1,720,998 research outputs found
Prediction of biological activities of volatile metabolites using molecular fingerprints and machine learning methods
No full textVolatile metabolites are small molecules, comprise a diverse chemical group with various biological activities and have high vapor pressures under ambient conditions. It is crucial to determine the biological activities of volatile metabolites as they play important roles in chemical ecology and human healthcare. In this study, we have accumulated 341 volatiles emitted by biological species associated with 11 types of biological activities and deposited the data into our database, which is called KNApSAcK Metabolite Ecology Database. Using this dataset, we have developed 72 classification models to predict biological activities of volatile metabolites by using various machine learning methods. Eight types of molecular fingerprints were used to represent the molecules, which are PubChem (881 bits), CDK (1024 bits), Extended CDK (1024bits), MACCS (166 bits), Klekota-Roth (4860 bits), Substructure (307 bits), Estate (79 bits), and atom pairs (780 bits). A new type of fingerprint was also proposed by combining all features of these eight fingerprints (Combine, 9121 bits). The best classification model was developed by our proposed fingerprint (Combine, 9121 bits) trained with gradient boosting method algorithm (GBM) with predictive accuracy at 94.43%. The results indicated that molecular fingerprints and machine learning methods could be useful for predicting biological activities of volatile metabolites
On the chaotic nature of biological signals using nonlinear data analysis methodology
Full text linkOrganized by School of Mechatronic Engineering (UniMAP) & co-organized by The Institution of Engineering Malaysia (IEM), 11th - 13th October 2009 at Batu Feringhi, Penang, Malaysia.In this study, we analyze the characteristic of biological signals using nonlinear data analysis methodology. Biological signals are not linear so to get a more accurate portrait of nonlinear signals, we must analyze them with nonlinear analysis
methods. The nonlinear analysis method is emerging as relatively new and rapidly growing in biomedical field. One of the most useful techniques in nonlinear data analysis is the concept of Lyapunov exponent. As we may know, Lyapunov exponent is often used to define whether a dynamical system is chaotic or not. If the system exhibits at least one positive Lyapunov exponent and is purely deterministic, then it is chaotic. In this work, we measure the finger pulse signal for twenty minutes in two different situations. Then, we analyze the finger pulse signal using nonlinear data analysis method. We extract and evaluate Lyapunov exponent parameters from the finger pulse signal. We finally find the positive value of Lyapunov
exponent and confirm the existence of chaotic nature in biological systems.Technical sponsored by IEEE Malaysia Sectio
Development of cellular neural network algorithm for detecting lung cancer symptoms
No full textLink to publisher's homepage at http://ieeexplore.ieee.org/Lung cancer is the most common of lethal types of cancer. One of the most important and difficult tasks a doctor has to carry out is the detection and diagnosis of cancerous lung nodules from x-ray image's result. Some of these lesions may not be detected because of camouflaged by the underlying anatomical structure, the low-quality of the images or the subjective and variable decision criteria used by doctors. Hence, a detection system using cellular neural network (CNN) is developed in order to help the doctors to recognize the doubtful lung cancer regions in x-ray films. In this study, a CNN algorithm for detecting the boundary and area of lung cancer in x-ray image has been proposed. Computer simulation result shows that our CNN algorithm is verified to detect some key lung cancer symptoms successfully and has been proved by radiologist
Design and development of an emotional stress indicator (ESI) kit
No full textProceedings of the IEEE Conference on Sustainable Utilization and Development in Engineering and Technology, 2012Emotional Stress Indicator (ESI) kit is a wearable sensor device that used to measure the human stress level. Many people out there do not aware about their level of stress that will give a big impact in their life. So this study is aimed to design and develop an Emotional Stress Indicator (ESI) kit which can display stress level among people. This ESI kit is constructed based on human skin resistance which is changed upon condition. Human skin offers some resistance to current and voltage. The skin resistance changes with the emotional state of the body. From galvanic skin response theory, resistance varies inversely proportional to the stress. Stress level is high when the resistance of skin is less. In the relaxed state, the resistance offered by the skin is as high as 2 megaohms or more, which reduces to 500 kilo-ohms or less when the emotional stress is too high. The reduction in skin resistance is caused by an increased blood flow and permeability followed by the physiological changes during high stress. This increases the electrical conductivity of the skin
Insight into Knapsack Metabolite Ecology Database: A Comprehensive Source of Species: Voc-Biological Activity Relationships
No full textImplementation of an improved cellular neural network algorithm for brain tumor detection
No full text
- …
