scholarly journals Understanding Smartwatch Battery Utilization in the Wild

Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3784 ◽  
Author(s):  
Morteza Homayounfar ◽  
Amirhossein Malekijoo ◽  
Aku Visuri ◽  
Chelsea Dobbins ◽  
Ella Peltonen ◽  
...  
Keyword(s):  
Real World ◽  
Binary Classification ◽  
Classification Problem ◽  
Machine Learning Algorithms ◽  
Indexing Method ◽  
In The Wild ◽  
Art Research ◽  
Battery Discharge ◽  
Changes Over Time ◽  
Application Developers

Smartwatch battery limitations are one of the biggest hurdles to their acceptability in the consumer market. To our knowledge, despite promising studies analyzing smartwatch battery data, there has been little research that has analyzed the battery usage of a diverse set of smartwatches in a real-world setting. To address this challenge, this paper utilizes a smartwatch dataset collected from 832 real-world users, including different smartwatch brands and geographic locations. First, we employ clustering to identify common patterns of smartwatch battery utilization; second, we introduce a transparent low-parameter convolutional neural network model, which allows us to identify the latent patterns of smartwatch battery utilization. Our model converts the battery consumption rate into a binary classification problem; i.e., low and high consumption. Our model has 85.3% accuracy in predicting high battery discharge events, outperforming other machine learning algorithms that have been used in state-of-the-art research. Besides this, it can be used to extract information from filters of our deep learning model, based on learned filters of the feature extractor, which is impossible for other models. Third, we introduce an indexing method that includes a longitudinal study to quantify smartwatch battery quality changes over time. Our novel findings can assist device manufacturers, vendors and application developers, as well as end-users, to improve smartwatch battery utilization.

scholarly journals Classification of unlabeled online media

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Sakthi Kumar Arul Prakash ◽  
Conrad Tucker
Keyword(s):  
Social Media ◽  
Real World ◽  
Graphical Model ◽  
Ground Truth ◽  
Classification Problem ◽  
Machine Learning Algorithms ◽  
Social Media Networks ◽  
Online Social Media ◽  
Wide Range

AbstractThis work investigates the ability to classify misinformation in online social media networks in a manner that avoids the need for ground truth labels. Rather than approach the classification problem as a task for humans or machine learning algorithms, this work leverages user–user and user–media (i.e.,media likes) interactions to infer the type of information (fake vs. authentic) being spread, without needing to know the actual details of the information itself. To study the inception and evolution of user–user and user–media interactions over time, we create an experimental platform that mimics the functionality of real-world social media networks. We develop a graphical model that considers the evolution of this network topology to model the uncertainty (entropy) propagation when fake and authentic media disseminates across the network. The creation of a real-world social media network enables a wide range of hypotheses to be tested pertaining to users, their interactions with other users, and with media content. The discovery that the entropy of user–user and user–media interactions approximate fake and authentic media likes, enables us to classify fake media in an unsupervised learning manner.

scholarly journals Prediction of Drug Side Effects with a Refined Negative Sample Selection Strategy

2020 ◽  
Vol 2020 ◽  
pp. 1-16 ◽  
Author(s):  
Haiyan Liang ◽  
Lei Chen ◽  
Xian Zhao ◽  
Xiaolin Zhang
Keyword(s):  
Side Effects ◽  
High Performance ◽  
Chemical Interaction ◽  
Binary Classification ◽  
Sample Selection ◽  
Interaction Network ◽  
Classification Problem ◽  
Machine Learning Algorithms ◽  
Selection Strategy ◽  
Negative Sample

Drugs are an important way to treat various diseases. However, they inevitably produce side effects, bringing great risks to human bodies and pharmaceutical companies. How to predict the side effects of drugs has become one of the essential problems in drug research. Designing efficient computational methods is an alternative way. Some studies paired the drug and side effect as a sample, thereby modeling the problem as a binary classification problem. However, the selection of negative samples is a key problem in this case. In this study, a novel negative sample selection strategy was designed for accessing high-quality negative samples. Such strategy applied the random walk with restart (RWR) algorithm on a chemical-chemical interaction network to select pairs of drugs and side effects, such that drugs were less likely to have corresponding side effects, as negative samples. Through several tests with a fixed feature extraction scheme and different machine-learning algorithms, models with selected negative samples produced high performance. The best model even yielded nearly perfect performance. These models had much higher performance than those without such strategy or with another selection strategy. Furthermore, it is not necessary to consider the balance of positive and negative samples under such a strategy.

scholarly journals Classification of unlabeled online media

2020 ◽  
Author(s):  
Sakthi Kumar Arul Prakash ◽  
Conrad Tucker
Keyword(s):  
Real World ◽  
Graphical Model ◽  
Classification Problem ◽  
Machine Learning Algorithms ◽  
Online Media ◽  
Media Content ◽  
Social Media Networks ◽  
Online Social Media ◽  
Wide Range

Abstract This work investigates the ability to classify misinformation in online social media networks in a manner that avoids the need forground truth labels. Rather than approach the classification problem as a task for humans or machine learning algorithms, thiswork leverages user-user and user-media (i.e.,media likes) interactions to infer the type of information (fake vs. authentic) beingspread, without needing to know the actual details of the information itself. To study the inception and evolution of user-userand user-media interactions over time, we create an experimental platform that mimics the functionality of real world socialmedia networks. We develop a graphical model that considers the evolution of this network topology to model the uncertainty(entropy) propagation when fake and authentic media disseminates across the network. The creation of a real-world socialmedia network enables a wide range of hypotheses to be tested pertaining to users, their interactions with other users, andwith media content. The discovery that the entropy of user-user, and user-media interactions approximates fake and authenticmedia likes, enables us to classify fake media in an unsupervised learning manner.

scholarly journals Logistic Regression for Health Profiling

2019 ◽  
Vol 8 (6S2) ◽  
pp. 974-977
Keyword(s):  
Logistic Regression ◽  
Ordinal Data ◽  
Binary Classification ◽  
Classification Problem ◽  
Machine Learning Algorithms ◽  
Classification Problems ◽  
Specific Product ◽  
Logistic Analysis ◽  
Medical Researcher ◽  
Diabetes Prediction

in an event when there is lots of risk factor then the logistic regression is used for predicting the probability. For binary and ordinal data the medical researcher increase the use of logistic analysis. Several classification problems like spam detection used logistic regression. If a customer purchases a specific product in Diabetes prediction or they will inspire with any other competitor, whether customer click on given advertisement link or not are some example. For two class classification the Logistic Regression is one of the most simple and common machine Learning algorithms. For any binary classification problem it is very easy to use as a basic approach. Deep learning is also its fundamental concept. The relationship measurement and description between dependent binary variable and independent variables can be done by logistic regression.

scholarly journals How to Effectively Collect and Process Network Data for Intrusion Detection?

Entropy ◽  
2021 ◽  
Vol 23 (11) ◽  
pp. 1532
Author(s):  
Mikołaj Komisarek ◽  
Marek Pawlicki ◽  
Rafał Kozik ◽  
Witold Hołubowicz ◽  
Michał Choraś
Keyword(s):  
Machine Learning ◽  
Intrusion Detection ◽  
Real World ◽  
Machine Learning Algorithms ◽  
Network Intrusion Detection ◽  
Minimal Amount ◽  
Security Breaches ◽  
Network Intrusion ◽  
Benchmark Datasets ◽  
In The Wild

The number of security breaches in the cyberspace is on the rise. This threat is met with intensive work in the intrusion detection research community. To keep the defensive mechanisms up to date and relevant, realistic network traffic datasets are needed. The use of flow-based data for machine-learning-based network intrusion detection is a promising direction for intrusion detection systems. However, many contemporary benchmark datasets do not contain features that are usable in the wild. The main contribution of this work is to cover the research gap related to identifying and investigating valuable features in the NetFlow schema that allow for effective, machine-learning-based network intrusion detection in the real world. To achieve this goal, several feature selection techniques have been applied on five flow-based network intrusion detection datasets, establishing an informative flow-based feature set. The authors’ experience with the deployment of this kind of system shows that to close the research-to-market gap, and to perform actual real-world application of machine-learning-based intrusion detection, a set of labeled data from the end-user has to be collected. This research aims at establishing the appropriate, minimal amount of data that is sufficient to effectively train machine learning algorithms in intrusion detection. The results show that a set of 10 features and a small amount of data is enough for the final model to perform very well.

scholarly journals Comparing classification algorithms for prediction on CROBEX data

2020 ◽  
Vol 6 (2) ◽  
pp. 4-11
Author(s):  
Silvija Vlah Jerić
Keyword(s):  
Binary Classification ◽  
Classification Problem ◽  
Machine Learning Algorithms ◽  
Stock Index ◽  
Support Vector ◽  
Automatic Identification ◽  
Classification Algorithms ◽  
Day Trading ◽  
Closing Price ◽  
Market Situation

AbstractThe main objective of this analysis is to evaluate and compare the various classification algorithms for the automatic identification of favourable days for intraday trading using the Croatian stock index CROBEX data. Intra-day trading refers to the acquisition and sale of financial instruments on the same trading day. If the increase between the opening price and the closing price of the same day is substantial enough to earn a profit by purchasing at the opening price and selling at the closing price, the day is considered to be favourable for intra-day trading. The goal is to discover relation between selected financial indicators on a given day and the market situation on the following day i.e. to determine whether a day is favourable for day trading or not. The problem is modelled as a binary classification problem. The idea is to test different algorithms and to give greater attention to those that are more rarely used than traditional statistical methods. Thus, the following algorithms are used: neural network, support vector machine, random forest, as well as k-nearest neighbours and naïve Bayes classifier as classifiers that are more common. The work is an extension of authors’ previous work in which the algorithms are compared on resamples resulting from tuning the algorithms, while here, each derived model is used to make predictions on new data. The results should add to the increasing corpus of stock market prediction research efforts and try to fill some gaps in this field of research for the Croatian market, in particular by using machine learning algorithms.

scholarly journals Predictive Models of Student College Commitment Decisions Using Machine Learning

Data ◽  
2019 ◽  
Vol 4 (2) ◽  
pp. 65 ◽  
Author(s):  
Kanadpriya Basu ◽  
Treena Basu ◽  
Ron Buckmire ◽  
Nishu Lal
Keyword(s):  
Machine Learning ◽  
Liberal Arts ◽  
Optimal Allocation ◽  
Binary Classification ◽  
Classification Problem ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Learning Techniques ◽  
Student College

Every year, academic institutions invest considerable effort and substantial resources to influence, predict and understand the decision-making choices of applicants who have been offered admission. In this study, we applied several supervised machine learning techniques to four years of data on 11,001 students, each with 35 associated features, admitted to a small liberal arts college in California to predict student college commitment decisions. By treating the question of whether a student offered admission will accept it as a binary classification problem, we implemented a number of different classifiers and then evaluated the performance of these algorithms using the metrics of accuracy, precision, recall, F-measure and area under the receiver operator curve. The results from this study indicate that the logistic regression classifier performed best in modeling the student college commitment decision problem, i.e., predicting whether a student will accept an admission offer, with an AUC score of 79.6%. The significance of this research is that it demonstrates that many institutions could use machine learning algorithms to improve the accuracy of their estimates of entering class sizes, thus allowing more optimal allocation of resources and better control over net tuition revenue.

scholarly journals Architecture for Trajectory-Based Fishing Ship Classification with AIS Data

Sensors ◽  
2020 ◽  
Vol 20 (13) ◽  
pp. 3782 ◽  
Author(s):  
David Sánchez Pedroche ◽  
Daniel Amigo ◽  
Jesús García ◽  
José Manuel Molina
Keyword(s):  
Real World ◽  
Binary Classification ◽  
Classification Problem ◽  
Automatic Identification ◽  
Identification System ◽  
Preparation Process ◽  
Data Preparation ◽  
Real World Data ◽  
Fishing Vessels ◽  
Ship Classification

This paper proposes a data preparation process for managing real-world kinematic data and detecting fishing vessels. The solution is a binary classification that classifies ship trajectories into either fishing or non-fishing ships. The data used are characterized by the typical problems found in classic data mining applications using real-world data, such as noise and inconsistencies. The two classes are also clearly unbalanced in the data, a problem which is addressed using algorithms that resample the instances. For classification, a series of features are extracted from spatiotemporal data that represent the trajectories of the ships, available from sequences of Automatic Identification System (AIS) reports. These features are proposed for the modelling of ship behavior but, because they do not contain context-related information, the classification can be applied in other scenarios. Experimentation shows that the proposed data preparation process is useful for the presented classification problem. In addition, positive results are obtained using minimal information.

scholarly journals Predicting Future Occurrence of Acute Hypotensive Episodes Using Noninvasive and Invasive Features

2021 ◽  
Vol 186 (Supplement_1) ◽  
pp. 445-451
Author(s):  
Yifei Sun ◽  
Navid Rashedi ◽  
Vikrant Vaze ◽  
Parikshit Shah ◽  
Ryan Halter ◽  
...  
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Real World ◽  
Short Term Memory ◽  
Model Performance ◽  
Learning Technologies ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Continuous Map

ABSTRACT Introduction Early prediction of the acute hypotensive episode (AHE) in critically ill patients has the potential to improve outcomes. In this study, we apply different machine learning algorithms to the MIMIC III Physionet dataset, containing more than 60,000 real-world intensive care unit records, to test commonly used machine learning technologies and compare their performances. Materials and Methods Five classification methods including K-nearest neighbor, logistic regression, support vector machine, random forest, and a deep learning method called long short-term memory are applied to predict an AHE 30 minutes in advance. An analysis comparing model performance when including versus excluding invasive features was conducted. To further study the pattern of the underlying mean arterial pressure (MAP), we apply a regression method to predict the continuous MAP values using linear regression over the next 60 minutes. Results Support vector machine yields the best performance in terms of recall (84%). Including the invasive features in the classification improves the performance significantly with both recall and precision increasing by more than 20 percentage points. We were able to predict the MAP with a root mean square error (a frequently used measure of the differences between the predicted values and the observed values) of 10 mmHg 60 minutes in the future. After converting continuous MAP predictions into AHE binary predictions, we achieve a 91% recall and 68% precision. In addition to predicting AHE, the MAP predictions provide clinically useful information regarding the timing and severity of the AHE occurrence. Conclusion We were able to predict AHE with precision and recall above 80% 30 minutes in advance with the large real-world dataset. The prediction of regression model can provide a more fine-grained, interpretable signal to practitioners. Model performance is improved by the inclusion of invasive features in predicting AHE, when compared to predicting the AHE based on only the available, restricted set of noninvasive technologies. This demonstrates the importance of exploring more noninvasive technologies for AHE prediction.

Sign in / Sign up

Export Citation Format

Share Document