This study examines and proposes standardization approaches to address the heterogeneous issues of metadata in drone imagery within the agricultural sector. Image metadata comes in various formats depending on different camera manufacturers, with most utilizing EXIF and XMP. The metadata of cameras used in fixed-wing and rotary-wing platforms, along with the metadata requirements in image alignment software, were analyzed for sensors like DJI XT2, MicaSense RedEdge-M, and Sentera Double4K. In the agricultural domain, multispectral imagery is crucial for vegetation analysis, making the provision of such imagery essential. Based on Pix4D SW, a comparative analysis of metadata attributes was performed, and necessary elements were compiled and presented as a proposed standardization (draft) in the form of tag information.

Nowadays, artificial intelligence model approaches such as machine and deep learning have been widely used to predict variations of water quality in various freshwater bodies. In particular, many researchers have tried to predict the occurrence of cyanobacterial blooms in inland water, which pose a threat to human health and aquatic ecosystems. Therefore, the objective of this study were to: 1) review studies on the application of machine learning models for predicting the occurrence of cyanobacterial blooms and its metabolites and 2) prospect for future study on the prediction of cyanobacteria by machine learning models including deep learning. In this study, a systematic literature search and review were conducted using SCOPUS, which is Elsevier’s abstract and citation database. The key results showed that deep learning models were usually used to predict cyanobacterial cells, while machine learning models focused on predicting cyanobacterial metabolites such as concentrations of microcystin, geosmin, and 2-methylisoborneol (2-MIB) in reservoirs. There was a distinct difference in the use of input variables to predict cyanobacterial cells and metabolites. The application of deep learning models through the construction of big data may be encouraged to build accurate models to predict cyanobacterial metabolites.

At a time when the demand for drones is increasing, a plan to utilize drone images was sought for efficient promotion of cadastral resurvey. To achieve the purpose of this study, the technical and legal status of drone images was reviewed, and through this, the possibility of using it for cadastral resurvey was primarily reviewed. subsequently, an experiment was conducted targeting the project district to examine whether drone images were applied to boundary extraction, which is the primary process of cadastral resurvey. As a result of the experiment, it was found that boundary extraction from images is possible. However, in some cases, it is impossible due to field conditions or image quality. Therefore, it is necessary first to apply cases where boundary extraction is possible to cadastral resurvey and seek solutions for some impossible cases. In particular, the image quality problem may have problems with the current technology, but it will also have problems with the existing drone equipment. So, standard for drone calibration should also be established. Finally, the cadastral resurvey surveying procedure using drones was also presented.

In this study, changes in the microbial ecosystem of the Yeongheungdo island coastal waters were investigated for five years to collect basic data. To evaluate the influence of distance from the coast on the microbial ecosystem, four sites, coastal Site (S1) and 0.75, 1.5, and 3 km away from the coast, were set up and the changes in physicochemical and biological factors were monitored. The results showed seasonal changes in water temperature, dissolved oxygen, salinity, and pH but with no significant differences between sites. For nutrients, the concentration of dissolved inorganic nitrogen increased from 6.4 μM in April-June to 16.4 μM in July-November, while that of phosphorus and silicon phosphate increased from 0.4 μM and 2.5 μM in April-June to 1.1 μM and 12.0 μM in July-November, respectively. Notably, phosphorus phosphate concentrations were lower in 2014-2015 (up to 0.2 μM) compared to 2016-2018 (up to 2.2 μM), indicating phosphorus limitation during this period. However, there were no differences in nutrients with distance from the coast, indicating that there was no effect of distance on nutrients. Phytoplankton (average 511 cells mL-1) showed relatively high biomass (up to 3,370 cells mL-1) in 2014-2015 when phosphorus phosphate was limited. Notably, at that time, the concentration of dissolved organic carbon was not high, with concentrations ranging from 1.1-2.3 mg L-1. However, no significant differences in biological factors were observed between the sites. Although this study revealed that there was no disturbance of the ecosystem, further research and more basic data on the microecosystem are necessary to understand the ecosystem of the Incheon.

On pig farms, the highest mortality rate is observed among nursing piglets. To reduce this mortality rate, farmers need to carefully observe the piglets to prevent accidents such as being crushed and to maintain a proper body temperature. However, observing a large number of pigs individually can be challenging for farmers. Therefore, our aim was to detect the behavior of piglets and sows in real-time using deep learning models, such as YOLOv4-CSP and YOLOv7-E6E, that allow for real-time object detection. YOLOv4-CSP reduces computational cost by partitioning feature maps and utilizing Cross-stage Hierarchy to remove redundant gradient calculation. YOLOv7-E6E analyzes and controls gradient paths such that the weights of each layer learn diverse features. We detected standing, sitting, and lying behaviors in sows and lactating and starving behaviors in piglets, which indicate nursing behavior and movement to colder areas away from the group. We optimized the model parameters for the best object detection and improved reliability by acquiring data through experts. We conducted object detection for the five different behaviors. The YOLOv4-CSP model achieved an accuracy of 0.63 and mAP of 0.662, whereas the YOLOv7-E6E model showed an accuracy of 0.65 and mAP of 0.637. Therefore, based on mAP, which includes both class and localization performance, YOLOv4-CSP showed the superior performance. Such research is anticipated to be effectively utilized for the behavioral analysis of fattening pigs and in preventing piglet crushing in the future.

We aimed to investigate the effect of environmental enrichment via toys on the behaviour and performance of weanling pigs. A total of 300 pigs (LYD) were housed in different pens with ten pigs per replicate and ten pigs per head divided into 3 groups. Group 1 was called “CON” and received no toys, group 2 was TOY-2, and pigs in this group had access to toys in the first 2 weeks, and lastly, pigs in TOY-4 were given toys in the fourth week. The pigs had access to feed and water ad-libitum. The individual pig behaviours in each group was recorded on days 14 and 28 (d 14 and 28) with a video camera for accuracy. The results showed higher (p<0.05) overall ADG in TOY-4 compared with CON, while the overall ADFI was higher (p<0.05) in TOY-supplemented groups compared to CON. Diarrhea incidence and fecal score were lower on D 14 in TOY-supplemented groups compared with CON. Behavioural features such as ear biting and fighting were lower (p<0.05) in TOY-supplemented groups compared with CON on D 14. Tail biting was lower (p<0.05) in TOY-2 compared with CON at D 14. Conversely, at D 28, tail biting was lower (p<0.05) in TOY-4 compared with CON. The ADG improved due to the toy supplied to reduce undesirable social behaviours. We concluded that the environmental enrichment of pens with toys can help to improve the welfare in weaning pigs, leading to a greater survivability and more production thereby improving farmer incomes.

본 연구의 목적은 회복탄력성이 정보처리에 미치는 영향을 연구하기 위함이다. 본 연구에서는 남자 고등학생 39 명을 무작위로 추출한 다음 회복탄력성 척도(KRQ-53) 점수에 따라 상위집단(13명), 중간집단(13명), 하위집단(13명) 에 무선 할당하였다. 실험 과제는 단순반응시간, 선택반응시간-1, 그리고 선택반응시간-2 였다. 피험자가 과제를 실시 하는 동안 Fp1, Fp2, F3, F4, Fz, Cz, Pz, C3 영역에서 사상관련전위(ERP)를 측정하였다. 본 연구의 결과, 첫째 세타 파의 경우 중간집단이 상위 및 하위 집단보다 높게 나타났다. 둘째, 알파를 분석한 결과, 상위집단이 중간 및 하위집 단보다 알파파가 높게 나타났다. 셋째, 미드-베타파를 분석한 결과 하위 및 중간집단의 미드 베타파가 상위집단보다 높은 것으로 나타났다. 넷째, P300 진폭은 선택반응시간-1에서 회복탄력성 중간집단이 상위 및 하위집단보다 높게 나타났다. 본 연구의 결과는 회복탄력성 수준에 따라 정보처리가 다르게 나타난다는 것을 보여준다.

본 연구는 습지의 중요성에 대한 연구이며, 경남 합천군 대양면 소재의 정양늪생태공원을 연구하였다. 먼저 기초조사를 바탕으로 시설물, 이용프로그램, 접근성 등을 조사하고 설문조사를 실시하였다. 설문 내용은 일반적인사항, 생태이용프로그램 조사, 이용행태조사, 이용만족도 조사, 도입 시설 및 프로그 램 만족도를 조사하였다. 그 결과 상당수의 설문에서 성별, 연령별 차이가 다소 나타났으며, 그에 대한 성별, 연령별 각각의 맞춤 서비스가 필요한 것으로 파악이 되었다. 연구를 종합적으로 살펴보면 타 생태 공원과의 차이보다 전체적인 시설물과 이용프로그램의 부제와 정양늪생태공원만의 특성 있는 역사적 이고 지역적인 시설물과 이용프로그램을 개발 육성하고 성별, 연령별 각각의 맞춤 서비스를 실시하는 것이 시급하다. 먼저 정양늪생태공원의 이용프로그램의 다양화가 필요하며, 본 연구에서 나타났듯이 성별, 연령별 그리고 지역특성적 이용프로그램의 개발이 시급하다. 다음으로는 이용공간의 다원화인 데 가장 시급한 것이 통합적 공간의 확충과 지역특성적 공간의 확충이 필요하다. 마지막으로 정양늪생 태공원의 이용시설의 관리 및 정비 인원을 확충하는 것이다. 이상의 연구결과로 유사한 습지에서도 기 초자료로 활용될 것으로 판단된다.

As the importance of artificial intelligence grows rapidly and emerges as a leader in technology, it is becoming an important variable in the next-generation industrial system along with the robot industry. In this study, a safety system was developed using deep learning technology to provide worker safety in a robot workplace environment. The implemented safety system has multiple cameras installed with various viewing directions to avoid blind spots caused by interference. Workers in various scenario situations were detected, and appropriate robot response scenarios were implemented according to the worker's risk level through IO communication. For human detection, the YOLO algorithm, which is widely used in object detection, was used, and a separate robot class was added and learned to compensate for the problem of misrecognizing the robot as a human. The performance of the implemented system was evaluated by operator detection performance by applying various operator scenarios, and it was confirmed that the safety system operated stably.

본 연구는 인체 및 온혈 동물의 기회감염 병원세균으로 알려진 Pseudomonas oryzihabitans에 의한 양파 구에 발생한 중심 흑화병의 첫 보고이다. 본 연구의 목적은 양파 구 흑화병을 일으키는 원인 병원체를 분리 및 동정하고 미생물학적 특성을 조사하는데 있다. 2021년 국내 양파 구에서 소비자 혐오감을 유발할 수 있는 세균 흑화병이 관찰되었다. 흑갈색 색소가 침착된 조직과 흑색 색소 과육 조직에서 그람음성, 비포자형성, 막대형 pseudomonad들이 분리되었다. 병원성 검정을 통해 형성된 인공 감염후 발생한 증상은 자연 감염과 같았고 멸균 증류수를 처리한 음성 대조구에서는 흑화병이 발견되지 않았다. 병원성 검정, API (analytical profile index) 시험, MALDI-TOF MS (Whole-cell matrix-assisted laser desorption/ionization time-of-flight mass spectrometry), 16S rRNA 유전자 영역 염기서열분석 및 유전적 유연관계분석을 통해 원인 병원체를 Pseudomonas oryzihabitans로 동정하였다. 대규모 포장 또는 수확후병으로 인한 양파 피해사례가 보고된 적은 없지만, 본 연구에서 얻은 결과는 P. oryzihabitans가 잠재적으로 양파의 글로벌 생산 및 운송과 식품 안전을 위협할 수 있음을 시사한다. 또한 인체 기회감염 병원체이기 때문에 양파로부터 언제든지 인체로 감염될 수 있는 위험성을 갖고 있다고 볼 수 있다.