In classification, regression, and other data mining applications, feature selection (FS) is an important pre-process step which helps avoid advert effect of noisy, misleading, and inconsistent features on the model performance. Formulating it into a global combinatorial optimization problem, researchers have employed metaheuristic algorithms for selecting the prominent features to simplify and enhance the quality of the high-dimensional datasets, in order to devise efficient knowledge extraction systems. However, when employed on datasets with extensively large feature-size, these methods often suffer from local optimality problem due to considerably large solution space. In this study, we propose a novel approach to dimensionality reduction by using Henry gas solubility optimization (HGSO) algorithm for selecting significant features, to enhance the classification accuracy. By employing several datasets with wide range of feature size, from small to massive, the proposed method is evaluated against well-known metaheuristic algorithms including grasshopper optimization algorithm (GOA), whale optimization algorithm (WOA), dragonfly algorithm (DA), grey wolf optimizer (GWO), salp swarm algorithm (SSA), and others from recent relevant literature. We used k-nearest neighbor (k-NN) and support vector machine (SVM) as expert systems to evaluate the selected feature-set. Wilcoxon’s ranksum non-parametric statistical test was carried out at 5% significance level to judge whether the results of the proposed algorithms differ from those of the other compared algorithms in a statistically significant way. Overall, the empirical analysis suggests that the proposed approach is significantly effective on low, as well as, considerably high dimensional datasets, by producing 100% accuracy on classification problems with more than 11,000 features.

An efficient Henry Gas Solubility Optimization for Feature Selection

Abstrak - Pembelajaran mesin merupakan bagian dari kecerdasan buatan yang banyak digunakan untuk memecahkan berbagai masalah. Artikel ini menyajikan ulasan pemecahan masalah dari penelitian-penelitian terkini dengan mengklasifikasikan machine learning menjadi tiga kategori: pembelajaran terarah, pembelajaran tidak terarah, dan pembelajaran reinforcement. Hasil ulasan menunjukkan ketiga kategori masih berpeluang digunakan dalam beberapa kasus terkini dan dapat ditingkatkan untuk mengurangi beban komputasi dan mempercepat kinerja untuk mendapatkan tingkat akurasi dan presisi yang tinggi. Tujuan ulasan artikel ini diharapkan dapat menemukan celah dan dijadikan pedoman untuk penelitian pada masa yang akan datang. Katakunci : pembelajaran mesin, pembelajaran reinforcement, pembelajaran terarah, pembelajaran tidak terarah Abstract - Machine learning is part of artificial intelligence that is widely used to solve various problems. This article reviews problem solving from the latest studies by classifying machine learning into three categories: supervised learning, unsupervised learning, and reinforcement learning. The results of the review show that the three categories are still likely to be used in some of the latest cases and can be improved to reduce computational costs and accelerate performance to get a high level of accuracy and precision. The purpose of this article review is expected to be able to find a gap and it is used as a guideline for future research. Keywords : machine learning, reinforcement learning, supervised learning, unsupervised learning

/pdf/pemanfaatan-machine-learning-dalam-berbagai-bidang-review-4mjsum5crp.pdf

Pemanfaatan Machine Learning dalam Berbagai Bidang: Review paper

In recent years, with an increase in the use of smartwatches among wearable devices, various applications for the device have been developed. However, the realization of a user interface is limited by the size and volume of the smartwatch. This study aims to propose a method to classify the user’s gestures without the need of an additional input device to improve the user interface. The smartwatch is equipped with an accelerometer, which collects the data and learns and classifies the gesture pattern using a machine learning algorithm. By incorporating the convolution neural network (CNN) model, the proposed pattern recognition system has become more accurate than the existing model. The performance analysis results show that the proposed pattern recognition system can classify 10 gesture patterns at an accuracy rate of 97.3%.

https://www.mdpi.com/1424-8220/18/9/2997/pdf

Smartwatch User Interface Implementation Using CNN-Based Gesture Pattern Recognition.

In next generation of smart computing environment, myriads of networked resources are pervasive and embedded into everyday consumer products and appliances. Still, most controller systems provide separate control user interfaces for different uses when users inevitably face an increased number of interfaces for control and interaction tasks in such environment. To simplify burdens of user and reduce complexities in control tasks, we propose a universal appliance controller based on mobile device with two selective interaction modes. First mode is a network scanning-based indirect interaction mode which provides fast and reliable connection to the appliances with specific filters in the networked environment. Second mode is a camera-based direct interaction mode which provides an intuitive interface as an input device. These two modes are interchangeable for different tasks and according to user's preference. Moreover, control user interface is personalized with preference described in user profile to reflect the user of the system better. To verify usefulness of our approach, we present a prototype in a smart home test bed. Through an initial user study, we demonstrate usability of our prototype through a set of mobile interaction tasks. Moreover, we note usability issues, limitations of our work and analyze the participants' feedback.

Design and implementation of a universal appliance controller based on selective interaction modes

Smart watches: A review of evolution in bio-medical sector

Purpose Observation of medical trainees' care performance by experts can be extremely helpful for ensuring safety and providing quality care. The advanced technology of smart glasses enables health professionals to video stream their operations to remote supporters for collaboration and cooperation. This study monitored the clinical situation by using smart glasses for remote cooperative training via video streaming and clinical decision-making through simulation based on a scenario of emergency nursing care for patients with arrhythmia. Participants and methods The clinical operations of bedside trainees, who is Google Glass Enterprise Edition 2(Glass EE2) wearers, were live streamed via their Google Glasses, which were viewed at a remote site by remote supporters via a desktop computer. Data were obtained from 31 nursing students using eight essay questions regarding their experience as desktop-side remote supporters. Results Most of the participants reported feeling uneasy about identifying clinical situations (84%), patients' condition (72%), and trainees' performance (69%). The current system demonstrated sufficient performance with a satisfactory level of image quality and auditory communication, while network and connectivity are areas that require further improvement. The reported barriers to identifying situations on the remote desktop were predominantly a narrow field of view and motion blur in videos captured by Glass EE2s, and using the customized mirror mode. Conclusion The current commercial Glass EE2 can facilitate enriched communication between remotely located supporters and trainees by sharing live videos and audio during clinical operations. Further improvement of hardware and software user interfaces will ensure better applicability of smart glasses and video streaming functions to clinical practice settings.

/pdf/google-glass-supported-cooperative-training-for-health-1gq6xf5xch.pdf

Google Glass-Supported Cooperative Training for Health Professionals: A Case Study Based on Using Remote Desktop Virtual Support

Today's consumer wearable devices such as smart-watches and fitness trackers suffer from limited usability owing to a small touchscreen. In order to overcome the limitation, there has been a lot of research focused on expanding the interaction space outside the small touchscreen. In this paper, we propose a motion based user interface to generate six input events using the built-in 9-axis sensors on consumer wearable devices. First, we present and design an interaction concept followed by implementations of machine learning based motion recognition and applications using the proposed user interface.

Implementation of smartwatch user interface using machine learning based motion recognition

Multi-Style License Plate Recognition System using K-Nearest Neighbors

Today's consumer wearable devices such as smart-watches and fitness trackers suffer from limited usability owing to a diminutive touchscreen integrated into the device. In this paper, we propose a motion-based user interface that uses built-in 6-axis sensors to express and identify four directional taps on the body of a movable wrist-worn device. We first present a concept and design of this user interface, followed by an implementation on a commercial smartwatch to demonstrate an enabling user interaction applied to consumer wearable devices.

Motion UI: Motion-based user interface for movable wrist-worn devices

277 Abstract: Extended reality-assisted training offers repeatable learning opportunities at a low cost. This paper proposes a smart glass application for training core nursing skills to nursing students, who often need to memorize and practice training sequences. The proposed smart glass application interactively presents a series of instructions to help students remember and perform two core nursing skills in the correct order. We conducted a usability test on 30 undergraduate nursing students in their third year using the smart glass application. Our initial findings show that many students have positively evaluated the possibility of using smart glasses for training, but have also encountered several challenges with the smart glass application’s user interface, which takes time to adapt.

/pdf/brief-paper-design-and-implementation-of-a-smart-glass-3wspe77ymg.pdf

Hyoseok Yoon

Papers

Google Glass-Supported Cooperative Training for Health Professionals: A Case Study Based on Using Remote Desktop Virtual Support

Implementation of smartwatch user interface using machine learning based motion recognition

Multi-Style License Plate Recognition System using K-Nearest Neighbors

Motion UI: Motion-based user interface for movable wrist-worn devices

Brief Paper: Design and Implementation of a Smart Glass Application for XR Assisted Training of Core Nursing Skills