Search results for " Neural Network"

Convolutional neural networks in skin cancer detection using spatial and spectral domain

2019

Skin cancers are world wide deathly health problem, where significant life and cost savings could be achieved if detection of cancer can be done in early phase. Hypespectral imaging is prominent tool for non-invasive screening. In this study we compare how use of both spectral and spatial domain increase classification performance of convolutional neural networks. We compare five different neural network architectures for real patient data. Our models gain same or slightly better positive predictive value as clinicians. Towards more general and reliable model more data is needed and collection of training data should be systematic. peerReviewed

Recommending Serendipitous Items using Transfer Learning

2018

Most recommender algorithms are designed to suggest relevant items, but suggesting these items does not always result in user satisfaction. Therefore, the efforts in recommender systems recently shifted towards serendipity, but generating serendipitous recommendations is difficult due to the lack of training data. To the best of our knowledge, there are many large datasets containing relevance scores (relevance oriented) and only one publicly available dataset containing a relatively small number of serendipity scores (serendipity oriented). This limits the learning capabilities of serendipity oriented algorithms. Therefore, in the absence of any known deep learning algorithms for recommend…

Thermal anomalies detection in a photovoltaic plant using artificial intelligence: Italy case studies

2021

This paper proposes the application of artificial intelligence techniques for the identification of thermal anomalies that occur in a photovoltaic system due to malfunctions or faults, with the aim to limit the energy production losses by detecting faults at an early stage. The proposed approach is based on a Thermographic Non-Destructive Test conducted with Unmanned Aerial Vehicles equipped with a thermal imaging camera, which allows the detection of abnormal operating conditions without interrupting the normal operation of the PV system rapidly and cost-effectively. The thermographic images and videos are automatically inspected using a Convolutional Neural Network, developed by an open-s…

Anonymization as homeomorphic data space transformation for privacy-preserving deep learning

2021

Industry 4.0 is largely data-driven nowadays. Owners of the data, on the one hand, want to get added value from the data by using remote artificial intelligence tools as services, on the other hand, they concern on privacy of their data within external premises. Ideal solution for this challenge would be such anonymization of the data, which makes the data safe in remote servers and, at the same time, leaves the opportunity for the machine learning algorithms to capture useful patterns from the data. In this paper, we take the problem of supervised machine learning with deep feedforward neural nets and provide an anonymization algorithm (based on the homeomorphic data space transformation),…

Are customer star ratings and sentiments aligned? A deep learning study of the customer service experience in tourism destinations

2023

AbstractThis study explores the consistency between star ratings and sentiments expressed in online reviews and how they relate to the different components of the customer experience. We combine deep learning applied to natural language processing, machine learning and artificial neural networks to identify how the positive and negative components of 20,954 online reviews posted on TripAdvisor about tourism attractions in Venice impact on their overall polarity and star ratings. Our findings showed that sentiment valence is aligned with star ratings. A cancel-out effect operates between the positive and negative sentiments linked to the service experience dimensions in mixed-neutral reviews.

The forecasting of the roadside pollutant levels to evaluate traffic management measures in Palermo.

2015

The road transport has become the major source of environmental degradation in urban centres. It produces negative externalities (i.e. pollution, delay, etc.) that are usually connected with the queues of traffic flows and the congestion of the road network. The quantitative estimation of roadside pollutant levels is very complex. Many variables are involved such as the type of vehicle (characterized by different antipollution devices, used fuels, engine temperatures, maintenance level of engines, etc.), the different cinematic conditions of the flows, the urban/road network structure, the weather conditions, etc. Therefore it is important to develop scientific tools able to predict roadsid…

An Automatic Method for Assessing Spiking of Tibial Tubercles Associated with Knee Osteoarthritis

2022

Efficient and scalable early diagnostic methods for knee osteoarthritis are desired due to the disease’s prevalence. The current automatic methods for detecting osteoarthritis using plain radiographs struggle to identify the subjects with early-stage disease. Tibial spiking has been hypothesized as a feature of early knee osteoarthritis. Previous research has demonstrated an association between knee osteoarthritis and tibial spiking, but the connection to the early-stage disease has not been investigated. We study tibial spiking as a feature of early knee osteoarthritis. Additionally, we develop a deep learning based model for detecting tibial spiking from plain radiographs. We collected an…

Application of artificial neural network and genetic algorithm to forecasting of wind power output

2007

DL_Track : Automated analysis of muscle architecture from B-mode ultrasonography images using deep learning

2023

B-mode ultrasound is commonly used to image musculoskeletal tissues, but one major bottleneck is data analysis. Manual analysis is commonly deployed for assessment of muscle thickness, pennation angle and fascicle length in muscle ultrasonography images. However, manual analysis is somewhat subjective, laborious and requires thorough experience. We provide an openly available algorithm (DL_Track) to automatically analyze muscle architectural parameters in ultrasonography images or videos of human lower limb muscles.
 We trained two different neural networks (classic U-net [Ronneberger et al., 2021] and U-net with VGG16 [Simonyan & Zisserman, 2015] pretrained encoder) one to detect …

Nonlinear black-box models for short-term forecasting of air temperature in the town of Palermo

2011

Weather data are crucial to correctly design buildings and their heating and cooling systems and to assess their energy performances. In the intensely urbanized towns the effect of climatic parameters is further emphasized by the Urban Heat Island (UHI) phenomenon, known as the increase in the air temperature of urban areas, compared to the one measured in the extra-urban areas. The analysis of the heat island needs detailed local climate data which can be collected only by a dedicated weather monitoring system. The Department of Energy and Environmental Researches of the University of Palermo (Italy) has built up a weather monitoring system that works 24 hours per day and makes data availa…