scholarly journals Predicting Cow's Delivery Using Movement and Position Data Based on Machine Learning

10.29007/bksq ◽  
2019 ◽  
Author(s):  
Yusuke Ono ◽  
Ryo Hatano ◽  
Hayato Ohwada ◽  
Hiroyuki Nishiyama
Keyword(s):  
Machine Learning ◽  
Inductive Logic ◽  
Logical Form ◽  
Dairy Farm ◽  
Machine Learning Model ◽  
Acceleration Data ◽  
Close Observation ◽  
Position Data ◽  
Series Acceleration ◽  
Novel Method

One of the major problem farmers face is that of a parturition accident. A parturition accident result in the death of the calf when the cow gives birth. In addition, it reduces the milk yield. The farmer must keep the cow under close observation for the last few days of pregnancy.A novel method to predict a cow’s delivery time automatically using time-series acceleration data and global position data by machine learning is proposed. The required data was collected by a small sensor device attached to the cow’s collar. An inductive logic programming (ILP) method was employed for a machine learning model as it can generate readable results in terms of a formula for first-order logic (FOL). To apply the machine learning technique, the collected data was converted to a logical form that includes predefined predicates of FOL. Using the obtained results, one can classify whether the cows are ready for delivery.Data was collected from 31 cows at the NAMIKI Dairy Farm Co. Ltd. Using the method described above, 130 readings were obtained. The five-fold cross-validation process verified the accuracy of the model at 56.79%.

A Novel Amino Acid Sequence-based Computational Approach to Predicting Cell-penetrating Peptides

2019 ◽  
Vol 15 (3) ◽  
pp. 206-211 ◽  
Author(s):  
Jihui Tang ◽  
Jie Ning ◽  
Xiaoyan Liu ◽  
Baoming Wu ◽  
Rongfeng Hu
Keyword(s):  
Machine Learning ◽  
Amino Acid ◽  
Amino Acid Position ◽  
Cell Penetrating Peptides ◽  
Support Vector ◽  
Cell Penetration ◽  
Drug Candidates ◽  
Machine Learning Model ◽  
Cell Penetrating ◽  
Novel Method

<P>Introduction: Machine Learning is a useful tool for the prediction of cell-penetration compounds as drug candidates. </P><P> Materials and Methods: In this study, we developed a novel method for predicting Cell-Penetrating Peptides (CPPs) membrane penetrating capability. For this, we used orthogonal encoding to encode amino acid and each amino acid position as one variable. Then a software of IBM spss modeler and a dataset including 533 CPPs, were used for model screening. </P><P> Results: The results indicated that the machine learning model of Support Vector Machine (SVM) was suitable for predicting membrane penetrating capability. For improvement, the three CPPs with the most longer lengths were used to predict CPPs. The penetration capability can be predicted with an accuracy of close to 95%. </P><P> Conclusion: All the results indicated that by using amino acid position as a variable can be a perspective method for predicting CPPs membrane penetrating capability.</P>

scholarly journals Machine Learning Model for Prediction of Diabetes Mellitus

2020 ◽  
Vol 8 (5) ◽  
pp. 2376-2381
Keyword(s):  
Diabetes Mellitus ◽  
Machine Learning ◽  
Learning Model ◽  
Endocrine Disease ◽  
Machine Learning Model ◽  
Novel Method ◽  
Prediction Of Diabetes ◽  
Accuracy Of Prediction

Today world is extensively affected by endocrine disease Diabetes Mellitus which is commonly known as diabetes. There is a need for an effective model which can predict diabetes and its types at the early stages with accuracy. To improve the accuracy of prediction and to achieve better efficiency, a new Machine Learning based Model (MLM) is proposed. This Machine Learning Model (MLM) has ability to predict the diabetes and its categories as type 1, type 2 and Gestational diabetic with which the patient is suffering from. The proposed Machine Learning Model is innovative for diagnosis of diabetes is more accurate as compared to other existing approaches.This is a novel method from which one can combine power of an expert system with the machine learning environment.

scholarly journals A Machine Learning Approach for Predicting Student Performance

2019 ◽  
pp. 462-465
Author(s):  
C. Selvi ◽  
R. Shalini ◽  
V. Navaneethan ◽  
L. Santhiya
Keyword(s):  
Machine Learning ◽  
Academic Performance ◽  
Student Performance ◽  
Learning Model ◽  
Learning Approach ◽  
Economic Prosperity ◽  
Machine Learning Model ◽  
Machine Learning Approach ◽  
Novel Method ◽  
Predicting Student Performance

An University’s reputation and its standard are weighted by its students performance and their part in the future economic prosperity of the nation, hence a novel method of predicting the student’s upcoming academic performance is really essential to provide a pre-requisite information upon their performances. A machine learning model can be developed to predict the student’s upcoming scores or their entire performance depending upon their previous academic performances.

scholarly journals Inferring Tracker-Advertiser Relationships in the Online Advertising Ecosystem using Header Bidding

2020 ◽  
Vol 2020 (1) ◽  
pp. 65-82
Author(s):  
John Cook ◽  
Rishab Nithyanand ◽  
Zubair Shafiq
Keyword(s):  
Machine Learning ◽  
Data Sharing ◽  
Online Advertising ◽  
Research Problem ◽  
Learning Model ◽  
Bidding Behavior ◽  
Server Side ◽  
Machine Learning Model ◽  
Novel Method ◽  
Client Side

AbstractOnline advertising relies on trackers and data brokers to show targeted ads to users. To improve targeting, different entities in the intricately interwoven online advertising and tracking ecosystems are incentivized to share information with each other through client-side or server-side mechanisms. Inferring data sharing between entities, especially when it happens at the server-side, is an important and challenging research problem. In this paper, we introduce Kashf: a novel method to infer data sharing relationships between advertisers and trackers by studying how an advertiser’s bidding behavior changes as we manipulate the presence of trackers. We operationalize this insight by training an interpretable machine learning model that uses the presence of trackers as features to predict the bidding behavior of an advertiser. By analyzing the machine learning model, we can infer relationships between advertisers and trackers irrespective of whether data sharing occurs at the client-side or the server-side. We are able to identify several server-side data sharing relationships that are validated externally but are not detected by client-side cookie syncing.

A novel method to predict nonvisible symptoms using machine learning in cancer palliative care

2021 ◽  
Author(s):  
Kazuki Shimada ◽  
Satoru Tsuneto
Keyword(s):  
Machine Learning ◽  
Palliative Care ◽  
Informed Consent ◽  
Cancer Patients ◽  
Prediction Accuracy ◽  
Patients With Cancer ◽  
Machine Learning Model ◽  
Background Data ◽  
Novel Method ◽  
Clinical Survey

Abstract Patients with cancer at the end of life may find it difficult to express their symptoms if they can no longer communicate verbally because of deteriorating health. In this study, we assessed these symptoms using machine learning. We conducted a clinical survey of 213 cancer patients from August 2015 to August 2016. We divided the reported symptoms into two groups—visible and nonvisible symptoms. Our machine learning model used patient background data and visible symptoms to predict nonvisible symptoms: pain, dyspnea, fatigue, drowsiness, anxiety, delirium, inadequate informed consent, and spiritual issues. The highest and/or lowest values for prediction accuracy, sensitivity, and specificity, respectively, are as follows: 88.0%/55.5%, 84.9%/3·3%, and 96.7%/24.1%. This work will facilitate better assessment and management of symptoms in patients with cancer.

scholarly journals A novel method of measuring flexibility of mind-wandering and its relationship to mindfulness and depression

2020 ◽  
Author(s):  
Issaku Kawashima ◽  
Toru Takahashi ◽  
Tomoki Kikai ◽  
Fukiko Sugiyama ◽  
Hiroaki Kumano
Keyword(s):  
Machine Learning ◽  
Mindfulness Meditation ◽  
Verbal Report ◽  
Mind Wandering ◽  
Machine Learning Model ◽  
Before And After ◽  
Measurement Methodology ◽  
Novel Method ◽  
Meditation Experience ◽  
Time Required

Mindfulness meditation might improve the flexibility of mind-wandering, that is, the ability to shift attention from mind-wandering. Flexibility of mind-wandering could mediate the relationship between mindfulness and improvement in depression. However, there have been no studies of this relationship because of limitations in measurement methodology. Since the mindfulness-based intervention, which instructs participants to be aware of the occurrence of, and their own engagement in, mind-wandering, might bias self-reports of mind wandering, a measurement method that does not rely on participants’ verbal report is needed. Therefore, we propose a novel method to evaluate the flexibility of mind-wandering, based on mind-wandering intensity estimation by machine-learning using electroencephalography. We estimated mind-wandering intensity using one-second electroencephalogram samples and a machine-learning model developed in previous research. Thus, we observed fluctuations in mind-wandering during a 14-minute meditation and defined the time required to shift attention from mind-wandering as an index of mind-wandering flexibility. We performed two experiments: The first targeted experienced meditators and the second assessed non-meditators before and after participating in a mindfulness-based intervention. These experiments revealed that flexibility of mind-wandering was correlated with the extent of meditation experience. In addition, the magnitude of the decrease in flexibility and severity of depression following the intervention were found to be correlated.

Machine Learning Accelerated Genetic Algorithms for Computational Materials Search

2018 ◽  
Author(s):  
Steen Lysgaard ◽  
Paul C. Jennings ◽  
Jens Strabo Hummelshøj ◽  
Thomas Bligaard ◽  
Tejs Vegge
Keyword(s):  
Machine Learning ◽  
Genetic Algorithm ◽  
Genetic Algorithms ◽  
Au Nanoparticles ◽  
Learning Model ◽  
Energy Calculations ◽  
Atomic Distribution ◽  
Machine Learning Model ◽  
Fold Reduction ◽  
Computational Materials

A machine learning model is used as a surrogate fitness evaluator in a genetic algorithm (GA) optimization of the atomic distribution of Pt-Au nanoparticles. The machine learning accelerated genetic algorithm (MLaGA) yields a 50-fold reduction of required energy calculations compared to a traditional GA.

BAND NN: A Deep Learning Framework For Energy Prediction and Geometry Optimization of Organic Small Molecules

2019 ◽  
Author(s):  
Siddhartha Laghuvarapu ◽  
Yashaswi Pathak ◽  
U. Deva Priyakumar
Keyword(s):  
Machine Learning ◽  
Density Functional ◽  
Computational Cost ◽  
Geometry Optimization ◽  
Dft Methods ◽  
Energy Prediction ◽  
Machine Learning Model ◽  
Equilibrium Structures ◽  
High Level ◽  
Non Equilibrium

Recent advances in artificial intelligence along with development of large datasets of energies calculated using quantum mechanical (QM)/density functional theory (DFT) methods have enabled prediction of accurate molecular energies at reasonably low computational cost. However, machine learning models that have been reported so far requires the atomic positions obtained from geometry optimizations using high level QM/DFT methods as input in order to predict the energies, and do not allow for geometry optimization. In this paper, a transferable and molecule-size independent machine learning model (BAND NN) based on a chemically intuitive representation inspired by molecular mechanics force fields is presented. The model predicts the atomization energies of equilibrium and non-equilibrium structures as sum of energy contributions from bonds (B), angles (A), nonbonds (N) and dihedrals (D) at remarkable accuracy. The robustness of the proposed model is further validated by calculations that span over the conformational, configurational and reaction space. The transferability of this model on systems larger than the ones in the dataset is demonstrated by performing calculations on select large molecules. Importantly, employing the BAND NN model, it is possible to perform geometry optimizations starting from non-equilibrium structures along with predicting their energies.

Sign in / Sign up

Export Citation Format

Share Document