Colon segmentation and colonic polyp detection using cellular neural networks and three-dimensional template matching

Abstract: In this study, an automatic three-dimensional computer-aided detection system for colonic polyps was developed. Computer-aided detection for computed tomography colonography aims at facilitating the detection of colonic polyps. First, the colon regions of whole computed tomography images were carefully segmented to reduce computational burden and prevent false positive detection. In this process, the colon regions were extracted by using a cellular neural network and then the regions of interest were determined. In order to improve the segmentation performance of the study, weights in the cellular neural network were calculated by three heuristic optimization techniques, namely genetic algorithm, differential evaluation and artificial immune system. Afterwards, a three-dimensional polyp template model was constructed to detect polyps on the segmented regions of interest. At the end of the template matching process, the volumes geometrically similar to the template were emhanced.     

Pitch angle control in wind turbines above the rated wind speed by multi-layer perceptron and radial basis function neural networks

In wind energy conversion systems, one of the operational problems is the changeability and discontinuity of wind. In most cases, wind speed can fluctuate rapidly. Hence, quality of produced energy becomes an important problem in wind energy conversion plants. Several control techniques have been applied to improve the quality of power generated from wind turbines. Pitch control is the most efficient and popular power control method, especially for variable-speed wind turbines. It is a useful method for power regulation above the rated wind speed. This paper proposes an artificial neural network-based pitch angle controller for wind turbines. In the simulations, a variable-speed wind turbine is modeled, and its operation is observed by using two types of artificial neural network controllers. These are multi-layer perceptrons with back propagation learning algorithm and radial basis function network. It is shown that the power output was successfully regulated during high wind speed, and as a result overloading or outage of the wind turbine was prevented.     

Durability properties of concrete with blended cements

The study of chloride‐induced corrosion started more than three decades ago, after extensive cases of damage were observed on reinforced concrete structures in coastal regions and on infrastructural objects exposed to salt action. Nowadays, the basis for sustainable concrete industry lies in these three aspects: reducing CO₂ emissions by using by‐products of other industries (slag, fly ash, silica fume) for cement production, conservation of natural resources by replacing part of the aggregate with recycled construction waste, as well as use of recycled water in concrete production, and finally, construction of durable concrete structures. Durability design procedures for reinforced concrete structures in aggressive environments are still to a large extent empirical, especially in the case of using blended cements. The type of cement has a considerable effect on the properties of concrete, especially concrete resistance to the penetration of chloride ions. The paper presents results of testing durability and deformational properties of concrete produced with quaternary‐blended cement. A clearer insight into these properties is a necessary starting point for the performance‐based design of concrete prepared with blended cements, leading to more durable and corrosion‐free concrete structures in aggressive environments.     

Friction and Wear Characteristics of Haynes 25, 188, and 214 Superalloys Against Hastelloy X up to 540 <Emphasis Type="Bold">°</Emphasis>C

As demand for more power increases, compression ratios, and operating temperatures keep rising. High speeds combined with high temperatures make turbomachinery sealing applications even more challenging. In order to confirm sufficient service life material pairs should be tested under conditions similar to engine operating conditions. This study presents high temperature friction and wear characteristics of cobalt/nickel superalloys, Haynes 25 (51Co–10Ni–20Cr–15W), Haynes 188 (39Co–22Ni–22Cr–14W), and Haynes 214 (75Ni–16Cr–3Fe–0.5Mn) sheets when rubbed against Hastelloy X (47Ni–22Cr–18Fe–9Mo) pins. Tests are conducted at 25, 200, 400, and 540 °C with a validated custom design linear reciprocating tribometer. Sliding speed and sliding distance are 1 Hz and 1.2 km, respectively. Friction coefficients are calculated with friction force data acquired from a load cell. Wear coefficients are calculated through weight loss measurements. Results indicate that Haynes 25 (H25) has the lowest friction coefficients at all test temperatures. Above 400 °C, H25 and Haynes 188 (H188) exhibit the best wear resistance. Protective cobalt oxide layers are formed on the H25 and H188 at 540 °C in addition to nickel, chrome, and tungsten oxides. Although, it has better oxidation resistance, Haynes 214 has relatively higher wear rates than other tested materials especially at low temperatures. However, its wear performance improves beyond 200 °C.     

Parkinson’s Disease tremor classification – A comparison between Support Vector Machines and neural networks

Deep Brain Stimulation has been used in the study of and for treating Parkinson’s Disease (PD) tremor symptoms since the 1980s. In the research reported here we have carried out a comparative analysis to classify tremor onset based on intraoperative microelectrode recordings of a PD patient’s brain Local Field Potential (LFP) signals. In particular, we compared the performance of a Support Vector Machine (SVM) with two well known artificial neural network classifiers, namely a Multiple Layer Perceptron (MLP) and a Radial Basis Function Network (RBN). The results show that in this study, using specifically PD data, the SVM provided an overall better classification rate achieving an accuracy of 81% recognition.     

Effects of premixed diethyl ether (DEE) on combustion and exhaust emissions in a HCCI-DI diesel engine

In this study, the effects of premixed ratio of diethyl ether (DEE) on the combustion and exhaust emissions of a single-cylinder, HCCI-DI engine were investigated. The experiments were performed at the engine speed of 2200 rpm and 19 N m operating conditions. The amount of the premixed DEE was controlled by a programmable electronic control unit (ECU) and the DEE injection was conducted into the intake air charge using low pressure injector. The premixed fuel ratio (PFR) of DEE was changed from 0% to 40% and results were compared to neat diesel operation. The percentages of premixed fuel were calculated from the energy ratio of premixed DEE fuel to total energy rate of the fuels. The experimental results show that single stage ignition was found with the addition of premixed DEE fuel. Increasing and phasing in-cylinder pressure and heat release were observed in the premixed stage of the combustion. Lower diffusion combustion was also occurred. Cycle-to cycle variations were very small with diesel fuel and 10% DEE premixed fuel ratio. Audible knocking occurred with 40% DEE premixed fuel ratio. NO_x-soot trade-off characteristics were changed and improvements were found simultaneously. NO_x and soot emissions decreased up to 19.4% and 76.1%, respectively, while exhaust gas temperature decreased by 23.8%. On the other hand, CO and HC emissions increased.     

Gold recovery from dilute gold solutions using DEAE-cellulose

The present work investigates gold recovery using DEAE-cellulose, a common biopolymer derivative, from synthetically prepared diluted gold-bearing solutions of 50 ppm. The effects of different recovery parameters on gold recovery efficiency were studied in detail. It was demonstrated that gold recovery efficiency increased with an increasing amount of sorbent, as well as increasing contact time. A gold recovery efficiency of 99% was attained under conditions of 20–40 g DEAE-cellulose per liter at a shaking rate of 130 rpm for 30 min at room temperature. On the other hand, with smaller amounts of sorbent (6 g/l), it was also possible to recover gold from the solution with 99% efficiency when the reaction temperature was increased to 60 °C. The shaking rate and temperature were demonstrated to play a vital role in the recovery process. It was also found that gold recovery by DEAE-cellulose is an intermediate-controlled process with an activation energy of 37.11 kJ/mol. The XRD pattern and SEM images revealed that the recovered gold was in the metallic form.     

Seepage from a Rectangular Ditch to the Groundwater Table

This study presents both a numerical and an experimental solution to seepage from a rectangular ditch or elongated pond to a groundwater table of infinite horizontal extent. Because of the unknown location of the free surface, the flow domain is transformed into the complex potential plane using the inverse formulation method, where the free surface becomes a straight line. The method of finite differences was used to solve the boundary value problem. The problem was also investigated experimentally using a sand tank model. For comparison purposes, a one-dimensional analytical solution is also presented. The results were compared with each other and with those available in the literature obtained with other solution techniques. The parameters affecting the seepage rate were investigated and the resulting relationships are presented in dimensionless graphs. It is believed that these graphs may be of use in design problems. The conditions for which the simplified one-dimensional analytical solution agrees well with the results of the sophisticated two-dimensional numerical solution are identified.     

Kinetic and equilibrium studies in removing lead ions from aqueous solutions by natural sepiolite

The capacity of sepiolite for the removal of lead ions from aqueous solution was investigated under different experimental conditions. The Langmuir and Freundlich equations, which are in common use for describing sorption equilibrium for wastewater-treatment applications, were applied to data. The constants and correlation coefficients of these isotherm models for the present system at different conditions such as pH, temperature and particle size were calculated and compared. The equilibrium process was well described by the Langmuir isotherm model and the maximum sorption capacity was found to be 93.4 mg/g for the optimal experimental condition. The thermodynamic parameters (DeltaG(o), DeltaH(o) and DeltaS(o)) for lead sorption on the sepiolite were also determined from the temperature dependence. The influences of specific parameters such as the agitation speed, particle size and initial concentration for the kinetic studies were also examined. The sorption kinetics were tested for first order reversible, pseudo-first order and pseudo-second order reaction and the rate constants of kinetic models were calculated. The best correlation coefficients were obtained using the pseudo-second order kinetic model, indicating that lead uptake process followed the pseudo-second order rate expression.