• 제목/요약/키워드: Non-support system form

검색결과 45건 처리시간 0.023초

머신러닝기반 범죄발생 위험지역 예측 (Predicting Crime Risky Area Using Machine Learning)

  • 허선영;김주영;문태헌
    • 한국지리정보학회지
    • /
    • 제21권4호
    • /
    • pp.64-80
    • /
    • 2018
  • 우리나라의 시민들은 범죄에 대한 일반적인 사항만을 알 수 있을 뿐, 자신이 범죄위험에 얼마나 노출되어 있는지를 파악하기 어렵다. 경찰의 입장에서도 범죄발생 지역을 예측할 수 있다면 경찰력이 부족한 상황에서 효율성 있게 범죄에 대처 가능할 것이지만 아직 우리나라에서는 예측시스템이 없고, 관련 연구도 매우 부족한 실정이다. 이에 본 연구에서는 범죄발생 위험지역 예측 자동화 시스템 개발의 첫 번째 단계로 빅데이터로 구축 가능한 범죄정보와 도시지역 자료를 바탕으로 머신러닝 방식을 통해 한국형 범죄발생 위험지역 예측 모형을 개발하고자 한다. 또한 시나리오를 가정하여 범죄발생 확률을 지도로 시각화함으로써 사용자의 이해도를 높이도록 하였다. 선행 연구 및 사례에서 범죄발생에 영향을 미치는 요인 중 빅데이터로 구축 가능한 범죄정보, 날씨정보(기온, 강수량, 풍속, 습도, 일조, 일사, 적설, 전운량), 지역정보(평균 건폐율, 평균 용적율, 평균 높이, 총 건축물수, 평균 공시지가, 평균 주거용도면적, 평균 지상층수)를 머신러닝에 활용할 수 있도록 데이터를 사전 처리하였다. 머신러닝 알고리즘으로서 지도학습 모형 중 다양한 분야에서 활용되며 정확도가 높다고 알려진 의사결정나무모형, 랜덤포레스트모형, Support Vector Machine(SVM)모형을 활용하여 범죄 예측 모형을 구축하고 비교 분석하였다. 그 결과 평균 제곱근 오차(Root Mean Square Error, RMSE)가 낮아 예측력이 높은 의사결정나무모형을 최적모형으로 선정하였다. 이를 바탕으로 가장 빈번하게 발생하는 절도와 폭력범죄를 대상으로 시나리오를 작성하여 범죄 발생 위험지역을 예측한 결과, 사례도시 J시는 위험지역이 3가지 패턴으로 발생하는 것으로 나타났으며, 각각 발생확률을 3 등급으로 구분하여 $250{\times}250m$ 단위의 지도형태로 시각화할 수 있었다. 본 연구는 향후 자동화 시스템으로 개발하여 시시각각으로 변하는 도시 상황에 따라 실시간으로 예측 결과를 시각화하여 제공함으로써 보다 범죄로부터 안전한 도시환경 조성에 기여하고자 한다.

Publication Report of the Asian-Australasian Journal of Animal Sciences over its History of 15 Years - A Review

  • Han, In K.
    • Asian-Australasian Journal of Animal Sciences
    • /
    • 제15권1호
    • /
    • pp.124-136
    • /
    • 2002
  • As an official journal of the Asian-Australasian Association of Animal Production Societies (AAAP), the Asian-Australasian Journal of Animal Sciences (AJAS) was born in February 1987 and the first issue (Volume 1, Number 1) was published in March 1988 under the Editorship of Professor In K. Han (Korea). By the end of 2001, a total of 84 issues in 14 volumes and 1,761 papers in 11,462 pages had been published. In addition to these 14 volumes, a special issue entitled "Recent Advances in Animal Nutrition" (April, 2000) and 3 supplements entitled "Proceedings of the 9th AAAP Animal Science Congress" (July, 2000) were also published. Publication frequency has steadily increased from 4 issues in 1988, to 6 issues in 1997 and to 12 issues in 2000. The total number of pages per volume and the number of original or review papers published also increased. Some significant milestones in the history of the AJAS include that (1) it became a Science Citation Index (SCI) journal in 1997, (2) the impact factor of the journal improved from 0.257 in 1999 to 0.446 in 2000, (3) it became a monthly journal (12 issues per volume) in 2000, (4) it adopted an English editing system in 1999, and (5) it has been covered in "Current Contents/Agriculture, Biology and Environmental Science since 2000. The AJAS is subscribed by 842 individuals or institutions. Annual subscription fees of US$ 50 (Category B) or US$ 70 (Category A) for individuals and US$ 70 (Category B) or US$ 120 (Category A) for institutions are much less than the actual production costs of US$ 130. A list of the 1,761 papers published in AJAS, listed according to subject area, may be found in the AJAS homepage (http://www.ajas.snu.ac.kr) and a very well prepared "Editorial Policy with Guide for Authors" is available in the Appendix of this paper. With regard to the submission status of manuscripts from AAAP member countries, India (235), Korea (235) and Japan (198) have submitted the most manuscripts. On the other hand, Mongolia, Nepal, and Papua New Guinea have never submitted any articles. The average time required from submission of a manuscript to printing in the AJAS has been reduced from 11 months in 1997-2000 to 7.8 months in 2001. The average rejection rate of manuscripts was 35.3%, a percentage slightly higher than most leading animal science journals. The total number of scientific papers published in the AJAS by AAAP member countries during a 14-year period (1988-2001) was 1,333 papers (75.7%) and that by non- AAAP member countries was 428 papers (24.3%). Japanese animal scientists have published the largest number of papers (397), followed by Korea (275), India (160), Bangladesh (111), Pakistan (85), Australia (71), Malaysia (59), China (53), Thailand (53), and Indonesia (34). It is regrettable that the Philippines (15), Vietnam (10), New Zealand (8), Nepal (2), Mongolia (0) and Papua New Guinea (0) have not actively participated in publishing papers in the AJAS. It is also interesting to note that the top 5 countries (Bangladesh, India, Japan, Korea and Pakistan) have published 1,028 papers in total indicating 77% of the total papers being published by AAAP animal scientists from Vol. 1 to 14 of the AJAS. The largest number of papers were published in the ruminant nutrition section (591 papers-44.3%), followed by the non-ruminant nutrition section (251 papers-18.8%), the animal reproduction section (153 papers-11.5%) and the animal breeding section (115 papers-8.6%). The largest portion of AJAS manuscripts was reviewed by Korean editors (44.3%), followed by Japanese editors (18.1%), Australian editors (6.0%) and Chinese editors (5.6%). Editors from the rest of the AAAP member countries have reviewed slightly less than 5% of the total AJAS manuscripts. It was regrettably noticed that editorial members representing Nepal (66.7%), Mongolia (50.0%), India (35.7%), Pakistan (25.0%), Papua New Guinea (25.0%), Malaysia (22.8%) and New Zealand (21.5%) have failed to return many of the manuscripts requested to be reviewed by the Editor-in-Chief. Financial records show that Korea has contributed the largest portion of production costs (68.5%), followed by Japan (17.3%), China (8.3%), and Australia (3.5%). It was found that 6 AAAP member countries have contributed less than 1% of the total production costs (Bangladesh, India, Indonesia, Malaysia, Papua New Guinea and Thailand), and another 6 AAAP member countries (Mongolia, Nepal and Pakistan, Philippine and Vietnam) have never provided any financial contribution in the form of subscriptions, page charges or reprints. It should be pointed out that most AAAP member countries have published more papers than their financial input with the exception of Korea and China. For example, Japan has published 29.8% of the total papers published in AJAS by AAAP member countries. However, Japan has contributed only 17.3% of total income. Similar trends could also be found in the case of Australia, Bangladesh, India, Indonesia, Malaysia and Thailand. A total of 12 Asian young animal scientists (under 40 years of age) have been awarded the AJAS-Purina Outstanding Research Award which was initiated in 1990 with a donation of US$ 2,000-3,000 by Mr. K. Y. Kim, President of Agribrands Purina Korea Inc. In order to improve the impact factor (citation frequency) and the financial structure of the AJAS, (1) submission of more manuscripts of good quality should be encouraged, (2) subscription rate of all AAAP member countries, especially Category B member countries should be dramatically increased, (3) a page charge policy and reprint ordering system should be applied to all AAAP member countries, and (4) all AAAP countries, especially Category A member countries should share more of the financial burden (advertisement revenue or support from public or private sector).

대한제국시기의 기록관리 (Record management in Great Han Empire)

  • 이영학
    • 기록학연구
    • /
    • 제19호
    • /
    • pp.153-192
    • /
    • 2009
  • 1894년 6월에 갑오정권이 새로 등장하면서 근대적 개혁정책을 실시해갔다. 기록관리제도에서도 이전과는 크게 달랐다. 정부의 각 부처에 독자적인 기록관리부서를 설치하고, 기록관리 프로세스를 규정한 법률안을 공포하였다. 또한 독자적 연호 표기 및 국한문 혼용을 포함하여 공문서 양식을 전면 변경하였으며, 공문서 원본의 보존을 확대하였다. 고종은 1897년 10월에 대한제국을 선포하고, 갑오정권기에 약화된 왕권을 강화하면서 자신이 구상하는 개혁정책을 실시해 갔다. 먼저 왕권을 제한하였던 내각을 폐지하고 의정부를 복설하였으며, 왕권 견제를 위해 왕실과 정부를 분리하면서 만들었던 궁내부를 한층 확대 강화해갔다. 아울러 황제권을 강화해가는 물리적 기반인 군대와 경찰 및 재정 등의 영역을 고종이 직접 장악해가는 정책을 실시하였다. 그리하여 원수부, 경부를 직접 창설하여 황제 직속으로 하였으며, 황제 산하의 재정적 기반을 구축하기 위해 궁내부 산하 내장원에서 국가의 여러 세금을 직접 징수하도록 하였다. 대한제국기의 기록관리제도는 갑오정권기의 그것을 계승하였다. 먼저 정부와 황제 직속의 권력기구에서는 기록관리부서를 설치하였다. 의정부와 정부 부서는 물론이고 황제권을 뒷받침하는 특별기구인 궁내부, 원수부, 경부, 통신원, 지계아문 등의 권력기관에서도 문서과와 기록과를 두어 기록관리를 독자적으로 행하도록 하였다. 정부 업무의 효율을 증가시키고 체계적으로 수행하기 위해서는 기록관리부서를 분립하는 것이 효과적이라고 여겼던 것이다. 다음으로 부서마다 약간 차이가 있지만, 현용기록과 비현용 기록을 관리하는 부서를 분립하였다. 대체로 문서과에서는 현용문서의 접수와 발송 및 기안을 담당하였으며, 기록과에서는 주요 문서 및 영구보존문서의 보존 및 편찬을 담당하도록 하였다. 이것은 기록의 생애주기(life cycle)를 고려하고, 기록물 평가를 염두에 두면서 기록관리를 행하고자 하는 인식이 근대적 형태로 발현되었던 것이다.

빅데이터와 딥러닝을 활용한 동물 감염병 확산 차단 (Animal Infectious Diseases Prevention through Big Data and Deep Learning)

  • 김성현;최준기;김재석;장아름;이재호;차경진;이상원
    • 지능정보연구
    • /
    • 제24권4호
    • /
    • pp.137-154
    • /
    • 2018
  • 조류인플루엔자와 구제역 같은 동물감염병은 거의 매년 발생하며 국가에 막대한 경제적 사회적 손실을 일으키고 있다. 이를 예방하기 위해서 그간 방역당국은 다양한 인적, 물적 노력을 기울였지만 감염병은 지속적으로 발생해 왔다. 최근 빅데이터와 딥러닝 기술을 활용하여 감염병의 예측모델을 개발하고자 하는 시도가 시작되고 있지만, 실제로 활용가능한 모델구축 연구와 사례보고는 활발히 진행되고 있지 않은 실정이다. KT와 과학기술정보통신부는 2014년부터 국가 R&D사업의 일환으로 축산관련 차량의 이동경로를 분석하여 예측하는 빅데이터 사업을 수행하고 있다. 동물감염병 예방을 위하여 연구진은 최초에는 차량이동 데이터를 활용한 회귀분석모델을 기반으로 한 예측모델을 개발하였다. 이후에는 기계학습을 활용하여 좀 더 정확한 예측 모델을 구성하였다. 특히, 2017년 예측모델에서는 시설물에 대한 확산 위험도를 추가하였고 모델링의 하이퍼 파라미터를 다양하게 고려하여 모델의 성능을 높였다. 정오분류표와 ROC 커브를 확인한 결과, 기계 학습 모델보다 2017년 구성된 모형이 우수함을 확인 할 수 있었다. 또한 2017에는 결과에 대한 설명을 추가하여 방역당국의 의사결정을 돕고 이해관계자를 설득할 수 있는 근거를 확보하였다. 본 연구는 빅데이터를 활용하여 동물감염병예방시스템을 구축한 사례연구로 모델주요변수값, 이에따른 실제예측성능결과, 그리고 상세하게 기술된 시스템구축 프로세스는 향후 감염병예방 영역의 지속적인 빅데이터활용 및 분석 모델 개발에 기여할 수 있을 것이다. 또한 본 연구에서 구축한 시스템을 통해 보다 사전적이고 효과적인 방역을 할 수 있을 것으로 기대한다.

한국전쟁의 교훈과 대비 -병력수(兵力數) 및 부대수(部隊數)를 중심으로- (The lesson From Korean War)

  • 윤일영
    • 안보군사학연구
    • /
    • 통권8호
    • /
    • pp.49-168
    • /
    • 2010
  • Just before the Korean War, the total number of the North Korean troops was 198,380, while that of the ROK(Republic of Korea) army troops 105,752. That is, the total number of the ROK army troops at that time was 53.3% of the total number of the North Korean army. As of December 2008, the total number of the North Korean troops is estimated to be 1,190,000, while that of the ROK troops is 655,000, so the ROK army maintains 55.04% of the total number of the North Korean troops. If the ROK army continues to reduce its troops according to [Military Reform Plan 2020], the total number of its troops will be 517,000 m 2020. If North Korea maintains the current status(l,190,000 troops), the number of the ROK troops will be 43.4% of the North Korean army. In terms of units, just before the Korean War, the number of the ROK army divisions and regiments was 80% and 44.8% of North Korean army. As of December 2008, North Korea maintains 86 divisions and 69 regiments. Compared to the North Korean army, the ROK army maintains 46 Divisions (53.4% of North Korean army) and 15 regiments (21.3% of North Korean army). If the ROK army continue to reduce the military units according to [Military Reform Plan 2020], the number of ROK army divisions will be 28(13 Active Division, 4 Mobilization Divisions and 11 Local Reserve Divisions), while that of the North Korean army will be 86 in 2020. In that case, the number of divisions of the ROK army will be 32.5% of North Korean army. During the Korean war, North Korea suddenly invaded the Republic of Korea and occupied its capital 3 days after the war began. At that time, the ROK army maintained 80% of army divisions, compared to the North Korean army. The lesson to be learned from this is that, if the ROK army is forced to disperse its divisions because of the simultaneous invasion of North Korea and attack of guerrillas in home front areas, the Republic of Korea can be in a serious military danger, even though it maintains 80% of military divisions of North Korea. If the ROK army promotes the plans in [Military Reform Plan 2020], the number of military units of the ROK army will be 32.5% of that of the North Korean army. This ratio is 2.4 times lower than that of the time when the Korean war began, and in this case, 90% of total military power should be placed in the DMZ area. If 90% of military power is placed in the DMZ area, few troops will be left for the defense of home front. In addition, if the ROK army continues to reduce the troops, it can allow North Korea to have asymmetrical superiority in military force and it will eventually exert negative influence on the stability and peace of the Korean peninsular. On the other hand, it should be reminded that, during the Korean War, the Republic of Korea was attacked by North Korea, though it kept 53.3% of troops, compared to North Korea. It should also be reminded that, as of 2008, the ROK army is defending its territory with the troops 55.04% of North Korea. Moreover, the national defense is assisted by 25,120 troops of the US Forces in Korea. In case the total number of the ROK troops falls below 43.4% of the North Korean army, it may cause social unrest about the national security and may lead North Korea's misjudgement. Besides, according to Lanchester strategy, the party with weaker military power (60% compared to the party with stronger military power) has the 4.1% of winning possibility. Therefore, if we consider the fact that the total number of the ROK army troops is 55.04% of that of the North Korean army, the winning possibility of the ROK army is not higher than 4.1%. If the total number of ROK troops is reduced to 43.4% of that of North Korea, the winning possibility will be lower and the military operations will be in critically difficult situation. [Military Reform Plan 2020] rums at the reduction of troops and units of the ground forces under the policy of 'select few'. However, the problem is that the financial support to achieve this goal is not secured. Therefore, the promotion of [Military Reform Plan 2020] may cause the weakening of military defence power in 2020. Some advanced countries such as Japan, UK, Germany, and France have promoted the policy of 'select few'. However, what is to be noted is that the national security situation of those countries is much different from that of Korea. With the collapse of the Soviet Unions and European communist countries, the military threat of those European advanced countries has almost disappeared. In addition, the threats those advanced countries are facing are not wars in national level, but terrorism in international level. To cope with the threats like terrorism, large scaled army trops would not be necessary. So those advanced European countries can promote the policy of 'select few'. In line with this, those European countries put their focuses on the development of military sections that deal with non-military operations and protection from unspecified enemies. That is, those countries are promoting the policy of 'select few', because they found that the policy is suitable for their national security environment. Moreover, since they are pursuing common interest under the European Union(EU) and they can form an allied force under NATO, it is natural that they are pursing the 'select few' policy. At present, NATO maintains the larger number of troops(2,446,000) than Russia(l,027,000) to prepare for the potential threat of Russia. The situation of japan is also much different from that of Korea. As a country composed of islands, its prime military focus is put on the maritime defense. Accordingly, the development of ground force is given secondary focus. The japanese government promotes the policy to develop technology-concentrated small size navy and air-forces, instead of maintaining large-scaled ground force. In addition, because of the 'Peace Constitution' that was enacted just after the end of World War II, japan cannot maintain troops more than 240,000. With the limited number of troops (240,000), japan has no choice but to promote the policy of 'select few'. However, the situation of Korea is much different from the situations of those countries. The Republic of Korea is facing the threat of the North Korean Army that aims at keeping a large-scale military force. In addition, the countries surrounding Korea are also super powers containing strong military forces. Therefore, to cope with the actual threat of present and unspecified threat of future, the importance of maintaining a carefully calculated large-scale military force cannot be denied. Furthermore, when considering the fact that Korea is in a peninsular, the Republic of Korea must take it into consideration the tradition of continental countries' to maintain large-scale military powers. Since the Korean War, the ROK army has developed the technology-force combined military system, maintaining proper number of troops and units and pursuing 'select few' policy at the same time. This has been promoted with the consideration of military situation in the Koran peninsular and the cooperation of ROK-US combined forces. This kind of unique military system that cannot be found in other countries can be said to be an insightful one for the preparation for the actual threat of North Korea and the conflicts between continental countries and maritime countries. In addition, this kind of technology-force combined military system has enabled us to keep peace in Korea. Therefore, it would be desirable to maintain this technology-force combined military system until the reunification of the Korean peninsular. Furthermore, it is to be pointed out that blindly following the 'select few' policy of advanced countries is not a good option, because it is ignoring the military strategic situation of the Korean peninsular. If the Republic of Korea pursues the reduction of troops and units radically without consideration of the threat of North Korea and surrounding countries, it could be a significant strategic mistake. In addition, the ROK army should keep an eye on the fact the European advanced countries and Japan that are not facing direct military threats are spending more defense expenditures than Korea. If the ROK army reduces military power without proper alternatives, it would exert a negative effect on the stable economic development of Korea and peaceful reunification of the Korean peninsular. Therefore, the desirable option would be to focus on the development of quality of forces, maintaining proper size and number of troops and units under the technology-force combined military system. The tableau above shows that the advanced countries like the UK, Germany, Italy, and Austria spend more defense expenditure per person than the Republic of Korea, although they do not face actual military threats, and that they keep achieving better economic progress than the countries that spend less defense expenditure. Therefore, it would be necessary to adopt the merits of the defense systems of those advanced countries. As we have examined, it would be desirable to maintain the current size and number of troops and units, to promote 'select few' policy with increased defense expenditure, and to strengthen the technology-force combined military system. On the basis of firm national security, the Republic of Korea can develop efficient policies for reunification and prosperity, and jump into the status of advanced countries. Therefore, the plans to reduce troops and units in [Military Reform Plan 2020] should be reexamined. If it is difficult for the ROK army to maintain its size of 655,000 troops because of low birth rate, the plans to establish the prompt mobilization force or to adopt drafting system should be considered for the maintenance of proper number of troops and units. From now on, the Republic of Korean government should develop plans to keep peace as well as to prepare unexpected changes in the Korean peninsular. For the achievement of these missions, some options can be considered. The first one is to maintain the same size of military troops and units as North Korea. The second one is to maintain the same level of military power as North Korea in terms of military force index. The third one is to maintain the same level of military power as North Korea, with the combination of the prompt mobilization force and the troops in active service under the system of technology-force combined military system. At present, it would be not possible for the ROK army to maintain such a large-size military force as North Korea (1,190,000 troops and 86 units). So it would be rational to maintain almost the same level of military force as North Korea with the combination of the troops on the active list and the prompt mobilization forces. In other words, with the combination of the troops in active service (60%) and the prompt mobilization force (40%), the ROK army should develop the strategies to harmonize technology and forces. The Korean government should also be prepared for the strategic flexibility of USFK, the possibility of American policy change about the location of foreign army, radical unexpected changes in North Korea, the emergence of potential threat, surrounding countries' demand for Korean force for the maintenance of regional stability, and demand for international cooperation against terrorism. For this, it is necessary to develop new approaches toward the proper number and size of troops and units. For instance, to prepare for radical unexpected political or military changes in North Korea, the Republic of Korea should have plans to protect a large number of refugees, to control arms and people, to maintain social security, and to keep orders in North Korea. From the experiences of other countries, it is estimated that 115,000 to 230,000 troops, plus ten thousands of police are required to stabilize the North Korean society, in the case radical unexpected military or political change happens in North Korea. In addition, if the Republic of Korea should perform the release of hostages, control of mass destruction weapons, and suppress the internal wars in North Korea, it should send 460,000 troops to North Korea. Moreover, if the Republic of Korea wants to stop the attack of North Korea and flow of refugees in DMZ area, at least 600,000 troops would be required. In sum, even if the ROK army maintains 600,000 troops, it may need additional 460,000 troops to prepare for unexpected radical changes in North Korea. For this, it is necessary to establish the prompt mobilization force whose size and number are almost the same as the troops in active service. In case the ROK army keeps 650,000 troops, the proper number of the prompt mobilization force would be 460,000 to 500,000.

  • PDF