• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.5A
• /
• pp.358-366
• /
• 2012

LED-ID (Light Emitting Diode - Identification) is one of the key technologies for identification, data transmission, and illumination simultaneously. This is the new paradigm in the identification technology environment. There are many issues are still now challenging to achieve high performance in LED-ID system. Collision issue is one of them. Actually this is the most significant issue in all identification system. LED-ID system also suffers from collision problem. In our system, collision occurs when two or more readers transmit data to tag at the same time or vice versa. There are many anti-collision protocols to resolve this problem; such as: Slotted ALOHA, Basic Frame Slotted ALOHA, Query Tree, Tree Splitting, and Q-Algorithm etc. In this paper, we propose modified Q-Algorithm to resolve collision at tag. The proposed protocol is based on Q-Algorithm and used the information of arrived readers to a tag from neighbor. The information includes transmitting slot number of readers and the number of readers that can be arrived in next slot. Our proposed protocol can reduce the numbers of collision slot and the successful time to identify all readers. In this paper our simulation and theoretical results are presented.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.435-446
• /
• 2020

With the ability to learn rules from training data, the machine learning model can classify unknown objects. At the same time, the dimension of hyperspectral data is usually large, which may cause an over-fitting problem. In this research, an identification methodology of tea diseases was proposed based on spectral reflectance and machine learning, including the feature selector based on the decision tree and the tea disease recognizer based on random forest. The proposed identification methodology was evaluated through experiments. The experimental results showed that the recall rate and the F1 score were significantly improved by the proposed methodology in the identification accuracy of tea disease, with average values of 15%, 7%, and 11%, respectively. Therefore, the proposed identification methodology could make relatively better feature selection and learn from high dimensional data so as to achieve the non-destructive and efficient identification of different tea diseases. This research provides a new idea for the feature selection of high dimensional data and the non-destructive identification of crop diseases.

• The KIPS Transactions:PartC
• /
• v.16C no.2
• /
• pp.267-274
• /
• 2009

For the implementation of a RFID system, an anti-collision algorithm is required to identify multiple tags within the range of a RFID Reader. There are two methods of anti-collision algorithms for the identification of multiple tags, conclusive algorithms based on tree and stochastic algorithms based on slotted ALOHA. In this paper, we propose a Dynamic Framed Slotted ALOHA-Slot Congestion(DFSA-SC) Algorithm. The proposed algorithm improves the efficiency of collision resolution. The performance of the proposed DFSA-SC algorithm is showed by simulation. The identification time of the proposed algorithm is shorter than that of the existing DFSA algorithm. Furthermore, when the bit duplication of the tagID is higher, the proposed algorithm is more efficient than Query Tree algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.3
• /
• pp.459-470
• /
• 2013

The discovery of nearest neighbors, without training in advance, has many applications, such as the formation of mosaic images, image matching, image retrieval and image stitching. When the quantity of data is huge and the number of dimensions is high, the efficient identification of a nearest neighbor (NN) is very important. This study proposes a variation of the KD-tree - the arbitrary KD-tree (KDA) - which is constructed without the need to evaluate variances. Multiple KDAs can be constructed efficiently and possess independent tree structures, when the amount of data is large. Upon testing, using extended synthetic databases and real-world SIFT data, this study concludes that the KDA method increases computational efficiency and produces satisfactory accuracy, when solving NN problems.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.14 no.6
• /
• pp.667-681
• /
• 2012

In general, risk management consists of a series of processes or steps including risk identification, risk analysis, risk evaluation, risk mitigation measures, and risk re-evaluation. In this paper, potential risk factors that occur in shield TBM tunnels were investigated based on many previous case studies and questionaries to tunnel experts. The risk factors were classified as geological, design or construction management features. Fault Tree was set up by dividing all feasible risks into four groups that associated with: cutter; machine confinement; mucking (driving) and segments. From the Fault Tree Analysis (FTA), 12 risk items were identified and the probability of failure of each chosen risk item was obtained.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.3 no.4
• /
• pp.212-220
• /
• 2022

DNA markers have been studied and used intensively to identify plant species based on molecular approaches. The genus Medicago belongs to the family Fabaceae and contains 87 species distributed from the Mediterranean to central Asia. Five species of Medicago are known to be distributed in South Korea; however, their morphological characteristics alone cannot distinguish the species. In this study, we analyzed the phylogenetic relationships using collected five species of Medicago from South Korea and 44 taxa nucleotide information from NCBI. The constructed phylogenetic tree using gibberellin 3-oxidase 1 and tRNA^Lys (UUU) to maturase K gene sequences showed the monophyly of the genus Medicago, with five species each forming a single clade. These results suggest that there are five species of Medicago distributed in South Korea. In addition, we designed polymerase chain reaction primers for species-specific detection of Medicago by comparing the plastid sequences. The accuracy of the designed primer pairs was confirmed for each Medicago species. The findings of this study provide efficient and novel species identification methods for Medicago, which will assist in the identification of wild plants for the management of alien species and living modified organisms.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.8 no.5
• /
• pp.285-293
• /
• 2013

The procedure of the arbitration which is the tag collision is essential because the multiple tags response simultaneously in the same frequency to the request of the Reader. This procedure is known as Anti-collision and it is a key technology in the RFID system. In this paper, we propose the Bit Pattern Prediction Algorithm(BPPA) for the efficient identification of the multiple tags. The BPPA is based on the tree algorithm using the time slot and identify the tag quickly and efficiently using accurate bit pattern prediction method. Through mathematical performance analysis, We proved that the BPPA is an O(n) algorithm by analyzing the worst-case time complexity and the BPPA's performance is improved compared to existing algorithms. Through MATLAB simulation experiments, we verified that the BPPA require the average 1.2 times query per one tag identification and the BPPA ensure stable performance regardless of the number of the tags.

• Korean Journal of Acupuncture
• /
• v.33 no.3
• /
• pp.102-113
• /
• 2016

Objectives : This study is aimed at developing and discussing the prediction model of blood stasis pattern of traditional Korean medicine(TKM) using machine learning algorithms: multiple logistic regression and decision tree model. Methods : First, we reviewed the blood stasis(BS) questionnaires of Korean, Chinese, and Japanese version to make a integrated BS questionnaire of patient-reported outcomes. Through a human subject research, patients-reported BS symptoms data were acquired. Next, experts decisions of 5 Korean medicine doctor were also acquired, and supervised learning models were developed using multiple logistic regression and decision tree. Results : Integrated BS questionnaire with 24 items was developed. Multiple logistic regression models with accuracy of 0.92(male) and 0.95(female) validated by 10-folds cross-validation were constructed. By decision tree modeling methods, male model with 8 decision node and female model with 6 decision node were made. In the both models, symptoms of 'recent physical trauma', 'chest pain', 'numbness', and 'menstrual disorder(female only)' were considered as important factors. Conclusions : Because machine learning, especially supervised learning, can reveal and suggest important or essential factors among the very various symptoms making up a pattern identification, it can be a very useful tool in researching diagnostics of TKM. With a proper patient-reported outcomes or well-structured database, it can also be applied to a pre-screening solutions of healthcare system in Mibyoung stage.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.8
• /
• pp.1619-1624
• /
• 2012

If multiple Tags in the RFID System transmit their IDs to the Reader at the same time, tag identification time is delayed due to collisions. Therefore, to reduce the reader's identification time, an efficient anti-collision technology is needed. In this paper, we propose a hybrid anti-collision method based on the QT and DFSA. Then, the performances of proposed method are compared with the existing method through extensive simulations.

• Journal of Information Processing Systems
• /
• v.11 no.1
• /
• pp.95-103
• /
• 2015

This paper presents a memory efficient tree based anti-collision protocol to identify memoryless RFID (Radio Frequency Identification) tags that may be attached to products. The proposed deterministic scheme utilizes two bit arrays instead of stack or queue and requires only ${\Theta}(n)$ space, which is better than the earlier schemes that use at least $O(n^2)$ space, where n is the length of a tag ID in a bit. Also, the size n of each bit array is independent of the number of tags to identify. Our simulation results show that our bit array scheme consumes much less memory space than the earlier schemes utilizing queue or stack.