Application of probabilistic neural network in the clinical diagnosis of cancers based on clinical chemistry data

As a recently developed and powerful classification tool, probabilistic neural network was used to distinguish cancer patients from healthy persons according to the levels of nucleosides in human urine. Two datasets (containing 32 and 50 patterns, respectively) were investigated and the total consistency rate obtained was 100% for dataset 1 and 94% for dataset 2. To evaluate the performance of probabilistic neural network, linear discriminant analysis and learning vector quantization network, were also applied to the classification problem. The results showed that the predictive ability of the probabilistic neural network is stronger than the others in this study. Moreover, the recognition rate for dataset 2 can achieve to 100% if combining, these three methods together, which indicated the promising potential of clinical diagnosis by combining different methods. (C) 2002 Elsevier Science B.V. All rights reserved.

Artificial neural network classification based on high-performance liquid chromatography of urinary and serum nucleosides for the clinical diagnosis of cancer

Nucleosides in human urine and serum have frequently been studied as a possible biomedical marker for cancer, acquired immune deficiency syndrome (AIDS) and the whole-body turnover of RNAs. Fifteen normal and modified nucleosides were determined in 69 urine and 42 serum samples using high-performance liquid chromatography (HPLC). Artificial neural networks have been used as a powerful pattern recognition tool to distinguish cancer patients from healthy persons. The recognition rate for the training set reached 100%. In the validating set, 95.8 and 92.9% of people were correctly classified into cancer patients and healthy persons when urine and serum were used as the sample for measuring the nucleosides. The results show that the artificial neural network technique is better than principal component analysis for the classification of healthy persons and cancer patients based on nucleoside data. (C) 2002 Elsevier Science B.V. All rights reserved.

Artificial neural network applied to diagnosis of lung cancer

Artificial neural network(ANN) approach was applied to classification of normal persons and lung cancer patients based on the metal content of hair and serum samples obtained by inductively coupled plasma atomic emission spectrometry (ICP-AES) for the two groups. This method was verified with independent prediction samples and can be used as an aiding means of the diagnosis of lung cancer. The case of predictive classification with one element missing in the prediction samples was studied in details, The significance of elements in hair and serum samples for classification prediction was also investigated.

The effect of land management on plant community composition, species diversity, and productivity of alpine Kobersia steppe meadow

Grassland degradation is widespread and severe on the Tibet Plateau. To explore management approaches for sustainable development of degraded and restored ecosystems, we studied the effect of land degradation on species composition, species diversity, and vegetation productivity, and examined the relative influence of various rehabilitation practices (two seeding treatments and a non-seeded natural recovery treatment) on community structure and vegetation productivity in early secondary succession. The results showed: (1) All sedge and grass species of the natural steppe meadow had disappeared from the severely degraded land. The above-ground and root biomass of severely degraded land were only 38 and 14.7%, respectively, of those of the control. So, the original ecosystem has been dramatically altered by land degradation on alpine steppe meadow. (2) Seeding measures may promote above-ground biomass, particularly grass biomass, and ground cover. Except for the grasses seeded, however, other grass and sedge species did not occur after seeding treatments in the sixth year of seeding. Establishment of grasses during natural recovery treatment progressed slowly compared with during seeding treatments. Many annual forbs invaded and established during the 6 years of natural recovery. In addition, there was greater diversity after natural recovery treatment than after seeding treatments. (3) The above-ground biomass after seeding treatment and natural recovery treatment were 114 and 55%, respectively, of that of the control. No significant differences in root biomass occurred among the natural recovery and seeded treatments. Root biomass after rehabilitation treatment was 23-31% that of the control.

The effect of land management on carbon and nitrogen status in plants and soils of alpine meadows on the Tibetan plateau

Large-scale grassland rehabilitation has been carried out on the severely degraded lands of the Tibetan plateau. The grasslands created provide a useful model for evaluating the recovery of ecosystem properties. The purposes of this research were: (1) to examine the relative influence of various rehabilitation practices on carbon and nitrogen in plants and soils in early secondary succession; and (2) to evaluate the degree to which severely degraded grassland altered plant and soil properties relative to the non-disturbed native community. The results showed: (1) The aboveground tissue C and N content in the control were 105-97 g m(-2) and 3.356gm(-2), respectively. The aboveground tissue C content in the mixed seed treatment, the single seed treatment, the natural recovery treatment and the severely degraded treatment was 137 per cent, 98 per cent, 49 per cent and 38 per cent, respectively, of that in the control. The corresponding aboveground tissue N content was 109 per cent, 84 per cent, 60 per cent and 47 per cent, respectively, of that in the control. (2) Root C and N content in 0-20 cm depths of the control had an 2 2 average 1606 gm(-2) and 30-36 gm(-2) respectively. Root C and N content in the rehabilitation treatments were in the range of 26-36 per cent and 35-53 per cent, while those in the severely degraded treatment were only 17 per cent and 26 per cent of that in the control. (3) In the control the average soil C and N content at 0-20 cm was 11307 gm(-2) and 846 gm(-2), respectively. Soil C content in the uppermost 20 cm in the seeded treatments, the natural recovery treatment and the severely degraded treatment was 67 per cent, 73 per cent and 57 per cent, respectively, while soil N content in the uppermost 20cm was 72 per cent, 82 per cent and 79 per cent, respectively, of that in the control. The severely degraded land was a major C source. Restoring the severely degraded lands to perennial vegetation was an alternative approach to sequestering C in former degraded systems. N was a limiting factor in seeding grassland. It is necessary for sustainable utilization of seeding grassland to supply extra N fertilizer to the soil or to add legume species into the seed mix. Copyright (c) 2005 John Wiley & Sons, Ltd.

The Role of Knowledge in Visual Shape Representation

This report shows how knowledge about the visual world can be built into a shape representation in the form of a descriptive vocabulary making explicit the important geometrical relationships comprising objects' shapes. Two computational tools are offered: (1) Shapestokens are placed on a Scale-Space Blackboard, (2) Dimensionality-reduction captures deformation classes in configurations of tokens. Knowledge lies in the token types and deformation classes tailored to the constraints and regularities ofparticular shape worlds. A hierarchical shape vocabulary has been implemented supporting several later visual tasks in the two-dimensional shape domain of the dorsal fins of fishes.

Roles of Knowledge in Motor Learning

The goal of this thesis is to apply the computational approach to motor learning, i.e., describe the constraints that enable performance improvement with experience and also the constraints that must be satisfied by a motor learning system, describe what is being computed in order to achieve learning, and why it is being computed. The particular tasks used to assess motor learning are loaded and unloaded free arm movement, and the thesis includes work on rigid body load estimation, arm model estimation, optimal filtering for model parameter estimation, and trajectory learning from practice. Learning algorithms have been developed and implemented in the context of robot arm control. The thesis demonstrates some of the roles of knowledge in learning. Powerful generalizations can be made on the basis of knowledge of system structure, as is demonstrated in the load and arm model estimation algorithms. Improving the performance of parameter estimation algorithms used in learning involves knowledge of the measurement noise characteristics, as is shown in the derivation of optimal filters. Using trajectory errors to correct commands requires knowledge of how command errors are transformed into performance errors, i.e., an accurate model of the dynamics of the controlled system, as is demonstrated in the trajectory learning work. The performance demonstrated by the algorithms developed in this thesis should be compared with algorithms that use less knowledge, such as table based schemes to learn arm dynamics, previous single trajectory learning algorithms, and much of traditional adaptive control.