با سلام خدمت کاربران در صورتی که با خطای سیستم پرداخت بانکی مواجه شدید از طریق کارت به کارت (6037997535328901 بانک ملی ناصر خنجری ) مقاله خود را دریافت کنید (تا مشکل رفع گردد).
ردیف | عنوان | نوع |
---|---|---|
1 |
Discovering unusual structures from exception using big data and machine learning techniques
کشف ساختارهای غیر معمول از استثناء با استفاده از داده های بزرگ و تکنیک های یادگیری ماشین-2019 Recently, machine learning (ML) has become a widely used technique in materials science study. Most
work focuses on predicting the rule and overall trend by building a machine learning model. However,
new insights are often learnt from exceptions against the overall trend. In this work, we demonstrate that
how unusual structures are discovered from exceptions when machine learning is used to get the relationship
between atomic and electronic structures based on big data from high-throughput calculation
database. For example, after training an ML model for the relationship between atomic and electronic
structures of crystals, we find AgO2F, an unusual structure with both Ag3+ and O2 2 , from structures whose
band gap deviates much from the prediction made by our model. A further investigation on this structure
might shed light into the research on anionic redox in transition metal oxides of Li-ion batterie. Keywords: Machine learning | Gradient boosting decision tree | Band gap | Unusual structures |
مقاله انگلیسی |
2 |
Decision tree underfitting in mining of gene expression data. An evolutionary multi-test tree approach
درخت تصمیم گیری در زمینه استخراج داده های بیان ژن یک رویکرد درخت چند آزمون تکاملی-2019 The problem of underfitting and overfitting in machine learning is often associated with a bias-variance trade-off. The underfitting most clearly manifests in the tree-based inducers when used to classify the gene expression data. To improve the generalization ability of decision trees, we are introducing an evo- lutionary, multi-test tree approach tailored to this specific application domain. The general idea is to apply gene clusters of varying size, which consist of functionally related genes in each splitting rule. It is achieved by using a few simple tests that mimic each other’s predictions and built-in information about the discriminatory power of genes. The tendencies to underfit and overfit are limited by the multi- objective fitness function that minimizes tree error, split divergence and attribute costs. Evolutionary search for multi-tests in internal nodes, as well as the overall tree structure, is performed simultaneously. This novel approach called Evolutionary Multi-Test Tree (EMTTree) may bring far-reaching benefits to the domain of molecular biology including biomarker discovery, finding new gene-gene interactions and high-quality prediction. Extensive experiments carried out on 35 publicly available gene expression datasets show that we managed to significantly improve the accuracy and stability of decision tree. Im- portantly, EMTTree does not substantially increase the overall complexity of the tree, so that the patterns in the predictive structures are kept comprehensible. Keywords: Data mining | Evolutionary algorithms | Decision trees | Underfitting | Gene expression data |
مقاله انگلیسی |
3 |
Algorithm to Predict the Outcome of Microvascular Decompression for Hemifacial Spasm: A Data-Mining Analysis Using a Decision Tree
الگوریتمی برای پیش بینی نتیجه کاهش فشار میکروارگانیسم برای اسپاسم خونریزی: تجزیه و تحلیل داده کاوی با استفاده از یک درخت تصمیم گیری-2019 Although microvascular decompression
(MVD) is the primary treatment for hemifacial spasm (HFS),
the postoperative course is variable. This study aimed to
develop a prediction model of the outcome of MVD in
patients with HFS by investigating influential factors.
- METHODS: Electronic medical records of 1624 patients
with HFS who underwent MVD from July 2004 to January
2015 were reviewed. The relationships between patientrelated,
disease-related, and surgery-related factors and
postoperative outcome were analyzed using multinomial
logistic regression. A predictive model for MVD outcome
was developed using decision tree analysis.
- RESULTS: The mean follow-up duration after surgery
was 30.2 months (median, 23.5 months; range, 6.0e133.3
months). For the 1624 patients, the overall improvement rate
was 90.5%. Overall, 984 patients (60.6%) showed improvement
of spasm immediately after surgery, 486 (29.9%)
experienced delayed improvement, and 154 (9.5%) showed
persistence of spasm. Outcome of patients with HFS after
MVD was predicted by 4 items: postoperative delayed
facial palsy, degree of preoperative spasm, intraoperative
indentation on the facial nerve, and sex. The patients were
classified into 6 categories and improvement of spasm
immediately after surgery showed 35%e91%, delayed
improvement 6%e46%, and persistence of spasm 0%e59%.
The accuracy of the developed prediction model was 0.608.
- CONCLUSIONS: Male sex, mild degree of preoperative
spasm, intraoperative indentation on the facial nerve, and
postoperative delayed facial palsy were better favorable prognostic factors of MVD in patients with HFS. This novel
algorithm may be useful to predict the outcome of MVD in
these patients |
مقاله انگلیسی |
4 |
Integrating machine learning into item response theory for addressing the cold start problem in adaptive learning systems
ادغام یادگیری ماشین در تئوری پاسخ به موارد برای پرداختن به مشکل شروع سرما در سیستم های یادگیری انطباقی-2019 Adaptive learning systems aim to provide learning items tailored to the behavior and needs of
individual learners. However, one of the outstanding challenges in adaptive item selection is that
often the corresponding systems do not have information on initial ability levels of new learners
entering a learning environment. Thus, the proficiency of those new learners is very difficult to be
predicted. This heavily impairs the quality of personalized items recommendation during the
initial phase of the learning environment. In order to handle this issue, known as the cold-start
problem, we propose a system that combines item response theory (IRT) with machine learning.
Specifically, we perform ability estimation and item response prediction for new learners by
integrating IRT with classification and regression trees built on learners’ side information. The
goal of this work is to build a learning system that incorporates IRT and machine learning into a
unified framework. We compare the proposed hybrid model to alternative approaches by conducting
experiments on two educational data sets. The obtained results affirmed the potential of
the proposed method. In particular, the obtained results indicate that IRT combined with
Random Forests provides the lowest error for the ability estimation and the highest accuracy in
terms of response prediction. This way, we deduce that the employment of machine learning in
combination with IRT could indeed alleviate the effect of the cold start problem in an adaptive
learning environment Keywords: Item response theory | Decision tree learning | Machine learning | Adaptive learning system | Cold-start problem |
مقاله انگلیسی |
5 |
Fall detection system for elderly people using IoT and Big Data
سیستم تشخیص سقوط برای سالمندان با استفاده از اینترنت اشیا و داده های بزرگ-2018 Falls represent a major public health risk worldwide for the elderly people. A fall not assisted in time can cause functional
impairment in an elder and a significant decrease in his mobility, independence and life quality. In that sense, the present work
proposes an innovative IoT-based system for detecting falls of elderly people in indoor environments, which takes advantages of
low-power wireless sensor networks, smart devices, big data and cloud computing. For this purpose, a 3D-axis accelerometer
embedded into a 6LowPAN device wearable is used, which is responsible for collecting data from movements of elderly people
in real-time. To provide high efficiency in fall detection, the sensor readings are processed and analyzed using a decision trees
based Big Data model running on a Smart IoT Gateway. If a fall is detected, an alert is activated and the system reacts
automatically by sending notifications to the groups responsible for the care of the elderly people. Finally, the system provides
services built on cloud. From medical perspective, there is a storage service that enables healthcare professional to access to falls
data for perform further analysis. On the other hand, the system provides a service leveraging this data to create a new machine
learning model each time a fall is detected. The results of experiments have shown high success rates in fall detection in terms of
accuracy, precision and gain.
Keywords: Fall detection; Internet-of-Things; Big Data, 6LowPAN; wearable sensor; Smart IoT Gateway; fall detection; decision tree learning algorithm; accelerometer; elderly people. |
مقاله انگلیسی |
6 |
Data mining-based high impedance fault detection using mathematical morphology
داده کاوی مبتنی بر تشخیص خطای امپدانس بالا با استفاده از مورفولوژی ریاضی-2018 High impedance fault (HIF) detection is a challenging task in power system protection because of
the random nature of current. HIFs are not efficiently detected by conventional protection sys
tems because of their low current magnitudes. The proposed method presents an intelligent HIF
protection technique using Mathematical Morphology (MM) and a data mining-based Decision
Tree (DT) model. The current signals are produced by a MATLAB / SIMULINK model of an actual
distribution system with real data. The features of these current signals are computed after
processing with MM filter. A data mining-based DT model is then generated using these features
of the current signals, and this DT model makes a final decision on classification into HIF and
non-HIF. The proposed scheme is tested on different HIF and non-HIF cases and the results were
found to be encouraging.
Keywords: High impedance fault ، Distribution system ، Mathematical morphology ، Decision tree ، Data mining |
مقاله انگلیسی |
7 |
Recovering area-to-mass ratio of resident space objects through data mining
بازیابی منطقه جرم به نسبت فضای ساکن اشیاء از طریق داده کاوی-2018 The area-to-mass ratio (AMR) of a resident space object (RSO) is an important parameter for improved space
situation awareness capability due to its effect on the non-conservative forces including the atmosphere drag force
and the solar radiation pressure force. However, information about AMR is often not provided in most space
catalogs. The present paper investigates recovering the AMR information from the consistency error, which refers
to the difference between the orbit predicted from an earlier estimate and the orbit estimated at the current
epoch. A data mining technique, particularly the random forest (RF) method, is used to discover the relationship
between the consistency error and the AMR. Using a simulation-based space catalog environment as the testbed,
this paper demonstrates that the classification RF model can determine the RSOs category AMR and the
regression RF model can generate continuous AMR values, both with good accuracies. Furthermore, the paper
reveals that by recording additional information besides the consistency error, the RF model can estimate the
AMR with even higher accuracy.
Keywords: Area-to-mass ratio ، Resident space object ، Data mining ، Decision tree ، Random forest ، Consistency error |
مقاله انگلیسی |
8 |
Educational data mining: Predictive analysis of academic performance of public school students in the capital of Brazil
داده کاوی آموزشی: تجزیه و تحلیل پیش بینی عملکرد تحصیلی دانش آموزان مدارس عمومی در پایتخت برزیل-2018 In this article, we present a predictive analysis of the academic performance of students in public schools of the
Federal District of Brazil during the school terms of 2015 and 2016. Initially, we performed a descriptive sta
tistical analysis to gain insight from data. Subsequently, two datasets were obtained. The first dataset contains
variables obtained prior to the start of the school year, and the second included academic variables collected two
months after the semester began. Classification models based on the Gradient Boosting Machine (GBM) were
created to predict academic outcomes of student performance at the end of the school year for each dataset.
Results showed that, though the attributes ‘grades and ‘absences were the most relevant for predicting the end
of the year academic outcomes of student performance, the analysis of demographic attributes reveals that
‘neighborhood’, ‘school’ and ‘age’ are also potential indicators of a students academic success or failure.
Keywords: Educational data mining ، Academic performance ، Predictive analysis ، Decision tree ، Gradient boosting machine ، H2O |
مقاله انگلیسی |
9 |
On Distributed Fuzzy Decision Trees for Big Data
درخت تصمیم گیری فازی توزیع شده برای داده های بزرگ-2018 Fuzzy decision trees (FDTs) have shown to be an effective solution in the framework of fuzzy classification. The approaches proposed so far to FDT learning, however, have generally
neglected time and space requirements. In this paper, we propose a
distributed FDT learning scheme shaped according to the MapReduceprogrammingmodelforgeneratingbothbinaryandmultiway
FDTs from big data. The scheme relies on a novel distributed fuzzy
discretizer that generates a strong fuzzy partition for each continuous attribute based on fuzzy information entropy. The fuzzy
partitions are, therefore, used as an input to the FDT learning algorithm, which employs fuzzy information gain for selecting the
attributes at the decision nodes. We have implemented the FDT
learning scheme on the Apache Spark framework. We have used
ten real-world publicly available big datasets for evaluating the
behavior of the scheme along three dimensions: 1) performance in
terms of classification accuracy, model complexity, and execution
time; 2) scalability varying the number of computing units; and
3) ability to efficiently accommodate an increasing dataset size.
We have demonstrated that the proposed scheme turns out to be
suitable for managing big datasets even with a modest commodity
hardware support. Finally, we have used the distributed decision
tree learning algorithm implemented in the MLLib library and the
Chi-FRBCS-BigData algorithm, a MapReduce distributed fuzzy
rule-based classification system, for comparative analysis
Index Terms: Apache spark, big data, fuzzy decision trees (FDTs), fuzzy discretizer, fuzzy entropy, fuzzy partitioning,MapReduce |
مقاله انگلیسی |
10 |
Applying Kansei Engineering and data mining to design door-to-door delivery service
استفاده از مهندسی Kansei و داده کاوی برای طراحی خدمات تحویل درب به درب-2018 This study proposes a service design approach integrating Kansei Engineering and a data mining technique, in
which Kansei Engineering is an ergonomic approach of customer-oriented product/service development and can
translate the users’ subjective perceptions into a design specifications. The integrated approach collects custo
mers’ relevant perceptual vocabulary and service properties based on the Kansei Engineering procedure.
Subsequently, it quantifies the relationship among service properties, perceptual responses and usage intention
through the data mining technique using a decision tree. A case of door-to-door delivery (D2DD) service is
adopted to demonstrate that the proposed approach can incorporate the customers’ feelings into the process of
service design or improvement and illustrate that the decision tree is suitable to be integrated with Kansei
Engineering. The analytical results show the influence of a combination of different service properties (resp.
perceptual responses) on a perceptual response (resp. usage intention). It is found that the combinations of
crucial perceptual responses result in positive (resp. negative) usage intention and the property combinations
result in these crucial perceptual responses. Accordingly, the D2DD service provider can improve or create its
service based on the research findings.
Keywords: Service design ، Kansei Engineering ، Decision tree ، Door-to-door delivery service |
مقاله انگلیسی |