A novel grey‐based feature ranking method for feature subset selection

Abstract

In this paper, a novel grey‐based feature ranking method for feature subset selection is proposed. The classification effectiveness of each attribute of a specific classification problem is proposed and then each attribute can be ranked. Features with higher classification effectiveness are more important and relevant and thus considered as the final feature subset for pattern classification. Experiments performed on various application domains are reported to demonstrate the performance of the proposed approach. The proposed approach yields better performance than other existing feature subset selection methods and is helpful for improving the classification accuracy in pattern classification.     

A real‐time feature extraction method for PVC detection in bedside monitor

Abstract

This paper describes a fast and very efficient feature extraction method for discrimination of QRS and Premature Ventricular Contraction (PVC) beats in a microprocessor‐based bedside monitoring system. It converts each QRS and PVC beat into a positive‐pulse waveform by signal preprocessing. Two characteristic factors, the positive‐pulse and the pulse duration, are calculated when the onset and end points of each pulse have been detected by threshold detection. The prominent feature is extracted from a product of these two factors. This algorithm has been examined using 40 different patients’ electrocardiograph (ECG). The accuracy of QRS detection was 99.3 percent in the tests performed. The identification sensitivity of PVC was 81.2 percent with 18‐ different arrhythmia patients.     

Measuring Piezoelectric Output—Fact or Friction?

Piezoelectric polymers are emerging as exceptionally promising materials for energy harvesting. While the theoretical figures of merit for piezoelectric polymers are comparable to ceramics, the measurement techniques need to be retrofitted to account for the different mechanical properties of the softer polymeric materials. Here, how contact electrification, including friction and contact separation, is often mistaken for piezoelectric charge is examined, and a perspective for how to separate these effects is provided. The state of the literature is assessed, and recommendations are made for clear and simple guidelines in reporting, for both sample geometry and testing methods, to enable accurate determination of piezoelectric figures of merit in polymers. Such improvements will allow an understanding of what types of material manipulation are required in order to enhance the piezoelectric output from polymers and enable the next generation of polymer energy harvester design.     

A new view on J-integrals in elastic–plastic materials

It is well known that the application of the conventional $J$ -integral is connected with severe restrictions when it is applied for elastic–plastic materials. The first restriction is that the $J$ -integral can be used only, if the conditions of proportional loading are fulfilled, e.g. no unloading processes should occur in the material. The second restriction is that, even if this condition is fulfilled, the $J$ -integral does not describe the crack driving force, but only the intensity of the crack tip field. Using the configurational force concept, Simha et al. (J Mech Phys Solids 56:2876–2895, 2008), have derived a $J$ -integral, $J^{\mathrm{ep}} $ , which overcomes these restrictions: $J^{\mathrm{ep}} $ is able to quantify the crack driving force in elastic–plastic materials in accordance with incremental theory of plasticity and it can be applied also in cases of non-proportionality, e.g. for a growing crack. The current paper deals with the characteristic properties of this new $J$ -integral, $J^{\mathrm{ep}}$ , and works out the main differences to the conventional $J$ -integral. In order to do this, numerical studies are performed to calculate the distribution of the configurational forces in a cyclically loaded tensile specimen and in fracture mechanics specimens. For the latter case contained, uncontained, and general yielding conditions are considered. The path dependence of $J^{\mathrm{ep}} $ is determined for both a stationary and a growing crack. Much effort is spent in the investigation of the path dependence of $J^{\mathrm{ep}} $ very close to the crack tip. Several numerical parameters are varied in order to separate numerical and physical effects and to deduce the magnitudes of the crack driving force for stationary and growing cracks. Interpretation of the numerical results leads to a new, completed picture of the $J$ -integral in elastic–plastic materials where $J^{\mathrm{ep}} $ and the conventional $J$ -integral complement each other. This new view allows us also to shed new light on a long-term problem, which has been called the “paradox of elastic–plastic fracture mechanics”.     

TESSA—A new greedy heuristic for facilities layout planning

TESSA is a heuristic for determining which facilities should be adjacent in a planar layout. Once the adjacencies are known the block plan can be constructed by existing techniques. TESSA overcomes problems with earlier heuristics for determining adjacencies as it does not require planarity testing nor does it restrict the type of layout produced. The algorithm is polynomial in time and produces good quality solutions, almost all of which are above 90% of the (often unattainable) upper bound.     

A new route to graphene starting from heavily ozonized fullerenes: Part 2—oxidation in air

Graphite oxide (GO) and heavily ozonized C₆₀ and C₇₀ fullerenes known as “fullerene ozopolymers” were studied by TGA-FTIR (Thermogravimetry coupled with FT-IR spectroscopy), DTG (Differential Thermogravimetry) and DTA (Differential Thermal Analysis) in air flow. It was found that GO burns at 70°C higher temperature than the fullerene ozopolymers. This different behavior toward the thermal oxidation of GO is due to the size of the oxidized and staked graphene layers which are expected to be significantly larger than those of the fullerene ozopolymers. Furthermore, the latter should necessarily have a buckybowl shaped structure which should favor their reactivity with oxygen.     

Thunder®: A new frontier in research for smart materials

A powerful new family of high-performance actuators and sensors is shaking up the motion control industry. These solid state devices, called Thunder^®, are capable of delivering extraordinarily high displacement at substantial forces in a compact, energy efficient package. Based on a patented NASA invention, Thunder is a unique, rugged and adaptable member of the ‘smart’ materials group of products. This article describes this new enabling technology and highlights ongoing research.     

A new in vitro–in vivo correlation for bioabsorbable magnesium stents from mechanical behavior

Correlating the in vitro and in vivo degradation of candidate materials for bioabsorbable implants is a subject of interest in the development of next-generation metallic stents. In this study, pure magnesium wire samples were corroded both in the murine artery (in vivo) and in static cell culture media (in vitro), after which they were subjected to mechanical analysis by tensile testing. Wires corroded in vivo showed reductions in strength, elongation, and the work of fracture, with additional qualitative changes between tensile profiles. The in vivo degradation was 2.2 ± 0.5, 3.1 ± 0.8, and 2.3 ± 0.3 times slower than corrosion in vitro in terms of effective tensile strength, strain to failure, and sample lifetime, respectively. Also, a combined metric, defined as strength multiplied by elongation, was 3.1 ± 0.7 times faster in vitro than in vivo. Consideration of the utility and restrictions of each metric indicates that the lifetime-based multiplier is the best suited to general use for magnesium, though other metrics could be used to deduce the mechanical properties of degradable implants in service.     

A new method of diagnosing the regenerative chatter in machining operations†

The concept and method of diagnosing the regenerative chatter are discussed in this paper. Both theoretical analysis and experimental results demonstrate that a certain corresponding relationship between the system stability and the phase shift angle ψ in the two wavy surface: one from the previous cut and another from the current cut, and hence, one can identify whether the chatter occurring in the cutting process is a regenerative chatter. The phase shift angle ψ is concerned with the chatter frequency and the rotational speed of the workpiece. In order to improve diagnostic accuracy, digital ZOOM FFT has been applied     

Re-visiting crash–speed relationships: A new perspective in crash modelling

Although speed is considered to be one of the main crash contributory factors, research findings are inconsistent. Independent of the robustness of their statistical approaches, crash frequency models typically employ crash data that are aggregated using spatial criteria (e.g., crash counts by link termed as a link-based approach). In this approach, the variability in crashes between links is explained by highly aggregated average measures that may be inappropriate, especially for time-varying variables such as speed and volume. This paper re-examines crash–speed relationships by creating a new crash data aggregation approach that enables improved representation of the road conditions just before crash occurrences. Crashes are aggregated according to the similarity of their pre-crash traffic and geometric conditions, forming an alternative crash count dataset termed as a condition-based approach. Crash–speed relationships are separately developed and compared for both approaches by employing the annual crashes that occurred on the Strategic Road Network of England in 2012. The datasets are modelled by injury severity using multivariate Poisson lognormal regression, with multivariate spatial effects for the link-based model, using a full Bayesian inference approach. The results of the condition-based approach show that high speeds trigger crash frequency. The outcome of the link-based model is the opposite; suggesting that the speed–crash relationship is negative regardless of crash severity. The differences between the results imply that data aggregation is a crucial, yet so far overlooked, methodological element of crash data analyses that may have direct impact on the modelling outcomes.     

A study of the feature‐based digital image stabilization system

Abstract

This article presents a digital image stabilization scheme that uses image processing techniques to compensate for undesirable image jitter due to vehicle or platform vibration to obtain a stabilized image display. The developed digital image stabilization system is based on the image combination approach combined with advanced image selection, feature detection, feature matching and pre‐rotation processing to produce crisp images. Using the Sobel edge detector, we calculate the magnitude of edge response as the judgment criteria for image transformation. To demonstrate the validity of the proposed technique, experimental results are given for some synthetic images.     

New cars — new materials

Due to more demanding requirements of car occupants in relation to comfort and safety enhancing measures, the weight of cars has been increasing, and as a result additional difficulties have been encountered in making lighter cars. In the development of every new car there is a search for new ways to combine the demands of the customers with reducing the weight of new cars. Further progress in optimizing steel body design can only take place gradually. Reinforced steel or tailored blanks are already in common use today. Even further reductions can be achieved by design in aluminium, magnesium or plastics. At Daimler–Benz, for example, the hard-top of the SL-sports-car is made of aluminium and the petrol tank partition panel of the SLK-roadster is made of die-cast magnesium. Lightweight design and, consequently, fuel saving will only be successfully realized, if proper materials are selected for appropriate parts.     

Non-saturated ion diffusion in concrete – A new approach to evaluate conductivity measurements

Non-saturated ion diffusion properties of cementitious materials were evaluated in an experimental study. To assess these properties, resistivity measurements have been performed on mortars with different binders (ordinary Portland cement – OPC, OPC with 5% silica fume, 40% slag and 70% slag, respectively) and different water-to-binder ratios (w/b, 0.38 and 0.53). Specimens have been conditioned to eight different climates with relative humidity (RH) from 100% to 33% RH in order to assess an effective diffusion coefficient. The results from the resistivity measurements have been corrected for changes of the conductivity of the pore solution when drying to different degrees of saturation.The diffusion coefficients for Portland cement binders within the range 100–59% RH are presented. They showed that the diffusion coefficient of the mortar with high w/b ratio was higher at high RH, but at low RH the opposite trend was found. By comparing these results with the corresponding desorption isotherms, it is shown that the diffusion coefficient for the two w/b ratios have the same dependency on the degree of saturation.     

Reactive extrusion and melt spinning—A new technological route to special fibres

This paper outlines the results of an online coupling of a twin screw (TS-) extruder with a melt spinning head. It deals with both theoretical and experimental investigations and the practical realization of such a (up to now rarely used) technological route in melt spinning to produce an elastomeric polyolefin fibre. This paper is a detailed continuation of former presentations (R. Beyreuther et al., in 14th PPS-Meeting. Yokohoma, Japan, June 98, Ext. Abs. S717–718; M. Hoffmann et al., in 15th PPS-Meeting, Hertogenbosch, NL, May/June 1999, Proc. Paper 144; M. Hoffmann et al., Chem. Fibers Int. (CFI) 49(5) (1999) p. 410; M. Hoffmann et al., in Polymerwerkst. '98, Tagungsb., S. 582, Merseburg, Germany, September 1998; R. Lü and H.-G. Fritz, in Polymerwerkst. '98, Tagungsb., S. 572, Merseburg, Germany, September 1998; R. Beyreuther et al., in 3rd ESAFORM Conf. on Mat. Forming, Proc., Stuttgart, Germany, April 2000, p. I-3; R. Beyreuther et al., in Int. Pol. Proc. XI, 1996, p.154; R. Beyreuther, H. Brünig and R. Vogel, in Polymeric Material Encyclopedia: Synthesis, Properties and Applications, Vol. 6 (CRC Press, Boca Raton, FL, 1996) p. 4061; R. Vogel, G. Schauer and R. Beyreuther, Chem. Fibers Inter. (CFI) 45 (1995) p. 268).     

A broad review about face recognition – feature extraction and recognition techniques

Abstract

Face recognition (FR) throws open a vast horizon of challenging tasks in the arena of facial image processing applications and computer visualisation, and hence has riveted keen interest during the last few years on account of its versatile applications in numerous spheres. Creating a useful facial design from initial face images is a very important gradient for victorious facial expression detection. Here, we furnish a report of several feature extraction and recognition methods which find themselves employed in the method of FR. The major aim of this survey is to assess the diverse FR methods according to their feature extraction and recognition techniques. From the analysis, we come to know about the feature extraction and recognition methods which have been elegant utilised in the FR procedure. They also vividly establish the technique which has performed excellently yielding superior FR precision by detecting face images more exactly. Moreover our study draws a concise picture of the feature extraction and recognition techniques and acts as a lodestar to the incoming intriguing investigators intending to increase their information about this innovative technique.     

RNA-Based Biocontrols—A New Paradigm in Crop Protection

Modern agribusiness plays a vital role in safeguarding and improving the production, quality, and quantity of food, feed, fiber, and fuel. Growing concerns over the impact of chemical pesticides on health and the environment have stimulated the industry to search for alternative and greener solutions. Over the last years, the RNA interference (RNAi) process has been identified as a very promising new approach to complement the arsenal of foliar spray, soil, or seed treatments applied as chemical and biological pest control agents, and of plant-incorporated protectants (PIPs). RNA-based active ingredients (AIs) possess a unique mode of action and can be implemented via both genetic modification (GM) and biocontrol approaches. RNA-based AIs promise to deliver the selectivity and sustainability desired in future crop protection agents. This is due to their utilization of a natural process to exert control and their high level of selectivity, which leads to reduced risk for non-target organisms (NTOs). This review discusses the advantages and limitations of RNA-based solutions in crop protection and recent research progress toward RNA-based biocontrols against the Colorado potato beetle (CPB), corn rootworm (CRW), and soy stink bug (SSB). Many challenges still exist on the road to the implementation of a broad range of RNA-based products and their widespread use and application. Despite these challenges, it can be expected that RNA-based AIs will become valuable new tools complementing the current arsenal of crop-protection solutions.