Type 2 Diabetes Risk Prediction Using Deep Convolutional Neural Network Based-Bayesian Optimization

Diabetes mellitus is a long-term condition characterized by hyperglycemia. It could lead to plenty of difficulties. According to rising morbidity in recent years, the world’s diabetic patients will exceed 642 million by 2040, implying that one out of every ten persons will be diabetic. There is no doubt that this startling figure requires immediate attention from industry and academia to promote innovation and growth in diabetes risk prediction to save individuals’ lives. Due to its rapid development, deep learning (DL) was used to predict numerous diseases. However, DL methods still suffer from their limited prediction performance due to the hyperparameters selection and parameters optimization. Therefore, the selection of hyper-parameters is critical in improving classification performance. This study presents Convolutional Neural Network (CNN) that has achieved remarkable results in many medical domains where the Bayesian optimization algorithm (BOA) has been employed for hyperparameters selection and parameters optimization. Two issues have been investigated and solved during the experiment to enhance the results. The first is the dataset class imbalance, which is solved using Synthetic Minority Oversampling Technique (SMOTE) technique. The second issue is the model's poor performance, which has been solved using the Bayesian optimization algorithm. The findings indicate that the Bayesian based-CNN model superbases all the state-of-the-art models in the literature with an accuracy of 89.36%, F1-score of 0.88.6, and Matthews Correlation Coefficient (MCC) of 0.88.6.     

Decision analysis of multi-pollutant control strategy for coal-fired power plant in Malaysia

The promulgation of Environmental Quality (Clean Air) Regulations 2014 on emissions from coal-fired power plants in Malaysia has prompted power plant operators to adopt emission control strategy that complies with the new emission limits. Currently, various emission control strategies are available to achieve the desired emission level. Each strategy offers unique advantages and disadvantages, depending on the objective of emissions control, process nature, and constraints on the resources incurred. To address this challenge, a proper decision-making analysis needs to be performed. In this paper, a systematic decision analysis methodology is proposed to select the most effective multi-pollutant control strategy that is compatible for coal-fired power plants in Malaysia. The methodology includes: (1) identification of pollutant emission from the plant under study and comparison with the stipulated emission limits, (2) establishment of emission factors, (3) selection of multi-pollutant control strategy, (4) identification of emission reduction factor for the pollutants and control technologies of interest, (5) determination of emission level from the selected multi-pollutant control strategy, and (6) prediction of ground-level concentration of pollutants. The decision analysis methodology is applied to a real case study of coal-fired power plant in Malaysia, which also currently faces a dilemma to comply with the additional and more stringent emission limits stipulated in the Environmental Quality (Clean Air) Regulations 2014. The proposed method is applicable for both the process concept under the design phase as well as the existing process plant.     

Zero-current Switching Series Resonant High-voltage DC-DC Converter with Series-connected Primary Windings of Center-tapped Transformer

Abstract—This article proposes a novel zero-current switching series resonant inverter-fed voltage multiplier based high-voltage DC-DC converter. The series resonant inverter in the proposed topology has two power switches (insulated-gate bipolar transistors), two resonant capacitors, and only one high-voltage transformer with center-tapped primary windings. The power switches are connected in the form of a half-bridge network. The leakage inductances of the transformer's primary windings together with resonant capacitors form two series resonant circuits. The series resonant circuits are fed alternately by operating power switches with an interleaved half-switching cycle. The secondary winding of the high-voltage transformer is connected to a voltage multiplier circuit to rectify and boost the voltage. The converter operates in discontinuous conduction mode, and its output voltage is regulated by pulse-frequency modulation. Therefore, all the power switches turn ON and OFF at the zero-current switching condition. The main features of the proposed converter are lower power loss, less cost, and smaller size compared to previously proposed series resonant high-voltage DC-DC converters. The experimental results of a 130-W prototype of the proposed converter are presented both for dynamic and steady-state operation. The results confirm the excellent operation and performance of the converter.     

Effects of dynamic vulcanization on tensile,morphological, and swelling properties of poly(vinyl chloride) (PVC)/epoxidized natural rubber (ENR)/(Kenaf core powder) composites

The effects of dynamic vulcanization on properties of poly(vinyl chloride) (PVC)/epoxidized natural rubber (ENR)/(kenaf core powder) composite were studied. Tensile properties indicated that the strength, elongation at break, and Young's modulus of the composites exhibited an increase for samples with dynamic vulcanization. Morphological analysis using scanning electron microscopy showed the interaction between ENR and PVC. There was no bonding between kenaf core powder and the PVC/ENR matrix owing to the different polarity of both components. Filler agglomerates increased, which leads to an increase of filler‐filler interaction and poor dispersion. Furthermore, swelling index indicated that the composite with dynamic vulcanization shows lower absorption of tolune compared with composites without dynamic vulcanization. J. VINYL ADDIT. TECHNOL., 22:206–212, 2016. © 2014 Society of Plastics Engineers     

Structure,texture and surface acidity studies of a series of mixed zinc–aluminum (60–90 molar % Al) phosphate catalysts

A series of mixed zinc–aluminum phosphate (ZnAlP) catalysts containing 40–90 aluminum molar % were synthesized by a coprecipitation method and characterized by nitrogen adsorption–desorption, X‐ray diffraction, FTIR spectroscopy, thermogravimetric analysis (TGA), differential thermal analysis (DTA), diffuse reflectance infrared Fourier transform spectroscopy (DRIFTS) and temperature programmed desorption (TPD) of ammonia. The presence of aluminum greatly affected the surface properties of Zn₃(PO₄)₂ by delaying the crystallization process of Zn₃(PO₄)₂. All amorphous samples were shown to be mesoporous and they contained two types of aluminum surface hydroxyl groups and one type of phosphorus hydroxyl group, as shown by DRIFT spectra. The specific surface area and the acidity of ZnAlP increased on increasing the aluminum content. On the other hand, a great difference in the texture and the concentration of surface acid sites was found by changing the precipitating agent and calcination temperature. Thus these factors also play an important role in the final properties of these catalysts. © 2001 Society of Chemical Industry     

Multimodal user interface for traffic incident management in control room

Efficient road traffic incident management (TIM) in metropolitan areas is crucial for the smooth traffic flow and the mobility and safety of community. TIM requires fast and accurate collection and retrieval of critical data, such as incident conditions and contact information for the intervention crew, public safety organisations and other resources. Access to critical data by traffic control operators can be facilitated through various human-computer interfaces. The judicious introduction of a multimodal interaction paradigm to the user interfaces (UIs) for incident handling in a metropolitan transport management centre is discussed. Two research prototypes supporting speech and gestural interactions have been developed on the basis of the User Centred Design methodology, and their evaluations have been conducted through user studies. The user studies on the prototypes suggest that multimodal UIs (MMUIs) can provide traffic control operators with intuitive, cognitively efficient ways to record traffic incident conditions, facilitate fast retrieval of contact details, and support time-critical incident handling. The research prototypes described herein represent some initial steps for the longer-term deployment of advanced MMUI systems for emergency management     

Flammability and mechanical properties of wood flour‐filled polypropylene composites

Polypropylene (PP) composites filled with wood flour (WF) were prepared with a twin‐screw extruder and an injection‐molding machine. Three types of ecologically friendly flame retardants (FRs) based on ammonium polyphosphate were used to improve the FR properties of the composites. The flame retardancy of the PP/WF composites was characterized with thermogravimetric analysis (TGA), vertical burn testing (UL94‐V), and limiting oxygen index (LOI) measurements. The TGA data showed that all three types of FRs could enhance the thermal stability of the PP/WF/FR systems at high temperatures and effectively increase the char residue formation. The FRs could effectively reduce the flammability of the PP/WF/FR composites by achieving V‐0 UL94‐V classification. The increased LOI also showed that the flammability of the PP/WF/FR composites was reduced with the addition of FRs. The mechanical property study revealed that, with the incorporation of FRs, the tensile strength and flexural strength were decreased, but the tensile and flexural moduli were increased in all cases. The presence of maleic anhydride grafted polypropylene (MAPP) resulted in an improvement of the filler–matrix bonding between the WF/intumescent FR and PP, and this consequently enhanced the overall mechanical properties of the composites. Morphological studies carried out with scanning electron microscopy revealed clear evidence that the adhesion at the interfacial region was enhanced with the addition of MAPP to the PP/WF/FR composites. © 2010 Wiley Periodicals, Inc. J Appl Polym Sci, 2010     

A generic approach to recognising isolated, nested and interacting features from 2D drawings

Many useful three-dimensional (3D)-feature recognition systems have been developed over the past few decades. However there is a shortage of feature recognition systems in the two-dimensional (2D) domain. This has an adverse effect on the realisation of CADCAM benefits in Small and Medium Enterprises. Here is an attempt to redress this deficit. This paper presents a hint-based feature recognition system which recognises machining features from 2D orthographic projections through a two-stage process of profile searching and feature completion. Three types of profiles: Type I, II or III are defined in this system. Together they are sufficient to describe most profiles, if not all, in any 2D drawing. Profile searching identifies these profiles while feature completion establishes the cavity emanating from these profiles using a multi-level top–down approach. This process enables the system to deal with the isolated, nested and interacting features using a common framework. The nested features are handled by applying the same reasoning used for isolated features recursively while interacting features are decomposed automatically by the process of profile searching into their constituent isolated features.     

A novel dengue fever (DF) and dengue haemorrhagic fever (DHF) analysis using artificial neural network (ANN)

Dengue fever (DF) is an acute febrile viral disease frequently presented with headache, bone or joint and muscular pains, and rash. A significant percentage of DF patients develop a more severe form of disease, known as dengue haemorrhagic fever (DHF). DHF is the complication of DF. The main pathophysiology of DHF is the development of plasma leakage from the capillary, resulting in haemoconcentration, ascites, and pleural effusion that may lead to shock following defervescence of fever. Therefore, accurate prediction of the day of defervescence of fever is critical for clinician to decide on patient management strategy. To date, no known literature describes of any attempt to predict the day of defervescence of fever in DF patients. This paper describes a non-invasive prediction system for predicting the day of defervescence of fever in dengue patients using artificial neural network. The developed system bases its prediction solely on the clinical symptoms and signs and uses the multilayer feed-forward neural networks (MFNN). The results show that the proposed system is able to predict the day of defervescence in dengue patients with 90% prediction accuracy.     

Decomposition of interacting machining features based on the reasoning on the design features

Currently, design and machining features diverge in meaning, even when they are interpreting the same object. This divergence of feature interpretation provides a venue for research work to reduce the complexity that arises in recognizing interacting machining features. Therefore, this paper demonstrates the recognition of design features with the aim to eventually decompose the interacting machining features. Loop driving recognition links the CAD data directly to the features to be recognized. The first step is to recognize the design features from B-Reps part. Then geometrical reasoning on these design features is employed to convert the design features to its respective machining features. The process of conversion is in fact the process of decomposing the interacting machining features without having to visit the B-Reps data again. The system takes into account the nesting of the design features that causes more interacting machining features to be decomposed. Finally, output data of both design and machining features are then displayed.