High-utility and diverse itemset mining

High-utility Itemset Mining (HUIM) finds patterns from a transaction database with their utility no less than a user-defined threshold. The utility of an itemset is defined as the sum of the utilities of its items. The utility notion enables a data analyst to associate a profit score with each item and thereof to a pattern. We extend the notion of high-utility with diversity to define a new pattern type called High-utility and Diverse pattern (HUD). The notion of diversity of a pattern captures the extent of the different categories covered by the selected items in the pattern. An application of diverse-pattern lies in the recommendation task where a system can recommend to a customer a set of items from a new class based on her previously bought items. Our notion of diversity is easy to compute and also captures the basic essence of a previously proposed diversity notion. The existing algorithm to compute frequent-diverse patterns is 2-phase, i.e., in the first phase, frequent patterns are computed, out of which diverse patterns are filtered out in the second phase. We, in this paper, give an integrated algorithm that efficiently computes high-utility and diverse patterns in a single phase. Our experimental study shows that our proposed algorithm is very efficient as compared to a 2-phase algorithm that extracts high-utility itemsets in the first phase and filters out the diverse itemsets in the second phase.

     

Biological trace element research: a multidisciplinary science

The last decade may be regarded as a crucial turning point in new developments in many areas of biological trace element research. It is slowly being recognized as a multidisciplinary science which requires a combination of biological insight and analytical awareness in planning the studies. It is also acknowledged that the complexities involved in dealing with the requirements of trace element research studies in the life sciences demand comprehensive planning of the investigations and use of a variety of techniques, thus bringing together a variety of talents. It cannot be emphasized enough that accurate analytical measurements on biologically and analytically "valid" samples hold the key for success in future biological trace element research studies. These aspects are illustrated.     

A Novel High Nitrogen Steel Powder Designed for Minimized Cr2N Precipitations

High nitrogen steels provide excellent mechanical properties and corrosion resistance but are prone to form precipitates which adversely affect the corrosion resistance and toughness. High nitrogen steel powders currently available in the market are not claimed to be precipitate free. It is critical to avoid these precipitates while retaining nitrogen in the dissolved form to realize the value of these powder alloys. However, retaining high level of dissolved nitrogen in steel powder during melt atomization process is very challenging. Instead, solid-state dissolution of nitrogen into the powder alloy followed by rapid cooling may provide a convenient approach to avoid precipitate formation compared to traditional melt processing. This study presents a solution treatment approach to achieve elevated dissolved nitrogen levels (~ 0.4 wt pct) in Fe–Mn–Cr powder alloy with negligible precipitation of nitrides. The influence of starting material, holding time, temperature and cooling rate on the resulting microstructure is presented. A fully austenite matrix with high dissolved nitrogen content resulted in powders with desired mechanical properties.

     

Synergic influence of a surfactant and ultrasonication on the preparation of soluble,conducting polydiphenylamine/silica‐nanoparticle composites

Conducting polydiphenylamine was used to encapsulate silica nanoparticles through the oxidative polymerization of diphenylamine in the presence of ultrasonic irradiation. The polymerization was performed in the presence of sodium lauryl sulfate as a surfactant. Experiments performed in the absence of ultrasound clearly demonstrated that the application of ultrasonication played multiple roles in the preparation of a composite of polydiphenylamine with silica nanoparticles. Ultrasonication dispersed the silica nanoparticles, converted sodium lauryl sulfate to lauryl alcohol, and augmented the dispersion of the silica‐nanoparticle/polydiphenylamine composite in an organic medium. Silica‐nanoparticle/polydiphenylamine composites were also prepared in the absence of ultrasound and/or sodium lauryl sulfate. The silica‐nanoparticle/polydiphenylamine composites were characterized with Fourier trans form infrared spectroscopy, ultraviolet–visible/near‐infrared spectroscopy, and thermogravimetric analysis. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 102: 3912–3918, 2006     

Role of adhesive–substrate compatibility in adhesion

For substrates such as polyesters having limited capacity for hydrogen bonding or other specific interactions, thermodynamic compatibility of the substrate and adhesive is shown to be a key factor in promoting bondability to the substrate. Such compatibility occurs, as shown by Abere, when the cohesive energy densities (CED) or solubility parameters (δ = √CED) of substrate and adhesive are matched. Investigations with polyester film-adhesive-film model systems with the use of a variety of nonpolar (hydrocarbon) and polar (chlorinated compounds, ethers, esters) adhesives illustrate how compatibility promotes bondability to poly(ethylene terephthalate). The poor adhesion of polyester fibers to resorcinol–formaldehyde–latex (RFL) adhesives is attributed to the incompatibility of resorcinol (δ = 16.0) with the polyester (δ = 10.3). Adhesion to RFL was improved by substituting the more compatible n-hexyl resorcinol (δ = 12.5) for resorcinol in RFL adhesives. Currently, the best adhesive systems for polyester tire yarns are those (e.g., isocyanate–epoxy) involving formation of urethane polymers having matching δ values with poly(ethylene terephthalate).     

Novel electrically conductive and ferromagnetic composites of poly(aniline‐co‐aminonaphthalenesulfonic acid) with iron oxide nanoparticles: Synthesis and characterization

Nanocomposites of iron oxide (Fe₃O₄) with a sulfonated polyaniline, poly(aniline‐co‐aminonaphthalenesulfonic acid) [SPAN(ANSA)], were synthesized through chemical oxidative copolymerization of aniline and 5‐amino‐2‐naphthalenesulfonic acid/1‐amino‐5‐naphthalenesulfonic acid in the presence of Fe₃O₄ nanoparticles. The nanocomposites [Fe₃O₄/SPAN(ANSA)‐NCs] were characterized by transmission electron microscopy (TEM), scanning electron microscopy (SEM), X‐ray diffraction (XRD), Fourier transform infrared (FTIR) spectroscopy, elemental analysis, UV–visible spectroscopy, thermogravimetric analysis (TGA), superconductor quantum interference device (SQUID), and electrical conductivity measurements. The TEM images reveal that nanocrystalline Fe₃O₄ particles were homogeneously incorporated within the polymer matrix with the sizes in the range of 10–15 nm. XRD pattern reveals that pure Fe₃O₄ particles are having spinel structure, and nanocomposites are more crystalline in comparison to pristine polymers. Differential thermogravimetric (DTG) curves obtained through TGA informs that polymer chains in the composites have better thermal stability than that of the pristine copolymers. FTIR spectra provide information on the structure of the composites. The conductivity of the nanocomposites (～ 0.5 S cm^?1) is higher than that of pristine PANI (～ 10^?3 S cm^?1). The charge transport behavior of the composites is explained through temperature difference of conductivity. The temperature dependence of conductivity fits with the quasi‐1D variable range hopping (quasi‐1D VRH) model. SQUID analysis reveals that the composites show ferromagnetic behavior at room temperature. The maximum saturation magnetization of the composite is 9.7 emu g^?1. © 2007 Wiley Periodicals, Inc. J Appl Polym Sci, 2007     

Melting points of synthetic wax esters

Saturated, monoenoic and dienoic wax esters, C₂₆−C₄₀, have been synthesized from even-numbered fatty alcohols and acids. In homologous series of saturated esters, the increments of melting points follow a regular trend except for those esters which have an acid moiety two carbon atoms shorter than the alcohol moiety. These wax esters have melting points higher than interpolation would predict. Monoenoic wax esters with the double bond in the alcohol chain have melting points about 10 C higher than their isomers with the double bond in the acid chain.     

Characterization and preparation of new multiwall carbon nanotube/conducting polymer composites by in situ polymerization

Composites based on poly(diphenyl amine) (PDPA) and multiwall carbon nanotubes (MWNTs) were prepared by chemical oxidative polymerization through two different approaches: in situ polymerization and intimate mixing. In in situ polymerization, DPA was polymerized in the presence of dispersed MWNTs in sulfuric acid medium for different molar composition ratios of MWNT and DPA. Intimate mixing of synthesized PDPA with MWNT was also used for the preparation of PDPA/MWNT composites. Transmission electron microscopy revealed that the diameter of the tubular structure for the composite was 10–20 nm higher than the diameter of pure MWNT. Scanning electron microscopy provided evidence for the differences in the morphology between the MWNTs and the composites. Raman and Fourier transform IR (FTIR) spectroscopy, thermogravimetric analysis, X‐ray diffraction, and UV–visible spectroscopy were used to characterize the composites and reveal the differences in the molecular level interactions between the components in the composites. The Raman and FTIR spectral results revealed doping‐type molecular interactions and coordinate covalent‐type interactions between MWNT and PDPA in the composite prepared by in situ polymerization and intimate mixing, respectively. The backbone structure of PDPA in the composite decomposed at a higher temperature (>340°C) than the pristine PDPA (～300°C). This behavior also favored the molecular level interactions between MWNT and PDPA in the composite. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 101: 3721–3729, 2006     

A model-based approximate λ-policy iteration approach to online evasive path planning and the video game Ms. Pac-Man

This paper presents a model-based approximate λ-policy iteration approach using temporal differences for optimizing paths online for a pursuit-evasion problem, where an agent must visit several target positions within a region of interest while simultaneously avoiding one or more actively pursuing adversaries. This method is relevant to applications, such as robotic path planning, mobile-sensor applications, and path exposure. The methodology described utilizes cell decomposition to construct a decision tree and implements a temporal difference-based approximate λ-policy iteration to combine online learning with prior knowledge through modeling to achieve the objectives of minimizing the risk of being caught by an adversary and maximizing a reward associated with visiting target locations. Online learning and frequent decision tree updates allow the algorithm to quickly adapt to unexpected movements by the adversaries or dynamic environments. The approach is illustrated through a modified version of the video game Ms. Pac-Man, which is shown to be a benchmark example of the pursuit-evasion problem. The results show that the approach presented in this paper outperforms several other methods as well as most human players.     

Simulation based alternatives for overall process improvement at the cardiac catheterization lab

Cardiac catheterization is one of the critical procedures in patient care. It is pertinent for all process related issues in this department to be handled with due priority. This research is a cross-functional effort with a leading hospital that was in its planning stage to implement an overall process improvement at its cardiac catheterization lab department. It has been determined that significant process delays exist in this department. One of the identified key factors to process improvement was to reduce patient turnaround time. Process mapping was used to study the system and identify potential sources of delays in the system. A set of qualitative recommendations were put forward. These recommendations, include the reduction of wait time of outpatients and inpatients and the reduction of non-value-added times such as transfer time of patients, were evaluated using a discrete event simulation approach. The simulation study shows that the daily operating hours at the catheterization lab could be reduced, aiding to reallocate staff for discharging other duties, as the hospital may require.