Instance-Based Regression by Partitioning Feature Projections

A new instance-based learning method is presented for regression problems with high-dimensional data. As an instance-based approach, the conventional method, KNN, is very popular for classification. Although KNN performs well on classification tasks, it does not perform as well on regression problems. We have developed a new instance-based method, called Regression by Partitioning Feature Projections (RPFP) which is designed to meet the requirement for a lazy method that achieves high levels of accuracy on regression problems. RPFP gives better performance than well-known eager approaches found in machine learning and statistics such as MARS, rule-based regression, and regression tree induction systems. The most important property of RPFP is that it is a projection-based approach that can handle interactions. We show that it outperforms existing eager or lazy approaches on many domains when there are many missing values in the training data.     

The effect of atmospheric plasma treatment of recycled carbon fiber at different plasma powers on recycled carbon fiber and its polypropylene composites

To increase the mechanical properties of recycled carbon fiber-reinforced polypropylene (PP) composites, recycled carbon fibers (RCF) were subjected to atmospheric plasma treatment at different plasma powers (100, 200, and 300 W). The changes on surface topography and roughness of RCF were examined by atomic force microscopy. Plasma treatment of RCF increased the roughness value of RCF. The variation of surface elemental compositions and tensile strength of RCF were determined by using X-ray photoelectron spectroscopy and tensile test, respectively. Plasma-treated RCF-reinforced PP composites were fabricated using high speed thermo-kinetic mixer. Plasma treatment of RCF at 100 W increased the tensile and flexural strength values of RCF-reinforced PP composites considerably by 17 and 11%, respectively. However, plasma treatment of RCF at higher plasma powers (200 W and 300 W) decreased tensile and flexural strength values of composites because of the etching of RCF. © 2018 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2019 , 136, 47131.     

Formulating Pantone colors by unused base inks,formulation software,and a spectrophotometer

Unused base inks that are not going to be used for printing production are considered to be hazardous materials. Their disposal is expensive, and strict environmental regulations should be followed for their disposal. As an alternative, this article describes how spectral data of unused base inks can be gathered and mixed to generate new colors to incorporate them back to print production for small‐volume jobs. In this study, 30 different Pantone colors were selected as target colors. The CIE L*a*b* spectral data of Pantone colors and unused base inks were gathered via a spectrophotometer. A commercial formulation software, based on multiflux theory and CIE L*a*b* color space, was used to formulate ink recipes that contained the base inks. To quantify the performance of ink recipes, they were mixed and printed using an offset printability tester. The CIELAB ΔE*_ab metric, developed by CIE, was used to detect the visual differences between the target Pantone Color and printed colors.     

Performance evaluation of a submerged membrane bioreactor for the treatment of brackish oil and natural gas field produced water

Produced water, which is co-produced during oil and gas manufacturing, represents one of the largest sources of oily wastewaters. Therefore, treatment of this produced water may improve the economic viability and lead to a new source of water for beneficial use. In this study a submerged hollow fiber membrane bioreactor (MBR) has been studied experimentally for the treatment of brackish oil and natural gas field produced water. This type of wastewater is also characterized with relatively moderate to high amount of salt, oil and total petroleum hydrocarbons (TPH). However, the bacteria which are growing in conventional activated sludge and MBR cannot survive at these strict conditions, therefore acclimation of the bacteria is of vital importance. The performance of the biological system, membrane permeability, the rate and extent of TPH biodegradability have been investigated under different sludge age and F/M ratios. The results obtained by gas chromatography analyses showed that the MBR system could be very effective in the removal of TPH from produced water and a significant improvement in the effluent quality was achieved.     

Cooperative communications with multilevel/AES-SD4-CPFSK in wireless sensor networks

In this paper, a new joint multilevel data encryption and channel coding mechanism is proposed, which is called ??multilevel/advanced encryption standard?Csystematic distance 4?Ccontinuous phase frequency shift keying?? (ML/AES-SD4-CPFSK). In the proposed scheme, we have not only taken advantage of spatial diversity gains but also optimally allocated energy and bandwidth resources among sensor nodes as well as providing high level of security and error protection for cooperative communications in wireless sensor networks. Relay protocols of cooperative communications, such as amplify-and-forward and decode-and-forward with/without adversary nodes, have been studied for 4CPFSK, 8CPFSK, and 16CPFSK of ML/AES-SD4-CPFSK. We have evaluated the error performances of multilevel AES for data encryption, multilevel SD-4 for channel coding, and various CPFSK types for modulation utilizing cooperative communications in wireless sensor networks. According to computer simulation results, significant diversity gain and coding gain have been achieved. As an example, bit error rate (BER) performance of 10^?5 value has been obtained at a signal-to-noise ratio (SNR) of ?6?dB for SD-4-CPFSK scheme in a compared related journal paper, whereas in our proposed system, we have reached the same BER value at a SNR of ?23?dB with amplify-and-forward with direct path signal protocol in 16-level AES, two-level SD-4 coded 16CPFSK, and at the same time, we have reached the same BER value at a SNR of ?22?dB with amplify-and-forward without direct path signal protocol in 16-level AES, two-level SD-4 coded 16CPFSK.     

Seismic microzonation of the historic peninsula of İstanbul

In this study, the geological and geotechnical conditions of old Istanbul (Fatih and Eminönü provinces) were investigated in detail and a seismic microzonation study was undertaken for this historical peninsula, which is the site of many ancient structures. Dynamic site response, liquefaction potential and slope stability analyses were carried out, based on field and laboratory tests and earthquake time histories computed with respect to probabilities of exceedance of 10 and 40% in 50 years. The output data obtained from the analyses were evaluated by GIS techniques, and ground shaking, liquefaction susceptibility and landslide hazard maps were prepared.     

Performance of Systematic Distance-4 Binary Linear Block Codes with Continuous Phase Frequency Shift Keying over MIMO Systems

Codes with full information rate (optimal), for example Hamming codes, provide the highest possible code rate R (R = k/n where k and n are the code dimension and length respectively) and it is an important property for a block code. Recently, the Systematic Distance-4 (SD-4) codes are proposed that allows generating all the optimal Hamming distance-4 binary linear block codes. Continuous Phase Frequency Shift Keying (CPFSK) provides low spectral occupancy and is suitable for power and bandwidth-limited channels such as satellite communication channels. MIMO technique is essential for modern wireless communication systems. In this article, we evaluated the error performances of SD-4 codes utilizing CPFSK modulation over MIMO Rician and Rayleigh channels via computer simulations and obtained outstanding results regarding coding gain.     

Reliability analysis of the complex mode indicator function and Hilbert Transform techniques for operational modal analysis

This study presents application of the CMIF and the Hilbert Transform techniques onto simulated response data obtained using a numerical model of a typical school building from Turkey. White noise is added to the data in order to achieve a noise to signal ratio of 5%. 100 Monte Carlo analysis sequences are carried out and the modal parameters (the frequencies, the mode shapes and the damping ratios) are identified at each Monte Carlo run for both techniques. The results are compared with the identifications obtained from the simulated data using stochastic subspace based system identification technique. The overall results of the study show that the mode shapes are clearly identified the best by using the CMIF technique. The damping ratios are estimated better by using the stochastic subspace based system identification technique whereas the frequencies are best determined by the CMIF. The results also show that both the CMIF and the Hilbert Transform techniques are sensitive to the type of window used as well as the averaging and the decimation process. It is apparent that the CMIF technique is as robust as the frequently used stochastic subspace based system identification technique and can be confidently used for modal parameter estimation of stiff low to mid rise reinforced concrete structures.