Добірка наукової літератури з теми "Method of k-means"

We propose a novel method for adaptive K-means clustering. The proposed method overcomes the problems of the traditional K-means algorithm. Specifically, the proposed method does not require prior knowledge of the number of clusters. Additionally, the initial identification of the cluster elements has no negative impact on the final generated clusters. Inspired by cell cloning in microorganism cultures, each added data sample causes the existing cluster ‘colonies’ to evaluate, with the other clusters, various merging or splitting actions in order for reaching the optimum cluster set. The proposed algorithm is adequate for clustering data in isolated or overlapped compact spherical clusters. Experimental results support the effectiveness of this clustering algorithm.

There are various methods of objects’ clusterization used in different areas of machine learning. Among the vast amount of clusterization methods, the K-means method is one of the most popular. Such a method has as pros as cons. Speaking about the advantages of this method, we can mention the rather high speed of objects clusterization. The main disadvantage is a necessity to know the number of clusters before the experiment. This paper describes the new way and the new method of clusterization, based on the K-means method. The method we suggest is also quite fast in terms of processing speed, however, it does not require the user to know in advance the exact number of clusters to be processed. The user only has to define the range within which the number of clusters is located. Besides, using suggested method there is a possibility to limit the radius of clusters, which would allow finding objects that express the criteria of one cluster in the most distinctive and accurate way, and it would also allow limiting the number of objects in each cluster within the certain range.

Two new initialization methods for K-means clustering are proposed. Both proposals are based on applying a divide-and-conquer approach for the K-means‖ type of an initialization strategy. The second proposal also uses multiple lower-dimensional subspaces produced by the random projection method for the initialization. The proposed methods are scalable and can be run in parallel, which make them suitable for initializing large-scale problems. In the experiments, comparison of the proposed methods to the K-means++ and K-means‖ methods is conducted using an extensive set of reference and synthetic large-scale datasets. Concerning the latter, a novel high-dimensional clustering data generation algorithm is given. The experiments show that the proposed methods compare favorably to the state-of-the-art by improving clustering accuracy and the speed of convergence. We also observe that the currently most popular K-means++ initialization behaves like the random one in the very high-dimensional cases.

<span>Learning class is a collection of several students in an educational institution. Every beginning of the school year the educational institution conducts a grouping class test. However, sometimes class grouping is not in accordance with the ability of students. For this reason, a system is needed to be able to see the ability of students according to the desired parameters. Determination of the weight of test scores is done using the K-Means method as a grouping method. Iteration or repetition process in the K-Means method is very important because the weight value is still very possible to change. Therefore, the repetition process is carried out to produce a value that does not change and is used to determine the ability level of students. The results of the class grouping test scores affect the ability of students. Application of K-Means method is used in building an information system grouping student admissions in an educational institution. Acceptance of students will be grouped into 3 groups of learning classes. The results of testing the system that applies K-Means method and based on data on the admission of prospective students from educational institutions have very high accuracy with an error rate of 0.074. </span>

The paper considers the approach to the detection of collective anomalies in time series, based on the use of clustering methods, in particular the method of k-means, as well as the effectiveness of their application.

Structural genomics is a field of study that strives to derive and analyze the structural characteristics of proteins through means of experimentation and prediction using software and other automatic processes. Alongside implications for more effective drug design, the main motivation for structural genomics concerns the elucidation of each protein’s function, given that the structure of a protein almost completely governs its function. Historically, the approach to derive the structure of a protein has been through exceedingly expensive, complex, and time consuming methods such as x-ray crystallography and nuclear magnetic resonance (NMR) spectroscopy.

In response to the inadequacies of these methods, three families of approaches developed in a relatively new branch of computer science known as bioinformatics. The aforementioned families include threading, homology-modeling, and the de novo approach. However, even these methods fail either due to impracticalities, the inability to produce novel folds, rampant complexity, inherent limitations, etc. In their stead, this work proposes the Fuzzy Greedy K-means Decision Forest model, which utilizes sequence motifs that transcend protein family boundaries to predict local tertiary structure, such that the method is cheap, effective, and can produce semi-novel folds due to its local (rather than global) prediction mechanism. This work further extends the FGK-DF model with a new algorithm, the Hierarchically Clustered-Hidden Markov Models (HC-HMM) method to extract protein primary sequence motifs in a more accurate and adequate manner than currently exhibited by the FGK-DF model, allowing for more accurate and powerful local tertiary structure predictions. Both algorithms are critically examined, their methodology thoroughly explained and tested against a consistent data set, the results thereof discussed at length.

Pristatomas duomenų gavybos ir grupavimo naudojimas paplitusiose sistemose bei sukurtas IT žinių portalo statistikos prototipas duomenų saugojimui, analizei ir peržiūrai atlikti. Siūlomas statistikos modulis duomenų saugykloje periodiškais laiko momentais vykdantis duomenų transformacijas. Portale prieinami statistiniai duomenys gali būti grupuoti. Sugrupuotą informaciją pateikus grafiškai, duomenys gali būti interpretuojami ir stebimi veiklos mastai. Panašių objektų grupėms išskirti pritaikytas vienas iš žinomiausių duomenų grupavimo metodų – lygiagretusis k-vidurkių metodas.
Presented data mining methods and clustering usage in current statistical systems and created statistics module prototype for data storage, analysis and visualization for IT knowledge portal. In suggested statistics prototype database periodical data transformations are performed. Statistical data accessed in portal can be clustered. Clustered information represented graphically may serve for interpreting information when trends may be noticed. One of the best known data clustering methods – parallel k-means method – is adapted for separating similar data clusters.

Abstract Cluster analysis has become one of the main tools used in extracting knowledge from data, which is known as data mining. In this area of data analysis, data of large dimensions are often processed, both in the number of objects and in the number of variables, which characterize the objects. Many methods for data clustering have been developed. One of the most widely used is a k-means method, which is suitable for clustering data sets containing large number of objects. It is based on finding the best clustering in relation to the initial distribution of objects into clusters and subsequent step-by-step redistribution of objects belonging to the clusters by the optimization function. The aim of this Ph.D. thesis was a comparison of selected variants of existing k-means methods, detailed characterization of their positive and negative characte- ristics, new alternatives of this method and experimental comparisons with existing approaches. These objectives were met. I focused on modifications of the k-means method for clustering of large number of objects in my work, specifically on the algorithms BIRCH k-means, filtering, k-means++ and two-phases. I watched the time complexity of algorithms, the effect of initialization distribution and outliers, the validity of the resulting clusters. Two real data files and some generated data sets were used. The common and different features of method, which are under investigation, are summarized at the end of the work. The main aim and benefit of the work is to devise my modifications, solving the bottlenecks of the basic procedure and of the existing variants, their programming and verification. Some modifications brought accelerate the processing. The application of the main ideas of algorithm k-means++ brought to other variants of k-means method better results of clustering. The most significant of the proposed changes is a modification of the filtering algorithm, which brings an entirely new feature of the algorithm, which is the detection of outliers. The accompanying CD is enclosed. It includes the source code of programs written in MATLAB development environment. Programs were created specifically for the purpose of this work and are intended for experimental use. The CD also contains the data files used for various experiments.

Covariance Matrix in target tracking algorithms has a critical role at multi- sensor track fusion systems. This matrix reveals the uncertainty of state es- timates that are obtained from diferent sensors. So, many subproblems of track fusion usually utilize this matrix to get more accurate results. That is why this matrix should be interchanged between the nodes of the multi-sensor tracking system. This thesis mainly deals with analysis of approximations of the covariance matrix that can best represent this matrix in order to efectively transmit this matrix to the demanding site. Kullback-Leibler (KL) Distance is exploited to derive some of the representations for Gaussian case. Also com- parison of these representations is another objective of this work and this is based on the fusion performance of the representations and the performance is measured for a system of a 2-radar track fusion system.

A pivotal moment in machine learning research was the creation of an important new research area, known as Ensemble Learning. In this work, we argue that ensembles are a very general concept, and though they have been widely used, they can be applied in more situations than they have been to date. Rather than using them only to combine the output of an algorithm, we can apply them to decisions made inside the algorithm itself, during the learning step. We call this approach Inner Ensembles. The motivation to develop Inner Ensembles was the opportunity to produce models with the similar advantages as regular ensembles, accuracy and stability for example, plus additional advantages such as comprehensibility, simplicity, rapid classification and small memory footprint. The main contribution of this work is to demonstrate how broadly this idea can be applied, and highlight its potential impact on all types of algorithms. To support our claim, we first provide a general guideline for applying Inner Ensembles to different algorithms. Then, using this framework, we apply them to two categories of learning methods: supervised and un-supervised. For the former we chose Bayesian network, and for the latter K-Means clustering. Our results show that 1) the overall performance of Inner Ensembles is significantly better than the original methods, and 2) Inner Ensembles provide similar performance improvements as regular ensembles.

Le vieillissement fait actuellement l'objet de toutes les attentions, constituant en effet un problème de santé publique majeur. Sa description reste cependant complexe en raison des intrications à la fois individuelles et collectives de sa conceptualisation et d'une dimension subjective forte. Les professionnels de santé sont de plus en plus obligés d'intégrer cette donnée dans leur réflexion et de proposer des protocoles de prise en charge adaptés. Le vieillissement est une évolution inéluctable du corps dont la quantification est établie par l'âge dépendant du temps dit " chronologique ". Ce critère âge est cependant imparfait pour mesurer l'usure réelle du corps soumise à de nombreux facteurs modificateurs dépendant des individus. Aussi, partant de réflexions déjà engagées et consistant à substituer cet âge chronologique par un critère composite appelé " âge biologique ", aboutissant à la création d'un indicateur ou score de vieillissement et sensé davantage refléter le vieillissement individuel, une nouvelle méthodologie est proposée adaptée à la pratique de médecine générale. Une première phase de ce travail a consisté à sonder les médecins généralistes sur leur perception et leur utilisation des scores cliniques en pratique courante par l'intermédiaire d'une enquête qualitative et quantitative effectuée en France métropolitaine. Cette étude a montré que l'adéquation entre l'utilisation déclarée et la conception intellectualisée des scores restait dissociée. Les scores constituent un outil d'aide à la prise en charge utile pour cibler une approche systémique souvent complexe dans la mesure où ils sont simples à utiliser (peu d'items et items adaptés à la pratique) et à la validité scientifiquement comprise par le médecin. Par ailleurs, l'âge du patient a été cité comme un élément prépondérant influençant le choix adéquat du score par le médecin généraliste. Cette base de travail a donc servi à proposer une modélisation de l'âge biologique dont la réflexion a porté tant sur le choix du modèle mathématique que des variables constitutives de ce modèle. Une sélection de variables marqueurs du vieillissement a été effectuée à partir d'une revue de la littérature et tenant compte de leur possible intégration dans le processus de soin en médecine générale. Cette sélection a été consolidée par une approche mathématique selon un processus de sélection ascendant à partir d'un modèle régressif. Une population dite " témoin " au vieillissement considéré comme normal a été ensuite constituée servant de base comparative au calcul de l'âge biologique. Son choix a été influencé dans un premier temps par les données de la littérature puis secondairement selon un tri par classification utilisant la méthode des nuées dynamiques. Un modèle de régression linéaire simple a ensuite été construit mais avec de données normalisées selon la méthode des copules gaussiennes suivi d'une étude des queues de distribution marginales. Les résultats ainsi obtenus laissent entrevoir des perspectives intéressantes de réflexion pour approfondir le calcul d'un âge biologique et du score en découlant en médecine générale, sa validation par une étude de morbidité constituant l'étape ultime de ce travail

This article reviews the literature concerning supervised and unsupervised classification of functional data. It first explains the meaning of unsupervised classification vs. supervised classification before discussing the supervised classification problem in the infinite-dimensional case, showing that its formal statement generally coincides with that of discriminant analysis in the classical multivariate case. It then considers the optimal classifier and plug-in rules, empirical risk and empirical minimization rules, linear discrimination rules, the k nearest neighbor (k-NN) method, and kernel rules. It also describes classification based on partial least squares, classification based on reproducing kernels, and depth-based classification. Finally, it examines unsupervised classification methods, focusing on K-means for functional data, K-means for data in a Hilbert space, and impartial trimmed K-means for functional data. Some practical issues, in particular real-data examples and simulations, are reviewed and some selected proofs are given.

In Playing to the Crowd, Nancy K. Baym examines the shift toward more personal connections with audiences, offering an entirely new approach to media cultures and industries as she does. The book argues that workers in many fields are under increased pressure get online and connect with others to further their careers, a trend that musicians have long led. Using a dialectical framework, the book draws on in depth-interviews with a range of professional musicians and other qualitative methods to show how the rise of digital communication platforms transformed artist-fan relationships into something that can feel personal. Part I explores music as a means of communication and as a commodity, drawing out the tension between its social and commercial values. Part II looks at audiences, showing how they developed fandoms in the 20^th century, how those fandoms came online, and the tension between participation and control musicians experience when they encounter online audiences. Part III looks at relationships, examining how, in contrast to the concert hall environment in which musicians and audiences may one have met, social media create a new potential and pressure for everyday, intimate relating and how musicians manage the tensions between closeness and distance this creates. Ultimately, the book argues that the relational labor musicians do is a significant mode of work, one which requires resources, skills, and strategies we must all understand.

Bones are multifunctional passive organs of movement that supports soft tissue and directly attached muscles. They also protect internal organs and are a reserve of calcium, phosphorus and magnesium. Each bone is covered with periosteum, and the adjacent bone surfaces are covered by articular cartilage. Histologically, the bone is an organ composed of many different tissues. The main component is bone tissue (cortical and spongy) composed of a set of bone cells and intercellular substance (mineral and organic), it also contains fat, hematopoietic (bone marrow) and cartilaginous tissue. Bones are a tissue that even in adult life retains the ability to change shape and structure depending on changes in their mechanical and hormonal environment, as well as self-renewal and repair capabilities. This process is called bone turnover. The basic processes of bone turnover are: • bone modeling (incessantly changes in bone shape during individual growth) following resorption and tissue formation at various locations (e.g. bone marrow formation) to increase mass and skeletal morphology. This process occurs in the bones of growing individuals and stops after reaching puberty • bone remodeling (processes involve in maintaining bone tissue by resorbing and replacing old bone tissue with new tissue in the same place, e.g. repairing micro fractures). It is a process involving the removal and internal remodeling of existing bone and is responsible for maintaining tissue mass and architecture of mature bones. Bone turnover is regulated by two types of transformation: • osteoclastogenesis, i.e. formation of cells responsible for bone resorption • osteoblastogenesis, i.e. formation of cells responsible for bone formation (bone matrix synthesis and mineralization) Bone maturity can be defined as the completion of basic structural development and mineralization leading to maximum mass and optimal mechanical strength. The highest rate of increase in pig bone mass is observed in the first twelve weeks after birth. This period of growth is considered crucial for optimizing the growth of the skeleton of pigs, because the degree of bone mineralization in later life stages (adulthood) depends largely on the amount of bone minerals accumulated in the early stages of their growth. The development of the technique allows to determine the condition of the skeletal system (or individual bones) in living animals by methods used in human medicine, or after their slaughter. For in vivo determination of bone properties, Abstract 10 double energy X-ray absorptiometry or computed tomography scanning techniques are used. Both methods allow the quantification of mineral content and bone mineral density. The most important property from a practical point of view is the bone’s bending strength, which is directly determined by the maximum bending force. The most important factors affecting bone strength are: • age (growth period), • gender and the associated hormonal balance, • genotype and modification of genes responsible for bone growth • chemical composition of the body (protein and fat content, and the proportion between these components), • physical activity and related bone load, • nutritional factors: – protein intake influencing synthesis of organic matrix of bone, – content of minerals in the feed (CA, P, Zn, Ca/P, Mg, Mn, Na, Cl, K, Cu ratio) influencing synthesis of the inorganic matrix of bone, – mineral/protein ratio in the diet (Ca/protein, P/protein, Zn/protein) – feed energy concentration, – energy source (content of saturated fatty acids - SFA, content of polyun saturated fatty acids - PUFA, in particular ALA, EPA, DPA, DHA), – feed additives, in particular: enzymes (e.g. phytase releasing of minerals bounded in phytin complexes), probiotics and prebiotics (e.g. inulin improving the function of the digestive tract by increasing absorption of nutrients), – vitamin content that regulate metabolism and biochemical changes occurring in bone tissue (e.g. vitamin D3, B6, C and K). This study was based on the results of research experiments from available literature, and studies on growing pigs carried out at the Kielanowski Institute of Animal Physiology and Nutrition, Polish Academy of Sciences. The tests were performed in total on 300 pigs of Duroc, Pietrain, Puławska breeds, line 990 and hybrids (Great White × Duroc, Great White × Landrace), PIC pigs, slaughtered at different body weight during the growth period from 15 to 130 kg. Bones for biomechanical tests were collected after slaughter from each pig. Their length, mass and volume were determined. Based on these measurements, the specific weight (density, g/cm3) was calculated. Then each bone was cut in the middle of the shaft and the outer and inner diameters were measured both horizontally and vertically. Based on these measurements, the following indicators were calculated: • cortical thickness, • cortical surface, • cortical index. Abstract 11 Bone strength was tested by a three-point bending test. The obtained data enabled the determination of: • bending force (the magnitude of the maximum force at which disintegration and disruption of bone structure occurs), • strength (the amount of maximum force needed to break/crack of bone), • stiffness (quotient of the force acting on the bone and the amount of displacement occurring under the influence of this force). Investigation of changes in physical and biomechanical features of bones during growth was performed on pigs of the synthetic 990 line growing from 15 to 130 kg body weight. The animals were slaughtered successively at a body weight of 15, 30, 40, 50, 70, 90, 110 and 130 kg. After slaughter, the following bones were separated from the right half-carcass: humerus, 3rd and 4th metatarsal bone, femur, tibia and fibula as well as 3rd and 4th metatarsal bone. The features of bones were determined using methods described in the methodology. Describing bone growth with the Gompertz equation, it was found that the earliest slowdown of bone growth curve was observed for metacarpal and metatarsal bones. This means that these bones matured the most quickly. The established data also indicate that the rib is the slowest maturing bone. The femur, humerus, tibia and fibula were between the values of these features for the metatarsal, metacarpal and rib bones. The rate of increase in bone mass and length differed significantly between the examined bones, but in all cases it was lower (coefficient b <1) than the growth rate of the whole body of the animal. The fastest growth rate was estimated for the rib mass (coefficient b = 0.93). Among the long bones, the humerus (coefficient b = 0.81) was characterized by the fastest rate of weight gain, however femur the smallest (coefficient b = 0.71). The lowest rate of bone mass increase was observed in the foot bones, with the metacarpal bones having a slightly higher value of coefficient b than the metatarsal bones (0.67 vs 0.62). The third bone had a lower growth rate than the fourth bone, regardless of whether they were metatarsal or metacarpal. The value of the bending force increased as the animals grew. Regardless of the growth point tested, the highest values were observed for the humerus, tibia and femur, smaller for the metatarsal and metacarpal bone, and the lowest for the fibula and rib. The rate of change in the value of this indicator increased at a similar rate as the body weight changes of the animals in the case of the fibula and the fourth metacarpal bone (b value = 0.98), and more slowly in the case of the metatarsal bone, the third metacarpal bone, and the tibia bone (values of the b ratio 0.81–0.85), and the slowest femur, humerus and rib (value of b = 0.60–0.66). Bone stiffness increased as animals grew. Regardless of the growth point tested, the highest values were observed for the humerus, tibia and femur, smaller for the metatarsal and metacarpal bone, and the lowest for the fibula and rib. Abstract 12 The rate of change in the value of this indicator changed at a faster rate than the increase in weight of pigs in the case of metacarpal and metatarsal bones (coefficient b = 1.01–1.22), slightly slower in the case of fibula (coefficient b = 0.92), definitely slower in the case of the tibia (b = 0.73), ribs (b = 0.66), femur (b = 0.59) and humerus (b = 0.50). Bone strength increased as animals grew. Regardless of the growth point tested, bone strength was as follows femur > tibia > humerus > 4 metacarpal> 3 metacarpal> 3 metatarsal > 4 metatarsal > rib> fibula. The rate of increase in strength of all examined bones was greater than the rate of weight gain of pigs (value of the coefficient b = 2.04–3.26). As the animals grew, the bone density increased. However, the growth rate of this indicator for the majority of bones was slower than the rate of weight gain (the value of the coefficient b ranged from 0.37 – humerus to 0.84 – fibula). The exception was the rib, whose density increased at a similar pace increasing the body weight of animals (value of the coefficient b = 0.97). The study on the influence of the breed and the feeding intensity on bone characteristics (physical and biomechanical) was performed on pigs of the breeds Duroc, Pietrain, and synthetic 990 during a growth period of 15 to 70 kg body weight. Animals were fed ad libitum or dosed system. After slaughter at a body weight of 70 kg, three bones were taken from the right half-carcass: femur, three metatarsal, and three metacarpal and subjected to the determinations described in the methodology. The weight of bones of animals fed aa libitum was significantly lower than in pigs fed restrictively All bones of Duroc breed were significantly heavier and longer than Pietrain and 990 pig bones. The average values of bending force for the examined bones took the following order: III metatarsal bone (63.5 kg) <III metacarpal bone (77.9 kg) <femur (271.5 kg). The feeding system and breed of pigs had no significant effect on the value of this indicator. The average values of the bones strength took the following order: III metatarsal bone (92.6 kg) <III metacarpal (107.2 kg) <femur (353.1 kg). Feeding intensity and breed of animals had no significant effect on the value of this feature of the bones tested. The average bone density took the following order: femur (1.23 g/cm3) <III metatarsal bone (1.26 g/cm3) <III metacarpal bone (1.34 g / cm3). The density of bones of animals fed aa libitum was higher (P<0.01) than in animals fed with a dosing system. The density of examined bones within the breeds took the following order: Pietrain race> line 990> Duroc race. The differences between the “extreme” breeds were: 7.2% (III metatarsal bone), 8.3% (III metacarpal bone), 8.4% (femur). Abstract 13 The average bone stiffness took the following order: III metatarsal bone (35.1 kg/mm) <III metacarpus (41.5 kg/mm) <femur (60.5 kg/mm). This indicator did not differ between the groups of pigs fed at different intensity, except for the metacarpal bone, which was more stiffer in pigs fed aa libitum (P<0.05). The femur of animals fed ad libitum showed a tendency (P<0.09) to be more stiffer and a force of 4.5 kg required for its displacement by 1 mm. Breed differences in stiffness were found for the femur (P <0.05) and III metacarpal bone (P <0.05). For femur, the highest value of this indicator was found in Pietrain pigs (64.5 kg/mm), lower in pigs of 990 line (61.6 kg/mm) and the lowest in Duroc pigs (55.3 kg/mm). In turn, the 3rd metacarpal bone of Duroc and Pietrain pigs had similar stiffness (39.0 and 40.0 kg/mm respectively) and was smaller than that of line 990 pigs (45.4 kg/mm). The thickness of the cortical bone layer took the following order: III metatarsal bone (2.25 mm) <III metacarpal bone (2.41 mm) <femur (5.12 mm). The feeding system did not affect this indicator. Breed differences (P <0.05) for this trait were found only for the femur bone: Duroc (5.42 mm)> line 990 (5.13 mm)> Pietrain (4.81 mm). The cross sectional area of the examined bones was arranged in the following order: III metatarsal bone (84 mm2) <III metacarpal bone (90 mm2) <femur (286 mm2). The feeding system had no effect on the value of this bone trait, with the exception of the femur, which in animals fed the dosing system was 4.7% higher (P<0.05) than in pigs fed ad libitum. Breed differences (P<0.01) in the coross sectional area were found only in femur and III metatarsal bone. The value of this indicator was the highest in Duroc pigs, lower in 990 animals and the lowest in Pietrain pigs. The cortical index of individual bones was in the following order: III metatarsal bone (31.86) <III metacarpal bone (33.86) <femur (44.75). However, its value did not significantly depend on the intensity of feeding or the breed of pigs.

AbstractCurrently, the safety assessment of radio-frequency (RF) heating using computational modeling is limited by the available numerical models which are not patient specific. However, RF-induced heating depends on the physical characteristics of the patient. The numerical model generation is difficult due to the highly time-consuming segmentation process. Therefore, having fewer types of segmented structures simplifies the generation of numerical models and reduces computational burden as a result. In this study, we used the k-means clustering method to reduce the number of dielectric properties of an existing numerical model and investigated the resulting difference in specific absorption rate (SAR) with respect to the number of clusters.

Cluster analysis of the efficiency of the recreational forest use of the region by separate components of the recreational forest use potential is provided in the article. The main stages of the cluster analysis of the recreational forest use level based on the predetermined components were determined. Among the agglomerative methods of cluster analysis, intended for grouping and combining the objects of study, it is common to distinguish the three most common types: the hierarchical method or the method of tree clustering; the K-means Clustering Method and the two-step aggregation method. For the correct selection of clusters, a comparative analysis of several methods was performed: arithmetic mean ranks, hierarchical methods followed by dendrogram construction, K- means method, which refers to reference methods, in which the number of groups is specified by the user. The cluster analysis of forestries by twenty analytical grounds was not proved by analysis of variance, so the re-clustering of certain objects was carried out according to the nine most significant analytical features. As a result, the forestry was clustered into four clusters. The conducted cluster analysis with the use of different methods allows us to state that their combination helps to select reasonable groupings, clearly illustrate the clustering procedure and rank the obtained forestry clusters.

The overall objective of the current proposal is to develop procedures to improve the pregnancy rate achieved following transfer of fresh or cryopreserved embryos produced in the laboratory into heat-stress recipients. The overall hypothesis is that pregnancy rate in heat-stressed lactating cows can be improved by use of embryo transfer and that additional gains in pregnancy rate can be achieved through development of procedures to cryopreserve embryos, select embryos most likely to establish and maintain pregnancy after transfer, and to enhance embryo competence for post-transfer survival through manipulation of culture conditions. The original specific objectives were to 1) optimize procedures for cryopreservation (Israel/US), 2) develop procedures for identifying embryos with the greatest potential for development and survival using the remote monitoring system called EmbryoGuard (Israel), 3) perform field trials to test the efficacy of cryopreservation and the EmbryoGuard selection system for improving pregnancy rates in heat-stressed, lactating cows (US/Israel), 4) test whether selection of fresh or frozen-thawed blastocysts based on measurement of group II caspase activity is an effective means of increasing survival after cryopreservation and post-transfer pregnancy rate (US), and 5) identify genes in blastocysts induced by insulin-like growth factor-1 (IGF-1) (US). In addition to these objectives, additional work was carried out to determine additional cellular determinants of embryonic resistance to heat shock. There were several major achievements. Results of one experiment indicated that survival of embryos to freezing could be improved by treating embryos with cytochalasin B to disrupt the cytoskeleton. An additional improvement in the efficacy of embryo transfer for achieving pregnancy in heat-stressed cows follows from the finding that IGF-1 can improve post-transfer survival of in vitro produced embryos in the summer but not winter. Expression of several genes in the blastocyst was regulated by IGF-1 including IGF binding protein-3, desmocollin II, Na/K ATPase, Bax, heat shock protein 70 and IGF-1 receptor. These genes are likely candidates 1) for developing assays for selection of embryos for transfer and 2) as marker genes for improving culture conditions for embryo production. The fact that IGF-1 improved survival of embryos in heat-stressed recipients only is consistent with the hypothesis that IGF-1 confers cellular thermotolerance to bovine embryos. Other experiments confirmed this action of IGF-1. One action of IGF-1, the ability to block heat-shock induced apoptosis, was shown to be mediated through activation of the phosphatidylinositol 3-kinase pathway. Other cellular determinants of resistance of embryos to elevated temperature were identified including redox status of the embryo and the ceramide signaling pathway. Developmental changes in embryonic apoptosis responses in response to heat shock were described and found to include alterations in the capacity of the embryo to undergo caspase-9 and caspase-3 activation as well as events downstream from caspase-3 activation. With the exception of IGF-1, other possible treatments to improve pregnancy rate to embryo transfer were not effective including selection of embryos for caspase activity, treatment of recipients with GnRH.and bilateral transfer of twin embryos. In conclusion, accomplishments achieved during the grant period have resulted in methods for improving post-transfer survival of in vitro produced embryos transferred into heat-stressed cows and have lead to additional avenues for research to increase embryo resistance to elevated temperature and improve survival to cryopreservation. In addition, embryo transfer of vitrified IVF embryos increased significantly the pregnancy rate in repeated breeder cows.

As a critical power source, the diesel engine is widely used in various situations. Diesel engine failure may lead to serious property losses and even accidents. Fault detection can improve the safety of diesel engines and reduce economic loss. Surface vibration signal is often used in non-disassembly fault diagnosis because of its convenient measurement and stability. This paper proposed a novel method for engine fault detection based on vibration signals using variational mode decomposition (VMD), K-means, and genetic algorithm. The mode number of VMD dramatically affects the accuracy of extracting signal components. Therefore, a method based on spectral energy distribution is proposed to determine the parameter, and the quadratic penalty term is optimized according to SNR. The results show that the optimized VMD can adaptively extract the vibration signal components of the diesel engine. In the actual fault diagnosis case, it is difficult to obtain the data with labels. The clustering algorithm can complete the classification without labeled data, but it is limited by the low accuracy. In this paper, the optimized VMD is used to decompose and standardize the vibration signal. Then the correlation-based feature selection method is implemented to obtain the feature results after dimensionality reduction. Finally, the results are input into the classifier combined by K-means and genetic algorithm (GA). By introducing and optimizing the genetic algorithm, the number of classes can be selected automatically, and the accuracy is significantly improved. This method can carry out adaptive multiple fault detection of a diesel engine without labeled data. Compared with many supervised learning algorithms, the proposed method also has high accuracy.