Explore the vast range of titles available.

This paper presents a new white blood cell classification system for the recognition of five types of white blood cells. We propose a new segmentation algorithm for the segmentation of white blood cells from smear images. The core idea of the proposed segmentation algorithm is to find a discriminating region of white blood cells on the HSI color space. Pixels with color lying in the discriminating region described by an ellipsoidal region will be regarded as the nucleus and granule of cytoplasm of a white blood cell. Then, through a further morphological process, we can segment a white blood cell from a smear image. Three kinds of features (i.e., geometrical features, color features, and LDP-based texture features) are extracted from the segmented cell. These features are fed into three different kinds of neural networks to recognize the types of the white blood cells. To test the effectiveness of the proposed white blood cell classification system, a total of 450 white blood cells images were used. The highest overall correct recognition rate could reach 99.11% correct. Simulation results showed that the proposed white blood cell classification system was very competitive to some existing systems.

In this paper, we treat optimization problems as a kind of reinforcement learning problems regarding an optimization procedure for searching an optimal solution as a reinforcement learning procedure for finding the best policy to maximize the expected rewards. This viewpoint motivated us to propose a Q -learning-based swarm optimization (QSO) algorithm. The proposed QSO algorithm is a population-based optimization algorithm which integrates the essential properties of Q -learning and particle swarm optimization. The optimization procedure of the QSO algorithm proceeds as each individual imitates the behavior of the global best one in the swarm. The best individual is chosen based on its accumulated performance instead of its momentary performance at each evaluation. Two data sets including a set of benchmark functions and a real-world problem—the economic dispatch (ED) problem for power systems—were used to test the performance of the proposed QSO algorithm. The simulation results on the benchmark functions show that the proposed QSO algorithm is comparable to or even outperforms several existing optimization algorithms. As for the ED problem, the proposed QSO algorithm has found solutions better than all previously found solutions.

Rehabilitation is the main therapeutic approach for reducing poststroke functional deficits in the affected upper limb; however, significant between-patient variability in rehabilitation efficacy indicates the need to target patients who are likely to have clinically significant improvement after treatment. Many studies have determined robust predictors of recovery and treatment gains and yielded many great results using linear approachs. Evidence has emerged that the nonlinearity is a crucial aspect to study the inter-areal communication in human brains and abnormality of oscillatory activities in the motor system is linked to the pathological states. In this study, we hypothesized that combinations of linear and nonlinear (cross-frequency) network connectivity parameters are favourable biomarkers for stratifying patients for upper limb rehabilitation with increased accuracy. We identified the biomarkers by using 37 prerehabilitation electroencephalogram (EEG) datasets during a movement task through effective connectivity and logistic regression analyses. The predictive power of these biomarkers was then tested by using 16 independent datasets (i.e. construct validation). In addition, 14 right handed healthy subjects were also enrolled for comparisons. The result shows that the beta plus gamma or theta network features provided the best classification accuracy of 92%. The predictive value and the sensitivity of these biomarkers were 81.3% and 90.9%, respectively. Subcortical lesion, the time poststroke and initial Wolf Motor Function Test (WMFT) score were identified as the most significant clinical variables affecting the classification accuracy of this predictive model. Moreover, 12 of 14 normal controls were classified as having favourable recovery. In conclusion, EEG-based linear and nonlinear motor network biomarkers are robust and can help clinical decision making.

Companies in the construction precast industry usually face lack of skilled manpower, overtime working, and complexity of manpower allocation. The objective of this research is to identify the complexity of precast components using Swarm-Inspired Projection (SIP) algorithm. After conducting a comprehensive literature review regarding precast production, clustering, classification, cost management, manpower allocation, and optimization, expertise from field/head-quarter supervision leads the way to SIP algorithm that drives collected data converted to certain clusters. Data collection was carried out to gather over 90% precast construction data in Taiwan for the recent decade. A total of 1,015,840 datasets were collected and then 772,212 datasets were taken into computation SIP algorithm after data filtering. Evaluation and comparison of models reveal SIP’s remarkable efficiency, halving processing time while delivering superior results. The study identifies four complexity tiers linked to the manufacturing of building precast elements. Significant variations exist among these tiers, with workload increments of 18.22%, 11.71%, and 30.08% between Level 1 and 2, Level 2 and 3, and Level 3 and 4, respectively.

Magnetic resonance imaging (MRI) offers the most detailed brain structure image available today; it can identify tiny lesions or cerebral cortical abnormalities. The primary purpose of the procedure is to confirm whether there is structural variation that causes epilepsy, such as hippocampal sclerotherapy, local cerebral cortical dysplasia, and cavernous hemangioma. Cerebrovascular disease, the second most common factor of death in the world, is also the fourth leading cause of death in Taiwan, with cerebrovascular disease having the highest rate of stroke. Among the most common are large vascular atherosclerotic lesions, small vascular lesions, and cardiac emboli. The purpose of this thesis is to establish a computer-aided diagnosis system based on small blood vessel lesions in MRI images, using the method of Convolutional Neural Network and deep learning to analyze brain vascular occlusion by analyzing brain MRI images. Blocks can help clinicians more quickly determine the probability and severity of stroke in patients. We analyzed MRI data from 50 patients, including 30 patients with stroke, 17 patients with occlusion but no stroke, and 3 patients with dementia. This system mainly helps doctors find out whether there are cerebral small vessel lesions in the brain MRI images, and to output the found results into labeled images. The marked contents include the position coordinates of the small blood vessel blockage, the block range, the area size, and if it may cause a stroke. Finally, all the MRI images of the patient are synthesized, showing a 3D display of the small blood vessels in the brain to assist the doctor in making a diagnosis or to provide accurate lesion location for the patient.

Neural networks have achieved great results in sound recognition, and many different kinds of acoustic features have been tried as the training input for the network. However, there is still doubt about whether a neural network can efficiently extract features from the raw audio signal input. This study improved the raw-signal-input network from other researches using deeper network architectures. The raw signals could be better analyzed in the proposed network. We also presented a discussion of several kinds of network settings, and with the spectrogram-like conversion, our network could reach an accuracy of 73.55% in the open-audio-dataset “Dataset for Environmental Sound Classification 50” (ESC50). This study also proposed a network architecture that could combine different kinds of network feeds with different features. With the help of global pooling, a flexible fusion way was integrated into the network. Our experiment successfully combined two different networks with different audio feature inputs (a raw audio signal and the log-mel spectrum). Using the above settings, the proposed ParallelNet finally reached the accuracy of 81.55% in ESC50, which also reached the recognition level of human beings.

Technological developments have made the construction industry efficient. The aim of this research is to solve communication interaction problems to build a project management platform using the interactive concept of natural language processing technology. A comprehensive literature review and expert interviews associated with techniques dealing with natural languages suggests the proposed system containing the Progressive Scale Expansion Network (PSENet), Convolutional Recurrent Neural Network (CRNN), and Bi-directional Recurrent Neutral Networks Convolutional Recurrent Neural Network (BRNN-CNN) toolboxes to extract the key words for construction projects contracts. The results show that a fully automatic platform facilitating contract management is achieved. For academic domains, the Contract Keyword Detection (CKD) mechanism integrating PSENet, CRNN, and BRNN-CNN approaches to cope with real-time massive document flows is novel in the construction industry. For practice, the proposed approach brings significant reduction for manpower and human error, an alternative for settling down misunderstanding or disputes due to real-time and precise communication, and a solution for efficient documentary management. It connects all contract stakeholders proficiently.

The human eye is a vital sensory organ that provides us with visual information about the world around us. It can also convey such information as our emotional state to people with whom we interact. In technology, eye tracking has become a hot research topic recently, and a growing number of eye-tracking devices have been widely applied in fields such as psychology, medicine, education, and virtual reality. However, most commercially available eye trackers are prohibitively expensive and require that the user’s head remain completely stationary in order to accurately estimate the direction of their gaze. To address these drawbacks, this paper proposes an inner corner-pupil center vector (ICPCV) eye-tracking system based on a deep neural network, which does not require that the user’s head remain stationary or expensive hardware to operate. The performance of the proposed system is compared with those of other currently available eye-tracking estimation algorithms, and the results show that it outperforms these systems.

The goal of the current study is to clarify the relationship between social information processing (e.g., visual attention to cues of hostility, hostility attribution bias, and facial expression emotion labeling) and aggressive tendencies. Thirty adults were recruited in the eye-tracking study that measured various components in social information processing. Baseline aggressive tendencies were measured using the Buss-Perry Aggression Questionnaire (AQ). Visual attention towards hostile objects was measured as the proportion of eye gaze fixation duration on cues of hostility. Hostility attribution bias was measured with the rating results for emotions of characters in the images. The results show that the eye gaze duration on hostile characters was significantly inversely correlated with the AQ score and less eye contact with an angry face. The eye gaze duration on hostile object was not significantly associated with hostility attribution bias, although hostility attribution bias was significantly positively associated with the AQ score. Our findings suggest that eye gaze fixation time towards non-hostile cues may predict aggressive tendencies.

Data-driven housing-market segmentation has been given increasing prominence for its objectiveness in identifying submarkets based on the housing data's underlying structures. However, when handling high-dimensionality housing dataset, traditional statistical-clustering methods have been found to tend to lose low-variance information of the dataset and be deficient in deriving the globally optimal number of submarkets. Accordingly, with the intention of achieving more rigorous high-dimensionality housing market segmentation, a swarm-inspired projection (SIP) algorithm is introduced by this study. Using a highdimensionality Taipei city's housing dataset in a case study, a comparison of the proposed SIP algorithm and a statistical-clustering method using the combination of principal component analysis (PCA) and K-means clustering is conducted in evaluating the predictive accuracy of hedonic price models of the housing submarkets. The results show that, as compared to the original single market, the segmented submarkets resulting from SIP algorithm are more homogenous and distinctive, where the resulted hedonic price models have high-level statistical explanation and disparate sets of hedonic prices for different submarkets. In addition, as compared to the use of a statistical-clustering method, SIP algorithm is found to obtain a more optimal number of submarkets, where the resulted hedonic price models are found to achieve greater improvement of statistical explanation and more stable reduction of prediction error. These findings highlight the advantages of our proposed SIP algorithm in high-dimensionality housing market segmentation, and thus it is hoped that the present research will serve as a practical tool to better inform further studies aimed at market-segmentation-related problems.