Image classification is one of the most important tasks in computer vision, since it can be used to retrieve, store, organize, and analyze digital images. In recent years, deep learning convolutional neural networks h...
详细信息
ISBN:
(纸本)9783030177959;9783030177942
Image classification is one of the most important tasks in computer vision, since it can be used to retrieve, store, organize, and analyze digital images. In recent years, deep learning convolutional neural networks have been successfully used to classify images surpassing previous state of the art performances. Moreover, using transfer learning techniques, very complex models have been successfully utilized for other tasks different from the original task for which they were trained for. Here, the influence of the color representation of the input images was tested when using a transfer learning technique in three different well-known convolutional models. The experimental results showed that color representation in the CIE-L*a*b* color space gave reasonably good results compared to the RGB color format originally used during training. These results support the idea that the features learned can be transferred to new models with images using different color channels such as the CIE-L*a*b* space, and opens up new research questions as to the transferability of image representation in convolutional neural networks.
This paper describes the process of designing and developing robotic technologies as prosthetics for the home space to respond to the needs and advance the quality of life of older adults. The trend demographics repor...
详细信息
ISBN:
(纸本)9783030325206;9783030325190
This paper describes the process of designing and developing robotic technologies as prosthetics for the home space to respond to the needs and advance the quality of life of older adults. The trend demographics report a significant increase of the number of older adults in the next decade in the United States, which would generate the most significant social transformations of the 21st century. Supporting older adult to age in place gracefully is a critical need. Even though there are a number of technologies that have been designed to support older adult, there are still challenges in their implementation and use, especially in products related to enabling communication. This project aims at exploring opportunities to expand the capabilities of existing homes and assist older adults in activities of daily life in their home. The project BUMP portrays a supportive human environment and how to extend older adults' home in other's homes. The significance of this project is to share pragmatic examples on how to better design technologies that are more natural, embedded and embodied communication tool for the older adult population.
Dementia causes cognitive dysfunction and deterioration of brain. Alzheimer Disease (AD) and Mild Cognitive Impairment (MCI) are most common forms of dementia. Globally, it is estimated that about 47 million people ar...
详细信息
ISBN:
(纸本)9789811500350;9789811500343
Dementia causes cognitive dysfunction and deterioration of brain. Alzheimer Disease (AD) and Mild Cognitive Impairment (MCI) are most common forms of dementia. Globally, it is estimated that about 47 million people are affected by dementia. Various researches suggest that AD and MCI share a number of equally severe cognitive deficits, but the pathophysiology has not yet been addressed in a comprehensive way. An attempt is made to observe the prognosis difference in these disorders and to analyze the tissue variation in T1-weighted MR brain images. Samples used in this analysis are obtained from IXI, MIRIAD, and ADNI 2 database. Initially, skull stripping is carried out using Robust Brain Extraction Tool (ROBEX), Brain Extraction Tool (BET), and Brain Surface Extractor (BSE). Further, segmentation of brain tissues is performed using multilevel minimum cross-entropy based Bacteria Foraging Algorithm (BFO) and Crow Search Algorithm (CSA). Various geometric features and Structure Tensor (ST) features are extracted from White Matter (WM), Gray Matter (GM), and Cerebrospinal Fluid (CSF) for normal, MCI, and AD to observe the structural changes. The result shows that ROBEX performs better delineation of brain. Minimum cross-entropy based CSA achieves better segmentation than BFO based on similarity measures and computation time. Further, ST features extracted from the brain tissues are able to show anatomical variation effectively than geometric features. It is identified from the ANOVA test that structure tensor features of GM shows better variation to discriminate normal, MCI, and AD images. Hence, this framework could be used to differentiate normal, MCI, and AD images such as cognitive disorders effectively.
In this paper, based on the evolution of the functional solution model, a number of different (function-behavior-structure) FBS functional design mapping models are presented. It has found many limitations of the exis...
详细信息
ISBN:
(纸本)9783030279288;9783030279271
In this paper, based on the evolution of the functional solution model, a number of different (function-behavior-structure) FBS functional design mapping models are presented. It has found many limitations of the existing function solving model. The reuse of knowledge and mapping of post-redesign are separated. The order of mapping is difficult to judge in the image, cannot be integrated into the innovation redesign stage. The order of mapping is blurry. And the changing environment is not expressed in the image. Therefore, this paper optimizes the design of the FBS mapping model for knowledge reuse, as well as images. An innovative design model S-FES including the above structure or behavior is proposed, which overcomes the above shortcomings and improves the efficiency of the FBS model. The practicality of the new model is illustrated by taking a shoe washing machine as an example.
Aerial robotics is evolving towards the design of bioinspired platforms capable of resembling the behavior of birds and insects during flight. The development of perception algorithms for navigation of ornithopters re...
详细信息
ISBN:
(纸本)9783030361501;9783030361495
Aerial robotics is evolving towards the design of bioinspired platforms capable of resembling the behavior of birds and insects during flight. The development of perception algorithms for navigation of ornithopters requires sensor data information to evaluate and solve the limitations presented during the flight of these platforms. However, the payload constraints and hardware complexity of ornithopters hamper the sensor data acquisition. This paper focuses on the development of a multi-sensor simulator to retrieve the sensor information captured during the landing maneuvers of ornithopters. The landing trajectory is computed by using a bioinspired trajectory generator relying on tau theory. Further, a dataset of the sensor information records obtained during the simulation of several landing trajectories is publicly available online.
We consider the effect of Single Server Queue Having Machine repair with catastrophes utilizing likelihood creating capacities that is inferred. Here, the likelihood producing capacities for the quantity of units in t...
详细信息
ISBN:
(数字)9789811501357
ISBN:
(纸本)9789811501357;9789811501340
We consider the effect of Single Server Queue Having Machine repair with catastrophes utilizing likelihood creating capacities that is inferred. Here, the likelihood producing capacities for the quantity of units in the line when the server is occupied and is on machine repair are numerically inferred. The normal quantities of units in the line when the server is occupied and is on machine repair are gotten. Numerical examination has improved the situation investigation of different execution measures for different estimations of parameters.
This work concerns to a web application Bus Ticket Reservation System that can be used in a bus transportation system in TEWU to reserve seats, cancellation of reservation and different types of route enquiries used o...
详细信息
ISBN:
(纸本)9783030290351;9783030290344
This work concerns to a web application Bus Ticket Reservation System that can be used in a bus transportation system in TEWU to reserve seats, cancellation of reservation and different types of route enquiries used on securing quick reservations. Also contains questions about the software development methods and models and questions about the interface system for Internet applications. To develop Bus Ticket Reservation System it is going to choose XP (Extreme Programming) methodology. In the future it is possible make the system more functional and user-friendly, and as a result may bring benefits in many bus transport companies.
When evaluating the learning styles of several individuals using the Honey-Alonso test, some users did not understand the meaning of several of the questions. This may be due to problems of context, tiredness in front...
详细信息
ISBN:
(纸本)9783030200404;9783030200398
When evaluating the learning styles of several individuals using the Honey-Alonso test, some users did not understand the meaning of several of the questions. This may be due to problems of context, tiredness in front of the extension of the test, lack of understanding or disinterest. The Honey-Alonso test consists of four groups of twenty questions each. Each group of questions allows identifying the level that an individual possesses on each one of the four learning styles. These styles are: active, reflective, theoretical and pragmatic. Answering a questionnaire of eighty questions is not an easy task from an andragogical point of view. This article proposes the creation of an educational video game designed with a script based on the questions of the Honey-Alonso test. The answers selected by the player are taken as a condition to determine the order of the next questions presented to the player.
The aim of the work was an analysis of the seven hyperelastic material models ability to capture tendon (from a sheep and domestic pig) response during quasi-static tensile loading. In the first step, animal tendons w...
详细信息
ISBN:
(纸本)9783030298852;9783030298845
The aim of the work was an analysis of the seven hyperelastic material models ability to capture tendon (from a sheep and domestic pig) response during quasi-static tensile loading. In the first step, animal tendons were tested under tensile loading;then the neo-Hookean, Mooney-Rivlin, Ogden, Humprey, Martins, Veronda-Wenstmann and Yeoh material models were fitted to tendons tensile data. Three different approaches to a modeling procedure were used: (1) models were fitted to tensile data for all tested specimens and coefficients of models were averaged, (2) on the base on registered tensile curves, one average stress-stretch curve was determined and then models were fitted, and (3) for two above described variants, the tensile data were limited to the first and second phase of elongation during fitting procedure and extrapolated to the third phase. Models sensitivity to limitation of experimental data and possibility of predicting tensile behavior in full range of elongation were analyzed. The range of experimental data used to fit the model was crucial factor for the predictive ability of each model.
Cervical cancer is a disease condition which makes cells on the human organ Cervix grow out of control. Among all women, it is the second most occurring type of cancer. Human papillomavirus is the cause of this diseas...
详细信息
ISBN:
(纸本)9783030372187;9783030372170
Cervical cancer is a disease condition which makes cells on the human organ Cervix grow out of control. Among all women, it is the second most occurring type of cancer. Human papillomavirus is the cause of this disease. Early stage detection of cancer helps in finalizing correct medication at the appropriate time. Diagnosis of cervical cancer involves human expertise to a greater extend. Advanced medical imaging enables computerized methods to identify the cancerous cells at beginning stage. Detecting the cervix type is very important as the type of treatment depends on the cervix type. We intend to propose a classification technique to predict the cervix type using Neural networks. From our earlier works, it is understood that the lack of powerful preprocessing techniques for finding Region of Interest(ROI) is missing in the literature. We have developed a Neural Network(UNet) based segmentation technique for cutting the ROI from the input image set. Finally, a CNN model is designed, developed and trained for classifying the cervix type. The applicability of transfer learning to cervix type prediction is also tried. A accuracy of 70% is obtained.
暂无评论