• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.9-13
• /
• 2023

In this study, we explored the potential of integrating interactive AI callbot technology into the medical consultation domain as part of a broader service development initiative. Aimed at enhancing patient satisfaction, the AI callbot was designed to efficiently address queries from hospitals' primary users, especially the elderly and those using phone services. By incorporating an AI-driven callbot into the hospital's customer service center, routine tasks such as appointment modifications and cancellations were efficiently managed by the AI Callbot Agent. On the other hand, tasks requiring more detailed attention or specialization were addressed by Human Agents, ensuring a balanced and collaborative approach. The deep learning model for voice recognition for this study was based on the Transformer model and fine-tuned to fit the medical field using a pre-trained model. Existing recording files were converted into learning data to perform SSL(self-supervised learning) Model was implemented. The ANN (Artificial neural network) neural network model was used to analyze voice signals and interpret them as text, and after actual application, the intent was enriched through reinforcement learning to continuously improve accuracy. In the case of TTS(Text To Speech), the Transformer model was applied to Text Analysis, Acoustic model, and Vocoder, and Google's Natural Language API was applied to recognize intent. As the research progresses, there are challenges to solve, such as interconnection issues between various EMR providers, problems with doctor's time slots, problems with two or more hospital appointments, and problems with patient use. However, there are specialized problems that are easy to make reservations. Implementation of the callbot service in hospitals appears to be applicable immediately.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.8 s.350
• /
• pp.35-46
• /
• 2006

When an RFID reader attempts to read the tags, interference might occur if the neighboring readers also attempt to communicate with the same tag at the same time or the neighboring readers use the same frequency simultaneously. These interferences cause the RFID reader collision. When the RFID reader collision occurs, either the command from the reader cannot be transmitted to the tags or the response of the tags cannot receive to the reader correctly, Therefore, the international standard for RFID and some papers proposed the methods to reduce the reader collision. Among those, Colorwave and Enhanced Colorwave is the reader anti-collision algorithm using the frame slotted ALOHA based a TDM(Time Division Multiplex) and are able to reduce the reader collision because theses change the frame size according to a collision probability. However, these can generate the reader collisions or interrupt the tag reading of other readers because the reader that collides with another reader randomly chooses a new slot in the frame. In this paper, we propose a new RFID reader anti-collision algorithm that each reader monitors the slots in the frame and chooses the slot having the minimum occupation probability when the reader collision occurs. Then we analyze the performance of the proposed algorithm using simulation tool.

• Journal of Broadcast Engineering
• /
• v.15 no.2
• /
• pp.224-231
• /
• 2010

In this paper, we analyze the performance of the cooperative relay communication system which uses orthogonal frequency division multiplexing(OFDM) with hierarchical subcarrier modulation. In the cooperative relay communication system, data transmission is accomplished in two time slots. In the first time slot, the source broadcasts the signal to the relay and to the destination. The relay demodulates the received signal, remodulates and forwards it to the destination in the second time slot. The source uses hierarchical modulation for subcarriers to deal with the signal-to-noise power ratio (SNR) difference in the source-relay and source-destination links. The bit error rate (BER) of the relay transmission system with hierarchical modulation depends on the hierarchical modulation parameter. First, we derive the relationship between BER and the parameter, and find the optimal parameter giving the minimum BER through computer simulations. Then, we analyze the performance of the proposed cooperative relay communication system according to the relay location. From this results, we find optimal relay location to maximize the BER performance.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.6 no.2
• /
• pp.66-90
• /
• 2007

The purpose of this study is to measure and analyze primary causes of indoor air pollution, including carbon dioxide, minute dust, and total volatile organic compounds, for each room before the beginning of a class through the time of discharge after the end of the class in general classrooms, computer rooms, and science rooms of three newly-established schools that opened in 2006, examine properties of indoor air environment in each room by educational activities at school, and determine effective management schemes; the results of this study can be summarized as follows: 1) As for implications for each item found in the mean for each place, since minute dust (PM10) was more likely to occur in time slots full of students' activities, such as a traveling class and a recess, than in the middle of a class and could be expected fully, it is necessary to make a scheme for cleaning in order to reduce minute dust within a room, for example, by usually using a vacuum cleaner indoors. 2) While carbon dioxide was expected to vary with the differences in the amount of breath between higher-graders and lower-graders in a general classroom but showed insignificant difference by grades, showing differences in pollution by four times at a maximum according to the opening of a window as expected, it is necessary to implement artificial or natural ventilation and take a positive measure, for example, by presenting a concrete ventilation scheme, in order to improve indoor air pollution at a room practice. 3) Total volatile organic compounds were found to exceed the standard by more than twice in general classrooms, science rooms, and computer rooms of the schools because of building materials, furnitures including desks and chairs, panels and boards for environment beautification, and items which could be detected even from students' clothes; while a field directly-reading tool was used, obtaining high reliability for the results, it is necessary to apply an analytical method based on process test separately for actual correct measurement if a significantly great amount of total volatile organic compounds appear as compared with other schools due to measuring expenses and consecutive measurements. 4) Since formaldehyde (HCHO) was generally found to exceed the standard in general classrooms, science rooms, and computer rooms, it is necessary to establish and operate a ventilator during a class in a computer room which requires airtightness and a science room in which an organic compound should be used for a class.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.5
• /
• pp.555-564
• /
• 2016

This paper proposes a time slot allocation scheme for military patrol environments. This proposal comes from analysis of traffic properties in a military patrol environment. In the near future, robots are expected to explore enemy grounds and measure threat, taking the place of human patrol. In order to control such robots, control messages must be extremely accurate. One mistake from the control center could cause a tragedy. Thus, high reliability must be guaranteed. Another goal is to maintain a continual flow of multimedia data sent from patrol robots. That is, QoS (Quality of Service) must be guaranteed. In order to transmit data while fulfilling both attributes, the per-path based centralized TDMA slot allocation scheme is recommended. The control center allocates slots to robots allowing synchronization among robots. Slot allocation collisions can also be avoided. The proposed scheme was verified through the ns-3 simulator. The scheme showed a higher packet delivery ratio than the algorithm in comparison. It also performed with shorter delay time in the downlink traffic transmission scenario than the algorithm in comparison.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.11
• /
• pp.846-850
• /
• 2009

Recently, wireless sensor networks have found their way into a wide variety of applications and systems with vastly varying requirements and characteristics such as environmental monitoring, smart spaces, medical applications, and precision agriculture. The sensor nodes are battery powered. Therefore, the energy is the most precious resource of a wireless sensor network since periodically replacing the battery of the nodes in large scale deployments is infeasible. Energy efficient mechanisms for gathering sensor readings are indispensable to prolong the lifetime of a sensor network as long as possible. There are two energy-efficient approaches to prolong the network lifetime in sensor networks. One is the compression scheme to reduce the size of sensor readings. When the communication conflict is occurred between two sensor nodes, the sender must try to retransmit its reading. The other is the MAC protocol to prevent the communication conflict. In this paper, we propose a novel approaches to reduce the size of the sensor readings in the MAC layer. The proposed scheme compresses sensor readings by allocating the time slots of the TDMA schedule to them dynamically. We also present a mathematical model to predict latency from collecting the sensor readings as the compression ratio is changed. In the simulation result, our proposed scheme reduces the communication cost by about 52% over the existing scheme.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.9A
• /
• pp.702-709
• /
• 2003

In this paper, we propose an efficient and QoS-aware MAC scheduling algorithm for Bluetooth, which considers both throughput and delay performance of each Master-Slave pair in scheduling decisions, and thus, attempts to maximize overall performance. The proposed algorithm, MTDPP (Modified Throughput-Delay Priority Policy), makes up for the drawbacks of T-D PP (Throughput-Delay Priority Policy) proposed in [6] and improves the performance. Since Bluetooth employs a master-driven TDD based scheduling algorithm, which is basically operated with the Round Robin policy, many slots may be wasted by POLL or NULL packets when there is no data waiting for transmission in queues. To overcome this link wastage problem, several algorithms have been proposed. Among them, queue state-based priority policy and low power mode-based algorithm can perform with high throughput and reasonable fairness. However, their performances may depend on traffic characteristics, i.e., static or dynamic, and they require additional computational and signaling overheads. In order to tackle such problems, we propose a new scheduling algorithm. Performance of our proposed algorithm is evaluated with respect to throughput and delay. Simulation results show that overall performances can be improved by selecting suitable parameters of our algorithm.

• The Journal of the Korea Contents Association
• /
• v.12 no.12
• /
• pp.71-79
• /
• 2012

In Japan, the number of late night animations has increased from the 2000s. In 2010, it exceeded the number of other Japanese animations playing between 6:00 to 23:00 (pre-late night). People watching these late night animations were mostly adolescents or older. Late night animations involve various niche themes, however, the ranges of the main characters' actions of these stories were narrower and more limited compared to the pre-late night animations. The causes for these differences in the scales of the settings were found by comparing the late night and pre-late night animations. The most popular animations from these two time slots were used in the analysis. Firstly, the main characters' ways of approaching their goals were analyzed. Secondly, the settings and directions that the main characters used were analyzed. Lastly, the main characters' degree of interactions with other people was analyzed. As a result of the analysis, the main characters' goals from the late night animations were often found to be commonplace and they tended to achieve their goals by very realistic means. In addition to that, the stories of these main characters revolved around small and familiar communities. Thus, their connections with people were comparatively smaller than those of pre-late night animations and were based upon shared interests. In other words, the differences in the scales of the settings between the two types of animations resulted from the stories of the late night animations revolving mainly around reality, communities, and relationships within the communities.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.1A
• /
• pp.96-103
• /
• 2000

The voice traffic is one of the most important real-time objects in WATM(Wireless Asynchronous Transfer Mode) networks. In this paper, we propose a new MAC(Medium Access'Control) protocol for the efficienttransmission of voice traffic over WATM networks in the multimedia environment and compare the performanceto existing similar protocols. The new protocol separates the reservation slot period for voice and that for data toguarantee some level of QoS(Quality of Service) in voice traffic. This is denoted by a slot assignment functiondepending on the frame size. According to the characteristics of voice traffic which is repeatedly in silent states,the protocol allocates voice reservation request slots dynamically with respect to the number of silent(off state)voice sources and also sends the first block of talkspurt restarted after silent period with a reservation requestslot to reduce the access delay.The simulation results show that the proposed protocol has better performance than Slotted Aloha in bandwidthefficiency, and can serve a certain level of QoS by the given slot assignment function even when the number ofvoice terminals varies dynamically. This means we can observe that the new MAC protocol is much better thanthe NC-PRMA(None Collision-Packet Reservation Multiple Access) protocol.

• Journal of Internet Computing and Services
• /
• v.14 no.5
• /
• pp.1-10
• /
• 2013

RFID(Radio Frequency Identification) system is non-contact identification technology. A basic RFID system consists of a reader, and a set of tags. RFID tags can be divided into active and passive tags. Active tags with power source allows their own operation execution and passive tags are small and low-cost. So passive tags are more suitable for distribution industry than active tags. A reader processes the information receiving from tags. RFID system achieves a fast identification of multiple tags using radio frequency. RFID systems has been applied into a variety of fields such as distribution, logistics, transportation, inventory management, access control, finance and etc. To encourage the introduction of RFID systems, several problems (price, size, power consumption, security) should be resolved. In this paper, we proposed an algorithm to significantly alleviate the collision problem caused by simultaneous responses of multiple tags. In the RFID systems, in anti-collision schemes, there are three methods: probabilistic, deterministic, and hybrid. In this paper, we introduce ALOHA-based protocol as a probabilistic method, and Tree-based protocol as a deterministic one. In Aloha-based protocols, time is divided into multiple slots. Tags randomly select their own IDs and transmit it. But Aloha-based protocol cannot guarantee that all tags are identified because they are probabilistic methods. In contrast, Tree-based protocols guarantee that a reader identifies all tags within the transmission range of the reader. In Tree-based protocols, a reader sends a query, and tags respond it with their own IDs. When a reader sends a query and two or more tags respond, a collision occurs. Then the reader makes and sends a new query. Frequent collisions make the identification performance degrade. Therefore, to identify tags quickly, it is necessary to reduce collisions efficiently. Each RFID tag has an ID of 96bit EPC(Electronic Product Code). The tags in a company or manufacturer have similar tag IDs with the same prefix. Unnecessary collisions occur while identifying multiple tags using Query Tree protocol. It results in growth of query-responses and idle time, which the identification time significantly increases. To solve this problem, Collision Tree protocol and M-ary Query Tree protocol have been proposed. However, in Collision Tree protocol and Query Tree protocol, only one bit is identified during one query-response. And, when similar tag IDs exist, M-ary Query Tree Protocol generates unnecessary query-responses. In this paper, we propose Adaptive M-ary Query Tree protocol that improves the identification performance using m-bit recognition, collision information of tag IDs, and prediction technique. We compare our proposed scheme with other Tree-based protocols under the same conditions. We show that our proposed scheme outperforms others in terms of identification time and identification efficiency.