Search

This paper presents a smart "e-nose" device to monitor indoor hazardous air. Indoor hazardous odor is a threat for seniors, infants, children, pregnant women, disabled residents, and patients. To overcome the limitations of using existing non-intelligent, slow-responding, deficient gas sensors, we propose a novel artificial-intelligent-based multiple hazard gas detector (MHGD) system that is mounted on a motor vehicle-based robot which can be remotely controlled. First, we optimized the sensor array for the classification of three hazardous gases, including cigarette smoke, inflammable ethanol, and off-flavor from spoiled food, using an e-nose with a mixing chamber. The mixing chamber can prevent the impact of environmental changes. We compared the classification results of all combinations of sensors, and selected the one with the highest accuracy (98.88%) as the optimal sensor array for the MHGD. The optimal sensor array was then mounted on the MHGD to detect and classify the target gases without a mixing chamber but in a controlled environment. Finally, we tested the MHGD under these conditions, and achieved an acceptable accuracy (70.00%).

Patients with sleep apnea (SA) are at increased risk of stroke and cardiovascular disease. Diagnosis of sleep apnea depends on the standard overnight polysomnography (PSG). In this study, the DREAM Apnea Database was used to evaluate the importance of the various features proposed in the literature for the analysis of sleep apnea. Various timeand frequency- domain features that include wavelet and power spectral density were extracted from ECG, EMG, EEG, airflow, SaO2, abdominal and thoracic recordings. Evaluation measures of one-way analysis of variance (ANOVA) and Rank-Sum test were used to test the performance of different features. The selected feature subset indicated that frequency-domain features outperform time-domain ones. This study will help in enhancing the detection accuracy of sleep apnea for the various polysomnography signals.

Lung cancer is one of the four major cancers in the world. Accurate diagnosing of lung cancer in the early stage plays an important role to increase the survival rate. Computed Tomography (CT)is an effective method to help the doctor to detect the lung cancer. In this paper, we developed a multi-level convolutional neural network (ML-CNN)to investigate the problem of lung nodule malignancy classification. ML-CNN consists of three CNNs for extracting multi-scale features in lung nodule CT images. Furthermore, we flatten the output of the last pooling layer into a one-dimensional vector for every level and then concatenate them. This strategy can help to improve the performance of our model. The ML-CNN is applied to ternary classification of lung nodules (benign, indeterminate and malignant lung nodules). The experimental results show that our ML-CNN achieves 84.81\% accuracy without any additional hand-craft preprocessing algorithm. It is also indicated that our model achieves the best result in ternary classification.

Cardiovascular disease clinical diagnosis is an essentially problem of pattern recognition. In the traditional intelligent diagnosis, the evaluation of classification algorithm is based on the final accuracy of the disease diagnosis. In this paper, a new classification method called Softmax regression model is proposed and it uses the known state data of two-layer neural network structure of the Softmax regression model for training and learning, and then calculate the probability of reclassification data belonging to each category. These categories are corresponding to the maximum probability and the classification result of the data to be classified. It provides a new method for classification of disease with higher speed and higher accuracy. Experiment is designed to compare with the K-nearest neighbours and BP neural networks, and also verify the classification accuracy of Softmax regression model. ECG data from MIT-BIH open database is considered for the experiment. The correct classification rate of the diagnosis reaches 94.44% which outperforms than K- nearest neighbor method (77.78%) and BP neural network (72.27%) in regards to the detection of the Cardiovascular disease.

This paper presents a two-class electroencephal-ography-based classification for classifying of driver fatigue (fatigue state versus alert state) from 43 healthy participants. The system uses independent component by entropy rate bound minimization analysis (ERBM-ICA) for the source separation, autoregressive (AR) modeling for the features extraction, and Bayesian neural network for the classification algorithm. The classification results demonstrate a sensitivity of 89.7%, a specificity of 86.8%, and an accuracy of 88.2%. The combination of ERBM-ICA (source separator), AR (feature extractor), and Bayesian neural network (classifier) provides the best outcome with a p-value < 0.05 with the highest value of area under the receiver operating curve (AUC-ROC = 0.93) against other methods such as power spectral density as feature extractor (AUC-ROC = 0.81). The results of this study suggest the method could be utilized effectively for a countermeasure device for driver fatigue identification and other adverse event applications.

This paper presents an improvement of classification performance for electroencephalography (EEG)-based driver fatigue classification between fatigue and alert states with the data collected from 43 participants. The system employs autoregressive (AR) modeling as the features extraction algorithm, and sparse-deep belief networks (sparse-DBN) as the classification algorithm. Compared to other classifiers, sparse-DBN is a semi supervised learning method which combines unsupervised learning for modeling features in the pre-training layer and supervised learning for classification in the following layer. The sparsity in sparse-DBN is achieved with a regularization term that penalizes a deviation of the expected activation of hidden units from a fixed low-level prevents the network from overfitting and is able to learn low-level structures as well as high-level structures. For comparison, the artificial neural networks (ANN), Bayesian neural networks (BNN), and original deep belief networks (DBN) classifiers are used. The classification results show that using AR feature extractor and DBN classifiers, the classification performance achieves an improved classification performance with a of sensitivity of 90.8%, a specificity of 90.4%, an accuracy of 90.6%, and an area under the receiver operating curve (AUROC) of 0.94 compared to ANN (sensitivity at 80.8%, specificity at 77.8%, accuracy at 79.3% with AUC-ROC of 0.83) and BNN classifiers (sensitivity at 84.3%, specificity at 83%, accuracy at 83.6% with AUROC of 0.87). Using the sparse-DBN classifier, the classification performance improved further with sensitivity of 93.9%, a specificity of 92.3%, and an accuracy of 93.1% with AUROC of 0.96. Overall, the sparse-DBN classifier improved accuracy by 13.8, 9.5, and 2.5% over ANN, BNN, and DBN classifiers, respectively.

Background: One of the key challenges of the biomedical cyber-physical system is to combine cognitive neuroscience with the integration of physical systems to assist people with disabilities. Electroencephalography (EEG) has been explored as a non-invasive method of providing assistive technology by using brain electrical signals., Methods: This paper presents a unique prototype of a hybrid brain computer interface (BCI) which senses a combination classification of mental task, steady state visual evoked potential (SSVEP) and eyes closed detection using only two EEG channels. In addition, a microcontroller based head-mounted battery-operated wireless EEG sensor combined with a separate embedded system is used to enhance portability, convenience and cost effectiveness. This experiment has been conducted with five healthy participants and five patients with tetraplegia., Results: Generally, the results show comparable classification accuracies between healthy subjects and tetraplegia patients. For the offline artificial neural network classification for the target group of patients with tetraplegia, the hybrid BCI system combines three mental tasks, three SSVEP frequencies and eyes closed, with average classification accuracy at 74% and average information transfer rate (ITR) of the system of 27 bits/min. For the real-time testing of the intentional signal on patients with tetraplegia, the average success rate of detection is 70% and the speed of detection varies from 2 to 4 s.

Accumulating evidence supports that acupuncture has been successfully used for the treatment of neurological disorders to improve cognitive function. This study was set to evaluate the efficacy of electroacupuncture (EA, using two acupoints: Baihui and Shenting) on clinical symptoms, cognitive function and brain-derived neurotrophic factor (BDNF) levels in patients with schizophrenia. Sixty-one inpatients diagnosed schizophrenia with DSM-IV criteria were recruited. The participants were randomly divided into an experimental group (n=30) and a control group (n=31). The patients were evaluated using the Positive and Negative Symptom Scale (PANSS), the Wisconsin Card Sorting Test (WCST) and Wechsler Memory Scale (WMS) at baseline and after EA treatment. There were no significant differences in the PANSS scores and serum BDNF levels between the experimental group and the control group, either at baseline or at the end of the 4-week study period. However, the EA treatment appeared to have significant benefits on memory and moderate benefits on executive functions and problem solving. Significant positive correlation was observed between the increase of BDNF levels and memory improvement after EA treatment. Our results indicated that EA treatment could improve cognitive function, and the cognitive benefits positively associate with serum BDNF levels in patients with schizophrenia., (Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.)

Introduction: Tenofovir disoproxil fumarate (TDF)-associated renal dysfunction may abate when TDF is replaced with abacavir (ABC). The extent to which the third drug atazanavir contributes to renal dysfunction is unclear., Methods: A retrospective analysis was conducted on adults who had plasma viral load (pVL)<200 copies/mL for≥six months while receiving TDF/lamivudine (3TC) - or TDF/emtricitabine (FTC)-based antiretroviral therapy (ART), then switched to ABC/3TC while retaining the third drug in the ART regimen. CD4, pVL, creatinine, estimated glomerular filtration rate (eGFR), serum phosphorus, urine albumin to creatinine ratio and serum lipids were compared between pre-switch baseline and 3, 6 and 12 months after the switch to ABC., Results: A total of 286 patients switched from TDF to ABC between 2004 and 2014: 232 (81%) male, median age 48 years (interquartile range (IQR) 42, 56). The third drug was atazanavir (± ritonavir) in 141 (49%) cases. The pVL was<50 copies/mL in 93 to 96% at all time points. Median serum creatinine was 93 µmol/L (IQR 80-111) at baseline and decreased to 88 µmol/L (IQR 78-98) at 12 months after the switch to ABC. Median eGFR increased from 74 (IQR 60-88) mL/min at baseline to 80 mL/min (IQR 69-89) at 12 months. Results were not significantly different between patients on atazanavir versus those on another third drug., Conclusions: Viral suppression was maintained among patients who switched from TDF/3TC or TDF/FTC to ABC/3TC. Serum creatinine and eGFR improved up to 12 months after switching to ABC/3TC, irrespective of whether or not patients were also receiving atazanavir±ritonavir.

Hypoglycemia is a very common in type 1 diabetic persons and can occur at any age. It is always threatening to the well-being of patients with Type 1 diabetes mellitus (T1DM) since hypoglycemia leads to seizures or loss of consciousness and the possible development of permanent brain dysfunction under certain circumstances. Because of that, an accurate continuing hypoglycemia monitoring system is a very important medical device for diabetic patients. In this paper, we proposed a non-invasive hypoglycemia monitoring system using the physiological parameters of electrocardiography (ECG) signal. To enhance the detection accuracy, extreme learning machine (ELM) is developed to recognize the presence of hypoglycemia. A clinical study of 16 children with T1DM is given to illustrate the good performance of ELM., (Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.)

This paper presents the classification of a three-class mental task-based brain-computer interface (BCI) that uses the Hilbert-Huang transform for the features extractor and fuzzy particle swarm optimization with cross-mutated-based artificial neural network (FPSOCM-ANN) for the classifier. The experiments were conducted on five able-bodied subjects and five patients with tetraplegia using electroencephalography signals from six channels, and different time-windows of data were examined to find the highest accuracy. For practical purposes, the best two channel combinations were chosen and presented. The three relevant mental tasks used for the BCI were letter composing, arithmetic, and Rubik's cube rolling forward, and these are associated with three wheelchair commands: left, right, and forward, respectively. An additional eyes closed task was collected for testing and used for on-off commands. The results show a dominant alpha wave during eyes closure with average classification accuracy above 90%. The accuracies for patients with tetraplegia were lower compared to the able-bodied subjects; however, this was improved by increasing the duration of the time-windows. The FPSOCM-ANN provides improved accuracies compared to genetic algorithm-based artificial neural network (GA-ANN) for three mental tasks-based BCI classifications with the best classification accuracy achieved for a 7-s time-window: 84.4% (FPSOCM-ANN) compared to 77.4% (GA-ANN). More comparisons on feature extractors and classifiers were included. For two-channel classification, the best two channels were O1 and C4, followed by second best at P3 and O2, and third best at C3 and O2. Mental arithmetic was the most correctly classified task, followed by mental Rubik's cube rolling forward and mental letter composing.

This paper focuses on the hybridization technology using rough sets concepts and neural computing for decision and classification purposes. Based on the rough set properties, the lower region and boundary region are defined to partition the input signal to a consistent (predictable) part and an inconsistent (random) part. In this way, the neural network is designed to deal only with the boundary region, which mainly consists of an inconsistent part of applied input signal causing inaccurate modeling of the data set. Owing to different characteristics of neural network (NN) applications, the same structure of conventional NN might not give the optimal solution. Based on the knowledge of application in this paper, a block-based neural network (BBNN) is selected as a suitable classifier due to its ability to evolve internal structures and adaptability in dynamic environments. This architecture will systematically incorporate the characteristics of application to the structure of hybrid rough-block-based neural network (R-BBNN). A global training algorithm, hybrid particle swarm optimization with wavelet mutation is introduced for parameter optimization of proposed R-BBNN. The performance of the proposed R-BBNN algorithm was evaluated by an application to the field of medical diagnosis using real hypoglycemia episodes in patients with Type 1 diabetes mellitus. The performance of the proposed hybrid system has been compared with some of the existing neural networks. The comparison results indicated that the proposed method has improved classification performance and results in early convergence of the network.

A system using electroencephalography (EEG) signals could enhance the detection of mental fatigue while driving a vehicle. This paper examines the classification between fatigue and alert states using an autoregressive (AR) model-based power spectral density (PSD) as the features extraction method and fuzzy particle swarm optimization with cross mutated of artificial neural network (FPSOCM-ANN) as the classification method. Using 32-EEG channels, results indicated an improved overall specificity from 76.99% to 82.02%, an improved sensitivity from 74.92 to 78.99% and an improved accuracy from 75.95% to 80.51% when compared to previous studies. The classification using fewer EEG channels, with eleven frontal sites resulted in 77.52% for specificity, 73.78% for sensitivity and 75.65% accuracy being achieved. For ergonomic reasons, the configuration with fewer EEG channels will enhance capacity to monitor fatigue as there is less set-up time required.

Hypoglycemia is a common side-effect of insulin therapy for patients with type 1 diabetes mellitus (T1DM) and is the major limiting factor to maintain tight glycemic control. The deficiency in glucose counter-regulation may even lead to severe hypoglycaemia. It is always threatening to the well-being of patients with T1DM since more severe hypoglycemia leads to seizures or loss of consciousness and the possible development of permanent brain dysfunction under certain circumstances. Thus, an accurate early detection on hypoglycemia is an important research topic. With the use of new emerging technology, an extreme learning machine (ELM) based hypoglycemia detection system is developed to recognize the presence of hypoglycemic episodes. From a clinical study of 16 children with T1DM, natural occurrence of nocturnal hypoglycemic episodes are associated with increased heart rates (p <; 0.06) and increased corrected QT intervals (p <; 0.001). The overall data were organized into a training set with 8 patients (320 data points) and a testing set with 8 patients (269 data points). By using the ELM trained feed-forward neural network (ELM-FFNN), the testing sensitivity (true positive) and specificity (true negative) for detection of hypoglycemia is 78 and 60% respectability.

Identification of protein-ligand binding site is an important task in structure-based drug design and docking algorithms. In the past two decades, different approaches have been developed to predict the binding site, such as the geometric, energetic, and sequence-based methods. When scores are calculated from these methods, the algorithm for doing classification becomes very important and can affect the prediction results greatly. In this paper, the support vector machine (SVM) is used to cluster the pockets that are most likely to bind ligands with the attributes of geometric characteristics, interaction potential, offset from protein, conservation score, and properties surrounding the pockets. Our approach is compared to LIGSITE, LIGSITE(CSC), SURFNET, Fpocket, PocketFinder, Q-SiteFinder, ConCavity, and MetaPocket on the data set LigASite and 198 drug-target protein complexes. The results show that our approach improves the success rate from 60 to 80 percent at AUC measure and from 61 to 66 percent at top 1 prediction. Our method also provides more comprehensive results than the others.

Hypoglycemia is dangerous and considered as a limiting factor of the glycemic control therapy for patients with type 1 diabetes mellitus (T1DM). Nocturnal hypoglycemia is especially feared because early warning symptoms are unclear during sleep so an episode of hypoglycemia may lead to a fatal effect on patients. The main objective of this paper is to explore the correlation between hypoglycemia and electroencephalography (EEG) signals. To do this, the EEG of five T1DM adolescents from an overnight insulin-induced study is analyzed by spectral analysis to extract four different parameters. We aim to explore the response of these parameters during the clamp study which includes three main phases of normal, hypoglycemia and recovery. We also look at data at the blood glucose level (BGL) of 3.3-3.9 mmol/l to find a threshold to distinguish between non-hypoglycemia and hypoglycemia states. The results show that extracted EEG parameters are highly correlated with patients' conditions during the study. It is also shown that at the BGL of 3.3 mmol/l, responses to hypoglycemia in EEG signals start to significantly occur.

Hypoglycemia is the most common but highly feared complication induced by the intensive insulin therapy in patients with type 1 diabetes mellitus (T1DM). Nocturnal hypoglycemia is dangerous because sleep obscures early symptoms and potentially leads to severe episodes which can cause seizure, coma, or even death. It is shown that the hypoglycemia onset induces early changes in electroencephalography (EEG) signals which can be detected non-invasively. In our research, EEG signals from five T1DM patients during an overnight clamp study were measured and analyzed. By applying a method of feature extraction using Fast Fourier Transform (FFT) and classification using neural networks, we establish that hypoglycemia can be detected efficiently using EEG signals from only two channels. This paper demonstrates that by implementing a training process of combining genetic algorithm and Levenberg-Marquardt algorithm, the classification results are improved markedly up to 75% sensitivity and 60% specificity on a separate testing set.

This paper presents a three-class mental task classification for an electroencephalography based brain computer interface. Experiments were conducted with patients with tetraplegia and able bodied controls. In addition, comparisons with different time-windows of data were examined to find the time window with the highest classification accuracy. The three mental tasks used were letter composing, arithmetic and imagery of a Rubik's cube rolling forward; these tasks were associated with three wheelchair commands: left, right and forward, respectively. An eyes closed task was also recorded for the algorithms testing and used as an additional on/off command. The features extraction method was based on the spectrum from a Hilbert-Huang transform and the classification algorithm was based on an artificial neural network with a fuzzy particle swarm optimization with cross-mutated operation. The results show a strong eyes closed detection for both groups with average accuracy at above 90%. The overall result for the combined groups shows an improved average accuracy of 70.6% at 1s, 74.8% at 2s, 77.8% at 3s, 79.6% at 4s and 81.4% at 5s. The accuracy for individual groups were lower for patients with tetraplegia compared to the able-bodied group, however, does improve with increased duration of the time-window.

The study presents a dielectrophoretic cell separation method via three-dimensional (3D) nonuniform electric fields generated by employing a periodic array of discrete but locally asymmetric triangular bottom microelectrodes and a continuous top electrode. Traversing through the microelectrodes, heterogeneous cells are electrically polarized to experience different strengths of positive dielectrophoretic forces, in response to the 3D nonuniform electric fields. The cells that experience stronger positive dielectrophoresis are streamed further in the perpendicular direction to the fluid flow, leaving the cells that experience weak positive dielectrophoresis, which continue to traverse the microelectrode array essentially along the laminar flow streamlines. The proposed method has achieved 87.3% pure live cells harvesting efficiency from a live/dead NIH-3T3 cells mixture, and separation of MG-63 cells from erythrocytes with a separation efficiency of 82.8%. The demonstrated cell separation shows promising applications of the DEP separator for cell separation in a continuous mode.

Hypoglycemia is the most common but highly feared side effect of the insulin therapy for patients with Type 1 Diabetes Mellitus (T1DM). Severe episodes of hypoglycemia can lead to unconsciousness, coma, and even death. The variety of hypoglycemic symptoms arises from the activation of the autonomous central nervous system and from reduced cerebral glucose consumption. In this study, electroencephalography (EEG) signals from five T1DM patients during an overnight clamp study were measured and analyzed. By applying a method of feature extraction using Fast Fourier Transform (FFT) and classification using neural networks, we establish that hypoglycemia can be detected non-invasively using EEG signals from only two channels. This paper demonstrates that a significant advantage can be achieved by implementing adaptive training. By adapting the classifier to a previously unseen person, the classification results can be improved from 60% sensitivity and 54% specificity to 75% sensitivity and 67% specificity.

Hypoglycemia, or low blood glucose, is the most common complication experienced by Type 1 diabetes mellitus (T1DM) patients. It is dangerous and can result in unconsciousness, seizures and even death. The most common physiological parameter to be effected from hypoglycemic reaction are heart rate (HR) and correct QT interval (QTc) of the electrocardiogram (ECG) signal. Based on physiological parameters, an intelligent diagnostics system, using the hybrid approach of adaptive neural fuzzy inference system (ANFIS), is developed to recognize the presence of hypoglycemia. The proposed ANFIS is characterized by adaptive neural network capabilities and the fuzzy inference system. To optimize the membership functions and adaptive network parameters, a global learning optimization algorithm called hybrid particle swarm optimization with wavelet mutation (HPSOWM) is used. For clinical study, 15 children with Type 1 diabetes volunteered for an overnight study. All the real data sets are collected from the Department of Health, Government of Western Australia. Several experiments were conducted with 5 patients each, for a training set (184 data points), a validation set (192 data points) and a testing set (153 data points), which are randomly selected. The effectiveness of the proposed detection method is found to be satisfactory by giving better sensitivity, 79.09% and acceptable specificity, 51.82%.

This paper presents a non-motor imagery tasks classification electroencephalography (EEG) based brain computer interface (BCI) for wheelchair control. It uses only two EEG channels and a better feature extractor to improve the portability and accuracy in the practical system. In addition, two different features extraction methods, power spectral density (PSD) and Hilbert Huang Transform (HHT) energy are compared to find a better method with improved classification accuracy using a Genetic Algorithm (GA) based neural network classifier. The results from five subjects show that using the original eight channels with three tasks, accuracy between 76% and 85% is achieved. With only two channels in combination with the best chosen task using a PSD feature extractor, the accuracy is reduced to between 65% and 79%. However, the HHT based method provides an improved accuracy between 70% and 84% for the classification of three discriminative tasks using two EEG channels.

For an electroencephalograph (EEG)-based brain computer interface (BCI) application, the use of gel on the hair area of the scalp is needed for low impedance electrical contact. This causes the set up procedure to be time consuming and inconvenient for a practical BCI system. Moreover, studies of other cortical areas are useful for BCI development. As a more convenient alternative, this paper presents the EEG based-BCI using the prefrontal cortex non-hair area to classify mental tasks at three electrodes position: Fp1, Fpz and Fp2. The relevant mental tasks used are mental arithmetic, ringtone, finger tapping and words composition with additional tasks which are baseline and eyes closed. The feature extraction is based on the Hilbert Huang Transform (HHT) energy method and the classification algorithm is based on an artificial neural network (ANN) with genetic algorithm (GA) optimization. The results show that the dominant alpha wave during eyes closed can still clearly be detected in the prefrontal cortex. The classification accuracy for five subjects, mental tasks vs. baseline task resulted in average accuracy is 73% and the average accuracy for pairs of mental task combinations is 72%.

The control of messenger RNA (mRNA) translation and degradation is important in regulation of eukaryotic gene expression. In the general and specialized mRNA decay pathways which involve 5(') →3(') decay, decapping is the central step because it is the controlling gate preceding the actual degradation of mRNA and is a site of numerous control inputs. Removal of the cap structure is catalyzed by a decapping holoenzyme composed of the catalytic Dcp2 subunit and the coactivator Dcp1. Decapping is regulated by decapping activators and inhibitors. Recent structural and kinetics studies indicated that Dcp1 and the substrate RNA promote the closed form of the enzyme and the catalytic step of decapping is rate limiting and accelerated by Dcp1. The conformational change between the open and closed decapping enzyme is important for controlling decapping, and regulation of this transition has been proposed to be a checkpoint for determining the fate of mRNAs. Here we summarize the past and recent advances on the structural and functional studies of protein factors involved in regulating mRNA decapping., (Copyright © 2010 John Wiley & Sons, Ltd.)

In this paper, evolvable block based neural network (BBNN) is presented for detection of hypoglycemia episodes. The structure of BBNN consists of a two-dimensional (2D) array of fundamental blocks with four variable input-output nodes and weight connections. Depending on the structure settings, each block can have one of four different internal configurations. To provide early detection of hypoglycemia episodes, the physiological parameters such as heart rate (HR) and corrected QT interval (QTc) of electrocardiogram (ECG) signal are used as the inputs of BBNN. The overall structure and weights of BBNN are optimized by an evolutionary algorithm called hybrid particle swarm optimization with wavelet mutation (HPSOWM). The optimized structures and weights of BBNN are capable to compensate large variations of ECG patterns caused by individual and temporal difference since a fixed structure classifiers are easy to fail to trace ECG signals with large variations. The ECG data of 15 patients are organized into a training set, a testing set and a validation set, each of which has randomly selected 5 patients. The simulation results shows that the proposed algorithm, BBNN with HPSOWM can successfully detect the hypoglycemic episodes in T1DM in term of testing sensitivity (76.74%) and test specificity (50.91%).

Hypoglycaemia is a serious side effect of insulin therapy in patients with diabetes. We measure physiological parameters (heart rate, corrected QT interval of the electrocardiogram (ECG) signal) continuously to provide early detection of hypoglycemic episodes in Type 1 diabetes mellitus (T1DM) patients. Based on the physiological parameters, an evolved fuzzy reasoning model (FRM) to recognize the presence of hypoglycaemic episodes is developed. To optimize the fuzzy rules and the fuzzy membership functions of FRM, an evolutionary algorithm called hybrid particle swarm optimization with wavelet mutation operation is investigated. All data sets are collected from Department of Health, Government of Western Australia for a clinical study. The results show that the proposed algorithm performs well in terms of the clinical sensitivity and specificity.

Nuclear export of mRNA is a critical event in mRNA biogenesis. Passage of mature messenger ribonucleoproteins (mRNPs) through nuclear pore complexes (NPCs) is facilitated by the Mex67/Mtr2 heterodimer. At the NPC cytoplasmic face, the DEAD-box RNA helicase Dbp5 remodels mRNPs by removing Mex67/Mtr2. This remodeling process prevents mRNPs from returning to the nucleus, thereby imposing unidirectionality on mRNA export. Biochemical studies show that Gle1 and inositol hexaphosphate (IP6) activate Dbp5's ATPase activity at the cytoplasmic face of NPC, therefore providing critical spatial regulation of mRNP remodeling during directional transport. Recent structural studies on Dbp5 in free form and in complex with its ligands (ADP, AMPPNP/RNA) as well as with cytoplasmic nucleoporin Nup214 reveal that the binding of ADP or AMPPNP/RNA induces large conformational changes of Dbp5, and RNA and NUP214 bind to Dbp5 in a mutually exclusive manner. These structural data combined with complementary functional analysis significantly advance our understanding on the mechanism governing mRNA export albeit some key issues remain elusive.

mRNA decay is critical for the regulation of gene expression and the quality control of mRNA. RNA helicases play a key role in eukaryotic mRNA decay. In general, RNA helicases utilize the energy of ATP hydrolysis to remodel RNA or RNA-protein complexes, resulting in the separation of RNA duplex strand and/or displacement of proteins from the RNA molecule in RNP (ribonucleoprotein) complexes. Recently, high-resolution crystal structures of RNA helicases in mRNA decay have contributed a great deal to our understanding of these key molecules. In the present review, we focus on the structural and mechanistic aspects of three RNA helicases, Dhh1, Upf1 and eIF4AIII, that are involved in eukaryotic mRNA decay.

Due to the rapid urbanization of the world population, a better understanding of the detrimental effects of exposure to urban air pollution on chronic lung disease is necessary. Strong epidemiological evidence suggests that exposure to particulate matter (PM) air pollution causes exacerbations of pre-existing lung conditions, such as, chronic obstructive pulmonary disease (COPD) resulting in increased morbidity and mortality. However, little is known whether a chronic, low-grade exposure to ambient PM can cause the development and progression of COPD. The deposition of PM in the respiratory tract depends predominantly on the size of the particles, with larger particles deposited in the upper and larger airways and smaller particles penetrating deep into the alveolar spaces. Ineffective clearance of this PM from the airways could cause particle retention in lung tissues, resulting in a chronic, low-grade inflammatory response that may be pathogenetically important in both the exacerbation, as well as, the progression of lung disease. This review focuses on the adverse effects of exposure to ambient PM air pollution on the exacerbation, progression, and development of COPD.

Edc3 is an enhancer of decapping and serves as a scaffold that aggregates mRNA ribonucleoproteins together for P-body formation. Edc3 forms a network of interactions with the components of the mRNA decapping machinery and has a modular domain architecture consisting of an N-terminal Lsm domain, a central FDF domain, and a C-terminal YjeF-N domain. We have determined the crystal structure of the N-terminally truncated human Edc3 at a resolution of 2.2 A. The structure reveals that the YjeF-N domain of Edc3 possesses a divergent Rossmann fold topology that forms a dimer, which is supported by sedimentation velocity and sedimentation equilibrium analysis in solution. The dimerization interface of Edc3 is highly conserved in eukaryotes despite the overall low sequence homology across species. Structure-based site-directed mutagenesis revealed dimerization is required for efficient RNA binding, P-body formation, and likely for regulating the yeast Rps28B mRNA as well, suggesting that the dimeric form of Edc3 is a structural and functional unit in mRNA degradation.

A new hybrid particle swarm optimization (PSO) that incorporates a wavelet-theory-based mutation operation is proposed. It applies the wavelet theory to enhance the PSO in exploring the solution space more effectively for a better solution. A suite of benchmark test functions and three industrial applications (solving the load flow problems, modeling the development of fluid dispensing for electronic packaging, and designing a neural-network-based controller) are employed to evaluate the performance and the applicability of the proposed method. Experimental results empirically show that the proposed method significantly outperforms the existing methods in terms of convergence speed, solution quality, and solution stability.

Background: Airflow limitation in COPD is due to a variable combination of small airway obstruction and centrilobular emphysema (CLE) and/or panlobular emphysema (PLE), but the relationship between these three different phenotypes is poorly understood. This study compares the severity of small airway obstruction in both forms of emphysema and determines its relationship with FEV(1)., Methods: We compared the lung histology of nonsmoking control subjects without emphysema (n = 10) to that of patients with CLE (n = 30) and PLE with (n = 8) and without alpha(1)-antitrypsin (AAT) deficiency (n = 11). The degree of airspace enlargement was measured using the mean interalveolar wall distance (IAWD) [mean linear intercept, Lm], and the evenness of airspace destruction was assessed by the coefficient of variation (CV) of the IAWD. The severity of small airway obstruction was determined by dividing total wall area by the length of the basement membrane to obtain wall thickness., Results: Lm was greater in all three subgroups of emphysema than in control subjects, and in AAT deficiency than in PLE or CLE. The CV of IAWD was greater in AAT deficiency and CLE than in control subjects and in CLE than in AAT deficiency or PLE. Although small airway wall thickness was greater in CLE and PLE with AAT deficiency than in control subjects, the association between wall thickness and both Lm and FEV(1) was observed only in CLE., Conclusions: Small airway wall thickening occurs in CLE and PLE with AAT deficiency but is more closely associated with degree of emphysema and airflow limitation in CLE.

To evaluate the role of inherited gene variations in GRIN1 (glutamate receptor, ionotropic NMDA1), BDNF (brain derived neurotrophic factor) genes in human bipolar disorder, we selected 4 single nucleotide polymorphisms in GRIN1, BDNF (2 SNPs in each gene) and made SNPs analysis in 100 unrelated cases and 100 controls by TaqMan. Then we compared genotypes differences between cases and controls. The software SHEsis was also used to make haplotype analysis. The significant results were obtained, showing that the SNPs in GRIN1 gene were related to the BP (P < 0.05). In addition, the combined haplotype T/G had a significant difference in the two groups (P < 0.05). The SNPs in BDNF gene showed no statistical significance. These results confirm that the GRIN1 gene confers susceptibility to bipolar disorder.

Purpose: To examine the possibility that structural damage to the brain may play a role in the pathogenesis of schizophrenia by measuring the level of plasma S-100B, a calcium-binding protein found predominantly in the cytosol of glial cells., Method: Fifty-seven Chinese psychiatric inpatients who met DSM-IV diagnosis of schizophrenia and 60 healthy controls were enrolled in the study. Patients were assessed with the Positive and Negative Symptoms Scale (PANSS) at admission and at 12 weeks after treatment. Plasma samples were collected from patients and controls and S-100B protein was assayed using ELISA., Results: (1) 29 of 57 patients (50.9%) showed increased S-100B level compared to the mean level of 60 healthy controls (p<0.005) vs. only 1 of 60 (1.67%) controls. The S-100B levels of unmedicated (0.119+/-0.059microg/L) and medicated patients (0.117+/-.0.057microg/L) were significantly higher than controls (0.067+/-0.022microg/L, both p<0.001), and S-100B levels of unmedicated patients were higher than those of medicated patients (p=0.024); (2) at admission, S-100B level was positively correlated with total score of PANSS (r=0.269, p=0.043), especially with negative subscore of PANSS (r=0.306, p=0.021), but the correlation was no longer present after patients were treated by anti-psychotic agents., Conclusion: The S-100B levels of patients with schizophrenia are significantly higher than that of healthy controls, and the S-100B level is associated with severity of psychopathology, particularly negative symptoms, indicating that patients with schizophrenia may suffer structural damage to central nervous system. The concentration of S-100B may also be associated with treatment progress.

The Sprouty proteins are increasingly being recognized to be deregulated in various types of cancers. This deregulation is often associated with aberrant signaling of receptor tyrosine kinases and its downstream effectors, leading to the mitogen-activated protein kinase (MAPK) signaling pathway. In human hepatocellular carcinoma, where the MAPK activity is enhanced via multiple hepatocarcinogenic factors, we observed a consistent reduced expression of the sprouty 2 (Spry2) transcript and protein in malignant hepatocytes compared with normal or cirrhotic hepatocytes. The expression pattern of Spry2 in hepatocellular carcinoma resembles that of several potential tumor markers of hepatocellular carcinoma and also that of several angiogenic factors and growth factor receptors. In contrast to previous studies of Spry2 down-regulation in other cancers, we have ruled out loss of heterozygosity or the methylation of promoter sites, two common mechanisms responsible for the silencing of genes with tumor suppressor properties. Functionally, we show that Spry2 inhibits both extracellular signal-regulated kinase signaling as well as proliferation in hepatocellular carcinoma cell lines, whereas knocking down Spry2 levels in NIH3T3 cells causes mild transformation. Our study clearly indicates a role for Spry2 in hepatocellular carcinoma, and an understanding of the regulatory controls of its expression could provide new means of regulating the angiogenic switch in this hypervascular tumor, thereby potentially controlling tumor growth.

This paper presents a fuzzy-tuned neural network, which is trained by an improved genetic algorithm (GA). The fuzzy-tuned neural network consists of a neural-fuzzy network and a modified neural network. In the modified neural network, a neuron model with two activation functions is used so that the degree of freedom of the network function can be increased. The neural-fuzzy network governs some of the parameters of the neuron model. It will be shown that the performance of the proposed fuzzy-tuned neural network is better than that of the traditional neural network with a similar number of parameters. An improved GA is proposed to train the parameters of the proposed network. Sets of improved genetic operations are presented. The performance of the improved GA will be shown to be better than that of the traditional GA. Some application examples are given to illustrate the merits of the proposed neural network and the improved GA.

Japanese encephalitis virus (JEV) transmission in Singapore appeared to have ceased after pig farming in Singapore was phased out from the early 1980s. However, the recent detection of neutralizing antibodies to JEV in a population of wild boars in an offshore island, as well as the notification of two human cases of JE in Singapore in 2001, prompted us to reconsider the presence and hence the public health threat of JEV in Singapore. We report here a serological study of animals, birds and humans for neutralizing antibodies to JEV. The results indicate that JEV may still be actively transmitted in the peripheral part of the Singapore island and that regular serological surveys of farm animals and birds, such as chickens, may be useful to further elucidate the activity of JEV in Singapore.

This paper presents the tuning of the structure and parameters of a neural network using an improved genetic algorithm (GA). It is also shown that the improved GA performs better than the standard GA based on some benchmark test functions. A neural network with switches introduced to its links is proposed. By doing this, the proposed neural network can learn both the input-output relationships of an application and the network structure using the improved GA. The number of hidden nodes is chosen manually by increasing it from a small number until the learning performance in terms of fitness value is good enough. Application examples on sunspot forecasting and associative memory are given to show the merits of the improved GA and the proposed neural network.

Purpose: To determine the importance of polyp size, orientation to the scan plane, collimation, scanner type (single or multislice helical), and radiation dose on computed tomography (CT) colonography computer-aided detection., Materials and Methods: Eight tissue-equivalent simulated polyps were placed into the interior of an air-filled acrylic tube placed within a water-filled box. Their sizes, expressed by diameter and height in millimeters, were 10 x 10, 10 x 7, 10 x 5, 10 x 3, 7 x 7, 7 x 5, 7 x 3, and 5 x 5. Detection of the polyps was performed by applying our prototype automated polyp detector software to 48 CT colonography data sets of the phantom acquired with different CT scanner settings., Results: We detected at least six of the eight polyps in 47 of 48 experiments. The two most frequently undetected polyps (7 x 7 and 5 x 5) had extreme eccentricity (their height was twice the radius of the base) and were most commonly missed for 90 degrees tube orientation, 5-mm collimation, and high table speed. False-positive detections occurred in only 5 of 48 experiments., Conclusion: Clinically significant 10-mm polyps can be detected with 100% sensitivity in all orientations, doses, collimations, and modes that we examined.

The application of green fluorescent protein (GFP) to identify the portal(s) of entry of bacterial pathogens in animal hosts was studied using the fish pathogen Edwardsiella tarda and blue gourami, Trichogaster trichopterus. An immersion challenge model was utilized to mimic natural infection conditions in fish. Gastrointestinal tract, gills and the body surface of fish were found to be the sites of entry of virulent E. tarda (PPD130/91) by histological and infection kinetics studies. On the other hand, avirulent E. tarda (PPD125/87) was mainly found in the gastrointestinal tract, and the bacterial population in tissue declined over a period of 7 days.

For differentiation of glomerular from urological hematuria more accurately, a new morphological classification of urinary erythrocytes was studied in 74 cases of glomerular and 58 cases of urological hematuria. For each urine sample, 100 urinary erythrocytes were observed with phase-contrast microscopy and classified into 5 "glomerular" shapes (G1-G5), 5 "urological" shapes (N1-N5) and an unclassified shape. The result was that occurrence of G1, G2, G3, G4, G5 or unclassified shape group appeared significantly (P < 0.01) higher in glomerular diseases than in urological diseases, and among them G1 was the most specific shape for glomerular hematuria. Using percentage of sigma G (G1 + G2 + G3 + G4 + G5) and setting the cut-off at 20%, the sensitivity and specificity for the diagnosis of glomerular diseases were 95.9%. When percentage of G1 (doughnut-like cell with one or more blebs) was used at a cut-off of 1%, sensitivity and specificity were 75.7% and 96.5% respectively. These results were more satisfactory as compared with those in most of the previous reports. Moreover, this new classification is more objective, accurate and clear.

To find out the relationship between soluble interleukin 2 receptor (sIL-2R) or free light chain immunoglobulins (FLCI) and the activity of lupus nephritis (LN), we determined sIL-2R by ELISA and FLCI by immunodiffusion in the urine of 30 patients with LN and 20 normal persons. We also studied the correlation of sIL-2R levels with clinical and serologic findings over 3 months in the patients. sIL-2R was significantly higher in the active LN patients (160 +/- 108U/ml) than in the normal controls (85 +/- 19U/ml, P < 0.01) and in the inactive LN patients (92 +/- 23 U/ml, P < 0.05), but their serum complements did not change significantly. The positive rate of urine FLCI was higher in the active LN patients than in the inactive LN patients (77% to 15%, P < 0.01) and the normal controls (negative). These results suggest that the urine sIL-2R and FLCI are sensitive markers for disease activity in LN.