Forest Research Articles

Electric energy abnormal data detection based on Isolation Forests

Electric energy abnormal data detection based on Isolation Forests

A preliminary study on prediction efficacy of multimodal MRI-based radiomics in combination with random forest model for preoperative glioma IDH1 gene type expression

Objective To preliminarily analyze the prediction efficiency of multimodal MRI-based radiomics model for preoperative glioma IDH1 gene expression type. Methods The MRI data of 108 surgery-proven glioma patients from May 2015 to January 2019 were retrospectively analyzed, and the MRI data included axial T1WI,T2WI,fluid attenuated inversion recovery (FLAIR),DWI imaging and enhanced T1WI sequence.Forty-seven cases were IDH1 mutant type, and 61 cases were IDH1 wild type. All patients were divided into training and validation groups according to the 7∶3 ratio of the random forest model. Seventy-three cases were in training group, and 35 cases were in validation group. Independent predictors of IDH1 mutation were screened by univariate analysis combined with multivariate logistic regression analysis (P<0.05) in order to construct a random forest diagnosis model of general clinical information and conventional MRI morphological features.General clinical information and conventional MRI morphological features included gender, age, umbers of cases of left and right hemispheres, location of tumors, maximum diameter of tumors, peritumoral edema, intratumoral cystic degeneration, enhancement and ADC value of tumors. The ROI was manually outlined by MaZda software in the most obvious level of 5 sequences of tumor mass and the radiomics features were extracted, including the gray-level co-occurrence matrix(GLCM), the run-length matrix(RUN), the absolute gradient(GRA),the auto-regressive model(ARM) and wavelets transform(WAV). The least absolute shrinkage and selection operator (LASSO)regression were used to select image radiomics features with a method of 10 fold cross -validation and to reduce the dimensions. The screened image radiomics labels were combined with the conventional morphological feature independent predictors to construct a multimodal MRI-based random forest model, and the validation data set was used to evaluate the accuracy and diagnostic efficiency of each model. The sensitivity and specificity of conventional MRI morphological feature model and multimodal MRI-based radiomics prediction model were evaluated dynamically by drawing ROC curves, and the prediction efficiency of the two models was quantified by using AUC statistical indicators. The model classification error rate under different outcomes and the classification error rate of out of bag(OOB)were used to evaluate the stability of the multimodal MRI-based random forest model. The contribution rate of each variable to the model was reflected by the characteristic variables importance assessment map. Results Univariate regression analysis of the conventional MRI morphological characteristics showed that peritumoral edema, cystic degeneration and enhancement were the three independent predictors of IDH1 gene expression (P<0.01). LASSO algorithm and 10-fold cross-validation identified six robust radiomic features including high frequency coefficients of wavelet transform (WavEnHH_s-4) of T2WI, S(4,4) inverse difference of gray uniformity measurement (InvDfMom),S(5,0) Entropy (entropy),WavEnHH_s-4 of T1WI enhancement, S(1,1) InvDfMom,S(1, -1) Entropy Difference (DifEntrp)of Flair.The error rate of classification for different outcomes and classification error rate of random forest OOB data of multimodal MRI radiomics diagnosis model finally stabilized at 10%. The results of Characteristic Variable Importance Assessment Map: Mean Decrease Accuracy and Mean Decrease Gini index were consistent, which showed that besides three conventional MRI morphological predictors peritumoral edema, enhancement and cystic degeneration, the radiomics labels also played a key role in the model. The results of ROC curve showed that the accuracy, specificity, sensitivity and AUC of conventional MRI morphological feature model were 82.7%, 68.4%, 90.9% and 0.835, respectively, and those of multimodal MRI-based radiomics model were 88.5%, 89.5%, 87.8% and 0.956 respectively. Conclusion Multimodal MRI-based radiomics random forest model can improve the predictive efficiency of preoperative glioma IDH1 gene expression type more quantitatively. Key words: Glioma; Texture; Radiomics; Magnetic resonance imaging

Adherence to insulin treatment in participants with type 2 diabetes: Comparison of logistic regression and conditional tree and forests to determine the effective factors

Objective: Type 2 diabetes is the most prevalent chronic disease in the world. Timely and appropriate control can significantly reduce the burdens and costs of this disease. Although insulin injection is the most efficient method to control type 2 diabetes, patients avoid this method for unknown reasons. The main aim of the present study is to determine the factors influential in non-adherence to insulin using tools and models that have not been applied in this field so far. Methods: The tendency to insulin injection in 457 patients with type 2 diabetes was investigated in this cross-sectional study using the classic logistic regression and new learning algorithms, including conditional tree, conditional forest, and random forest. Different fits were compared so that the best model can be determined to identify the factors in non-adherence to insulin. Results: Although random forest had the highest accuracy among the fitted models, all the methods had a relative consensus that having life insurance, academic education, and insulin injection experience in immediate family members increase the tendency to accept insulin therapy. Our results also showed that younger patients and those who were committed to a specific diet better approved insulin therapy. Conclusions: The reasons for non-adherence to insulin can be summarized in economic and psychological aspects. Therefore, the health system policies are recommended to address economic issues and also raise public awareness about this treatment method.

Structural plasticity and species distribution in a peri-urban mangrove of Southeastern Brazil

The goal of this study was to evaluate the structural plasticity and distribution of mangrove species in the Estuarine System of Greater Vitoria (ESGV). Four areas distributed along the estuary were analyzed. Fringe and basin forests were sampled in each station. Concomitantly to the forest sampling, interstitial salinity was measured in the field, and sediment was collected for analysis of organic matter (OM) content. There was variation in species distribution along the ESGV. Regarding the structural variables, comparative analysis between physiographic types indicated that basin forests were more mature than fringe forests. OM content values were higher in basin forests. There was an inverse relationship between values of mean DBH (Diameter at Breast Height) and live trunk density (R2 = 0.8795, p <0.0001), and a positive relationship between OM content in the sediment and mean DBH (R2 = 0.3215, p = 0.00593). Multivariate analysis evidenced the formation of three groups: The first with higher structural development and dominated by Rhizophora mangle, in areas with higher OM content; the second dominated by Laguncularia racemosa with more impoverished soils; and third group, which aggregated plots subjected to environmental and anthropic stress (like tree cutting), restricted to more urbanized areas. Key words: Forest maturity, organic matter, multivariate analysis.

Classification of forest engineering department students' requirements from university by Kano’s model

Bu makalenin amaci, orman muhendisligi bolumu ogrencilerinin egitim surecinde universitenin karsilamasini umduklari gereksinimlerinin belirlenmesidir. Calisma kapsaminda dersler, kariyer hedefleri, yabanci dil, akademisyenler, altyapi ve sosyal-kulturel etkinliklere yonelik olarak belirlenen 31 gereksinim Kano modeli ile degerlendirilmistir. Bu gereksinimlerin 25’i beklenen/dogrusal gereksinim olarak belirlenmistir. Yani bu gereksinimlerin giderilmesine yonelik calismalarin yapilmasi ogrencilerin memnuniyet duzeyini arttiracak, yapilmamasi durumunda ise ogrencilerde memnuniyetsizlik olusacaktir. Dersler ile ilgili olan stajlarin denetimi, tasarim icerikli derslerin mufredatta yer almasi, secmeli derslerin sayisinin arttirilmasi ve bolum disi derslerin programda yer almasi ise ogrenciler icin onem arz etmemektedir. Yani bu gereksinimlerin giderilmesi ya da giderilmemesi durumunda memnuniyette bir degisiklik olmayacaktir. Ote yandan ogrenciler tarafindan uygulamacilarin derslerde deneyimlerini paylasmalari ve ikinci bir yabanci dilin programda yer almasi heyecan verici gereksinimler olarak belirlenmistir.

L’utopico e le sue conquiste. Idee, pratiche e simboli

This article investigates the conquests of the utopian and the current spaces of possibility. This multiprospective exploration is composed of three movements: ideas, practices, and symbols. The first part considers the concepts of utopianism, from its origins and developments in literature, to the principles recurring in ideal worlds. The second part concerns the practices of the utopian, from historical incarnations to current examples of effective realizations – including some “minimalist” daily practices – based on ethnographic experiences in intentional communities, autonomous regions, and informal settlements. The third part examines the symbols of the conquest of the utopian. The occupations of forests in different geographical areas (including the Hambacher Forst) introduce scenarios opened by the recent mobilizations against the climate crisis. The interrelationship between ideas, practices, and symbols are the subject of theoretical reflections, which come from classical literature to the latest contributions on communitarianism and grassroot movements.

O pedagogo nos espaços escolar e não escolar: a cidadania no trânsito

A profissão do pedagogo tem delineado em sua história um perfil caleidoscópico, dada a pluralidade de papeis atribuídos na contemporaneidade a esse profissional, configurando-se esse ponto numa das problemáticas de sua identidade. As Diretrizes Curriculares do Curso de Pedagogia (2006) foi um documento que abriu novos espaços de ação laboral e discussões nesse campo. Nesse artigo, objetivamos argumentar sobre o papel do pedagogo na esfera da Educação para a Cidadania no Trânsito, quer seja no espaço escolar ou não escolar. A pesquisa é de natureza qualitativa, bibliográfica e parte documental. Essa temática se abre como um espaço epistêmico repleto de complexidades e desafios para o que fazer do pedagogo, especialmente por ampliar consideravelmente a trama gnosiológica quanto ao papel que esse profissional desempenha na sociedade. Dos resultados, elucidamos que ensinar a educação para a cidadania no trânsito ainda é um espaço que se encontra como mata virgem epistêmica diante da natureza do trabalho do pedagogo. Revelamos ainda que educar para o trânsito, não é o mesmo que educar para a cidadania, já que o vocábulo cidadania carrega em si questões emblemáticas quanto à educação de cidadãos autônomos, sensíveis, reflexivos e participativos, em prol de uma sociedade humanizada.

Aerobic biotransformation of 6:2 fluorotelomer sulfonic acid in soil

Per- and polyfluoroalkyl substances (PFASs) have been widely used in numerous industrial and household products due to its hydrophobic and lipophobic nature. As the main active ingredient, PFASs have been widely used in aqueous film forming foam (AFFF) used to fight liquid-fueled fires. As the electrochemical fluorination (ECF)-based PFASs were gradually phased out by major PFAS manufacturers worldwide, fluorotelomer-based PFASs, such as 6:2 fluorotelomer sulfonic acid (6:2 FTSA, [F(CF2)6CH2CH2SO3H]) and its precursors, have been widely detected in soil and groundwater effected by firefighting training activities. A few precursors (e.g., 6:2 fluorotelomer alcohol, 6:2 FTOH, [F(CF2)6CH2CH2OH]) have been well studied, but there are still leaving major gaps in understanding of 6:2 FTSA fate and aerobic biotransformation in soil. Soil collected from forest area was dosed with 6:2 FTSA to investigate its biotransformation rate and to identify major transformation products in a flow-through soil incubation system over 90 d. The overall mass balance at day 90 in sterile and live treatments averaged 97.4% and 76.8%, respectively, suggesting that there may be soil-bound residues and conjugates between fluorinated transformation products and dissolved soil components only in live test system not in the sterile soil. The 6:2 FTSA biotransformation was relatively low with a half-life more than 56 d, and 33% of initial 6:2 FTSA remained at day 90. According to the transformation products and the results in 6:2 FTSA biodegradation, the pathways of 6:2 FTSA aerobic biodegradation in the soil were proposed. The volatile 5:2 secondary alcohol (5:2 sFTOH, [F(CF2)5CH(OH)CH3]) and 5:2 fluorotelomer ketone (5:2 FT ketone, [F(CF2)5COCH3]) were the most abundant intermediate transformation products at the beginning, and reached highest at day 7 and 14, respectively. Perfluoropentanoic acid (PFPeA, [F(CF2)4COOH]) and perfluorohexanoic acid (PFHxA, [F(CF2)5COOH]) were produced as end products by 6:2 FTSA through desulfonation, oxidation and other reactions. In another minor pathway, 5:3 polyfluorinated acid (5:3 acid, [F(CF2)5CH2CH2COOH]) and perfluorobutanoic acid (PFBA, [F(CF2)3COOH]) were also formed. The concentrations of these end products, including PFBA, PFPeA, PFHxA, and 5:3 acid, increased in all experiment period. At day 90, the generations of PFPeA, PFHxA, 5:3 acid, and PFBA at a yield of 20.4 mol%, 6.5 mol%, 9.5 mol%, and 1.0 mol% were observed. Perfluoroheptanoic acid (PFHpA, [F(CF2)6COOH]) was not detected in the soil, suggesting that there was no α-oxidation in the process of 6:2 FTSA biotransformation in live soil. NaOH-acetonitrile extraction plus ENVI-Carb™ clean up could breakdown the binding between 5:3 acid and organic matter of the soil, and an enhancement factor up to 18 could be achieved for 5:3 acid by this cleanup method. The sorption of 6:2 FTSA to soil could low the biotransformation. The enzymatic desulfonation step may limit 6:2 FTSA biotransformation in aerobic soil. This study indicates that 6:2 FTSA may be persistent in aerobic soil, and a potential source of short chain perfluorocarboxylic acids (PFCAs) in soil. More studies need to be done to understanding the fate of AFFF-related polyfluoroalkyl precursors in soil environment in the future work.

ESTIMACIÓN DE LA BIOMASA EN UN BOSQUE BAJO MANEJO DE Pinus patula Schltdl. et Cham. EN ZACUALTIPÁN, HIDALGO

&#x0D; &#x0D; &#x0D; Con el objetivo de estimar la cantidad de biomasa en la vegetación arbórea de bosques manejados de Pinus patula se realizó el presente estudio en el Ejido La Mojonera, en Zacualtipán, Hidalgo, México. Este ejido cuenta con un plan de manejo forestal bajo el sistema silvícola de “Árboles padres”. El bosque está dividido en áreas de corta señaladas con la anualidad en la que se ha efectuado la corta de regeneración. Para estimar la biomasa aérea de P. patula se ajustaron ecuaciones simultáneas de regresión tomando en cuenta los diferentes componentes de la estructura de un árbol (fuste, ramas, follaje y corteza). La cantidad de biomasa arbórea del bosque manejado se obtuvo aplicando las ecuaciones generadas y mediante datos de inventario. La biomasa contenida en el arbolado incrementó con una tasa de 6.7 Mg ha-1 en 25 años. El rodal que había sido cortado en 1982 (rodal de mayor edad producto de la corta) presentó una acumulación de biomasa relativamente similar a la contenida en el arbolado de un área que aún no ha sido intervenida (166.6 y 184.03 Mg ha-1, respectivamente). Por tanto, es posible aseverar que los bosques manejados funcionan eficientemente como fijadores y sumideros de carbono, considerando el esquema de manejo que se esté aplicando.&#x0D; &#x0D; &#x0D;

Using Electronic Health Records and Machine Learning to Predict Postpartum Depression.

Postpartum depression (PPD) is one of the most frequent maternal morbidities after delivery with serious implications. Currently, there is a lack of effective screening strategies and high-quality clinical trials. The ability to leverage a large amount of detailed patient data from electronic health records (EHRs) to predict PPD could enable the implementation of effective clinical decision support interventions. To develop a PPD prediction model, using EHRs from Weill Cornell Medicine and NewYork-Presbyterian Hospital between 2015-17, 9,980 episodes of pregnancy were identified. Six machine learning algorithms, including L2-regularized Logistic Regression, Support Vector Machine, Decision Tree, Naïve Bayes, XGBoost, and Random forest were constructed. Our model's best prediction performance achieved an AUC of 0.79. Race, obesity, anxiety, depression, different types of pain, antidepressants, and anti-inflammatory drugs during pregnancy were among the significant predictors. Our results suggest a potential for applying machine learning to EHR data to predict PPD and inform healthcare delivery.

Can Solo Practitioners Survive in Value-Based Healthcare? Validating a Predicative Model for ED Utilization.

The health industry will see increased implementations of value-based models. This study validates a predictive model for determining emergency room utilization. Data from 2991 records are used for the analysis. To validate the model we used Poisson and random forest models. The results indicate that patients with one of six chronic conditions, who missed scheduled appointments or had higher body mass indexes were more likely to utilize the emergency department.

Development of a Machine Learning Model Predicting an ICU Admission for Patients with Elective Surgery and Its Prospective Validation in Clinical Practice.

Frequent utilization of the Intensive Care Unit (ICU) is associated with higher costs and decreased availability for patients who urgently need it. Common risk assessment tool, like the ASA score, lack objectivity and do account only for some influencing parameters. The aim of our study was (1) to develop a reliable machine learning model predicting ICU admission risk after elective surgery, and (2) to implement it in a clinical workflow. We used electronic medical records from more than 61,000 patients for modelling. A random forest model outperformed other methods with an area under the curve of 0.91 in the retrospective test set. In the prospective implementation, the model achieved a sensitivity of 73.3% and a specificity of 80.8%. Further research is essential to determine physicians' attitudes to machine learning models and assess the long term improvement of ICU management.

An Improvised Classification Model for Predicting Delirium.

With the vast increase of digital healthcare data, there is an opportunity to mine the data for understanding inherent health patterns. Although machine-learning techniques demonstrated their applications in healthcare to answer several questions, there is still room for improvement in every aspect. In this paper, we are demonstrating a method that improves the performance of a delirium prediction model using random forest in combination with logistic regression.

Using Machine Learning on Home Health Care Assessments to Predict Fall Risk.

Falls are the leading cause of injuries among older adults, particularly in the more vulnerable home health care (HHC) population. Existing standardized fall risk assessments often require supplemental data collection and tend to have low specificity. We applied a random forest algorithm on readily available HHC data from the mandated Outcomes and Assessment Information Set (OASIS) with over 100 items from 59,006 HHC patients to identify factors that predict and quantify fall risks. Our ultimate goal is to build clinical decision support for fall prevention. Our model achieves higher precision and balanced accuracy than the commonly used multifactorial Missouri Alliance for Home Care fall risk assessment. This is the first known attempt to determine fall risk factors from the extensive OASIS data from a large sample. Our quantitative prediction of fall risks can aid clinical discussions of risk factors and prevention strategies for lowering fall incidence.

Towards Automating Location-Specific Opioid Toxicosurveillance from Twitter via Data Science Methods.

Social media may serve as an important platform for the monitoring of population-level opioid abuse in near real-time. Our objectives for this study were to (i) manually characterize a sample of opioid-mentioning Twitter posts, (ii) compare the rates of abuse/misuse related posts between prescription and illicit opiods, and (iii) to implement and evaluate the performances ofsupervised machine learning algorithms for the characterization of opioid-related chatter, which can potentially automate social media based monitoring in the future.. We annotated a total of 9006 tweets into four categories, trained several machine learning algorithms and compared their performances. Deep convolutional neural networks marginally outperformed support vector machines and random forests, with an accuracy of 70.4%. Lack of context in tweets and data imbalance resulted in misclassification of many tweets to the majority class. The automatic classification experiments produced promising results, although there is room for improvement.

Diversity and phitosociology of Araucaria forest fragments in small rural property in the State of Paraná - Brazil

O objetivo desta pesquisa foi analisar as características florísticas de seis fragmentos de Floresta Ombrófila Mista situados em pequenas propriedades rurais localizadas em Fernandes Pinheiro e compará-los em relação à diversidade alfa e beta. Utilizaram-se 26 parcelas de 2.000 m² divididas em 130 subparcelas de 400 m² distribuídas em seis pequenos fragmentos florestais. Os parâmetros fitossociológicos e índices de Shannon, Simpson e Pielou de cada fragmento, além do Coeficiente de Jaccard para formação de grupos a 50% de similaridade foram determinados. Os índices de Shannon dos fragmentos foram avaliados um a um pelo Teste de Hutcheson. No total, foram registradas 103 espécies de 69 gêneros e 35 famílias, sendo as famílias mais abundantes, Myrtaceae e Lauraceae. Dos seis fragmentos analisados, a Araucária não foi a principal espécie apenas no Fragmento 6, o mais descaracterizado. O Fragmento 3, mesmo sendo o menor, apresentou os melhores resultados para biodiversidade (S = 64 e H’ = 3,390). O Teste de Hutcheson enfatizou que os Fragmentos 3 e 6 diferem dos demais, da mesma forma, o coeficiente de Jaccard também evidenciou menor similaridade florística entre esses dois fragmentos em relação aos demais. Concluiu-se que há elevada heterogeneidade entre pequenos fragmentos florestais próximos, além de evidenciar a disparidade em relação a grandes remanescentes.

Identification of strategic molecules for future circular supply chains using large reaction networks

Networks of chemical reactions represent relationships between molecules within chemical supply chains and promise to enhance planning of multi-step synthesis routes from bio-renewable feedstocks. This study aims to identify strategic molecules in chemical reaction networks that may potentially play a significant role within the future circular economy. We mine Reaxys® database in order to assemble a network of chemical reactions. We describe molecules within the network by a portfolio of graph theoretical features, and identify strategic molecules with an isolation forest search algorithm. In this work we have identified a list of potential strategic molecules and indicated possibilities for reaction planning using these. This is exemplified by a potential supply chain of functional molecules from bio-waste streams that could be used as feedstocks without being converted to syngas. This work extends the methodology of analysis of reaction networks to the generic problem of development of new reaction pathways based on novel feedstocks.

Body size and genetic variation in the White-tipped Plantcutter (Phytotoma rutila: Cotingidae) suggest ecological divergence across the Chaco–Andes dry forest belt

Fil: Rodriguez Cajarville, Maria Jose. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Oficina de Coordinacion Administrativa Parque Centenario. Museo Argentino de Ciencias Naturales "Bernardino Rivadavia"; Argentina

RFQAmodel: Random Forest Quality Assessment to identify a predicted protein structure in the correct fold

While template-free protein structure prediction protocols now produce good quality models for many targets, modelling failure remains common. For these methods to be useful it is important that users can both choose the best model from the hundreds to thousands of models that are commonly generated for a target, and determine whether this model is likely to be correct. We have developed Random Forest Quality Assessment (RFQAmodel), which assesses whether models produced by a protein structure prediction pipeline have the correct fold. RFQAmodel uses a combination of existing quality assessment scores with two predicted contact map alignment scores. These alignment scores are able to identify correct models for targets that are not otherwise captured. Our classifier was trained on a large set of protein domains that are structurally diverse and evenly balanced in terms of protein features known to have an effect on modelling success, and then tested on a second set of 244 protein domains with a similar spread of properties. When models for each target in this second set were ranked according to the RFQAmodel score, the highest-ranking model had a high-confidence RFQAmodel score for 67 modelling targets, of which 52 had the correct fold. At the other end of the scale RFQAmodel correctly predicted that for 59 targets the highest-ranked model was incorrect. In comparisons to other methods we found that RFQAmodel is better able to identify correct models for targets where only a few of the models are correct. We found that RFQAmodel achieved a similar performance on the model sets for CASP12 and CASP13 free-modelling targets. Finally, by iteratively generating models and running RFQAmodel until a model is produced that is predicted to be correct with high confidence, we demonstrate how such a protocol can be used to focus computational efforts on difficult modelling targets. RFQAmodel and the accompanying data can be downloaded from http://opig.stats.ox.ac.uk/resources.

Frequency of forest walking is not associated with prevalence of hypertension based on cross-sectional studies of a general Japanese population: a reconfirmation by the J-MICC Daiko Study.

ABSTRACTForest walking or Shinrin-yoku is a health promotion activity in Japan. Although some studies have reported the acute effects of walking a few hours in forested areas in reducing blood pressure level compared to other environments, studies investigating whether successive walking has long-term effects in lowering blood pressure levels or lowering prevalence of hypertension are rare. This study aimed to reconfirm the presence or absence of an association between the frequency of forest walking and prevalence of hypertension in a Japanese population. This J-MICC Daiko Study was conducted targeting residents in Nagoya City. A total of 5,109 participants (1,452 men and 3,657 women; age, mean ± standard deviation: 52.5 ± 10.3 years) were included in the analysis. Age-adjusted blood pressure level by frequency of forest walking was not significant. After adjusting for age and lifestyle, the adjusted odds ratios (aORs) of the most frequent group (n=88, 1.7%; once a week or more group) relative to the less than once a month group (n=4,558, 89.2%) for prevalence of hypertension were not also significant [0.80 (95% CI: 0.40–1.62) for men and 1.48 (95% CI: 0.73–3.00) for women]. This study reconfirmed that either lowering blood pressure level or lowering the prevalence of hypertension is not associated with frequency of forest walking, similar to the results of our previous J-MICC Shizuoka Study. Given that these two studies were cross-sectional studies, cohort studies investigating the causal relationship are required to evaluate the effect of frequent forest walking on the prevention of hypertension.