Áñ°Üã±â Ãß°¡     ½ÃÀÛÆäÀÌÁö·Î ¼³Á¤ óÀ½À¸·Î  l  ·Î±×ÀΠ l  È¸¿ø°¡ÀÔ  l  »çÀÌÆ®¸Ê

>
ȸ¿ø°¡ÀÔ   l   ¾ÆÀ̵ð/ºñ¹Ð¹øȣã±â
¡®Á¦38ȸ 2023³â »ó¹Ý±â ...
¡®Á¦37ȸ 2022³â ÇϹݱâ ...
Á¦37ȸ ¡¸2022³â ÇϹݱâ ...
 
HOME > ÇؿܽÃÀåÁ¤º¸ > ÃֽŴº½º
[2023] [¹Ì±¹] ¿ùÅзç´ë ¿¬±¸ÆÀ, AI È°¿ë ¹Ì¼¼Çöó½ºÆ½ ã¾Æ³»´Â ¹æ¹ý °³¹ß
À̸§ °ü¸®ÀÚ waterindustry@hanmail.net ÀÛ¼ºÀÏ 2023.12.07 Á¶È¸¼ö 429
ÆÄÀÏ÷ºÎ

[¹Ì±¹] ¿ùÅзç´ë ¿¬±¸ÆÀ, AI È°¿ë ¹Ì¼¼Çöó½ºÆ½ ã¾Æ³»´Â ¹æ¹ý °³¹ß

50% ´õ ºü¸£°í 20% ´õ ³ôÀº Á¤È®µµ ÀÔÀÚ ºÐ¼®ÇÏ´Â Çöó½ºÆ½ ³Ý AI µµ±¸ °³¹ß



¹Ì±¹ ¿öÅзç´ëÇб³ ÇÐÁ¦°£ ¿¬±¸ÆÀÀº ÀΰøÁö´É(AI)À» È°¿ëÇØ ¹Ì¼¼Çöó½ºÆ½À» ÀÌÀüº¸´Ù ´õ ºü¸£°í Á¤È®ÇÏ°Ô ½Äº°ÇÏ°í ÀÖ´Ù. [»çÁøÁ¦°ø(Photo Source) = University of Waterloo]

 

¹Ì±¹ ¿öÅзç´ëÇб³ ÇÐÁ¦°£ ¿¬±¸ÆÀÀº ÀΰøÁö´É(AI)À» È°¿ëÇØ ¹Ì¼¼Çöó½ºÆ½À» ÀÌÀüº¸´Ù ´õ ºü¸£°í Á¤È®ÇÏ°Ô ½Äº°ÇÑ´Ù.


¹Ì¼¼Çöó½ºÆ½Àº ½ÄÇ°¿¡¼­ ÈçÈ÷ ¹ß°ßµÇ¸ç, ½É°¢ÇÑ È¯°æ ÇÇÇظ¦ ÀÏÀ¸Å°´Â À§ÇèÇÑ ¿À¿°¹°ÁúÀÌ´Ù. ¹Ì¼¼Çöó½ºÆ½À» Á¦°ÅÇϱâ À§Çؼ­´Â ã¾Æ³»´Â °ÍÀÌ ¿ì¼±ÀÌ´Ù.


¿¬±¸ÆÀÀÇ Ã·´Ü ¿µ»ó ½Äº° ½Ã½ºÅÛÀº ¼ö ó¸®Àå°ú ½ÄÇ° »ý»ê ¾÷°è°¡ ¹Ì¼¼Çöó½ºÆ½ÀÌ È¯°æ°ú Àΰ£ °Ç°­¿¡ ¹ÌÄ¥ ¼ö ÀÖ´Â ÀáÀçÀû ¿µÇâÀ» ¿ÏÈ­Çϱâ À§ÇÑ Á¤º¸¿¡ ÀÔ°¢ÇÑ °áÁ¤À» ³»¸®´Â µ¥ µµ¿òÀÌ µÉ ¼ö ÀÖ´Ù.


Á¾ÇÕÀûÀÎ À§Çè ºÐ¼® ¹× Á¶Ä¡ °èȹ¿¡´Â Á¤È®ÇÑ ½Äº°À» ±â¹ÝÀ¸·Î ÇÑ ¾çÁúÀÇ Á¤º¸°¡ ÇÊ¿äÇÏ´Ù. ÀÌ ÇÁ·ÎÁ§Æ®ÀÇ Ã¥ÀÓÀÚÀÎ ¿þÀÎ ÆÄÄ¿(Wayne Parker) ¹Ú»ç¿Í ¿¬±¸ÁøÀº ÀÔÀÚ¸¦ ´Ù¾çÇÑ ºûÀÇ ÆÄÀå¿¡ ³ëÃâ½ÃÅ°´Â °í±Þ ºÐ±¤¹ýÀ» »ç¿ëÇØ ÇöÁ¸ÇÏ´Â ¸¹Àº ¹Ì¼¼Çöó½ºÆ½À» ¿­°ÅÇÏ°í ½Äº°ÇÏ¸ç ¼³¸íÇÒ ¼ö ÀÖ´Â °­·ÂÇÑ ºÐ¼® µµ±¸¸¦ ã¾Ò´Ù. ´Ù¾çÇÑ À¯ÇüÀÇ Çöó½ºÆ½Àº ºûÀÌ ³ëÃâµÇ¸é ¼­·Î ´Ù¸¥ ½ÅÈ£¸¦ »ý¼ºÇÑ´Ù. ÀÌ·¯ÇÑ ½ÅÈ£´Â ÀÔÀÚ°¡ ¹Ì¼¼ Çöó½ºÆ½ ÀÎÁö ¾Æ´ÑÁö¸¦ Ç¥½ÃÇÏ´Â µ¥ »ç¿ëÇÒ ¼ö ÀÖ´Â Áö¹®°ú °°Àº ¿ªÇÒÀ» ÇÑ´Ù.


[»çÁøÁ¦°ø(Photo Source) = University of Waterloo]

[»çÁøÁ¦°ø(Photo Source) = University of Waterloo]

 

¿¬±¸ÁøÀÌ Á¾Á¾ ¹ß°ßÇÏ´Â ¹®Á¦´Â ½ÇÇè½Ç ȯ°æ¿¡¼­ '½ÅÈ£'À» È帮°Ô ÇÒ ¼ö ÀÖ´Â Á¦Á¶ ÷°¡Á¦¿Í ÃæÀüÀç°¡ Á¸ÀçÇϱ⠶§¹®¿¡ ¹Ì¼¼Çöó½ºÆ½ÀÌ ´Ù¾çÇÑ Á¾·ù·Î ³ªÅ¸³­´Ù´Â °ÍÀÌ´Ù. ÀÌ·Î ÀÎÇØ ´Ù¾çÇÑ Á¾·ùÀÇ ¹Ì¼¼Çöó½ºÆ½»Ó¸¸ ¾Æ´Ï¶ó À¯±â ¹°Áú·ÎºÎÅÍ ¹Ì¼¼Çöó½ºÆ½À» ½Äº°ÇÏ´Â °ÍÀÌ Á¾Á¾ ¾î·Á¿öÁø´Ù. ¹Ì¼¼Çöó½ºÆ½ÀÇ ¹Ì¹¦ÇÑ ÆÐÅÏ°ú ½ÅÈ£¸¦ ¾Ë¾Æ³»±â À§ÇØ Àΰ£ÀÇ °³ÀÔÀÌ ¿ä±¸µÇ´Âµ¥, ÀÌ´Â ½Ã°£ÀÌ ¿À·¡°É¸®°í ¿À·ù°¡ ¹ß»ýÇϱ⠽±´Ù.


ÆÄÄ¿ ¿öÅзç´ëÇб³ Åä¸ñȯ°æ°øÇаú ±³¼ö´Â ¡°¹Ì¼¼Çöó½ºÆ½Àº ´Ù¸¥ È­Çй°ÁúÀ» Èí¼öÇÒ ¼ö ÀÖ´Â ¼Ò¼ö¼º ¹°Áú¡±À̶ó¸ç "¹®Á¦°¡ ¾ó¸¶³ª ½É°¢ÇÑÁö¿¡ ´ëÇØ °úÇÐÀº °è¼Ó ¹ßÀüÇÏ°í ÀÖÁö¸¸, ÀÌ·ÐÀûÀ¸·Î ¹Ì¼¼Çöó½ºÆ½ÀÌ ¸ÔÀ̻罽¿¡¼­ µ¶¼º ¹°ÁúÀÇ ÃàÀûÀ» °­È­ÇÏ°í ÀÖÀ» °¡´É¼ºÀÌ ÀÖ´Ù"°í ¸»Çß´Ù.


ÆÄÄ¿ ±³¼ö´Â ¿öÅÐ·ç ½Ã½ºÅÛ ¼³°è °øÇаú ±³¼öÀÌÀÚ Ä³³ª´Ù ÀΰøÁö´É ¹× ÀǷ῵»ó ºÐ¾ßÀÇ ÀÇÀåÀÎ ¾Ë·º»ê´õ ¿ý(Alexander Wong)¹Ú»ç¿¡°Ô µµ¿òÀ» ¿äûÇØ ÀÌÀü ¹æ¹ýº¸´Ù ¾à 50% ´õ ºü¸£°í 20% ´õ ³ôÀº Á¤È®µµ·Î ´ë·®ÀÇ ÀÔÀÚ¸¦ ½Å¼ÓÇÏ°Ô ºÐ¼®ÇÒ ¼ö ÀÖ´Â Çöó½ºÆ½ ³Ý(PlasticNet)À̶ó´Â AI µµ±¸¸¦ °³¹ßÇß´Ù.


[»çÁøÁ¦°ø(Photo Source) = University of Waterloo]

Çöó½ºÆ½³Ý ¿¬±¸ÆÀÀÎ ¿þÀÎ ÆÄÄ¿ ±³¼ö, ÇÁ·©Å© ÁÖ Àü ¹Ú»ç°úÁ¤»ý, ¾Ë·º»ê´õ ¿ý ±³¼öÀÇ ¸ð½À. [»çÁøÁ¦°ø(Photo Source) = University of Waterloo]


ÀÌ µµ±¸´Â ȯ°æÀ» º¸È£ÇÏ°í Áö¼Ó°¡´ÉÇÑ ¹Ì·¡¿¡ ±â¿©ÇÒ ¿¬±¸¿¡ Âü¿©Çϱâ À§ÇØ ¿öÅÐ·ç ¿¬±¸¿øÀÌ ¼³°èÇÑ ÃֽŠÁö¼Ó °¡´ÉÇÑ ±â¼úÀÌ´Ù.


¿ý ±³¼ö´Â "ºÐ±¤ ½ÅÈ£·ÎºÎÅÍ ¹Ì¼¼Çöó½ºÆ½ ½Äº°À» Çâ»ó½ÃÅ°±â À§ÇØ µö·¯´× ½Å°æ¸ÁÀ» ±¸ÃàÇß´Ù"¸ç "±âÁ¸ ¹®Çå ÀÚ·á¿Í ÀÚü Á¦ÀÛÇÑ À̹ÌÁö¸¦ ¹ÙÅÁÀ¸·Î ¹Ì¼¼Çöó½ºÆ½ÀÇ ´Ù¾çÇÑ ±¸¼ºÀ» ÀÌÇØÇÏ°í Áö¹®ÀÇ Ç°Áú¿¡ »ó°ü¾øÀÌ ºü¸£°í Á¤È®ÇÏ°Ô Â÷À̸¦ ÆľÇÇÒ ¼ö ÀÖµµ·Ï ÈÆ·ÃÇß´Ù"°í ¼³¸íÇß´Ù.


ÆÄÄ¿ ±³¼öÀÇ Àü ¹Ú»ç°úÁ¤»ýÀÎ ÇÁ·©Å© ÁÖ(Frank Zhu)´Â Áö¿ª Çϼö ó¸®Àå¿¡¼­ ºÐ¸®µÈ ¹Ì¼¼ Çöó½ºÆ½À» ´ë»óÀ¸·Î ½Ã½ºÅÛÀ» Å×½ºÆ®Çß´Ù. °á°ú´Â Àü·Ê ¾ø´Â ¼Óµµ¿Í Á¤È®¼ºÀ¸·Î ¹Ì¼¼Çöó½ºÆ½À» ½Äº°ÇÒ ¼ö ÀÖÀ½À» º¸¿©ÁØ´Ù. ÀÌ Á¤º¸´Â ó¸®Àå¿¡¼­ ÀÌ·¯ÇÑ ¹°ÁúÀ» ÅëÁ¦ÇÏ°í Á¦°ÅÇϱâ À§ÇÑ È¿°úÀûÀÎ Á¶Ä¡¸¦ ½ÃÇàÇÒ ¼ö ÀÖµµ·Ï ÈûÀ» ½Ç¾îÁÙ ¼ö ÀÖ´Ù.


´ÙÀ½ ´Ü°è´Â Áö¼ÓÀûÀÎ ÇнÀ°ú Å×½ºÆ®»Ó¸¸ ¾Æ´Ï¶ó PlasticNet ½Ã½ºÅÛ¿¡ ´õ ¸¹Àº µ¥ÀÌÅ͸¦ Á¦°øÇØ ´Ù¾çÇÑ ¿ä±¸ »çÇ׿¡ Àû¿ëÇÒ ¼ö ÀÖ´Â ¹Ì¼¼Çöó½ºÆ½ ½Äº° ±â´ÉÀÇ Ç°ÁúÀ» Çâ»ó½ÃÅ°´Â °ÍÀÌ´Ù.


ÀÌ ¿¬±¸¿¡ ´ëÇÑ ÀÚ¼¼ÇÑ ³»¿ëÀº ȯ°æ ¿À¿°(Environmental Pollution)¿¡ °ÔÀçµÈ ¿¬±¸ ³í¹® "ÃÊÁ¡¸é ¹è¿­(FPA) ¸¶ÀÌÅ©·Î FT-IR À̹Ì¡À» ÅëÇÑ ¹Ì¼¼ Çöó½ºÆ½(MP) ÀÚµ¿ ÀνÄÀ» À§ÇÑ µö ·¯´× È°¿ë"¿¡¼­ È®ÀÎÇÒ ¼ö ÀÖ´Ù.


[¿ø¹®º¸±â]


Using AI to find microplastics

Researchers use AI to identify toxic substances in wastewater with greater accuracy and speed


 

An interdisciplinary research team from the University of Waterloo is using artificial intelligence (AI) to identify microplastics faster and more accurately than ever before.


Microplastics are commonly found in food and are dangerous pollutants that cause severe environmental damage – finding them is the key to getting rid of them.


The research team¡¯s advanced imaging identification system could help wastewater treatment plants and food production industries make informed decisions to mitigate the potential impact of microplastics on the environment and human health.


A comprehensive risk analysis and action plan requires quality information based on accurate identification. In search of a robust analytical tool that could enumerate, identify and describe the many microplastics that exist, project lead Dr. Wayne Parker and his team, employed an advanced spectroscopy method which exposes particles to a range of wavelengths of light. Different types of plastics produce different signals in response to the light exposure. These signals are like fingerprints that can also be employed to mark particles as microplastic or not.


The challenge researchers often find is that microplastics come in wide varieties due to the presence of manufacturing additives and fillers that can blur the ¡°fingerprints¡± in a lab setting. This makes identifying microplastics from organic material, as well as the different types of microplastics, often difficult. Human intervention is usually required to dig out subtle patterns and cues, which is slow and prone to error.


¡°Microplastics are hydrophobic materials that can soak up other chemicals,¡± said Parker, a professor in Waterloo¡¯s Department of Civil and Environmental Engineering. ¡°Science is still evolving in terms of how bad the problem is, but it¡¯s theoretically possible that microplastics are enhancing the accumulation of toxic substances in the food chain.¡±


Parker approached Dr. Alexander Wong, a professor in Waterloo¡¯s Department of Systems Design Engineering and the Canada Research Chair in Artificial Intelligence and Medical Imaging for assistance. With his help, the team developed an AI tool called PlasticNet that enables researchers to rapidly analyze large numbers of particles approximately 50 per cent faster than prior methods and with 20 per cent more accuracy.


The tool is the latest sustainable technology designed by Waterloo researchers to protect our environment and engage in research that will contribute to a sustainable future.


¡°We built a deep learning neural network to enhance microplastic identification from the spectroscopic signals,¡± said Wong. ¡°We trained it on data from existing literature sources and our own generated images to understand the varied make-up of microplastics and spot the differences quickly and correctly— regardless of the fingerprint quality.¡±


Parker¡¯s former PhD student, Frank Zhu, tested the system on microplastics isolated from a local wastewater treatment plant. Results show that it can identify microplastics with unprecedented speed and accuracy. This information can empower treatment plants to implement effective measures to control and eliminate these substances.


The next steps involve continued learning and testing, as well as feeding the PlasticNet system more data to increase the quality of its microplastics identification capabilities for application across a broad range of needs.


More information about this work can be found in the research paper, ¡°Leveraging deep learning for automatic recognition of microplastics (MPs) via focal plane array (FPA) micro-FT-IR imaging¡±, published in Environmental Pollution.


[Ãâó = University of Waterloo(https://uwaterloo.ca/news/media/using-ai-find-microplastics) / 2023³â 12¿ù 5ÀÏ]

¨Ï±Û·Î¹ú¹°»ê¾÷Á¤º¸¼¾ÅÍ(www.waterindustry.co.kr) ¹«´ÜÀüÀç ¹× Àç¹èÆ÷±ÝÁö
ÀÌÀü±Û [¹Ì±¹] ¿¬¹æ±¹Åä°³¹ß±¹, ´ã¼öÈ­ ¹× Á¤¼ö ¿¬±¸ ÇÁ·Î±×·¥ ÅëÇØ 220¸¸ ´Þ·¯ Áö¿ø
´ÙÀ½±Û [»ç¿ìµð] »ç¿ìµð°³¹ß±â±Ý, ·Î°Ç ¼ö·Â¹ßÀü ÇÁ·ÎÁ§Æ®¿¡ 1¾ï´Þ·¯ °³¹ßÂ÷°ü Á¦°ø
±Û·Î¹ú¹°»ê¾÷Á¤º¸¼¾ÅÍ.   ¼¾ÅÍÀå : ¹èö¹Î
ÁÖ¼Ò : ¼­¿ï½Ã ¼ÛÆı¸ »ïÀüµ¿ 72-3 À¯¸²ºôµù 5Ãþ TEL (02) 3431-0210   FAX (02) 3431-0260   E-mail waterindustry@hanmail.net
COPYRIGHT(C) 2012 ±Û·Î¹ú¹°»ê¾÷Á¤º¸¼¾ÅÍ. ALL RIGHT RESERVED.