åǥÁö

[GT] ÆÄŲ½¼º´°ú °£Áú, ½Å°æÁ¶Àý ĨÀ¸·Î ÇØ°á

ÀúÀü·Â Ĩ ¼³°è, ¸Ó½Å ·¯´× ¾Ë°í¸®Áò ¹× ¼ÒÇÁÆ® À̽ÄÇü Àü±ØÀ» °áÇÕÇÏ¿© ÆÄŲ½¼º´ ¹× °£ÁúÀÇ Áõ»óÀ» °¨ÁöÇÏ°í ¿ÏÈ­ÇÒ ¼ö ÀÖ´Â Æó¼â ·çÇÁ ½Å°æ Á¶Àý ½Ã½ºÅÛ ¿Â ĨÀÎ ¡®´º..



[GT] ÆÄŲ½¼º´°ú °£Áú, ½Å°æÁ¶Àý ĨÀ¸·Î ÇØ°á

By Uisub Shin, IEEE JOURNAL OF SOLID-STATE CIRCUITS, November 2022, Vol. 57, Iss.11

¼öõ¸¸ ¸íÀÇ »ç¶÷µéÀÌ ÆÄŲ½¼º´°ú °£Áú·Î °íÅë¹Þ°í ÀÖ´Ù. ±×¿¡ µû¸¥ ÀÎÀû, ÀçÁ¤Àû ºñ¿ëÀº ¾öû³ª´Ù.

´ÙÇàÈ÷ ¿¬±¸ÀÚµéÀÌ ÀÌÁ¦ ÀúÀü·Â Ĩ ¼³°è, ¸Ó½Å ·¯´× ¾Ë°í¸®Áò ¹× ¼ÒÇÁÆ® À̽ÄÇü Àü±ØÀ» °áÇÕÇÏ¿© ÆÄŲ½¼º´ ¹× °£ÁúÀÇ Áõ»óÀ» °¨ÁöÇÏ°í ¿ÏÈ­ÇÒ ¼ö ÀÖ´Â Æó¼â ·çÇÁ ½Å°æ Á¶Àý ½Ã½ºÅÛ ¿Â ĨÀÎ ¡®´ºÆ®·²Æ®¸®(NeuralTree)¡¯¸¦ »ý»êÇÒ ¼ö ÀÖ°Ô µÇ¾ú´Ù.

´ºÆ®·²Æ®¸®´Â ½Å°æ¸ÁÀÇ Á¤È®¼º°ú ÀÇ»ç °áÁ¤ Æ®¸® ¾Ë°í¸®ÁòÀÇ Çϵå¿þ¾î È¿À²¼ºÀ» È°¿ëÇÑ´Ù. ½Å°æ º¸Çü ÀÀ¿ë ÇÁ·Î±×·¥¿ë ¼Õ°¡¶ô ¿òÁ÷ÀÓ°ú °°Àº ¸ÖƼ Ŭ·¡½º ÀÛ¾÷»Ó¸¸ ¾Æ´Ï¶ó ¹ßÀÛ ¶Ç´Â ¶³¸² °¨Áö¸¦ À§ÇØ º¹ÀâÇϸ鼭µµ ¿¡³ÊÁö È¿À²ÀûÀÎ ½Å°æ ÀÎÅÍÆäÀ̽º¸¦ ÅëÇÕÇÒ ¼ö ÀÖ¾ú´ø °ÍÀº À̹øÀÌ Ã³À½ÀÌ´Ù.

ÀÌ ¿¬±¸ °á°ú´Â 2022³â IEEE ±¹Á¦ ¹ÝµµÃ¼ ȸ·Î ÄÁÆÛ·±½º¿¡¼­ ¹ßÇ¥µÇ¾ú°í, ¹ÝµµÃ¼ ȸ·Î ¼³°è ºÐ¾ß ÃÖ¿ì¼ö ±¹Á¦ÇмúÁö IEEE ¹ÝµµÃ¼ ȸ·Î Àú³Î(IEEE Journal of Solid-State Circuits)¿¡ °ÔÀçµÇ¾ú´Ù.

´ºÆ®·²Æ®¸®´Â ³úÆÄ¿¡¼­ ½Å°æ ¹ÙÀÌ¿À¸¶Ä¿¸¦ ÃßÃâÇÏ¿© ÀÛµ¿ÇÑ´Ù. ÀÌÈÄ ½ÅÈ£¸¦ ºÐ·ùÇÏ°í ÀÓ¹ÚÇÑ °£Áú ¹ßÀÛ ¶Ç´Â ÆÄŲ½¼º´ ¶³¸²À» ¿¹°íÇÏ´ÂÁö ¿©ºÎ¸¦ ³ªÅ¸³½´Ù. Áõ»óÀÌ °¨ÁöµÇ¸é ¿ª½Ã Ĩ¿¡ ÀÖ´Â ½Å°æÀڱرⰡ È°¼ºÈ­µÇ¾î À̸¦ Â÷´ÜÇϱâ À§ÇØ Àü±â ÆÞ½º¸¦ »ý¼ºÇÑ´Ù. ÀÌ´Â ¿ÂĨ ºÐ±Þ±â(on-chip classifier)¸¦ È°¿ëÇØ ÃÖÃÊ·Î ½Ã¿¬ÇÑ ÆÄŲ½¼º´ ¶³¸² °¨Áö »ç·Ê¿¡ ÇØ´çÇÑ´Ù.

¿¬±¸ÀÚµéÀº ´ºÆ®·²Æ®¸®ÀÇ µ¶Æ¯ÇÑ ¼³°è°¡ ÃֽŠ±â¼ú¿¡ ºñÇØ Àü·Ê ¾ø´Â ¼öÁØÀÇ È¿À²¼º°ú ´Ù¿ë¼ºÀ» ÀÌ ½Ã½ºÅÛ¿¡ Á¦°øÇÑ´Ù°í ¼³¸íÇÑ´Ù. Áï, ÀÌ Ä¨Àº ÀÌÀü ¸Ó½Å ·¯´× ³»Àå ÀåÄ¡ÀÇ 32°³º¸´Ù ÈξÀ ´õ ¸¹Àº 256°³ÀÇ ÀÎDz ä³ÎÀ» ÀÚ¶ûÇÑ´Ù. À̸¦ ÅëÇØ ´õ ¸¹Àº °íÇØ»óµµ µ¥ÀÌÅ͸¦ ó¸®ÇÒ ¼ö ÀÖ´Ù.

¶ÇÇÑ Ä¨ÀÇ Å©±â°¡ ¸Å¿ì ÀÛÀºµ¥ À̸¦ ÅëÇØ ´õ ¸¹Àº ä³Î·Î È®ÀåÇÒ ¼ö ÀÖ´Â °Å´ëÇÑ ÀáÀç·ÂÀ» Á¦°øÇÏ°í ÀÖ´Ù. ¶ÇÇÑ ¡®¿¡³ÊÁö Àνġ¯ ÇнÀ ¾Ë°í¸®ÁòÀÇ ÅëÇÕÀ» ÅëÇØ, ´ºÆ®·²Æ®¸®´Â ¸Å¿ì ³ôÀº ¿¡³ÊÁö È¿À²¼ºÀ» °®Ãß°í ÀÖ´Ù.

ĨÀÇ ¸Ó½Å ·¯´× ¾Ë°í¸®ÁòÀº ¡®°£Áú¡¯°ú ¡®ÆÄŲ½¼º´¡¯ ȯÀÚÀÇ µ¥ÀÌÅÍ ¼¼Æ®¿Í ÇØ´ç µÎ ¹üÁÖ¿¡ ´ëÇÑ ¸Å¿ì Á¤±³ÇÏ°Ô ºÐ·ùµÈ »çÀü ±â·Ï ½Å°æ ½ÅÈ£¿¡ ±â¹ÝÇÏ¿© ÇнÀµÈ °ÍÀÌ´Ù.

´ÙÀ½ ´Ü°è·Î ¿¬±¸ÀÚµéÀº ½Å°æ ½ÅÈ£ÀÇ ÁøÈ­¸¦ µû¶óÀâ±â À§ÇØ ¿ÂĨ ¾Ë°í¸®Áò ¾÷µ¥ÀÌÆ®¸¦ È°¼ºÈ­ÇÏ´Â µ¥ °ü½ÉÀÌ ÀÖ´Ù. ½Å°æ ½ÅÈ£´Â °è¼Ó º¯Çϱ⠶§¹®¿¡ ÀÌ ´Ü°è´Â ¸Å¿ì Áß¿äÇÏ´Ù. Áï, ½Ã°£ÀÌ Áö³²¿¡ µû¶ó ¾÷µ¥ÀÌÆ®ÇÏÁö ¾ÊÀ¸¸é ½Å°æ ÀÎÅÍÆäÀ̽º ¼º´ÉÀÌ ÀúÇϵȴÙ. À̸¦ ÇØ°áÇÏ´Â ÇÑ °¡Áö ¹æ¹ýÀº ¿ÂĨ ¾÷µ¥ÀÌÆ®, Áï ½º½º·Î ¾÷µ¥ÀÌÆ®ÇÒ ¼ö ÀÖ´Â ¾Ë°í¸®ÁòÀ» È°¼ºÈ­ÇÏ´Â °Í¿¡ ÀÖ´Ù.

- IEEE JOURNAL OF SOLID-STATE CIRCUITS, November 2022, Vol. 57, Iss.11, ¡°NeuralTree: A 256-Channel 0.227-¥ìJ/Class Versatile Neural Activity Classification And Closed-Loop Neuromodulation SoC,¡± by Uisub Shin, et al. © 2023 IEEE. All rights reserved.

To view or purchase this article, please visit:
https://ieeexplore.ieee.org/document/9905664
[GT] NeuralTree: A 256-Channel 0.227-¥ìJ/Class Versatile Neural Activity Classification and Closed-Loop Neuromodulation SoC

By Uisub Shin, IEEE JOURNAL OF SOLID-STATE CIRCUITS, November 2022, Vol. 57, Iss.11

Tens of millions of people suffer from Parkinson¡¯s disease and epilepsy. The resulting human and financial cost of is staggering.

Fortunately, researchers have now been able to combine low-power chip design, machine learning algorithms, and soft implantable electrodes to produce NeuralTree, a closed-loop neuromodulation system-on-a-chip that can detect and alleviate symptoms of Parkinson¡¯s disease and epilepsy.

NeuralTree benefits from the accuracy of a neural network and the hardware efficiency of a decision tree algorithm. It¡¯s the first time we¡¯ve been able to integrate such a complex, yet energy-efficient neural interface for seizure or tremor detection, as well as for multiclass tasks such as finger movement classification for neuro-prosthetic applications.
The results of this research were presented at the 2022 IEEE International Solid-State Circuits Conference and published in the IEEE Journal of Solid-State Circuits.

NeuralTree functions by extracting neural biomarkers from brain waves. It then classifies the signals and indicates whether they herald an impending epileptic seizure or Parkinsonian tremor. If a symptom is detected, a neurostimulator - also located on the chip - is activated, sending an electrical pulse to block it. This is the first demonstration of Parkinsonian tremor detection with an on-chip classifier.

The researchers explain that NeuralTree¡¯s unique design gives the system an unprecedented degree of efficiency and versatility compared to the state-of-the-art.

The chip boasts 256 input channels, compared to 32 for previous machine-learning-embedded devices; this allows more high-resolution data to be processed on the implant.
 
The chip¡¯s extremely small size gives it great potential for scalability to more channels. And the integration of an ¡®energy-aware¡¯ learning algorithm makes NeuralTree highly energy efficient.

The chip¡¯s machine learning algorithm was trained on datasets from both epilepsy and Parkinson¡¯s disease patients, and accurately classified pre-recorded neural signals from both categories.

As a next step, the team is interested in enabling on-chip algorithmic updates to keep up with the evolution of neural signals. That¡¯s important because neural signals change; so, over time the performance of a neural interface will decline unless updated. One way to address that is to enable on-chip updates, or algorithms that can update themselves.

IEEE JOURNAL OF SOLID-STATE CIRCUITS, November 2022, Vol. 57, Iss.11, ¡°NeuralTree: A 256-Channel 0.227-¥ìJ/Class Versatile Neural Activity Classification And Closed-Loop Neuromodulation SoC,¡± by Uisub Shin, et al. © 2023 IEEE. All rights reserved.

To view or purchase this article, please visit:
https://ieeexplore.ieee.org/document/9905664