Early Risk Prediction of Diabetes Based on GA-Stacking

Early risk prediction of diabetes could help doctors and patients to pay attention to the disease and intervene as soon as possible, which can effectively reduce the risk of complications. In this paper, a GA-stacking ensemble learning model is proposed to improve the accuracy of diabetes risk prediction. Firstly, genetic algorithms (GA) based on Decision Tree (DT) is used to select individuals with high adaptability, that is, a subset of attributes suitable for diabetes risk prediction. Secondly, the optimized convolutional neural network (CNN) and support vector machine (SVM) are used as the primary learners of stacking to learn attribute subsets, respectively. Then, the output of CNN and SVM is used as the input of the mate learner, the fully connected layer, for classification. Qingdao desensitization physical examination data from 1 January 2017 to 31 December 2019 is used, which includes body temperature, BMI, waist circumference, and other indicators that may be related to early diabetes. We compared the performance of GA-stacking with K-nearest neighbor (KNN), SVM, logistic regression (LR), Naive Bayes (NB), and CNN before and after adding GA through the average prediction time, accuracy, precision, sensitivity, specificity, and F1-score. Results show that prediction efficiency can be improved by adding GA. GA-stacking has higher prediction accuracy. Moreover, the strong generalization ability and high prediction efficiency of GA-stacking have also been verified on the early-stage diabetes risk prediction dataset published by UCI.

Fully-discrete, decoupled, second-order time-accurate and energy stable finite element numerical scheme of the Cahn-Hilliard binary surfactant model confined in the Hele-Shaw cell

We consider the numerical approximation of the binary fluid surfactant phase-field model confined in a Hele-Shaw cell, where the system includes two coupled Cahn-Hilliard equations and Darcy equations. We develop a fully-discrete finite element scheme with some desired characteristics, including linearity, second-order time accuracy, decoupling structure, and unconditional energy stability. The scheme is constructed by combining the projection method for the Darcy equation, the quadratization approach for the nonlinear energy potential, and a decoupling method of using a trivial ODE built upon the ``{zero-energy-contribution}" feature. The advantage of this scheme is that not only can all variables be calculated in a decoupled manner, but each equation has only constant coefficients at each time step. We strictly prove that the scheme satisfies the unconditional energy stability and give a detailed implementation process. Various numerical examples are further carried out to prove the effectiveness of the scheme, in which the benchmark Saffman-Taylor fingering instability problems in various flow regimes are simulated to verify the weakening effects of surfactant on surface tension.

Skin Lesion Segmentation in Dermoscopy Imagery

The main purpose of this study is to find an optimum method for segmentation of skin lesion images. In the present world, Skin cancer has proved to be the most deadly disease. The present research paper has developed a model which encompasses two gradations, the first being pre-processing for the reduction of unwanted artefacts like hair, illumination or many other by enhanced technique using threshold and morphological operations to attain higher accuracy and the second being segmentation by using k-mean with optimized Firefly Algorithm (FFA) technique. The online image database from the International Skin Imaging Collaboration (ISIC) archive dataset and dermatology service of Hospital Pedro Hispano (PH2) dataset has been used for input sample images. The parameters on which the proposed method is measured are sensitivity, specificity, dice coefficient, jacquard index, execution time, accuracy, error rate. From the results, authors have observed proposed model gives the average accuracy value of huge number of cancer images using ISIC dataset is 98.9% and using PH2 dataset is 99.1% with minimize average less error rate. It also estimates the dice coefficient value 0.993 using ISIC and 0.998 using PH2 datasets. However, the results for the rest of the parameters remain quite the same. Therefore the outcome of this model is highly reassuring.

Research on Combined Forecasting of Cooling Load Based on Advanced Cuckoo Search and Improved Particle Swarm Optimization

This study aims to improve the real-time accuracy of cooling load forecasting for heating, ventilating and air-conditioning systems (HVAC). This article takes the cooling load in a study room in Qingdao, China, which has been put into use for the first time, as the research object, and establishes a TRNSYS simulation platform to obtain sufficient load data. After using the mean influence value (MIV) and Spearman correlation coefficient to screen the characteristic variables, a hybrid algorithm (CS-CPSO) based on cuckoo search (CS) and particle swarm optimization (PSO) is proposed. Firstly, the iterative extremum is introduced to PSO, secondly, mechanism of levy random flight to generate random new nest in CS is used to initialize PSO particles adaptively, Finally, the optimization algorithm is applied to optimize the back propagation (BP) and support vector regression (SVR) load training models (WBP, WSVR, RBP, RSVR) of the working day (W) and rest day (R), respectively. The maximum grey correlation coefficient is utilized to establish the both models (CS-CPSO-CW, CS-CPSO-CR) of the working day (W) and rest day (R) based on CS-CPSO. In this way, the forecasting results are optimized and then compared with the regression prediction method. The analysis shows that the accuracy of the optimized BP model and SVR model are improved and fully considering the differences, the accuracy of the cooling load prediction is effectively promoted by separately, optimal selection between the prediction values of advanced models (CS-CPSO-WBP, CS-CPSO-WSVR and CS-CPSO-RBP, CS-CPSO-RSVR) gives full play to each algorithm’s advantages and makes up for their shortcomings, and it greatly increases reliability and improves accuracy, which in turn provides the basis for the optimal plan, control, and operation of the HVAC.

Artificial Intelligence for Creating Low Latency and Predictive Intrusion Detection with Security Enhancement in Power Systems

Advancement in network technology has vastly increased the usage of the Internet. Consequently, there has been a rise in traffic volume and data sharing. This has made securing a network from sophisticated intrusion attacks very important to preserve users’ information and privacy. Our research focuses on combating and detecting intrusion attacks and preserving the integrity of online systems. In our research we first create a benchmark model for detecting intrusions and then employ various combinations of feature selection techniques based upon ensemble machine learning algorithms to improve the performance of the intrusion detection system. The performance of our model was investigated using three evaluation metrics namely: elimination time, accuracy and F1-score. The results of the experiment indicated that the random forest feature selection technique had the minimum elimination time, whereas the support vector machine model had the best accuracy and F1-score. Therefore, conclusive evidence could be drawn that the combination of random forest and support vector machine is suitable for low latency and highly accurate intrusion detection systems.

Developing Procedural Generation Tools for Video Game Audio Designers

<p>In video games, audio is often a vital element in the creation of immersive gaming experiences. One set of techniques that are particularly well suited to attaining this immersion are procedural audio techniques. These techniques enable enhanced immersion through supporting close synchronisation between player and game state in ways that are difficult to achieve with other game audio techniques. While this is the case, there is a lack of GUI and script-based tools that support the use of such techniques. This thesis explores this lack, and documents the development of two new video game tools for the creation of procedurally generated audio. The first of these tools is a Musical Instrument Digital Interface (MIDI) library that supports the playback and real-time manipulation of MIDI files in the Unity game engine. The tool achieves real-time procedural audio, yet fails to meet required levels of time accuracy and is only a partial success. The second tool developed is a plugin hosting application that enables the use of the popular audio plugin format, VST2, in the Unity game engine. The tool succeeds in achieving VST2 effect plugin loading and, at the time of the completion of this thesis, is the only tool capable of embedding such plugins into applications developed in a major game engine. This will be of significant benefit to game developers who wish to achieve a high degree of immersivity in the music and sound design in their games.</p>

Validation of a Novel Wearable Multistream Data Acquisition and Analysis System for Ergonomic Studies

Nowadays, the growing interest in gathering physiological data and human behavior in everyday life scenarios is paralleled by an increase in wireless devices recording brain and body signals. However, the technical issues that characterize these solutions often limit the full brain-related assessments in real-life scenarios. Here we introduce the Biohub platform, a hardware/software (HW/SW) integrated wearable system for multistream synchronized acquisitions. This system consists of off-the-shelf hardware and state-of-art open-source software components, which are highly integrated into a high-tech low-cost solution, complete, yet easy to use outside conventional labs. It flexibly cooperates with several devices, regardless of the manufacturer, and overcomes the possibly limited resources of recording devices. The Biohub was validated through the characterization of the quality of (i) multistream synchronization, (ii) in-lab electroencephalographic (EEG) recordings compared with a medical-grade high-density device, and (iii) a Brain-Computer-Interface (BCI) in a real driving condition. Results show that this system can reliably acquire multiple data streams with high time accuracy and record standard quality EEG signals, becoming a valid device to be used for advanced ergonomics studies such as driving, telerehabilitation, and occupational safety.

Advanced CRISPR-Cas Effector Enzyme-Based Diagnostics for Infectious Diseases, Including COVID-19

Rapid and precise diagnostic tests can prevent the spread of diseases, including worldwide pandemics. Current commonly used diagnostic methods include nucleic-acid-amplification-based detection methods and immunoassays. These techniques, however, have several drawbacks in diagnosis time, accuracy, and cost. Nucleic acid amplification methods are sensitive but time-consuming, whereas immunoassays are more rapid but relatively insensitive. Recently developed CRISPR-based nucleic acid detection methods have been found to compensate for these limitations. In particular, the unique collateral enzymatic activities of Cas12 and Cas13 have dramatically reduced the diagnosis times and costs, while improving diagnostic accuracy and sensitivity. This review provides a comprehensive description of the distinct enzymatic features of Cas12 and Cas13 and their applications in the development of molecular diagnostic platforms for pathogen detection. Moreover, it describes the current utilization of CRISPR-Cas-based diagnostic techniques to identify SARS-CoV-2 infection, as well as recent progress in the development of CRISPR-Cas-based detection strategies for various infectious diseases. These findings provide insights into designing effective molecular diagnostic platforms for potential pandemics.

Developing Procedural Generation Tools for Video Game Audio Designers

<p>In video games, audio is often a vital element in the creation of immersive gaming experiences. One set of techniques that are particularly well suited to attaining this immersion are procedural audio techniques. These techniques enable enhanced immersion through supporting close synchronisation between player and game state in ways that are difficult to achieve with other game audio techniques. While this is the case, there is a lack of GUI and script-based tools that support the use of such techniques. This thesis explores this lack, and documents the development of two new video game tools for the creation of procedurally generated audio. The first of these tools is a Musical Instrument Digital Interface (MIDI) library that supports the playback and real-time manipulation of MIDI files in the Unity game engine. The tool achieves real-time procedural audio, yet fails to meet required levels of time accuracy and is only a partial success. The second tool developed is a plugin hosting application that enables the use of the popular audio plugin format, VST2, in the Unity game engine. The tool succeeds in achieving VST2 effect plugin loading and, at the time of the completion of this thesis, is the only tool capable of embedding such plugins into applications developed in a major game engine. This will be of significant benefit to game developers who wish to achieve a high degree of immersivity in the music and sound design in their games.</p>

Age-related decline in function of ON and OFF visual pathways

PurposeSimple psychophysical paradigm is available as a digital application in iOS devices such as iPad to measure the function of ON and OFF visual pathways. However, an age-matched normative database is not readily available. The purpose of the study is to evaluate the response of ON and OFF visual pathways as a function of age.Methods158 normal healthy adults (84 males and 74 females) whose age ranged 18-80 years participated in the study. None of them had any ocular disease (except cataract of grade II or less) and visual acuity of ≤ 20/25. Monocular testing (only one eye) was performed on the ‘EyeSpeed’ application on an iPad at 40cm distance. The targets ranged between 1 to 3 light or dark squares presented randomly in a noise background and participants responded by indicating the number of squares by touching the screen as fast as possible. The main outcome variables are reaction time, accuracy and performance index (1 / speed * accuracy).ResultsThe median reaction time was shorter (Median (IQR): 1.53s (0.49) [dark] Vs 1.76s (0.58) [light], p < 0.001) and accuracy was higher (97.21% (3.30) [dark] Vs 95.15% (5.10) [light], p < 0.001) for dark targets than the light targets. Performance index and reaction time for both target types significantly correlated with age (ρ = −0.41 to −0.43; p < 0.001).ConclusionsThis normative database will be useful to quantify disease-specific defects. More importantly, the ON pathway function can potentially serve as a surrogate for rod photoreceptor function.