Preference Matrix Research Articles

A Novel Framework for Fault Diagnosis Using Kernel Partial Least Squares Based on an Optimal Preference Matrix

In the standard kernel partial least squares (KPLS), the mapped data in the feature space need to be centralized before extraction of new score vectors. However, each vector of the centralized variables is often uniformly distributed, and some original features that can reflect the contribution of each variable to fault diagnosis might be lost. As a result, it might lead to misleading interpretations of the principal components and to increasing the false alarm rate for fault detection. To cope with these difficulties, a novel data-driven framework using KPLS based on an optimal preference matrix (OPM) is presented in this paper. In fault monitoring, an OPM is proposed to change the distribution of the variable and to readjust the eigenvalues of the covariance matrix. To obtain the OPM, the objective function can be determined in terms of the squared prediction error and Hotelling's T-squared (T <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) statistics. Two optimization algorithms, genetic algorithm and particle swarm optimization algorithm, are extended to maximize effectiveness of the OPM. Compared with traditional methods, the proposed method can overcome the drawback of original features loss of the centralized mapped data in the feature subspace and improve the accuracy of fault diagnosis. Also, few extra computation costs are needed in fault detection. Extensive experimental results on both the Tennessee Eastman benchmark process and the case study of the aluminum electrolytic production process give credible fault diagnosis.

Analisis Kelayakan Penggantian Nozzle Soot Blower pada PT. PJB UP Paiton Unit 1 dan 2

&lt;span class="fontstyle0"&gt;High electricity demand requires power companies to maintain the efficiency of every generation process. One factor affecting the efficiency of the production system is the reliability of the machine. Nozzle is a sparepart of the tool used to clean slaging on the wall of the boiler is Soot Blower . Soot Blower's current condition consumes steam nearly 400,000 kg/year from the ideal condition 332,000 kg/year. The high consumption of steam causes the high cost of coal and low efficiency Soot Blower. One alternative that can be offered is to replace the Nozzle with a new type that has a lower pressure that is Nozzle Gemini. The new alternative compared based on operational analysis that see comparison from preference matrix weight and financial analysis that see comparison on 10 year projection by Net Present Value(NPV), IRR and PP analysis. And it is known on both analysis of Gemini Nozzle usage is feasible to be applied.&lt;/span&gt;

Factorization Bandits for Interactive Recommendation

We perform online interactive recommendation via a factorization-based bandit algorithm. Low-rank matrix completion is performed over an incrementally constructed user-item preference matrix, where an upper confidence bound based item selection strategy is developed to balance the exploit/explore trade-off during online learning. Observable contextual features and dependency among users (e.g., social influence) are leveraged to improve the algorithm's convergence rate and help conquer cold-start in recommendation. A high probability sublinear upper regret bound is proved for the developed algorithm, where considerable regret reduction is achieved on both user and item sides. Extensive experimentations on both simulations and large-scale real-world datasets confirmed the advantages of the proposed algorithm compared with several state-of-the-art factorization-based and bandit-based collaborative filtering methods.

A development plan for the south-eastern part of Pag island with an emphasis on olive-growing

Regardless of the fact that the traditional usage of rural landscapes was agricultural, a degradation of landscape values, as well as an onset of natural succession, occur due to contemporary lifestyle. This can lead to negative effects regarding land-use change. This paper focuses on the south-eastern part of Pag island and explores the possibilities for the revitalisation of its neglected areas by envisioning its future development as an olive-growing region. The final goal was to define a planning procedure framework which would enable the creation of a strategic vision to be transformed into a comprehensive spatial development strategy for the research area. This area encompasses the territory between Kaštela in the north-west and the Pag’s bridge in the south-east which administratively belongs to the Zadar County and includes the Town of Pag, and the Kolan and Povljana municipalities. Olive-growing has been recognized as the strategic choice for development because of its tradition in the area and the potential integration with other relatable activities. Based on the SWOT analysis, an appropriate mission, a vision and strategic goals were defined for developing Pag as an olive-growing region. Further landscape planning methods included (1) the Lynch mapping analysis, (2) the Forman and Godron landscape ecology analysis and (3) the landscape pattern analysis. The results were then used together with digital orthophoto imagery to overlay and analyse relevant information. Hand drawings as well as AutoCAD, ArcGIS and image editing computer programmes were used in the process. This analytical phase was then followed by the development of several alternative spatial zonings, diagrams and concepts based on a preferable neighbourhood matrix and the activity sizing table. The planning process resulted in a concept for spatial development of the research area which would enable the implementation of the strategic vision. The main goal of this planning procedure was to preserve and improve the rural landscape of Pag island.

Mining Coherent Topics With Pre-Learned Interest Knowledge in Twitter

Discovering semantic coherent topics from the large amount of user-generated content (UGC) in social media would facilitate many downstream applications of intelligent computing. Topic models, as one of the most powerful algorithms, have been widely used to discover the latent semantic patterns in text collections. However, one key weakness of topic models is that they need documents with certain length to provide reliable statistics for generating coherent topics. In Twitter, the users’ tweets are mostly short and noisy. Observations of word co-occurrences are incomprehensible for topic models. To deal with this problem, previous work tried to incorporate prior knowledge to obtain better results. However, this strategy is not practical for the fast evolving UGC in Twitter. In this paper, we first cluster the users according to the retweet network, and the users’ interests are mined as the prior knowledge. Such data are then applied to improve the performance of topic learning. The potential cause for the effectiveness of this approach is that users in the same community usually share similar interests, which will result in less noisy sub-data sets. Our algorithm pre-learns two types of interest knowledge from the data set: the interest-word-sets and a tweet-interest preference matrix . Furthermore, a dedicated background model is introduced to judge whether a word is drawn from the background noise. Experiments on two real life twitter data sets show that our model achieves significant improvements over state-of-the-art baselines.

Interval MULTIMOORA method with target values of attributes based on interval distance and preference degree: biomaterials selection

A target-based MADM method covers beneficial and non-beneficial attributes besides target values for some attributes. Such techniques are considered as the comprehensive forms of MADM approaches. Target-based MADM methods can also be used in traditional decision-making problems in which beneficial and non-beneficial attributes only exist. In many practical selection problems, some attributes have given target values. The values of decision matrix and target-based attributes can be provided as intervals in some of such problems. Some target-based decision-making methods have recently been developed; however, a research gap exists in the area of MADM techniques with target-based attributes under uncertainty of information. We extend the MULTIMOORA method for solving practical material selection problems in which material properties and their target values are given as interval numbers. We employ various concepts of interval computations to reduce degeneration of uncertain data. In this regard, we use interval arithmetic and introduce innovative formula for interval distance of interval numbers to create interval target-based normalization technique. Furthermore, we use a pairwise preference matrix based on the concept of degree of preference of interval numbers to calculate the maximum, minimum, and ranking of these numbers. Two decision-making problems regarding biomaterials selection of hip and knee prostheses are discussed. Preference degree-based ranking lists for subordinate parts of the extended MULTIMOORA method are generated by calculating the relative degrees of preference for the arranged assessment values of the biomaterials. The resultant rankings for the problem are compared with the outcomes of other target-based models in the literature.

Development of a prototype blood fractionation cartridge for plasma analysis by paper spray mass spectrometry

Drug monitoring of biofluids is often time consuming and prohibitively expensive. Analysis of dried blood spots offers advantages, such as reduced sample volume, but depends on extensive sample preparation and the presence of a trained lab technician. Paper spray mass spectrometry allows rapid analysis of small molecules from blood spots with minimal sample preparation, however, plasma is often the preferred matrix for bioanalysis. Plasma spots can be analyzed by paper spray MS, but a centrifugation step to isolate the plasma is required. We demonstrate here the development of a paper spray cartridge containing a plasma fractionation membrane to perform automatic on-cartridge plasma fractionation from whole blood samples. Three commercially available blood fractionation membranes were evaluated based on: 1) accuracy of drug concentration determination in plasma, and 2) extent of cell lysis and/or penetration. The accuracy of drug concentration determination was quantitatively determined using high performance liquid chromatography–mass spectrometry (HPLC–MS). While the fractionation membranes were capable of yielding plasma samples with low levels of cell lysis, the membranes did exhibit drug binding to varying degrees, as indicated by a decrease in the drug concentration relative to plasma obtained by centrifugation. Using the membrane exhibiting the lowest binding, we developed a composite paper spray cartridge incorporating the selected fractionation membrane. Quantitative analysis of the plasma samples by paper spray MS yielded results similar to those found with HPLC–MS, but without the need for offline extraction or chromatography.

Interval target-based VIKOR method supported on interval distance and preference degree for machine selection

By considering target values for attributes in addition to beneficial and non-beneficial attributes, a traditional MADM technique is converted to a comprehensive form. In many machine selection problems, some attributes have given target values. The target value regarding a machine attribute can be reported as a range of data. Some target-based decision-making methods have recently been developed; however, a research gap exists in the area. For example, fuzzy axiomatic design approach presents a target-based decision-making supported on common area of membership functions of alternative ratings and target values of attributes. However, it has detects on finding a complete ranking because of probable infinite values of assessment index. Two target-based VIKOR models with interval data exist in the literature; however, the target values of attributes or ratings of alternatives on attributes are crisp numbers in the models and their formulations may have some limitations. The present paper tries to fill the gap by developing the VIKOR method with both interval target values of attributes and interval ratings of alternatives on attributes. Moreover, we attempt to utilize the power of interval computations to minimize degeneration of uncertain information. In this regard, we employ interval arithmetic and introduce a new normalization technique based on interval distance of interval numbers. We use a preference matrix to determine extremum and rank interval numbers. Two machine selection problems concerning punching equipment and continuous fluid bed tea dryer are solved employing the proposed method. Preference-degree-based ranking lists are formed by calculating the relative degrees of preference for the arranged assessment values of the candidate machines. The resultant rankings for the problems are compared with the results of fuzzy axiomatic design approach and the interval target-based MULTIMOORA method and its subordinate parts.

Evidence of ochratoxin A conjugates in urine samples from infants and adults

Ochratoxin A (OTA), a mycotoxin with nephrotoxic and carcinogenic properties, is an important contaminant of food and feed. Analysis of OTA in human biological fluids (blood, urine, or breast milk) has documented frequent exposure to this mycotoxin, yet at quite variable levels in different population groups across the world. Urine is the preferred matrix in biomonitoring since sample collection is non-invasive and better accepted by study participants. As only a small fraction of the ingested OTA is excreted in urine, determination of urinary OTA requires sensitive analytical techniques, and phase-II-metabolites should be also considered as biomarkers of exposure. Yet, data published so far on the presence of OTA-glucuronide/sulfate in human urine have been contradictory. In this study, urines (n = 38) from two groups of breastfed infants (German and Turkish) and from German adults were now analysed for the presence of OTA glucuronides or sulfates by an indirect method, i.e. by comparing the levels of OTA (aglycone) in urines without and after enzymatic hydrolysis with ß-glucuronidase/arylsulfatase. Additionally, ochratoxin A-8-β-glucuronide and open lactone ochratoxin A-8-β-glucuronide were synthesized to serve as reference materials for metabolite analysis. Attempts for definitive confirmation of glucuronides of OTA via direct identification in LC-MS/MS analysis were hampered by the lower ionizability of the conjugates compared to the parent compound. Considerable increases in OTA levels were found after enzymatic hydrolysis in several (not all) urine samples and provide clear evidence for the excretion of OTA-conjugates. The latter observation is of importance, since OTA phase-II-metabolites may escape detection when direct methods are applied for urinary biomarker analysis. In conclusion, enzymatic hydrolysis of urine samples is highly advisable in order to avoid an underestimation of the OTA-exposure.

Exploiting long‐term and short‐term preferences and RFID trajectories in shop recommendation

SummaryShop recommendation in large shopping malls is useful in the mobile internet era. With the maturity of indoor positioning technology, customers' indoor trajectories can be captured by radio frequency identification devices readers, which provides a new way to analyze customers' potential preferences. In this paper, we design three methods for the top‐N shop recommendation problem. The first method is an improved matrix factorization method fusing estimated prior customer preference matrix that is constructed by Session‐based Temporal Graph computing. The second method is a Bayesian personalized ranking method based on the first method. The third method is by tensor decomposition combined with Session‐based Temporal Graph. Besides, we exploit customer history radio frequency identification devices trajectory information to find customers' frequent paths and revise predicted rating values to improve recommendation accuracy. Our methods are effective in modeling customers' temporal dynamics. At the same time, our approach considers repeated recommendation of the same shop by designing rating update rules. The test dataset is formed by JoyCity customer behavior records. JoyCity is a large‐scale modern shopping center in downtown Shanghai, China. The results show that our approaches are effective and outperform previous state‐of‐the‐art approaches. Copyright © 2016 John Wiley &amp; Sons, Ltd.

Development and fabrication of a two-layer tissue engineered osteochondral composite using hybrid hydrogel-cancellous bone scaffolds in a spinner flask

Biological treatment using engineered osteochondral composites has received growing attention for the repair of cartilage defects. Osteochondral composites combined with a dynamic culture provide great potential for improving the quality of constructs and cartilage regeneration as dynamic conditions mimic the in vivo condition where cells were constantly subjected to mechanical and chemical stimulation. In the present study, biophasic composites were produced in vitro consisting of cell-hydrogel (CH) and cell-cancellous bone (CB) constructs, followed by culturing in a dynamic system in a spinner flask. The aim of this study was to investigate cell behaviors (i.e. cell growth, differentiation, distribution and matrix deposition) cultured in different constructs under static and dynamic circumstances. As a result, we found that mechanical stimulation promoted osteogenic and chondrogenic differentiation of cells as indicated by the increased expression of ALP and glycosaminoglycan (GAG) in either bone or cartilage substitute materials. Dynamic culture yielded a preferable extracellular matrix production, particularly in hydrogel scaffolds. In addition, the enhanced mass transfer contributed to the interface formation, cells infiltration and distribution in the osteochondral composites. This study demonstrates that osteochondral composites incorporated with a dynamic culture improved the performance of the constructs, providing the basis for a promising tool and a better strategy for the rapid fabrication of osteochondral substitutes and regeneration of injured cartilage.

New specific and sensitive biomonitoring methods for chemicals of emerging health relevance.

In this publication the challenges to cope for the aim to obtain innovative biomonitoring methods in our laboratory are visualized for di(2-propylheptyl)phthalate, 2-mercaptobenzothiazole, 3,5-di-tert-butyl-4-hydroxytoluene, 4-nonylphenol, 4-tert-octylphenol, 3-(4-methylbenzylidene)camphor, 4,4'-methylene diphenyl diisocyanate, and Hexabromocyclododecane. For these substances new specific markers were explored based on animal or human kinetic data with urine being the preferred matrix compared to blood. The determination of these markers was complex in all cases, because the sample preparation as well as the detection by high performance liquid chromatography, capillary gas chromatography coupled to tandem mass spectrometers or high resolution mass spectrometry should enable the lowest possible detection limit by use of minimal biological sample volumes. To get a first hint of a possible background level, the analytical methods were applied to urine samples of about 40 persons for each chemical. For Di(2-propylheptyl)phthalate and 2-Mercaptobenzothiazole first results are presented from population biomonitoring.

Using extension sets to aggregate partial rankings in a flexible setting

This paper deals with the rank aggregation problem in a general setting; in particular, we approach the problem for any kind of ranking: complete or incomplete and with or without ties. The underlying idea behind our approach is to take into account the so-called extension set of a ranking, that is, the set of permutations that are compatible with the given ranking. In this way we aim to manage the uncertainty inherent to this problem, when not all the items are ranked and/or when some items are equally preferred. We develop two approaches: a general one based on this idea, and a constrained version in which the extension set is limited by not allowing non-ranked items to be placed in an existent bucket of tied items. We test our proposal by coupling it with two different algorithms. We formalize our approaches mathematically and also carry out an extensive experimental evaluation by using 22 datasets. The results show that the use of our extension sets-based approaches to compute the precedence matrix, clearly outperforms the standard way of computing the preference matrix by only using the information explicitly provided by the rankings in the sample.

Improved Personalized Recommendation based on Causal Association Rule and Collaborative Filtering

There are usually limited user evaluation of resources on a recommender system, which caused an extremely sparse user rating matrix, and this greatly reduce the accuracy of personalized recommendation, especially for new users or new items. This paper presents a recommendation method based on rating prediction using causal association rules. First, users and items are mapped into two feature vectors, which would be minded later to get the causal association rules from the perspective of data mining; then based on the casual association rules, the authors create a preference matrix which would predict the rating of the items that users have not rated; finally a nearest neighbor similarity measure method is designed for personalized recommendation. Experiment shows that the algorithm efficiently improves the recommendation comparing to traditional methods.

A novel framework to alleviate the sparsity problem in context-aware recommender systems

ABSTRACTRecommender systems have become indispensable for services in the era of big data. To improve accuracy and satisfaction, context-aware recommender systems (CARSs) attempt to incorporate contextual information into recommendations. Typically, valid and influential contexts are determined in advance by domain experts or feature selection approaches. Most studies have focused on utilizing the unitary context due to the differences between various contexts. Meanwhile, multi-dimensional contexts will aggravate the sparsity problem, which means that the user preference matrix would become extremely sparse. Consequently, there are not enough or even no preferences in most multi-dimensional conditions. In this paper, we propose a novel framework to alleviate the sparsity issue for CARSs, especially when multi-dimensional contextual variables are adopted. Motivated by the intuition that the overall preferences tend to show similarities among specific groups of users and conditions, we first explore to construct one contextual profile for each contextual condition. In order to further identify those user and context subgroups automatically and simultaneously, we apply a co-clustering algorithm. Furthermore, we expand user preferences in a given contextual condition with the identified user and context clusters. Finally, we perform recommendations based on expanded preferences. Extensive experiments demonstrate the effectiveness of the proposed framework.

A method based on trust model for large group decision-making with incomplete preference information

A new method of solving large group decision-making problems with incomplete preference information is proposed in this paper. First, we introduce the trust viewpoint of access control, which belongs to the information technology field. Second, we establish subjective trust degree (i.e., direct trust degree) and objective trust degree (i.e., indirect trust degree) to better evaluate the level of trust and propose a compensation method based on a trust model to transfer the incomplete preference matrix into a complete preference matrix. Third, by adopting the method based on clustering to solve decision makers' weights, a ranking of alternatives is obtained by synthesizing the weights and the complete preference matrix. To obtain a more reasonable clustering result, we redefine the distance similarity formula based on analysis of the previous problems, then combine it with cosine similarity to propose a double clustering model. Finally, a numerical example is used to demonstrate the effectiveness of the proposed method in this paper and comparison and analysis are conducted.

Hybrid Decision-making Method for Emergency Response System of Unattended Train Operation Metro

Suitable selection of the emergency alternatives is a critical issue in emergency response system of Unattended Train Operation (UTO) metro system of China. However, there is no available method for dispatcher group in Operating Control Center (OCC) to evaluate the decision under emergency situation. It was found that the emergency decision making in UTO metro system is relative with the preferences and the importance of multi-dispatcher in emergency. Regarding these factors, this paper presents a hybrid method to determinate the priority weights of emergency alternatives, which aggregates the preference matrix by constructing the emergency response task model based on the Weighted Ordered Weighted Averaging (WOWA) operator. This calculation approach derives the importance weights depending on the dispatcher emergency tasks and integrates it into the Ordered Weighted Averaging (OWA) operator weights based on a fuzzy membership relation. A case from train fire is given to demonstrate the feasibility and practicability of the proposed methods for Group Multi-Criteria Decision Making (GMCDM) in emergency management of UTO metro system. The innovation of this research is paving the way for a systematic emergency decision-making solution which connects the automatic metro emergency response system with the GMCDM theory.

Human neutrophil elastase peptide sensors conjugated to cellulosic and nanocellulosic materials: part I, synthesis and characterization of fluorescent analogs

Here we describe the synthesis and characterization of peptide conjugated cellulose and nanocellulose materials as sensors for fluorescent detection of human neutrophil elastase (HNE). The cellulose sensor surfaces selected are filter paper (FP) and print cloth (PC) fabric, which are composed of processed cotton fibers. The nanocellulose based sensors have transducer surfaces comprised of cellulose nanocrystals (wCNC) and microfibrillated cellulose (MFC) derived from wood that are fabricated as wood nanocellulose composites (wNCCs) consisting of blended quantities of nanocrystalline and MFC at 66/33 and 50/50 ratios. These ratios were selected to examine the effect of significantly different CNC loadings had on surface area and peptide uptake. The fluorescent peptide HNE substrate, n-succinyl-Ala-Pro-Ala-4-amido-7-methylcoumarin (Pep) was attached to both cellulosic and nanocellulosic matrices and conjugated peptide analogs were confirmed by mass spectrometry (MS) and infrared (IR). The nanocellulose biosensors wCNC-Pep (3c) and wNCC-Pep (4c, 66/33 and 5c, 50/50) have higher levels of peptide incorporation than the cellulosic biosensors FP-Pep (1c) and PC-Pep (2c). The range of incorporation for the cellulosic sensors is 7–25 μg/mg and for the nanocellulose sensors 30–80 μg/mg. The degree of substitution of peptide was found to be in the order of approximate number of peptides per 200 anhydroglucose residues, 1 in PC-Pep (2c), 2 in FP-Pep (1c), 4 in wNCC-Pep (5c, 50/50), 6 in wNCC-Pep (4c, 66/33), and 12 in wCNC-Pep (3c). The specific surface areas of the sensors ranged from 0.016 to 261 m2 g−1 and correlated with degree of substitution of peptide on the cellulosic and nanocellulosic surfaces. Of the cellulose and nanocellulose biosensors, the wCNC-Pep (3c) has the highest level of peptide incorporation and the highest specific surface area, which makes it the preferred sensor matrix for human neutrophil elastase.

지표평균법 및 PROMETHEE 결과 종합에 의한 홍수위험도 분석

This study has performed the flood risk assessment in order to provide preliminary information in the establishment of flood risk management and damage reduction strategies. The twelve representative flood risk factors were carefully selected for the flood risk assessment based on the P-S-R(Pressure-State-Response) classification system, and spatially constructed for the nationwide 812 standard watersheds of the national water resource unit map. The relative flood risk was estimated by the two methods; the one is a FRI(Flood Risk Index) by averaging the three flooding indexes such as PI(Pressure Index), SI(State Index), and RI(Response Index) by each four flood risk factor classified from the twelve factors, and the other is the PROMETHEE(Preference Ranking Organization METHod for Enrichment Evaluation) by estimating a complete outranking from the preference matrix analysis for the twelve alternatives. This study has newly presented the final flood risk determined by the higher risk value of two flood risk assessment results, which is expected to be used to identify flooding risk areas in terms of the integrated flood risk management.

A Review on Fruit Juice Probiotication: Pomegranate

Foods and beverages containing live microbes (probiotics) are increasingly promoted by health professionals nowadays. The probiotic products in the market are mostly milk-based products, for instance yoghurts. There has been a high demand for the non-dairy probiotic products from those having the lactose intolerance problem and/or worry about the high cholesterol content. Therefore, fruit is now becoming the preferable matrix for probiotic delivery in human body. Fruits could be another promising carrier for probiotic strains, particularly from the genera of Lactobacilli and Bifidobacteria. Somehow, the cell viability and stability are highly fruit and strain dependent, in addition to the processing factors and storage temperature. In the present review, fruits, particularly pomegranate is critically highlighted as a potential fruity vehicle for probiotic microbiota. Pomegranate contains bioactive secondary metabolites (anthocyanins, ellagic acid derivatives and hydrolyzable tannins) and non-digestible carbohydrates (prebiotics). The low pH value of pomegranate juice could be compromised by mixing with other fruits or by protecting probiotics from acidic environment by microencapsulation. This review covers the previous works which were carried out on the fruit-based probiotic foods and beverages, supported by the mechanistic explanation on the action of probiotics in human body.