishing, and costs are reduced considerably. The framework adopts a generalized methodology to tackle the condition monitoring and quality control processes. This allows for a broader adaptation of the solutions in different CNC machines with unique setups and configurations, a challenge that other data-driven approaches in the literature have found difficult to overcome.
RESUMO
Internet-of-Things systems are increasingly being installed in buildings to transform them into smart ones and to assist in the transition to a greener future. A common feature of smart buildings, whether commercial or residential, is environmental sensing that provides information about temperature, dust, and the general air quality of indoor spaces, assisting in achieving energy efficiency. Environmental sensors though, especially when combined, can also be used to detect occupancy in a space and to increase security and safety. The most popular methods for the combination of environmental sensor measurements are concatenation and neural networks that can conduct fusion in different levels. This work presents an evaluation of the performance of multiple late fusion methods in detecting occupancy from environmental sensors installed in a building during its construction and provides a comparison of the late fusion approaches with early fusion followed by ensemble classifiers. A novel weighted fusion method, suitable for imbalanced samples, is also tested. The data collected from the environmental sensors are provided as a public dataset.
RESUMO
Human activity recognition (HAR) has made significant progress in recent years, with growing applications in various domains, and the emergence of wearable and ambient sensors has provided new opportunities in the field [...].
Assuntos
Atividades Humanas , Reconhecimento Psicológico , HumanosRESUMO
Modern Internet connectivity provides the ability to perform efficient communications between the control centre of a healthcare system and the internal management processes of the emergency departments in clinics. Based on this, resource management is improved when exploiting the available efficient connectivity for adapting to the operating state of the system. An efficient order of patient treatment tasks inside the emergency department can reduce in real-time the average treatment time per patient. The motivation to use adaptive methods and specifically evolutionary metaheuristics for this time-sensitive task, is the exploitation of the runtime conditions which may vary according to the patient incoming flow and the severity of each specific case. In this work, an evolutionary method improves the efficiency in the emergency department, according to the dynamically structured treatment task order. Specifically, the average time inside the ED is reduced at a small expense of the execution time. This renders similar methods as candidates for resource-allocating tasks.
Assuntos
Comunicação , Serviço Hospitalar de Emergência , Humanos , Tempo de Reação , Internet , MotivaçãoRESUMO
Seniors, in order to be able to fight loneliness, need to communicate with other people and be engaged in activities to keep their minds active to increase their social capital. There is an intensified interest in the development of social virtual reality environments, either by commerce or by academia, to address the problem of social isolation of older people. Due to the vulnerability of the social group involved in this field of research, the need for the application of evaluation methods regarding the proposed VR environments becomes even more important. The range of techniques that can be exploited in this field is constantly expanding, with visual sentiment analysis being a characteristic example. In this study, we introduce the use of image-based sentiment analysis and behavioural analysis as a technique to assess a social VR space for elders and present some promising preliminary results.
Assuntos
Análise de Sentimentos , Realidade Virtual , Humanos , Idoso , Solidão , Isolamento SocialRESUMO
Central nervous system diseases (CNSDs) lead to significant disability worldwide. Mobile app interventions have recently shown the potential to facilitate monitoring and medical management of patients with CNSDs. In this direction, the characteristics of the mobile apps used in research studies and their level of clinical effectiveness need to be explored in order to advance the multidisciplinary research required in the field of mobile app interventions for CNSDs. A systematic review of mobile app interventions for three major CNSDs, i.e., Parkinson's disease (PD), multiple sclerosis (MS), and stroke, which impose significant burden on people and health care systems around the globe, is presented. A literature search in the bibliographic databases of PubMed and Scopus was performed. Identified studies were assessed in terms of quality, and synthesized according to target disease, mobile app characteristics, study design and outcomes. Overall, 21 studies were included in the review. A total of 3 studies targeted PD (14%), 4 studies targeted MS (19%), and 14 studies targeted stroke (67%). Most studies presented a weak-to-moderate methodological quality. Study samples were small, with 15 studies (71%) including less than 50 participants, and only 4 studies (19%) reporting a study duration of 6 months or more. The majority of the mobile apps focused on exercise and physical rehabilitation. In total, 16 studies (76%) reported positive outcomes related to physical activity and motor function, cognition, quality of life, and education, whereas 5 studies (24%) clearly reported no difference compared to usual care. Mobile app interventions are promising to improve outcomes concerning patient's physical activity, motor ability, cognition, quality of life and education for patients with PD, MS, and Stroke. However, rigorous studies are required to demonstrate robust evidence of their clinical effectiveness.
Assuntos
Aplicativos Móveis , Esclerose Múltipla , Doença de Parkinson , Acidente Vascular Cerebral , Humanos , Qualidade de Vida , Esclerose Múltipla/terapia , Doença de Parkinson/terapia , Acidente Vascular Cerebral/terapiaRESUMO
This paper discusses the importance of detecting breaking events in real time to help emergency response workers, and how social media can be used to process large amounts of data quickly. Most event detection techniques have focused on either images or text, but combining the two can improve performance. The authors present lessons learned from the Flood-related multimedia task in MediaEval2020, provide a dataset for reproducibility, and propose a new multimodal fusion method that uses Graph Neural Networks to combine image, text, and time information. Their method outperforms state-of-the-art approaches and can handle low-sample labelled data.
RESUMO
An essential factor toward ensuring the security of individuals and critical infrastructures is the timely detection of potentially threatening situations. To this end, especially in the law enforcement context, the availability of effective and efficient threat assessment mechanisms for identifying and eventually preventing crime- and terrorism-related threatening situations is of utmost importance. Toward this direction, this work proposes a hidden Markov model-based threat assessment framework for effectively and efficiently assessing threats in specific situations, such as public events. Specifically, a probabilistic approach is adopted to estimate the threat level of a situation at each point in time. The proposed approach also permits the reflection of the dynamic evolution of a threat over time by considering that the estimation of the threat level at a given time is affected by past observations. This estimation of the dynamic evolution of the threat is very useful, since it can support the decisions by security personnel regarding the taking of precautionary measures in case the threat level seems to adopt an upward trajectory, even before it reaches the highest level. In addition, its probabilistic basis allows for taking into account noisy data. The applicability of the proposed framework is showcased in a use case that focuses on the identification of potential threats in public events on the basis of evidence obtained from the automatic visual analysis of the footage of surveillance cameras.
RESUMO
Emotion recognition is a key attribute for realizing advances in human-computer interaction, especially when using non-intrusive physiological sensors, such as electroencephalograph (EEG) and electrocardiograph. Although functional connectivity of EEG has been utilized for emotion recognition, the graph theory analysis of EEG connectivity patterns has not been adequately explored. The exploitation of brain network characteristics could provide valuable information regarding emotions, while the combination of EEG and peripheral physiological signals can reveal correlation patterns of human internal state. In this work, a graph theoretical analysis of EEG functional connectivity patterns along with fusion between EEG and peripheral physiological signals for emotion recognition has been proposed. After extracting functional connectivity from EEG signals, both global and local graph theory features are extracted. Those features are concatenated with statistical features from peripheral physiological signals and fed to different classifiers and a Convolutional Neural Network (CNN) for emotion recognition. The average accuracy on the DEAP dataset using CNN was 55.62% and 57.38% for subject-independent valence and arousal classification, respectively, and 83.94% and 83.87% for subject-dependent classification. Those scores went up to 75.44% and 78.77% for subject-independent classification and 88.27% and 90.84% for subject-dependent classification using a feature selection algorithm, exceeding the current state-of-the-art results.
Assuntos
Eletroencefalografia , Redes Neurais de Computação , Humanos , Eletroencefalografia/métodos , Nível de Alerta , Emoções/fisiologia , AlgoritmosRESUMO
The CoFly-WeedDB contains 201 RGB images (â¼436 MB) from the attached camera of DJI Phantom Pro 4 from a cotton field in Larissa, Greece during the first stages of plant growth. The 1280 × 720 RGB images were collected while the Unmanned Aerial Vehicle (UAV) was performing a coverage mission over the field's area. During the designed mission, the camera angle was adjusted to -87°, vertically with the field. The flight altitude and speed of the UAV were equal to 5 m and 3 m/s, respectively, aiming to provide a close and clear view of the weed instances. All images have been annotated by expert agronomists using the LabelMe annotation tool, providing the exact boundaries of 3 types of common weeds in this type of crop, namely (i) Johnson grass, (ii) Field bindweed, and (iii) Purslane. The dataset can be used alone and in combination with other datasets to develop AI-based methodologies for automatic weed segmentation and classification purposes.
RESUMO
Manufacturing companies increasingly become "smarter" as a result of the Industry 4.0 revolution. Multiple sensors are used for industrial monitoring of machines and workers in order to detect events and consequently improve the manufacturing processes, lower the respective costs, and increase safety. Multisensor systems produce big amounts of heterogeneous data. Data fusion techniques address the issue of multimodality by combining data from different sources and improving the results of monitoring systems. The current paper presents a detailed review of state-of-the-art data fusion solutions, on data storage and indexing from various types of sensors, feature engineering, and multimodal data integration. The review aims to serve as a guide for the early stages of an analytic pipeline of manufacturing prognosis. The reviewed literature showed that in fusion and in preprocessing, the methods chosen to be applied in this sector are beyond the state-of-the-art. Existing weaknesses and gaps that lead to future research goals were also identified.
Assuntos
Comércio , Indústrias , Previsões , Humanos , Armazenamento e Recuperação da InformaçãoRESUMO
The Video Browser Showdown addresses difficult video search challenges through an annual interactive evaluation campaign attracting research teams focusing on interactive video retrieval. The campaign aims to provide insights into the performance of participating interactive video retrieval systems, tested by selected search tasks on large video collections. For the first time in its ten year history, the Video Browser Showdown 2021 was organized in a fully remote setting and hosted a record number of sixteen scoring systems. In this paper, we describe the competition setting, tasks and results and give an overview of state-of-the-art methods used by the competing systems. By looking at query result logs provided by ten systems, we analyze differences in retrieval model performances and browsing times before a correct submission. Through advances in data gathering methodology and tools, we provide a comprehensive analysis of ad-hoc video search tasks, discuss results, task design and methodological challenges. We highlight that almost all top performing systems utilize some sort of joint embedding for text-image retrieval and enable specification of temporal context in queries for known-item search. Whereas a combination of these techniques drive the currently top performing systems, we identify several future challenges for interactive video search engines and the Video Browser Showdown competition itself.
RESUMO
The details presented in this article revolve around a sophisticated monitoring framework equipped with knowledge representation and computer vision capabilities, that aims to provide innovative solutions and support services in the healthcare sector, with a focus on clinical and non-clinical rehabilitation and care environments for people with mobility problems. In contemporary pervasive systems most modern virtual agents have specific reactions when interacting with humans and usually lack extended dialogue and cognitive competences. The presented tool aims to provide natural human-computer multi-modal interaction via exploitation of state-of-the-art technologies in computer vision, speech recognition and synthesis, knowledge representation, sensor data analysis, and by leveraging prior clinical knowledge and patient history through an intelligent, ontology-driven, dialogue manager with reasoning capabilities, which can also access a web search and retrieval engine module. The framework's main contribution lies in its versatility to combine different technologies, while its inherent capability to monitor patient behaviour allows doctors and caregivers to spend less time collecting patient-related information and focus on healthcare. Moreover, by capitalising on voice, sensor and camera data, it may bolster patients' confidence levels and encourage them to naturally interact with the virtual agent, drastically improving their moral during a recuperation process.
RESUMO
The continuing advancements in technology have resulted in an explosion in the use of interconnected devices and sensors. Internet-of-Things (IoT) systems are used to provide remote solutions in different domains, like healthcare and security. A common service offered by IoT systems is the estimation of a person's position in indoor spaces, which is quite often achieved with the exploitation of the Received Signal Strength Indication (RSSI). Localization tasks with the goal to locate the room are actually classification problems. Motivated by a current project, where there is the need to locate a missing child in crowded spaces, we intend to test the added value of using an accelerometer along with RSSI for room-level localization and assess the performance of ensemble learning methods. We present here the results of this preliminary approach of the early and late fusion of RSSI and accelerometer features in room-level localization. We further test the performance of the feature extraction from RSSI values. The classification algorithms and the fusion methods used to predict the room were evaluated using different protocols applied to a public dataset. The experimental results revealed better performance of the RSSI extracted features, while the accelerometer's individual performance was poor and subsequently affected the fusion results.
Assuntos
Acelerometria , Algoritmos , Criança , HumanosRESUMO
Social media play an important role in the daily life of people around the globe and users have emerged as an active part of news distribution as well as production. The threatening pandemic of COVID-19 has been the lead subject in online discussions and posts, resulting to large amounts of related social media data, which can be utilised to reinforce the crisis management in several ways. Towards this direction, we propose a novel framework to collect, analyse, and visualise Twitter posts, which has been tailored to specifically monitor the virus spread in severely affected Italy. We present and evaluate a deep learning localisation technique that geotags posts based on the locations mentioned in their text, a face detection algorithm to estimate the number of people appearing in posted images, and a community detection approach to identify communities of Twitter users. Moreover, we propose further analysis of the collected posts to predict their reliability and to detect trending topics and events. Finally, we demonstrate an online platform that comprises an interactive map to display and filter analysed posts, utilising the outcome of the localisation technique, and a visual analytics dashboard that visualises the results of the topic, community, and event detection methodologies.
RESUMO
The rise of Internet of Things (IoT), coupled with the advances in Artificial Intelligence technologies and cloud-based applications, have caused fundamental changes in the way societies behave. Enhanced connectivity and interactions between physical and cyber worlds create 'smart' solutions and applications to serve society's needs. Water is a vital resource and its management is a critical issue. ICT achievements gradually deployed within the water industry provide an alternative, smart and novel way to improve water management efficiently. Contributing to this direction, we propose a unified framework for urban water management, exploiting state-of-the-art IoT solutions for remote telemetry and control of water consumption in combination with machine learning-based processes. The SMART-WATER platform aims to foster water utility companies by enhancing water management and decision-making processes, providing innovative solutions to consumers for smart water utilisation.
Assuntos
Inteligência Artificial , Água , Indústrias , TecnologiaRESUMO
Analysts and journalists face the problem of having to deal with very large, heterogeneous, and multilingual data volumes that need to be analyzed, understood, and aggregated. Automated and simplified editorial and authoring process could significantly reduce time, labor, and costs. Therefore, there is a need for unified access to multilingual and multicultural news story material, beyond the level of a nation, ensuring context-aware, spatiotemporal, and semantic interpretation, correlating also and summarizing the interpreted material into a coherent gist. In this paper, we present a platform integrating multimodal analytics techniques, which are able to support journalists in handling large streams of real-time and diverse information. Specifically, the platform automatically crawls and indexes multilingual and multimedia information from heterogeneous resources. Textual information is automatically summarized and can be translated (on demand) into the language of the journalist. High-level information is extracted from both textual and multimedia content for fast inspection using concept clouds. The textual and multimedia content is semantically integrated and indexed using a common representation, to be accessible through a web-based search engine. The evaluation of the proposed platform was performed by several groups of journalists revealing satisfaction from the user side.
RESUMO
Interactive video retrieval tools developed over the past few years are emerging as powerful alternatives to automatic retrieval approaches by giving the user more control as well as more responsibilities. Current research tries to identify the best combinations of image, audio and text features that combined with innovative UI design maximize the tools performance. We present the last installment of the Video Browser Showdown 2015 which was held in conjunction with the International Conference on MultiMedia Modeling 2015 (MMM 2015) and has the stated aim of pushing for a better integration of the user into the search process. The setup of the competition including the used dataset and the presented tasks as well as the participating tools will be introduced . The performance of those tools will be thoroughly presented and analyzed. Interesting highlights will be marked and some predictions regarding the research focus within the field for the near future will be made.