The American Conference of Governmental Industrial Hygienists (ACGIH) Threshold Limit Values (TLVs) for lifting provides risk zones for assessing two-handed lifting tasks. This paper describes two computational models...
详细信息
The American Conference of Governmental Industrial Hygienists (ACGIH) Threshold Limit Values (TLVs) for lifting provides risk zones for assessing two-handed lifting tasks. This paper describes two computational models for identifying the lifting risk zones using gyroscope information from five inertial measurement units (IMUs) attached to the lifter. Two models were developed: (1) the ratio model using body segment length ratios of the forearm, upper arm, trunk, thigh, and calf segments, and (2) the ratio + length model using actual measurements of the body segments in the ratio model. The models were evaluated using data from 360 lifting trials performed by 10 subjects (5 males and 5 females) with an average age of 51.50 (+/- 9.83) years. The accuracy of the two models was compared against data collected by a laboratory-based motion capture system as a function of 12 ACGIH lifting risk zones and 3 grouped risk zones (low, medium, and high). Results showed that only the ratio + length model provides acceptable estimates of lifting risk with an average of 69% accuracy level for predicting one of the 3 grouped zones and a higher rate of 92% for predicting the high lifting zone.
Background: Checking appropriateness of blood transfusion for quality assurance required enormous usage of time and human resources from the healthcare system. We report here a new machine learning algorithm for check...
详细信息
Background: Checking appropriateness of blood transfusion for quality assurance required enormous usage of time and human resources from the healthcare system. We report here a new machine learning algorithm for checking blood transfusion quality. Materials and methods: The multilayer perceptron neural network (MLPNN) was designed to learn an expert's judgement from 4946 clinical cases. The accuracy in predicting the blood transfusion was then reported. Results: We achieved a 96.8% overall accuracy rate, with a 99% match rate to the experts' judgement on those appropriate cases and 90.9% on the inappropriate cases. Conclusions: Machine learning algorithm can accurately match to human judgement by feeding in pre-surgical information and key laboratory variables.
A new algorithm has been designed and tested to identify protein, or any other macromolecular, complexes that have been widely reported in mass spectral data. The program takes advantage of the appearance of multiply ...
详细信息
A new algorithm has been designed and tested to identify protein, or any other macromolecular, complexes that have been widely reported in mass spectral data. The program takes advantage of the appearance of multiply charged ions that are common to both electrospray ionization and, to a lesser extent, matrix-assisted laser desorption/ionization (MALDI) mass spectra. The algorithm, known as COMPLX for the COMposition of Protein-Ligand compleXes, is capable of identifying complexes for any protein or macromolecule with a binding partner of molecular mass up to 100000 Da. It does so by identifying ion pairs present in a mass spectrum that, when they share a common charge, have an m/z value difference that is an integer fraction of a ligand or binding partner molecular mass. Several additional criteria must be met in order for the result to be ranked in the output file including that all m/z values for ions of the protein or complex have progressively lower values as their assigned charge increases, the difference between the m/z values for adjacent charge states (z, z+1) decrease as the assigned charge state increases, and the ratio of any two m/z values assigned to a protein or complex is equal to the inverse ratio of their charge., The entries that satisfy these criteria are then ranked according to the appearance of ions in the mass spectrum associated with the binding partner, the length of a continuous series of charges across any set of ions for a protein and complex and the lowest error recorded for the molecular mass of the ligand or binding partner. A diverse range of hypothetical and experimental mass spectral data were used to implement and test the program, including those recorded for antibody-peptide, protein-peptide and protein-heme complexes. Spectra of increasing complexity, in terms of the number of ions input, were also successfully analysed in which the number of input m/z values far exceeds the few associated with a macromolecular complex. Thus the
In order to increase the productivity of turning processes, several attempts have been made in the recent past for tool wear estimation and classification in turning operations. The tool flank and crater wear can be p...
详细信息
In order to increase the productivity of turning processes, several attempts have been made in the recent past for tool wear estimation and classification in turning operations. The tool flank and crater wear can be predicted by a number of models including statistical, pattern recognition, quantitative and neural network models. In this paper, a computer algorithm of new quantitative models for flank and crater wear estimation is presented. First, a quantitative model based on a correlation between increases in feed and radial forces and the average width of flank wear is developed. Then another model which relates acoustic emission (AE(rms)) in the turning operation with the flank and crater wear developed on the tool is presented. The flank wear estimated by the first model is then employed in the second model to predict the crater wear on the tool insert. The influence of flank and crater wear on AE(rms) generated during the turning operation has also been investigated. Additionally, chip-flow direction and tool-chip rake face interfacing area are also examined. The experimental results indicate that the computer program developed, based on the algorithm mentioned above, has a high accuracy for estimation of tool flank wear. (C) 2002 Elsevier Science Ltd. All rights reserved.
The main results are as follows. (1) Let f is an element of C[0, 1] change its sign a finite number of times;then the degree of copositive approximation of f by splines with n equally spaced knots is bounded by C omeg...
详细信息
The main results are as follows. (1) Let f is an element of C[0, 1] change its sign a finite number of times;then the degree of copositive approximation of f by splines with n equally spaced knots is bounded by C omega(3)(f, 1/n) for n large enough. This rate is the best in the sense that omega(3) cannot be replaced by omega(4). (2) An algorithm is developed based on the proof. (3) The first result above holds for a copositive polynomial approximation of f. (4) If f is an element of C-1[0, 1], then the degree of approximation by copositive splines of order r is bounded by Cn(-1)omega(r-1)(f', 1/n). The results on f is an element of C[0, 1] fill a gap left by S. *** [Israel J. Math., 78 (1992), pp. 75-83], and Y. K. Hu, D. Leviatan, and X. M. Yu [J. Anal., 1 (1993), pp. 85-90;J. Approx, Theory, 80 (1995), pp. 204-218].
According to the characteristics of the physical model of autonomous robot, such as strong nonlinearity and many external interference factors, a robot autonomous judgment system based on computer algorithm is propose...
详细信息
According to the characteristics of the physical model of autonomous robot, such as strong nonlinearity and many external interference factors, a robot autonomous judgment system based on computer algorithm is proposed in this paper. The system can accomplish the approximate linearization of decomposed variables by using dynamic feedback control algorithm, so as to achieve the purpose of initial effective control. The adaptive performance of computer algorithm can effectively solve the compensation control needed by uncertain model and other disturbances. Finally, the proposed algorithm is verified by using MATLAB simulation software. The experimental results show that the proposed algorithm has good dynamic performance and strong robustness.
Introduction Bleeding is increasingly considered an important end point in clinical platelet transfusion studies. Accurate recording and adjudication into well-defined bleeding grades, however, remains a major challen...
详细信息
Introduction Bleeding is increasingly considered an important end point in clinical platelet transfusion studies. Accurate recording and adjudication into well-defined bleeding grades, however, remains a major challenge. Methods We developed a computer algorithm for automatic adjudication. The algorithm's results were compared to those of three independent adjudicators. Results For one of 1186 bleeding days, the clinical report form (CRF) was filled out incorrectly, and the algorithm therefore missed one grade-1 skin bleed. For two bleeding days, the adjudicators incorrectly classified a grade-2 skin bleed as grade-1 while the algorithm correctly classified these days. The algorithm saved approximately six person-hours of adjudication time for the adjudication of 1186 days from 60 patients. Discussion The algorithm can be an invaluable tool for adjudicating large amounts of bleeding data.
Teamwork skills are commonly evaluated by human assessors, which can be logistically challenging and resource intensive. Technological advancements provide an opportunity for a new assessment method - virtual behaviou...
详细信息
Teamwork skills are commonly evaluated by human assessors, which can be logistically challenging and resource intensive. Technological advancements provide an opportunity for a new assessment method - virtual behavioural simulations with self-scoring algorithms. This study explores whether a rule-based algorithm can match human assessors at evaluating teamwork skills. 206 undergraduate students completed a virtual simulation assessment, where they interacted with "teammates" (represented by chatbots) using natural language. In this study, students' teamwork skills were assessed independently by a computer algorithm and two human experts based on the transcripts of their conversations with "teammates" (chatbots). The relative accuracy of these assessments was evaluated against peer- and self-evaluations of teamwork. The assessment scores generated by the algorithm and human experts were highly correlated with each other and were comparable in their ability to predict teamwork. The scores generated by the algorithm were slightly more correlated with peer-evaluations than those generated by human experts (r = .25 and r = .17, respectively;p = .21). The results indicate that AI-based techniques offer a promising method of skill assessment to support learning and acquisition teamwork skills.
Background Digital image analysis has been introduced into the diagnosis of skin lesions based on dermoscopic pictures. Objectives To develop a computer algorithm for the diagnosis of melanocytic lesions and to compar...
详细信息
Background Digital image analysis has been introduced into the diagnosis of skin lesions based on dermoscopic pictures. Objectives To develop a computer algorithm for the diagnosis of melanocytic lesions and to compare its diagnostic accuracy with the results of established dermoscopic classification rules. Methods In the Department of Dermatology, University of Tuebingen, Germany, 837 melanocytic skin lesions were prospectively imaged by a dermoscopy video system in consecutive patients. Of these lesions, 269 were excised and examined by histopathology: 84 were classified as cutaneous melanomas and 185 as benign melanocytic naevi. The remaining 568 lesions were diagnosed by dermoscopy as benign. Digital image analysis was performed in all 837 benign and malignant melanocytic lesions using 64 different analytical parameters. Results For lesions imaged completely (diameter less than or equal to 12 mm), three analytical parameters were found to distinguish clearly between benign and malignant lesions, while in incompletely imaged lesions six parameters enabled differentiation. Based on the respective parameters and logistic regression analysis, a diagnostic computer algorithm for melanocytic lesions was developed. Its diagnostic accuracy was 82% for completely imaged and 84% for partially imaged lesions. All 837 melanocytic lesions were classified by established dermoscopic algorithms and the diagnostic accuracy was found to be in the same range (ABCD rule 78%, Menzies' score 83%, seven-point checklist 88%, and seven features for melanoma 81%). Conclusions A diagnostic algorithm for digital image analysis of melanocytic lesions can achieve the same range of diagnostic accuracy as the application of dermoscopic classification rules by experts. The present diagnostic algorithm, however, still requires a medical expert who is qualified to recognize cutaneous lesions as being of melanocytic origin.
The reliability of network topology is examined using the Event Space Technique. An algorithm is developed to computerize the process of identifying optimal redundancy. A relationship between link reliability and netw...
详细信息
ISBN:
(纸本)0780381149
The reliability of network topology is examined using the Event Space Technique. An algorithm is developed to computerize the process of identifying optimal redundancy. A relationship between link reliability and network reliability is formulated. Cost-effectiveness was implemented for the optimum redundancy of an Optical Fibre Network (OFN) serving as a backbone to a mobile telecommunication system. The TIME dotCom (TDC) was taken as a model upon which the study is based.
暂无评论