• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.11-16
• /
• 2021

At the present time, the number of accidents has enlarged speedily and in country like India per day there are about 204 accidents occurred. Accidents of two-wheeler compose a foremost segment of every accident and it can be true for the reason that two-wheelers like bikes not able to produce as many as security measurements normally incorporated in cars, truks and bus etc. General main rootcost of the two-wheeler accidents happen only when people community not remember to wearing a device helmet and during the driving time feels like sleep condition, alcohol disbursement, many of the drivers doesn't know heavy vehicles like Loory and buses approaching into very closer to their two wheelers, contravention of two wheelers in traffic rules and regulations. Let's overcome the above situations; our important objective is to develop an intelligent system device that can successfully facilitate in avoidance of every kind of problems. Suppose any of the above stated situations occurs, at that moment how system device identify and represents the commanders and community, and finally the stated situation be able to taken care of straight away without any further delay. A smart intelligent helmet system is a defending head covering used by rider for making bike riding safer than earlier. This is finished by incorporating sophisticated features like detecting the usage of helmet by the rider, connected Bluetooth module in helmet. In order to maintain the temperature inside the helmet device we need to include CPU fan module inside the device. RF based helmet prevents road accidents and identify whether people community is not using a component helmet or used. Main responsibility of the system is to detect accidents by vibration sensors, accelerometers and also with the help of modules global positioning system and global system for mobile commnicaiton module. A wireless communication device used to discover the accident area site location and likewise notifying the two-wheeler drived people's relatives and short message text information passed to the positioned hospitals.

• 스마트미디어저널
• /
• 제2권4호
• /
• pp.20-26
• /
• 2013

This paper presents an approach to Mongolian car plate recognition using artificial neural network. Our proposed method consists of two steps: detection and recognition. In detection step, we implement Flood fill algorithm. In recognition step we proceed to segment the plate for each Cyrillic character, and use an Artificial Neural Network (ANN) machine - learning algorithm to recognize the character. We have learned the theory of ANN and implemented it without using any library. A total of 150 vehicles images obtained from community entrance gates have been tested. The recognition algorithm shows an accuracy rate of 89.75%.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 추계학술발표대회
• /
• pp.380-382
• /
• 2022

Extracting informative representation of molecules using graph neural networks(GNNs) is crucial in AI-driven drug discovery. Recently, the graph research community has been trying to replicate the success of self supervised in natural language processing, with several successes claimed. However, we find the benefit brought by self-supervised learning on applying varitional auto-encoders can be potentially effective on molecular data.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권1호
• /
• pp.43-48
• /
• 2016

We propose plain fingerprint classification based on a core stochastic algorithm that effectively uses a core stochastic model, acquiring more fingerprint minutiae and direction, in order to increase matching performance. The proposed core stochastic algorithm uses core presence/absence and contains a ridge direction and distribution map. Simulations show that the fingerprint classification accuracy is improved by more than 14%, on average, compared to other algorithms.

• Smart Structures and Systems
• /
• 제15권3호
• /
• pp.577-592
• /
• 2015

Damage quantification is a major goal of the SHM community. Methodologies to introduce a quantity for actual condition of a structure into the assessment process are desired. The idea that the condition of a structure is represented in the character of its dynamic response is fully accepted by the SHM community. The VCLIFE methodology quantifies condition analyzing input from monitoring.

• 한국IT서비스학회지
• /
• 제12권2호
• /
• pp.153-170
• /
• 2013

As global competition of enterprises heats up recently, there is a growing the need to introduce business knowledge platform. Many enterprises work with other partners in a variety of situations and collaboration has emerged as new competitiveness of them. Collaboration improves the performance of members, and besides it has an important bearing on innovation, result, and increased productivity of enterprise. Lots of businesses, locally and abroad, extend the environment of collaboration and try to share business contents efficiently. In addition, they look into ways of invigorating collaboration by providing community tools. Corporations and Governments around the world are pushing smart work to respond effectively to this paradigm change. Smart work provides many types of collaboration and raises the productivity. Various infrastructures should be constructed for activating smart work. Most of all, core technology is to be developed. Virtual Cluster is the space of collaboration corresponding to change in business paradigm. In overseas policy of Virtual Cluster has been already enforced as an alternative to geographical cluster. The establishment and development of collaboration platform through Virtual Cluster can contribute to business competitiveness by smart work.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.945-951
• /
• 2022

The major objective of this research is to evaluate performance of improved intersections for response time to emergency vehicle preemption. Smart technologies have been introduced to civil infrastructure systems for resilient communities. The technologies need to evaluate their effectiveness and feasibility to confirm their introduction. This research focuses on the performance of emergency vehicle preemption, represented by response time, when smart intersections are introduced in a community. The response time is determined by not only intersections but also a number of factors such as traffic, distance, road conditions, and incident types. However, the evaluation of emergency response has often ignored factors related to emergency vehicle routes. In this respect, this research synthetically analyzes geospatial and incident data using each route of emergency vehicle and conducts before-and-after evaluations. The changes in performance are analyzed by the impact of smart intersections on response time through Bayesian regression models. The result provides measures of the project's performance. This study will contribute to the body of knowledge on modeling the impacts of technology application and integrating heterogeneous data sets. It will provide a way to confirm and prove the effectiveness of introducing smart technologies to our communities.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2007년도 학술대회 1부
• /
• pp.796-801
• /
• 2007

유비쿼터스 지능 공간(Ubiquitous Smart Space)에서 동적으로 발생하는 다양한 문제를 협업을 통하여 해결할 수 있는 방법론으로 제안된 커뮤니티 컴퓨팅 (Community Computing) 모델을 기반으로 하는 개발 도구(Community Computing Development Tool Kit : CDTK)를 사용하면 특정 문제를 해결할 수 있는 커뮤니티 컴퓨팅 어플리케이션이 생성된다. 이 커뮤니티 컴퓨팅 어플리케이션이 실제로 유비쿼터스 지능 공간에 존재하는 uT-entity에 이식되어 동작하기 위해서 uT-entity의 종류에 상관없이 커뮤니티 컴퓨팅 어플리케이션이 배포될 수 있는 환경을 필요로 한다. 본 연구에서는 CDTK를 이용하여 생성된 커뮤니티 컴퓨팅 어플리케이션이 uT-entity에 배포(Deployment)되어 각 uT-entity가 커뮤니티의 멤버로 참여하여 멤버간의 협업을 통해 목적(Goal)을 달성할 수 있도록 지원하는 어플리케이션 프레임워크인 멤버 프레임워크(Member Framework)를 제안하고, 이를 이클립스 리치클라이언트 플랫폼(Rich Client Platform) 기반의 플러그인(Plug-In)으로 설계하고자 한다.

• 한국멀티미디어학회논문지
• /
• 제18권2호
• /
• pp.97-105
• /
• 2015

When people go to travel, sometimes one writes many articles about the destination. Existing travel information services such as Blog, Internet Cafe, and SNS are difficult to provide realistic information since the provided information may not be a place directly on the road. This paper presents a travel information system including recommended courses, theme courses, and travel map. In addition, the proposed system can provide the functions of writing, reading, and deleting a message note that stores the travel information based on the augmented reality if a defined marker among the community members is recognized in a smartphone App. Therefore, this paper can present an implementation method for new community system using augmented reality and image processing as well as providing the conventional travel information services, and allows the user to take advantage of the realistic and accurate information.

• International journal of advanced smart convergence
• /
• 제11권4호
• /
• pp.216-226
• /
• 2022

In this study, we selected and trained 9 people in the diaphragm training group and 9 people in the power-breath training group among elderly people aged 65 or older living in the community, and investigated the effect of combined training using respiratory equipment on lung function, balance, and life satisfaction. We conducted the elderly to do combined exercises, twice a week for a total of 6 weeks, that include the breathing training by diaphragm, the breathing training using Power-breath equipment, and the training using a theraband. We evaluated the changes in the lung function, the balance, and the life satisfaction before and after the intervention for our study subjects.As a result of our measurement, lung function, balance, and life satisfaction showed significant changes in the experimental group that performed the combined training using Power-breath equipment. As a result of the study, we confirmed that the elderly in the community had a positive effect on the life satisfaction by improving lung function and balance ability after conducting a combined training using respiratory equipment.