A new deep convolutional neural network model for classifying breast cancer histopathological images and the hyperparameter optimisation of the proposed model

The Journal of Supercomputing - Deep learning algorithms have yielded remarkable results in medical diagnosis and image analysis, besides their contribution to improvements in a number of fields...     

Blending science and public policies for remediation of a degraded ecosystem: Jackfish Bay, north shore of Lake Superior, Ontario, Canada

The Jackfish Bay Remedial Action Plan is the first of Lake Superior's Areas of Concern (AOCs) to consider recognition as an Area in Recovery (AiR). As a result of a high degree of complexity and uncertainty, ecosystem recovery in Jackfish Bay has been determined using a combination of regulatory policies and scientific evidence and extensive public and expert-based decision making. As a result, the conceptualization of the AiR status in Jackfish Bay has been developed with the adaptive management and the ecosystem approach, which provide the basic principles of assessing, monitoring, and managing the Area of Concern. To determine the status of beneficial use impairments caused by effluent from the Terrace Bay Pulp Inc., three public advisory committees—an academic panel of experts, a government technical review committee, and the Jackfish Bay Public Area in Recovery Review Committee (PARRC)—reviewed relevant scientific data and documents, including peer-reviewed publications, to assess changes in pollution levels in Jackfish Bay and improvements to aquatic, biotic, and benthic environments of the bay. The public decision-making process concluded with recommendations by the PARRC to develop a systematic monitoring program so that the ecosystem recovery process in the bay could be assessed on a continued basis, leading to its eventual delisting as an AOC. The entire process provides an example of blending science and public policies for remediation of a degraded ecosystem on the Great Lakes.     

A new approach based on a discrete hidden Markov model using the Rocchio algorithm for the diagnosis of heart valve diseases

Abstract: Application of the Doppler ultrasound technique in the diagnosis of heart diseases has been increasing in the last decade since it is non‐invasive, practicable and reliable. In this study, a new approach based on the discrete hidden Markov model (DHMM) is proposed for the diagnosis of heart valve disorders. For the calculation of hidden Markov model (HMM) parameters according to the maximum likelihood approach, HMM parameters belonging to each class are calculated by using training samples that only belong to their own classes. In order to calculate the parameters of DHMMs, not only training samples of the related class but also training samples of other classes are included in the calculation. Therefore HMM parameters that reflect a class's characteristics are more represented than other class parameters. For this aim, the approach was to use a hybrid method by adapting the Rocchio algorithm. The proposed system was used in the classification of the Doppler signals obtained from aortic and mitral heart valves of 215 subjects. The performance of this classification approach was compared with the classification performances in previous studies which used the same data set and the efficiency of the new approach was tested. The total classification accuracy of the proposed approach (95.12%) is higher than the total accuracy rate of standard DHMM (94.31%), continuous HMM (93.5%) and support vector machine (92.67%) classifiers employed in our previous studies and comparable with the performance levels of classifications using artificial neural networks (95.12%) and fuzzy‐C‐means/CHMM (95.12%).     

An ERP software selection process with using artificial neural network based on analytic network process approach

An enterprise resource planning (ERP) software selection is known to be multi attribute decision making (MADM) problem. This problem has been modeled according with analytic network process (ANP) method due to fact that it considers criteria and sub criteria relations and interrelations in selecting the software.Opinions of many experts are obtained while building ANP model for the selection ERP then opinions are reduced to one single value by methods like geometric means so as to get desired results. To use ANP model for the selection of ERP for a new organization, a new group of expert’s opinions are needed. In this case the same problem will be in counter. In the proposed model, when ANP and ANN models are setup, an ERP software selection can be made easily by the opinions of one single expert. In that case calculation of geometric mean of answers that obtained from many experts will be unnecessary. Additionally the effect of subjective opinion of one single decision maker will be avoided. In terms of difficulty, ANP has some difficulties due to eigenvalue and their limit value calculation.An ANN model has been designed and trained with using ANP results in order to calculate ERP software priority. The artificial neural network (ANN) model is trained by results obtained from ANP. It seems that there is no any major difficulty in order to predict software priorities with trained ANN model. By this results ANN model has been come suitable for using in the selection of ERP for another new decision.     

Adaptive neuro-fuzzy inference system for diagnosis of the heart valve diseases using wavelet transform with entropy

Listening via stethoscope is a preferential method, being used by physicians for distinguishing normal and abnormal cardiac systems. On the other hand, listening with stethoscope has a number of constraints. The interpretation of various heart sounds depends on physician’s ability of hearing, experience, and skill. Such limitations may be reduced by developing biomedical-based decision support systems. In this study, a biomedical-based decision support system was developed for the classification of heart sound signals, obtained from 120 subjects with normal, pulmonary, and mitral stenosis heart valve diseases via stethoscope. Developed system comprises of three stages. In the first stage, for feature extraction, obtained heart sound signals were separated to its sub-bands using discrete wavelet transform (DWT). In the second stage, entropy of each sub-band was calculated using Shannon entropy algorithm to reduce the dimensionality of the feature vectors via DWT. In the third stage, the reduced features of three types of heart sound signals were used as input patterns of the adaptive neuro-fuzzy inference system (ANFIS) classifiers. Developed method reached 98.33% classification accuracy, and it was showed that purposed method is effective for detection of heart valve diseases.     

An integrated modeling method for assessment of quality systems applied to aerospace manufacturing supply chains

In highly regulated industries such as aerospace, the introduction of new quality standard can provide the framework for developing and formulating innovative novel business models which become the foundation to build a competitive, customer-centric enterprise. A number of enterprise modeling methods have been developed in recent years mainly to offer support for enterprise design and help specify systems requirements and solutions. However, those methods are inefficient in providing sufficient support for quality systems links and assessment. The implementation parts of the processes linked to the standards remain unclear and ambiguous for the practitioners as a result of new standards introduction. This paper proposed to integrate new revision of AS/EN9100 aerospace quality elements through systematic integration approach which can help the enterprises in business re-engineering process. The assessment capability model is also presented to identify impacts on the existing system as a result of introducing new standards.     

Comparison of OR and AI methods in discrete manufacturing using fuzzy logic

Since 1950s the techniques of Operations Research (OR) and Optimization have been utilized to increase the efficiency of the production systems. With the widespread use of computers, it has even become easier to deal with industrial problems. However the complexity of the problems still reveals the difficulty in providing solutions. The use of artificial intelligence (AI) seems to attract the attention of the researcher to overcome to the difficulties. This has already been realized with several successful applications. In this study, the use of AI and OR techniques is compared using fuzzy logic. The progress of manufacturing systems, characteristics of production processes, system managements and system behavior are taken into account. The study is focussed on only discrete manufacturing.     

Design and eco-technoeconomic analyses of SOFC/GT hybrid systems accounting for long-term degradation effects

This study compares two SOFC/GT (solid oxide fuel cell with gas turbine) hybrid systems to that of two standalone SOFC systems via eco-technoeconomic analyses that account for long-term degradation effects. Four cases were examined: 1) standalone SOFC plant without a steam bottoming cycle; 2) standalone SOFC plant with a steam bottoming cycle; 3) SOFC/GT hybrid plant without a steam bottoming cycle; and 4) SOFC/GT with a steam bottoming cycle. This study employed a real-time 1D SOFC model with an empirical degradation calculation integrated with steady-state balance-of-plant models. Simulations used Matlab Simulink R2017a, Aspen Plus V10, and Python 3.7.4 with a pseudo steady-state approach. The results showed that, with some trade-offs, the SOFC/GT hybrid plant with the steam bottoming cycle is the best option, with an overall efficiency of 44.6% _LHV, an LCOE (levelized cost of electricity) of $US 77/MWh, and a CCA (cost of CO₂ avoided) of -$US 49.3/tonneCO₂e. The sensitivity analysis also indicated that SOFC/GT hybrid plants were less sensitive to SOFC price compared to standalone SOFC plants. The sensitivity analysis indicated that using a larger gas turbine and replacing the SOFC stack less frequently was the better design choice for the SOFC/GT hybrid plant.     

Separation and adsorption properties of poly styrene‐graft‐ethyl methacrylate copolymer for zinc,copper, and cobalt ions in water samples

In this article, separation and adsorption properties of poly styrene‐graft‐ethyl methacrylate copolymer for zinc, copper, and cobalt ions in water samples were investigated. For this aim, some experimental and analytical parameters such as solution pH, sample flow rate, type of eluting agent, and sample solution volume were optimized. The adsorbed metal ions on polymeric resin were eluted with 5 ml of 2 mol l^?1 HNO₃ and they were determined by flame atomic absorption spectrometry. In optimized conditions, the adsorption capacities for Zn, Cu, and Co were obtained as 6.8, 5.2, and 7.5 mg g^?1, respectively. The detection limits were calculated as 0.82 μg l^?1 for Zn, 1.24 μg l^?1 for Cu, and 0.68 μg l^?1 for Co from standard deviation of the blank (50 ml, pH 5.8) measurements 10 replicates. The relative standard deviation of recoveries for seven replicate analyses of Zn, Cu, and Co ions (50 ml of 0.10 mg l^?1) were found as 2.4, 2.8, and 1.5%, respectively. The accuracy of method was checked with certified reference material (NIST SRM 1643e, trace elements in water) and the developed method was successfully applied to tap water, commercial drinking water, and mineral water samples. POLYM. ENG. SCI., 54:1555–1559, 2014. © 2013 Society of Plastics Engineers