CIIC - Capítulos de livros
URI permanente para esta coleção:
Navegar
Entradas recentes
- Multicriteria Models for Learning Ordinal Data: A Literature ReviewPublication . Sousa, Ricardo; Yevseyeva, Iryna; Pinto da Costa, Joaquim F.; Cardoso, Jaime S.Operations Research (OR) and Artificial Intelligence (AI) disciplines have been playing major roles on the design of new intelligent systems. Recently, different contributions from both fields have been made on the models design for problems with multi-criteria. The credit scoring problem is an example of that. In this problem, one evaluates how unlikely a client will default with his payments. Client profiles are evaluated, being their results expressed in terms of an ordinal score scale (Excelent Good Fair Poor). Intelligent systems have then to take in consideration different criteria such as payment history, mortgages, wages among others in order to commit their outcome. To achieve this goal, researchers have been delving models capable to render these multiple criteria encompassed on ordinal data. The literature presents a myriad of different methods either on OR or AI fields for the multi-criteria models. However, a description of ordinal data methods on these two major disciplines and their relations has not been thoroughly conducted yet. It is key for further research to identify the developments made and the present state of the existing methods. It is also important to ascertain current achievements and what the requirements are to attain intelligent systems capable to capture relationships from data. In this chapter one will describe techniques presented for over more than five decades on OR and AI disciplines applied to multi-criteria ordinal problems.
- Layer Thickness Evaluation Between Medical Imaging and Additive ManufacturingPublication . Almeida, Henrique A.; Vasco, Joel; Correia, Mário Simões; Ruben, Rui; Ruben, RuiAdditive manufacturing (AM) applied to the orthopaedic and surgical domains provided access to newer solutions for customised implants, customised scaffolds or even organ printing. These solutions are based on imagological data, gathered from CT-scans and/or MRI-scans. The compromise between patient’s radiation exposition and resolution along the focus direction plays an important role for the successful production of biological products. Scan detail can be increased with a thinner scanning thickness to obtain the required biological features for replication. On the other hand, a thinner scan thickness requires more scanning slices and therefore, higher exposition time to radiation. Literature shows that a maximum amount of radiation is admissible for humans, requiring an optimized approach concerning the acquisition of internal details of the human body tissues. State-of-the-art scans offer focus resolution in the range of 100 to 200 µm, although such resolution is not used for the patient’s protection. In fact, in clinical practice distance between slices are in the range of 1 to 6 mm. Concerning the AM processes that are able to use biocompatible materials, different layer thicknesses are available upon the final application in spite of the digital layer thickness that was applied during the medical imaging exam. The layer thickness during production also details the mechanical properties of the implant, with an additional aspect that the geometric data is based on information of a different layer thickness. This study intends to discuss the layer thickness used in medical imaging, the layer thickness used in AM systems providing public awareness of the operating gap between medical imaging systems and AM systems. A brief description of the accumulated errors is also presented.
- UAV Flight Simulator to Improve Elders’ Quality of LifePublication . Crespo, Christian Bustamante; Idrovo, Graciela Guerrero; Rodrigues, Nuno; Pereira, AntónioThe quality of life in older people deteriorates faster, depending if these have a sedentary lifestyle. Technology is used as a tool in various fields and there are some applications that have been developed to encourage sports through entertainment, this is the case of the Nintendo Wii. The positive impact of this kind of application has been the base in the development of this research. Our proposal focuses on the easy handling of a drone by sensing arm movements through wearable devices, and providing an immersive experience of being in a different place using virtual reality glasses. The aim is to promote the user's cognitive development, due to the hand-eye coordination required to control the drone. Finally, this research, manages to integrate virtual reality with Bluetooth technologies, establishing real-time communication with wearable devices and human movement.
- Building and Using an Ontology of Preference-Based Multiobjective Evolutionary AlgorithmsPublication . Li, Longmei; Yevseyeva, Iryna; Basto-Fernandes, Vitor; Trautmann, Heike; Jing, Ning; Emmerich, MichaelIntegrating user preferences in Evolutionary Multiobjective Optimization (EMO) is currently a prevalent research topic. There is a large variety of preference handling methods (originated from Multicriteria decision making, MCDM) and EMO methods, which have been combined in various ways. This paper proposes a Web Ontology Language (OWL) ontology to model and systematize the knowledge of preferencebased multiobjective evolutionary algorithms (PMOEAs). Detailed procedure is given on how to build and use the ontology with the help of Prot´eg´e. Different use-cases, including training new learners, querying and reasoning are exemplified and show remarkable benefit for both EMO and MCDM communities.
- A Hybrid AIS-SVM Ensemble Approach for Text ClassificationPublication . Antunes, Mário; Silva, Catarina; Ribeiro, Bernardete; Correia, ManuelIn this paper we propose and analyse methods for expanding state-of-the-art performance on text classification. We put forward an ensemble-based structure that includes Support Vector Machines (SVM) and Artificial Immune Systems (AIS). The underpinning idea is that SVM-like approaches can be enhanced with AIS approaches which can capture dynamics in models. While having radically different genesis, and probably because of that, SVM and AIS can cooperate in a committee setting, using a heterogeneous ensemble to improve overall performance, including a confidence on each system classification as the differentiating factor. Results on the well-known Reuters-21578 benchmark are presented, showing promising classification performance gains, resulting in a classification that improves upon all baseline contributors of the ensemble committee.
- Anthropometrics and Ergonomics in Pregnant WomenPublication . Almeida, Henrique de Amorim; Teixeira Ascenso, Rita Margarida; Oliveira, EunicePregnancy is a women life event that impacts her own and offspring’s life; surprisingly, few systematic and scientific maternal information is available in the literature for anthropometric and ergonomic purposes. Regarding ergonomics, some authors state that guidelines should be design for pregnant women. These guidelines may consider anthropometric issues such as changes in weight and distribution of mass, which influence mobility, home and labour performance, mood and cognition. Anthropometrics allows the body measurement, but in pregnancy women are sparingly characterized, besides Body Mass Index and few other parameters. Ergonomics not only aids in the design process of work or home layouts, but also contains several evaluation tools to determine the level of risk of musculoskeletal disorders of daily or labour tasks. Some of these tools are very specific and others have certain conditions that should be met before using them. The purpose of this study is to present an overview of guidelines and discuss which anthropometric and ergonomic evaluation tools may be used, and under which conditions can be implemented in pregnant women.
- Security Monitoring in a Low Cost Smart Home for the ElderlyPublication . Ferreira, Gabriel; Penicheiro, Paulo; Bernardo, Ruben; Neves, Álvaro; Mendes, Luís; Barroso, João; Pereira, AntónioThe general increase in life expectancy and the consequent ageing of the general population impose major challenges to modern societies. Most elderly people experience the typical problems related to old age, such as chronic health problems, as well as sensory and cognitive impairments. In addition, in today’s modern societies, where families have less and less time to look after their older relatives, the isolation of the elderly is a real concern and a highly recurrent problem, which is enhanced when they live alone. To solve, or at least minimize, these problems, a smart home monitoring system was developed, as presented and described in this paper. This solution is implemented based on a sensory network which detects anomalous behaviors, immediately triggering a warning to the caregiver or family. A strong concern when developing a project of this kind is the physical security of the elderly. Houses tend to have hazardous objects and characteristics that may inflict serious injuries to their occupants or, in extrema, even death. As time goes by, the elderly start losing muscle mass and osteoporosis may appear, as well as vision and hearing impairments, which increase the likelihood of falling. Several other serious accidents may also occur, such as gas leaks, floods and fire outbreaks. Therefore, this population would strongly benefit from a solution which helps predict and even prevent accidents before they happen.
- Low-Cost Smart Surveillance System for Smart CitiesPublication . Brás Pereira, Rúben Filipe; Correia, Diogo; Mendes, Luís; Rabadão, Carlos; Barroso, João; Pereira, AntónioThe safety of people and spaces is of paramount importance for societies. With time, the implementation of safety measures is rapidly changing from a need to a priority. Video surveillance systems play a key role in the surveillance of crucial and critical areas as these systems help the authorities keep places safer. With the rapid growth of technology and the implementation of the smart city concept, it is becoming possible to develop and deploy wide area surveillance systems. The ease with which these systems can be installed in private and public spaces (e.g., homes, streets and parks) allow for the creation of ubiquitous monitored environments. Rapid intervention responses to any abnormal situation or the use of recorded video as evidence are some advantages of the use of this type of surveillance systems. Although ubiquitous video surveillance systems are relevant for present modern societies, their cost is still high. To solve or, at least to mitigate this problem, a low-cost smart surveillance system was developed, which is presented and described in this paper. The developed surveillance system, based on available low-cost technology, can help keep critical spaces under surveillance 24/7. The proposed solution was found to have a minimal cost, a low bandwidth, and to be scalable and adaptable to every client’s needs. Thus, the solution can be used by anybody (private and public) and applied in different contexts (e.g., residential, industrial). The system can provide still images, captured from surveillance video cameras, real time video and real time video processing, which can be used for motion detection. When this happens, the user is warned via an e-mail containing the identification of the respective surveillance camera. Only the relevant video events are sent, recorded and maintained in the cloud platform system, consequently reducing the amount of storage space required to maintain all the historical video events. The results of the tests carried out show that it is possible to stream a video from the surveillance cameras with an insignificant delay and that motion detection can be attained through real time video processing. The system presented potentiates a low-cost solution for a smart city in the surveillance field.
- Traffic Management in Rural NetworksPublication . Emiliano, Rodrigo; Silva, Fernando; Frazão, Luis Alexandre Lopes; Barroso, João; Pereira, AntónioThe internet is increasingly present in people's lives, being used in diverse tasks, such as checking e-mail up to online gaming and streaming. The so-called "killer applications" are applications that, when not properly identified and prevented, have more impact on the network, making it slow. When these applications are used on networks with limited resources, as happens in rural networks, they cause a large load on the network, making it difficult its use for work purposes. It is important then to recognize and characterize this traffic to take action so that it does not cause network problems. With that in mind, the work presented in this paper describes the research and identification of cost free traffic analysis solutions that can help to overcome such problems. For that, we perform preliminary testing and a performance comparison of those tools, focusing on testing particular types of network traffic. After that, we describe the analysis and subsequent modification of the source code for storing important traffic data for the tests, as well as the test scenarios in laboratory and real-life environments. These tasks are aimed on collecting information that assists in taking action to improve the allocation of network resources to priority traffic.
- Solving the weighted ring edge-loading problem without demand splitting using a Hybrid Differential Evolution AlgorithmPublication . Bernardino, Anabela; Bernardino, Eugénia; Sanchez-Perez, Juan Manuel; Gomez-Pulido, Juan Antonio; Vega-Rodriguez, Miguel AngelIn the last few years we have seen a significant growth in Synchronous Optical Network (SONET) deployments in telecommunication service providers. With growth of data traffic, network operators seek network-engineering tools to extract the maximum benefits out of the existing infrastructure. This has suggested a number of new optimization problems, most of them in the field of combinatorial optimization. We address here the Weighted Ring Edge-Loading Problem (WRELP). The WRELP is an important optimization problem arising in a popular ring topology for communication networks - given a set of nodes connected along a bi-directional SONET ring, the objective is to minimize the maximum load on the edges (pairwise) of a ring. Our procedure includes some original features, including the application of Hybrid Differential Evolution. We also perform comparisons with standard Differential Evolution, Genetic Algorithm and Tabu Search.