Computer-aided Evaluation System Research Articles

Multiple Game and Computer-Aided Evaluation System Design of Computer Software Legal Protection Policy

This article has deeply studied the two kinds of computer software legal protection policies ISO17799 and ISO13355, and analyzed the conceptual model and relational model of the multiple game. On this basis, the concept of computer-aided evaluation based on computer law is proposed, and a computer-aided evaluation system is designed, which effectively realizes asset evaluation based on multiple games and threat and vulnerability evaluation based on probability statistics. And on the basis of referring to the risk assessment process and based on the actual needs of the system, a highly operable assessment process that is convenient for computer implementation is proposed.

Glomerular Lesion Recognition Based on Pathology Images With Annotation Noise via Noisy Label Learning

Background: Glomerular lesion recognition is one of the most crucial steps in the diagnosis of kidney disease. Deep learning, which relies on large numbers of pathology images, assists pathologists to access glomerular lesions more efficiently, objectively and accurately. However, due to different pathological development of glomeruli, complicated lesion patterns, and limited resolution of pathology images, there is annotation noise in datasets, making the deep learning model under- or over-fit. Methods: In this paper, we propose a novel noisy label learning model for lesion recognition in glomerular datasets with annotation noise. The model integrates uncertainty-based noisy label discriminator, contrastive learning, and consistency regularization to achieve high signal-to-noise supervision, pathology feature extraction, and utilization of pathology images. Results: We constructed large-scale glomerular datasets from 870 kidney disease cases using different stainings including Periodic acid–Schiff (PAS), Masson Trichrome (MT) and Periodic Schiff-Methenamine (PASM). Intensive experiments demonstrated the superiority of the proposed model for glomerular lesion recognition compared to other methods, as 25% of the lesions had f <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> - score above 85%, 43.75% had f <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> - score above 80%, and 75% had f <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> - score at or above 70%. Additionally, further experiments demonstrate the effectiveness of each module. Conclusions: The noisy label learning model proposed is able to recognize the most glomerular lesions, with the annotation noise discrimination and large amounts of pathology images utilization, laying the foundation for the development of computer-aided evaluation system for renal pathology.

Rule Representation for Nursing-Care Process Evaluation Using Decision Tree Techniques

Improving the quality of nursing care is crucial to maintaining the quality of life. Our objective is to develop a computer-aided evaluation system that enables nursing experts to improve the quality of nursing care. In our previous works, some classification systems based on fuzzy logic, neural networks, and SVMs were developed. Although a classification system with high performance for all nursing-care datasets is desirable, we focus on how to visualize the classification results in this paper. It is important to visualize the results for our nursing-care text classification system because the computer-aided system has to explain the reasons for obtaining such results to human experts. In this paper, a tree-type expression is considered for visualizing the classification results. To visualize classification results with the tree-type expression, we consider a decision tree technique. Word existence, dependency relations, and phrase-based feature vector definitions have been proposed in our previous works. In the present study, these three types of feature vector definitions are compared with one another from the viewpoint of understandability.

Discussion on the Usage of Computer-Assisted Method in Evaluation of Enterprise Financial Management

The main goal of modern enterprise financial management is the maximization of enterprise value. As our country's market economic system improved gradually, accession to the WTO and the information technology revolution, will change the current development pattern of Chinese enterprises. Face the global financial crisis and enhance their enterprise value, improve competitiveness become the central task of our country enterprise development. In enterprise financial management, Scientific evaluate to the realization degree of the financial management objectives and analyze the realization factors impact on the financial management objectives is essential[. To establish the evaluation index system of enterprise financial management goal, especially set up computer aided evaluation system, can avoid to a certain extent experience evaluation and one-sided evaluation of misjudgment, can make us scientific understand the status quo of China's enterprises, find restrict factors which may constraint the promoting competitiveness of our enterprises, constantly improve the enterprise's own value.

The Study and Application of Intelligent Uncertainty of Measurement with CAES

This paper discusses the relevant concepts, algorithms and the practical evaluation process on the intelligent evaluation of uncertainty of mechanical measurement with the use of computer technology (such as Computer-Aided Evaluation System). Through the optimization and integration of evaluation process, key points and regulative relationship, the author makes use of computer-aided calculation and database technology to achieve standardization of evaluation process, intelligent data analysis and automatic calculation of uncertainty.

Taking gender into account: Brief report on a survey of music therapists’ attitudes to future use of a proposed computer aided evaluation system: The music therapy logbook

Analysis of an international survey of music therapists working in the field of neuro-disability (N=44) identified differences in attitude between female and male therapists towards future use of a computer-aided recording and analysis system, the main purpose of which is to track changes in a client's and therapist's use of music over time. This article, a follow up report on the original survey (Streeter, 2010), examines the effects of respondent gender on attitude in order to identify issues that will need to be taken into account during the next phase of research and development. Results indicate that male music therapists may hold more positive opinions about computer-aided practice evaluation than female music therapists. However, the data also shows that female respondents were more concerned than their male counterparts about the ethical and practical issues that might arise if they were to introduce computer-aided evaluation at work. Both genders expressed excitement at the prospect of a specialist system designed to record, store, and quantify changes in music play between a music therapist and a patient.

Dynamic Breast MRI: Does Lower Temporal Resolution Negatively Affect Clinical Kinetic Analysis?

The purpose of this study was to compare the differences in kinetic assessments of lesions at breast MRI performed with higher and lower temporal resolution. All consecutively evaluated BI-RADS category 4, 5, and 6 lesions imaged with breast MRI and pathologically confirmed from October 2005 to August 2009 were identified. Patients underwent MRI with one of two dynamic contrast-enhanced protocols: one with 90-second (October 2005-June 2006) and another with 180-second (July 2006-August 2009) temporal resolution. Studies were processed with a computer-aided evaluation system with initial and delayed contrast-enhanced time points with the k-space centered 90 and 450 seconds after contrast injection. Initial-phase peak enhancement, delayed-phase predominant curve type, and worst curve type were recorded and compared for benign and malignant lesions across protocols. The analysis set comprised 993 lesions: 145 imaged with the 90-second acquisition (17 benign, 28 ductal carcinoma in situ [DCIS], 100 invasive cancer) and 848 imaged with the 180-second acquisition (212 benign, 145 DCIS, 491 invasive cancer). Peak enhancement was significantly higher for both benign lesions (p = 0.01) and invasive cancers (p = 0.0008) with the 180-second protocol. Peak enhancement of DCIS was similar in the two protocols (p = 0.88). Delayed-phase kinetics were similar for the two protocols for both benign and malignant lesions when defined by predominant or worst curve type. Although it has lower temporal resolution, a 180-second acquisition may be preferable because it allows higher spatial resolution and captures higher initial-phase peak enhancement without loss of delayed-phase kinetic information.

SU-E-T-788: DICOM-Based Electronic Patient Record (ePR) System with Computer-Aided Evaluation (CAE) of Intensity Modulated Radiation Therapy (IMRT) Plans

Purpose: To develop a DICOM‐based electronic patient record system with computer‐aided evaluation (CAE) of intensity modulated radiation therapy(IMRT) plans and to assess the technical aspects of the system and its performance. Methods: The system was developed using the WampServer version 2.0, a package of Apache web server 2.2, PHP 5.2 and MySQL 5.1 to facilitate evaluation of IMRT plans in any Web browser. After tracing the clinical workflow, a set of routines were written to parse key data items from the DICOM‐RT objects. To save planners from tedious manual evaluation, the direct relationships between the DVH curve to the corresponding CTimages, RT dose data and ROI contours were visualized. Extraction of both overdose and underdose regions was based on the edge‐based approach. Followed by reconstruction of ROI contours, the grid doses were constructed by multiplying each pixel value stored in the Image pixel module with the Dose Grid Scaling attribute in the RT Dose module. Graphic User Interfaces (GUIs) were created to allow planners to establish customized plan acceptance criteria and query for evaluation results. Thirty IMRT plans were collected for technical verification and performance validation. Results: The CAE system was successfully developed, allowing better appreciation of resultant plans. There was no statistical difference between CAE results and those obtained manually by experienced planners on all datasets. With prompt problem detection feature, the direct relationship between the DVH data to the corresponding inhomogeneity regions on CT slices could be shown within an average of 20 seconds. Conclusions: The CAE system will represent a breakthrough in the routine IMRT planning workflow by eliminating all tedious manual evaluation steps and introducing remote plan evaluation across multiple locations by the local area network and Internet. The concept could also be adopted in the evaluation of plans other than IMRT.

NOVA: a computer-aided system to monitor proper behaviour of plant components in the Gundremmingen nuclear power plant (KRB II)

In the Gundremmingen nuclear power plant (KRB II), a computer-aided evaluation system for signal messages of the process computer has been developed to application maturity and installed. The self-acting system checks sequences of automatic operations for their proper function. Results are available only minutes after an action has happened. The high level of detail permits to detect faults before they result in system failure or loss. Since all short-time safety functions are performed automatically, these consistent and detailed checks increase the safety substantially. In addition, the NOVA-System makes it possible to search all over the signal message report for certain signals as well as to produce an overview protocol of the current (or a past) status of the Plant.

A computer-aided evaluation system for sectored-type multipole electrostatic deflectors

An interactive computer aided design and evaluation system for sectored-type electrostatic deflectors has been developed; the geometrical dimensions of a deflector are measured and a computer model is constructed; the wide area deflection properties can be estimated from the computer model and displayed graphically; the evaluation can be made interactively with the graphical outputs. Given focusing and deflection field, the pattern distortion of a shaped beam caused by higher order θ components of the deflection field can also be estimated by the system. Furthermore, an effective modification scheme to improve the deflection properties of a deflector can be found by changing the shape of electrode in the computer model.

Computer-aided system for evaluation of rock and gas outburst hazards (in Polish) : Balicki, W; Halota, W Mech Autom Gorn, V18, N12, Dec 1980, P17–23

Computer-aided system for evaluation of rock and gas outburst hazards (in Polish) : Balicki, W; Halota, W Mech Autom Gorn, V18, N12, Dec 1980, P17–23