An intelligent hybrid approach for hepatitis disease diagnosis: Combining enhanced k‐means clustering and improved ensemble learning

In real world, the automatic detection of liver disease is a challenging problem among medical practitioners. The intent of this work is to propose an intelligent hybrid approach for the diagnosis of hepatitis disease. The diagnosis is performed with the combination of k‐means clustering and improved ensemble‐driven learning. To avoid clinical experience and to reduce the evaluation time, ensemble learning is deployed, which constructs a set of hypotheses by using multiple learners to solve a liver disease problem. The performance analysis of the proposed integrated hybrid system is compared in terms of accuracy, true positive rate, precision, f‐measure, kappa statistic, mean absolute error, and root mean squared error. Simulation results showed that the enhanced k‐means clustering and improved ensemble learning with enhanced adaptive boosting, bagged decision tree, and J48 decision tree‐based intelligent hybrid approach achieved better prediction outcomes than other existing individual and integrated methods.     

Tool path generation framework for accurate manufacture of complex 3D sheet metal parts using single point incremental forming

The prototyping of complex sheet metal parts using single point incremental forming (SPIF) requires the generation of optimal tool paths and/or tool path sequences that ensure that the formed part is within geometric design specifications. The presence of a multitude of features on complex parts leads to multiple inaccuracy inducing phenomena occurring simultaneously due to interactions between the features. This paper proposes a network analysis methodology using topological conceptual graphs to capture the effects of different phenomena on the final accuracy of a sheet metal part manufactured by SPIF. Using this framework optimized tool paths can be generated that compensate for the inaccuracy inducing behavior. Tool path generation algorithms to create partial tool paths that account for the accuracy of specific features in the part based on the proposed framework are also presented. Finally, the creation of integrated tool paths maintaining complementarity between tool paths and desired continuity behavior using non-uniform cubic B-splines is illustrated. A number of case studies demonstrating the applicability of the integrated framework are discussed, where the maximum deviations in the part are significantly reduced and the average absolute deviations for the complete part are brought down to less than 0.5 mm.     

Comparing the Performance of Organic Solvent Nanofiltration Membranes in Non-Polar Solvents

Organic solvent nanofiltration (OSN) is gradually expanding from academic research to industrial implementation. The need for membranes with low and sharp molecular weight cutoffs that are able to operate under aggressive OSN conditions is increasing. However, the lack of comparable and uniform performance data frustrates the screening and membrane selection for processes. Here, a collaboration is presented between several academic and industrial partners analyzing the separation performance of 10 different membranes using three model process mixtures. Membrane materials range from classic polymeric and thin film composites (TFCs) to hybrid ceramic types. The model solutions were chosen to mimic cases relevant to today's industrial use: relatively low molar mass solutes (330–550 Da) in n-heptane, toluene, and anisole.     

Prediction and optimization of electroplated Ni-based coating composition and thickness using central composite design and artificial neural network

Journal of Applied Electrochemistry - The choice of the electroplating conditions of Ni-based alloys has always been a serious research question. In this study, an artificial neural network based...     

Electricity generation in low cost microbial fuel cell made up of earthenware of different thickness

Performance of four microbial fuel cells (MFC-1, MFC-2, MFC-3 and MFC-4) made up of earthen pots with wall thicknesses of 3, 5, 7 and 8.5 mm, respectively, was evaluated. The MFCs were operated in fed batch mode with synthetic wastewater having sucrose as the carbon source. The power generation decreased with increase in the thickness of the earthen pot which was used to make the anode chamber. MFC-1 generated highest sustainable power density of 24.32 mW/m(2) and volumetric power of 1.04 W/m(3) (1.91 mA, 0.191 V) at 100 Ω external resistance. The maximum Coulombic efficiencies obtained in MFC-1, MFC-2, MFC-3 and MFC-4 were 7.7, 7.1, 6.8 and 6.1%, respectively. The oxygen mass transfer and oxygen diffusion coefficients measured for earthen plate of 3 mm thickness were 1.79 × 10(-5) and 5.38 × 10(-6) cm(2)/s, respectively, which implies that earthen plate is permeable to oxygen as other polymeric membranes. The internal resistance increased with increase in thickness of the earthen pot MFCs. The thickness of the earthen material affected the overall performance of MFCs.     

IIR system identification using cat swarm optimization

Conventional derivative based learning rule poses stability problem when used in adaptive identification of infinite impulse response (IIR) systems. In addition the performance of these methods substantially deteriorates when reduced order adaptive models are used for such identification. In this paper the IIR system identification task is formulated as an optimization problem and a recently introduced cat swarm optimization (CSO) is used to develop a new population based learning rule for the model. Both actual and reduced order identification of few benchmarked IIR plants is carried out through simulation study. The results demonstrate superior identification performance of the new method compared to that achieved by genetic algorithm (GA) and particle swarm optimization (PSO) based identification.     

An integrated intelligent computing model for the interpretation of EMG based neuromuscular diseases

Intelligent computing system (ICS) and knowledge-based system (KBS) have been widely used in the detection and interpretation of EMG (electromyography) based diseases. Heuristic-based detection methods of EMG parameters for a particular disease have also been reported in the literature but little effort has been made by researchers to combine rule-based reasoning (RBR) and case-based reasoning of KBS, and ANN (artificial neural nets) of ICS. Integrating the methods in KBS and ICS improves the computational and reasoning efficiency of the problem-solving strategy. We have developed an integrated model of CBR and RBR for generating cases, and ANN for matching cases for the interpretation and diagnosis of neuromuscular diseases. We have hierarchically structured the neuromuscular diseases in terms of their physio-pyscho (muscular, cognitive and psychological) parameters and EMG based parameters (amplitude, duration, phase etc.). Cumulative confidence factor is computed at different node from lowest to highest level of hierarchal structure in the process of diagnosis of the neuromuscular diseases. The diseases considered are Duchenne muscular dystrophy, Polymyostits, Endocrine myopathy, Metabolic myopathy, Neuropathy, Poliomyletis and Myasthenia gravis. The basic objective of this work is to develop an integrated model of RBR, CBR and ANN in which RBR is used to hierarchically correlate the sign and symptom of the disease and also to compute cumulative confidence factor (CCF) of the diseases. CBR is used for diagnosing the neuromuscular diseases and to find the relative importance of sign and symptoms of a diseases to other diseases and ANN is used for matching process in CBR.     

Event-triggered sliding mode control for a class of nonlinear systems

ABSTRACT

Event-triggering strategy is one of the real-time control implementation techniques which aims at achieving minimum resource utilisation while ensuring the satisfactory performance of the closed-loop system. In this paper, we address the problem of robust stabilisation for a class of nonlinear systems subject to external disturbances using sliding mode control (SMC) by event-triggering scheme. An event-triggering scheme is developed for SMC to ensure the sliding trajectory remains confined in the vicinity of sliding manifold. The event-triggered SMC brings the sliding mode in the system and thus the steady-state trajectories of the system also remain bounded within a predesigned region in the presence of disturbances. The design of event parameters is also given considering the practical constraints on control execution. We show that the next triggering instant is larger than its immediate past triggering instant by a given positive constant. The analysis is also presented with taking delay into account in the control updates. An upper bound for delay is calculated to ensure stability of the system. It is shown that with delay steady-state bound of the system is increased than that of the case without delay. However, the system trajectories remain bounded in the case of delay, so stability is ensured. The performance of this event-triggered SMC is demonstrated through a numerical simulation.