scholarly journals THICKNESS ACCURACY OF TEAK BARK BY ARTIFICIAL INTELLIGENCE

FLORESTA ◽  
2019 ◽  
Vol 49 (3) ◽  
pp. 449
Author(s):  
Diogo Guido Streck Vendruscolo ◽  
Clebson Lima Cerqueira ◽  
Samuel de Pádua Chaves e Carvalho ◽  
Reginaldo Antonio Medeiros ◽  
Raiane Scandiane da Silva
Keyword(s):  
Artificial Intelligence ◽  
Tectona Grandis ◽  
Graphical Analysis ◽  
Tree Bark ◽  
Bark Thickness ◽  
Relative Height ◽  
Modeling Techniques ◽  
Input Variables ◽  
The One ◽  
Statistical Indicators

Estimates of tree bark thickness are fundamental for forest management, however, the degree of precision is conditioned to the adoption of efficient modeling techniques. The objective of this study was to evaluate and propose a model of artificial neural networks to estimate the thickness of the tree bark of Tectona grandis (Teak). The data originated from the measurement of 68 dominant trees, ranging in age from 6 to 33 years. The thickness of the bark was correlated with variables inherent to the tree, being: diameter in the different positions of the stem (di); diameter at 1.3 m height (dbh); total height (ht); relative height (hi_rel); and age (id). The trained networks were of the multilayer perceptron type, and a linear regression model was adjusted as a comparative support. The accuracy of the estimates was evaluated through statistical indicators and graphical analysis. The results showed a strong correlation between bark thickness and tree diameter, as well as relative height, with values above 0.70. Age also exerted a strong influence on the thickness of the bark of the trees. The artificial intelligence technique has demonstrated the potential for such application and the model proposed with the input variables: diameter, relative height and age was the one that presented the best statistical performance, and thus was the most suitable for predicting the bark in Teak trees.

scholarly journals Height, volume and form factor equations for Tectona grandis L.f. in Alta Floresta (MT)

2020 ◽  
Vol 1 (1) ◽  
pp. 27
Author(s):  
Adriana Coimbra de Morais ◽  
Thelma Shirlen Soares ◽  
Edmilson Santos Cruz
Keyword(s):  
Form Factor ◽  
Tectona Grandis ◽  
Information Criterion ◽  
Graphical Analysis ◽  
Coefficient Of Determination ◽  
Total Height ◽  
Pearson Coefficient ◽  
The Mean ◽  
The One ◽  
Tectona Grandis L.F

Studies on allometric models are essential for quantifying the potential of a stand, especially when the objective is to know the wood stock through estimates. This study aimed to select height, volume and artificial form factor equations for a teak stand with data from a sample with 81 trees at 96 months in different diameter classes. The correlation analysis was performed between the variables total height, diameter with and without bark at 1.30 m soil height (dbhcc and dbhsc), total volume with and without bark (VTcc and VTsc) and artificial form factor with and without bark (ffcc and ffsc), using the Pearson coefficient. Six models were evaluated for each category: height, volume and artificial form factor, which were selected by the following criteria: analysis of variance, adjusted coefficient of determination, standard error of estimate, Akaike information criterion and graphical analysis of residues. The selected equations were validated by applying the L & O test. The variables dbhcc, dbhsc, HT, VTcc and VTsc presented significant correlations, ranging from moderate to very strong, the others presented weak correlation. The model that presented the best relation of total height to diameter was the model of Azevedo and contributors. For the total volume with and without bark, Schumacher and Hall model in its logarithmic form was the one that presented the best results. The adjusted models for artificial form factor did not present satisfactory results and, therefore, the use of average form factor is recommended. The mean form factor values by diameter class ranged from 0.4498 to 0.7139 and 0.4480 to 0.7075 for diameter with and without bark, respectively.

scholarly journals Development of a Taper Equation for Teak (Tectona grandis L.f.) Growing in Western Thailand

2021 ◽  
Vol 19 (3) ◽  
pp. 176-185
Author(s):  
Thanapol Choochuen ◽  
◽  
Warong Suksavate ◽  
Ponthep Meunpong ◽  
◽  
...  
Keyword(s):  
Goodness Of Fit ◽  
Tectona Grandis ◽  
Graphical Analysis ◽  
Statistical Testing ◽  
Bark Thickness ◽  
Tropical Hardwood ◽  
Hardwood Species ◽  
Height Prediction ◽  
Taper Equation ◽  
Leave One Out

Teak is an important and valuable tropical hardwood species. In this study, we developed and evaluated suitable taper equations for teak growing in Western Thailand using a formulation of Goodwin cubic polynomial model combined with a bark thickness model. The best taper model calibration was selected based on goodness-of-fit and leave-one-out cross validation statistical testing. In total, 12 different model calibrations were tested, with Thong Pha Phum (TPP) 2 being the most suitable for teak in Western Thailand. The mean prediction error of three validation statistics: (prediction of diameter under bark given height; prediction of height given diameter under bark; and prediction of under bark volume given log length) were within 10% and the overall validation index was 5.454, which was the lowest when compared to other calibrations. A comparison of TPP 2 with a teak taper equation developed for Northern Thailand, using a graphical analysis of the stem shape and bark thickness, indicated that the teak trees growing in the two regions have similar stem shapes, but the trees in Western Thailand tend to have a thicker bark. These results will also help in further work as they indicate that bark thickness equations are particularly important.

Analysis of statistical indicators of the population of Saint Petersburg with malignant neoplasms of pancreas

2021 ◽  
Vol 23 (2) ◽  
pp. 155-164
Author(s):  
Vladislav E. Moiseenko ◽  
Alexander V. Pavlovsky ◽  
Dmitry A. Granov ◽  
Larisa V. Kochorova ◽  
Inna V. Dodonova ◽  
...  
Keyword(s):  
Pancreatic Cancer ◽  
Stage Iv ◽  
Malignant Neoplasms ◽  
Number Of Patients ◽  
Incidence And Mortality ◽  
Significant Downward Trend ◽  
Accumulation Index ◽  
One Year ◽  
The One ◽  
Statistical Indicators

Morbidity and mortality from pancreatic cancer is an urgent medical and social problem. Evaluation of statistical indicators in dynamics makes it possible to identify organizational and clinical problems in providing care to patients with malignant neoplasms of the pancreas. Medical and statistical indicators of incidence of malignant pancreatic neoplasms in St. Petersburg residents are evaluated. The assessment of medical and statistical indicators of the incidence of malignant neoplasms of the pancreas in residents of St. Petersburg. Statistical data were studied for the period from 2014 to 2019. The increase in the "rough" indicator of primary morbidity changed from 417.99 per 100 thousand population in 2014 to 505.6 in 2019. In the structure of primary cancer incidence, the indicator of active detection of pancreatic cancer glands in 2014 amounted to 3.6%, in 2019 3.8%. The proportion of patients with diagnoses confirmed morphologically increased from 48.9% to 61.4%. The proportion of patients with newly diagnosed stage IV of the disease changed from 39.5% in 2014 to 51.4% in 2019, and in patients with stage III in 2019 it was 33.3% (a decrease in comparison with 2014 15.3%). In 2019, the disease was diagnosed at stage II in 15.2% of patients. The proportion of patients with stage I in 2019 was 6.6%, this indicator in 2014 was registered at the level of 19.2%. From 2014 to 2019, the one-year mortality rate did not change and amounted to 67.9 and 67.4%, respectively (the decrease was 0.7%). Over the past 5 years, there has been no significant downward trend in the "rough" incidence and mortality rates from pancreatic cancer. However, in the dynamics, there was an increase in the number of patients registered for 5 or more years, and an increase in the accumulation index of the contingent of patients with pancreatic cancer.

scholarly journals A Survey of Techniques for Constructing Chinese Knowledge Graphs and Their Applications

2018 ◽  
Vol 10 (9) ◽  
pp. 3245 ◽  
Author(s):  
Tianxing Wu ◽  
Guilin Qi ◽  
Cheng Li ◽  
Meng Wang
Keyword(s):  
Artificial Intelligence ◽  
Question Answering ◽  
Knowledge Representation And Reasoning ◽  
Knowledge Graph ◽  
Development History ◽  
One Belt One Road ◽  
History Of ◽  
Knowledge Graphs ◽  
The One ◽  
The Impact

With the continuous development of intelligent technologies, knowledge graph, the backbone of artificial intelligence, has attracted much attention from both academic and industrial communities due to its powerful capability of knowledge representation and reasoning. In recent years, knowledge graph has been widely applied in different kinds of applications, such as semantic search, question answering, knowledge management and so on. Techniques for building Chinese knowledge graphs are also developing rapidly and different Chinese knowledge graphs have been constructed to support various applications. Under the background of the “One Belt One Road (OBOR)” initiative, cooperating with the countries along OBOR on studying knowledge graph techniques and applications will greatly promote the development of artificial intelligence. At the same time, the accumulated experience of China in developing knowledge graphs is also a good reference to develop non-English knowledge graphs. In this paper, we aim to introduce the techniques of constructing Chinese knowledge graphs and their applications, as well as analyse the impact of knowledge graph on OBOR. We first describe the background of OBOR, and then introduce the concept and development history of knowledge graph and typical Chinese knowledge graphs. Afterwards, we present the details of techniques for constructing Chinese knowledge graphs, and demonstrate several applications of Chinese knowledge graphs. Finally, we list some examples to explain the potential impacts of knowledge graph on OBOR.

scholarly journals El sesgo de la máquina en la toma de decisiones en el proceso penal.

2020 ◽  
Vol 6 (2) ◽  
pp. 54-71
Author(s):  
Raquel Borges Blázquez
Keyword(s):  
Artificial Intelligence ◽  
The Other ◽  
Human Being ◽  
Criminal Process ◽  
Ethical Problems ◽  
Intelligent Machines ◽  
Other Hand ◽  
Toma De Decisiones ◽  
Legal Thinking ◽  
The One

Artificial intelligence has countless advantages in our lives. On the one hand, computer’s capacity to store and connect data is far superior to human capacity. On the other hand, its “intelligence” also involves deep ethical problems that the law must respond to. I say “intelligence” because nowadays machines are not intelligent. Machines only use the data that a human being has previously offered as true. The truth is relative and the data will have the same biases and prejudices as the human who programs the machine. In other words, machines will be racist, sexist and classist if their programmers are. Furthermore, we are facing a new problem: the difficulty to understand the algorithm of those who apply the law.This situation forces us to rethink the criminal process, including artificial intelligence and spinning very thinly indicating how, when, why and under what assumptions we can make use of artificial intelligence and, above all, who is going to program it. At the end of the day, as Silvia Barona indicates, perhaps the question should be: who is going to control global legal thinking?

scholarly journals The Legal Aspects of Artificial Intelligence based on the EU Experience

Law and World ◽  
2021 ◽  
Vol 7 (5) ◽  
pp. 8-13
Keyword(s):  
Artificial Intelligence ◽  
Legal Framework ◽  
Legal Aspects ◽  
Public And Private ◽  
Legal Questions ◽  
Technological Advances ◽  
Clear Vision ◽  
Routine Tasks ◽  
The One ◽  
The Eu

In the digital era, technological advances have brought innovative opportunities. Artificial intelligence is a real instrument to provide automatic routine tasks in different fields (healthcare, education, the justice system, foreign and security policies, etc.). AI is evolving very fast. More precisely, robots as re-programmable multi-purpose devices designed for the handling of materials and tools for the processing of parts or specialized devices utilizing varying programmed movements to complete a variety of tasks.1 Regardless of opportunities, artificial intelligence may pose some risks and challenges for us. Because of the nature of AI ethical and legal questions can be pondered especially in terms of protecting human rights. The power of artificial intelligence means using it more effectively in the process of analyzing big data than a human being. On the one hand, it causes loss of traditional jobs and, on the other hand, it promotes the creation of digital equivalents of workers with automatic routine task capabilities. “Artificial intelligence must serve people, and therefore artificial intelligence must always comply with people’s rights,” said Ursula von der Leyen, President of the European Commission.2 The EU has a clear vision of the development of the legal framework for AI. In the light of the above, the article aims to explore the legal aspects of artificial intelligence based on the European experience. Furthermore, it is essential in the context of Georgia’s European integration. Analyzing legal approaches of the EU will promote an approximation of the Georgian legislation to the EU standards in this field. Also, it will facilitate to define AI’s role in the effective digital transformation of public and private sectors in Georgia.

scholarly journals Artificial intelligence and copyright

2021 ◽  
pp. 15-22
Author(s):  
Daryna Prylypko
Keyword(s):  
Artificial Intelligence ◽  
Computer Program ◽  
Key Words ◽  
Automatic Generation ◽  
The Other ◽  
International Level ◽  
Human Agent ◽  
Foreign Countries ◽  
The One ◽  
Justice Practice

Key words: copyright, work, artificial intelligence, computer program In the article, the problemsof legislation of Ukraine regarding the issues of copyright on works created due to artificialintelligence were analyzed. Particularly, who is the owner of copyright ofworks created due to artificial intelligence. On the one hand, it could be a developer ofa computer program, from the other hand, it could be a client or an employer. Because,it could happen that there is a situation when robots created something newand original, e.g., how it happened with the project “New Rembrandt”. In this case,computers created a unique portrait of Rembrandt. And here is a question, where isin this portrait original and intellectual works of developers of these computers andprograms. In the contrast, this portrait could be created without people who developedspecial machines, programs, and computers. The article’s author proposes to addinto Ukrainian legislation with following norm: the owner of the copyright createddue to artificial intelligence should be a natural person who uses artificial intelligencefor these purposes within the official relationship or on the basis of a contract. In caseof automatic generation of such work by artificial intelligence, the owner of copyrightshould be the developer.Also, another question arises, particularly, who will be responsible for the damagecaused by the artificial intelligence. As an example, of the solution for this issue Resolution2015/2103 (INL) was given, where is mentioned that human agent could be responsiblefor the caused damage. Because, it is not always a developer is responsiblefor the damage.Also, the legislation and justice practice of foreign countries was explored. Theways of overcoming mentioned problems in legislation of Ukraine were proposed.Such as changing our legislation and giving the exact explanation in who is the ownerof copyright on works created due to artificial intelligence and in which cases this personcould become an owner of the copyright. However, probably, these issues shouldbe resolved at international level regarding globalization.

Roughness sub-layer wind speed model for tropical wooded areas

2022 ◽  
pp. 0309524X2110500
Author(s):  
Gustavo Richmond-Navarro ◽  
Mariana Montenegro-Montero ◽  
Pedro Casanova-Treto ◽  
Franklin Hernández-Castro ◽  
Jorge Monge-Fallas
Keyword(s):  
Artificial Intelligence ◽  
Wind Speed ◽  
Functional Relationship ◽  
Polynomial Function ◽  
Evolutionary Search ◽  
Search Technique ◽  
Humidity Sensors ◽  
Wind Speeds ◽  
The One ◽  
Future Work

There are few reports in the literature regarding wind speed near the ground. This work presents a model for wind speed from 4 m above the ground, based on year-round measurements in two meteorological towers. Each tower is equipped with anemometers at five heights, as well as thermometers and pressure and relative humidity sensors. The data is processed using Eureqa artificial intelligence software, which determines the functional relationship between variables using an evolutionary search technique called symbolic regression. Using this technique, models are found for each month under study, in which height and temperature are the variables that most affect wind speed. The model that best predicts the measured wind speeds is then selected. A polynomial function directly proportional to height and temperature is identified as the one that provides the best predictions of wind speed on average, within the rough sub-layer. Finally, future work is identified on testing the model at other locations.

scholarly journals Artificial intelligence method to classify ophthalmic emergency severity based on symptoms: a validation study

BMJ Open ◽  
2020 ◽  
Vol 10 (7) ◽  
pp. e037161
Author(s):  
Hyunmin Ahn
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Model Performance ◽  
Armed Forces ◽  
Validation Data ◽  
Data Set ◽  
Orange Yellow ◽  
Hospital Visits ◽  
Input Variables ◽  
Fully Connected

ObjectivesWe investigated the usefulness of machine learning artificial intelligence (AI) in classifying the severity of ophthalmic emergency for timely hospital visits.Study designThis retrospective study analysed the patients who first visited the Armed Forces Daegu Hospital between May and December 2019. General patient information, events and symptoms were input variables. Events, symptoms, diagnoses and treatments were output variables. The output variables were classified into four classes (red, orange, yellow and green, indicating immediate to no emergency cases). About 200 cases of the class-balanced validation data set were randomly selected before all training procedures. An ensemble AI model using combinations of fully connected neural networks with the synthetic minority oversampling technique algorithm was adopted.ParticipantsA total of 1681 patients were included.Major outcomesModel performance was evaluated using accuracy, precision, recall and F1 scores.ResultsThe accuracy of the model was 99.05%. The precision of each class (red, orange, yellow and green) was 100%, 98.10%, 92.73% and 100%. The recalls of each class were 100%, 100%, 98.08% and 95.33%. The F1 scores of each class were 100%, 99.04%, 95.33% and 96.00%.ConclusionsWe provided support for an AI method to classify ophthalmic emergency severity based on symptoms.

Sign in / Sign up

Export Citation Format

Share Document