I was only nine when my grandfather first described to me the horrors he witnessed six years earlier
我9岁那年，祖父第一次向我讲述了那场他6年前见证的恐怖意外事件，
when human stampedes killed 39 people in our hometown of Nashik, India.
当时在我们家乡印度纳西克，有39人因为踩踏事件而遇难。
It was during the 2003 Nashik Kumbh Mela, one of the world's largest religious gatherings.
那是在2003年纳西克的大壶节，世界最大的宗教聚会之一。
Every 12 years, over 30 million Hindu worshippers descend upon our city
每隔12年就有超过3千万印度教教徒蜂拥而至我们的城市，
which is built only for 1.5 million people -- and stay for 45 days.
在这原本只能容纳150万人的城市中待上45天。
The main purpose is to wash away all their sins by bathing in the river Godavari.
这个节日的主要目的是通过在哥达瓦里河洗澡，洗去他们身上所有的罪孽。
And stampedes may easily happen because a high-density crowd moves at a slow pace.
踩踏事件往往很容易发生，因为人群密度高，行走缓慢。
Apart from Nashik, this event happens in three other places in India, with varying frequency,
除了纳西克，踩踏在印度其他三个地方也有发生，出现的频率各不相同，
and between 2001 and 2014, over 2,400 lives have been lost in stampedes at these events.
2001年2014年间，超过2400人因为节日踩踏事件而失去生命。
What saddened me the most is seeing people around me resigning to the city's fate
让我最难过的是，看到人们无视城市的宿命，
in witnessing the seemingly inevitable deaths of dozens at every Kumbh Mela.
坐视每次大壶节上看似不可避免的几十人的死亡。
I sought to change this, and I thought, why can't I try to find a solution to this?
我想要改变现状。我想，为什么我不能找到方法解决这个问题？
Because I knew it is wrong. Having learned coding at an early age and being a maker, I considered the wild idea...
因为我知道这是不对的。我早年学过编程，作为一个手艺人（这里指程序员），我想到了一个疯狂的点子...
I considered the wild idea of building a system that would help regulate the flow of people
我想到了一个大胆的想法：可以构建一个系统，用来帮助调控人流，
and use it in the next Kumbh Mela in 2015, to have fewer stampedes and, hopefully, fewer deaths.
并在2015年的下一个大壶节，降低踩踏事件，希望这个系统能带来更少的伤亡。
It seemed like a mission impossible, a dream too big, especially for a 15-year-old,
这看起来像不可能完成的任务，完全是异想天开，尤其对于一个15岁的人来讲，
yet that dream came true in 2015, when not only did we succeed in reducing the stampedes and their intensity,
但梦想在2015年成真了，我们不仅成功降低了踩踏事件发生的次数和密度，
but we marked 2015 as the first Nashik Kumbh Mela to have zero stampedes.
也在2015年实现了大壶节历史上首次零踩踏事件的突破。
It was the first time in recorded history that this event passed without any casualties.
这是有历史记录以来第一次这个节日上没有任何人员伤亡。
How did we do it? It all started when I joined an innovation workshop by MIT Media Lab in 2014 called the Kumbhathon
我们是如何做到的？这一切始于我加入的由MIT媒体实验室在2014年设立的名叫大壶马拉松的创新研讨会，
that aimed at solving challenges faced at the grand scale of Kumbh Mela.
目的是解决大壶节面临的大规模人群挑战。
Now, we figured out to solve the stampede problem, we wanted to know only three things:
现在，我们知道要解决踩踏问题，只需要知道三件事情：
the number of people, the location, and the rate of the flow of people per minute.
人数、他们的位置和每分钟人流的速度。
So we started to look for technologies that would help us get these three things.
所以我们开始寻找可以帮我们得到这三种信息的科技。
Can we distribute radio-frequency tokens to identify people?
我们可以通过无线标记来识别人群吗？
We figured out that it would be too expensive and impractical to distribute 30 million tags.
我们发现，这个方法可能太昂贵且不实用，需要分发超过3千万标记。
Can you use CCTV cameras with image-processing techniques?
能不能用带图像识别的电子摄像头呢？
Again, too expensive for that scale,
同样，对于此等人群规模实在太昂贵了，
along with the disadvantages of being non-portable and being completely useless in the case of rain,
而且还有不够便携的缺点，遇到雨天这样的天气时基本毫无用处，
which is a common thing to happen in Kumbh Mela. Can we use cell phone tower data?
大壶节遇到下雨可是非常平常的事情。我们可以使用蜂窝基站的数据吗？
It sounds like the perfect solution, but the funny part is,
这听起来像是个完美的解决方法，但有趣的是，
most of the people do not carry cell phones in events like Kumbh Mela.
很多人在大壶节这样的节日上根本不带手机。
Also, the data wouldn't have been granular enough for us.
而且这个数据对我们而言粒度不够。
So we wanted something that was real-time, low-cost, sturdy and waterproof,
所以我们想要真正实时的、低成本的、坚固的、防水的，
and it was easy to get the data for processing.
而且便于获取数据的方案。
So we built Ashioto, meaning "footstep" in Japanese,
所以我们构建了“Ashioto”系统，在日语中意思是“脚步声”，
as it consists of a portable mat which has pressure sensors which can count the number of people walking on it,
这种垫子便携而且自带压力传感器，可以计算出行走的人群数量，
and sends the data over the internet to the advanced data analysis software we created.
还能把数据通过互联网传递给我们构建的数据分析软件。
The possible errors, like overcounting or double-stepping, were overcome using design interventions.
可能存在的诸如过度计算或重复计算脚步的误差，也通过干预措施被消除了。
The optimum breadth of the mat was determined to be 18 inches,
垫子的最佳宽度被设计为18英寸，
after we tested many different versions and observed the average stride length of a person.
这是我们在测试了许多不同版本以及计算人们步伐的平均跨度后得出的。

Otherwise, people might step over the sensor.
不然人们可能会跨过传感器。
We started with a proof of concept built in three days, made out of cardboard and aluminum foil.
然后我们开始对花费了三天时间用纸板和铝箔制做的传感器进行概念测试。
It worked, for real. We built another one with aluminum composite panels and piezoelectric plates,
方法奏效了，真的。我们用铝复合板和压电版做了另外一块，
which are plates that generate a small pulse of electricity under pressure.
可以在压力下产生小电流脉冲。
We tested this at 30 different pilots in public, in crowded restaurants, in malls, in temples, etc., to see how people reacted.
我们在30多个不同的公众场合测试了这个装置，在拥挤的餐厅、商场和寺庙等等，来了解人们的表现。
And people let us run these pilots because they were excited to see localites work on problems for the city.
人们同意我们进行这些测试，因为他们非常乐于看到有当地人在解决城市问题。
I was 15 and my team members were in their early 20s.
我当时15岁，团队的平均年龄也就是20出头。
When the sensors were colored, people would get scared and would ask us questions like,
但给传感器上色后，人们开始觉得害怕，并问我们诸如此类的问题，
"Will I get electrocuted if I step on this?"
“走在上面，会不会被电到？”
Or, if it was very obvious that it was an electronic sensor on the ground, they would just jump over it.
或者，如果在路上遇到很明显是电子传感板的东西，他们可能会跳过去。
So we decided to design a cover for the sensor so that people don't have to worry what it is on the ground.
所以我们决定给传感器加个盖板，这样人们就不用担心放在地上的是什么了。
So after some experimentation, we decided to use an industrial sensor,
在经过几次实验后，我们打算使用工业级的传感器，
used as a safety trigger in hazardous areas as the sensor, and a black neoprene rubber sheet as the cover.
这种传感器在危险地区被用作安全触发器，并用一块黑色的氯丁橡胶板作为盖子。
Now, another added benefit of using black rubber was that dust naturally accumulates over the surface,
另一个使用黑色橡胶板的好处是，灰尘会自然聚集在表面，
eventually camouflaging it with the ground.
最终伪装成土地表面的样子。
We also had to make sure that the sensor is no higher than 12 millimeters.
我们还需要确保传感器的厚度不能超过12毫米。
Otherwise, people might trip over it, which in itself would cause stampedes.
否则人们会被绊倒，这本身就会引起踩踏。
We don't want that. So we were able to design a sensor which was only 10 millimeters thick.
我们可不想这样。所以我们设计了只有10毫米厚的传感器。
Now the data is sent to the server in real time, and a heat map is plotted,
现在数据实时传回服务器了，热点图生成了，
taking into account all the active devices on the ground.
基于地面这些所有的活跃设备。
The authorities could be alerted if the crowd movement slowed down or if the crowd density moved beyond a desired threshold.
政府部门就可以知道人群慢了下来，或者人群密度超过了期望的阀值。
We installed five of these mats in the Nashik Kumbh Mela 2015,
我们在2015年纳西克大壶节上安装了5块传感垫子，
and counted over half a million people in 18 hours,
在18个小时内统计出了超过50万人，
ensuring that the data was available in real time at various checkpoints, ensuring a safe flow of people.
确保了不同采集点数据的可用性和实时性，确保了人流的安全。
Now, this system, eventually, with other innovations, is what helped prevent stampedes altogether at that festival.
现在这个系统，最终和其他创新一起，帮助我们避免了节日踩踏发生。
The code used by Ashioto during Kumbh Mela will soon be made publicly available, free to use for anyone.
大壶节的Ashioto使用的代码马上就会公开发布，任何人都可以免费获取。
I would be glad if someone used this code to make many more gatherings safer.
我非常乐于见到有人能够使用这个代码，去让更多有人群聚集的场合变得更安全。
Having succeeded at Kumbh Mela has inspired me to help others who may also suffer from stampedes.
在大壶节的成功实践，激发了我去帮助其他遭遇了踩踏事件的地方。
The design of the system makes it adaptable to pretty much any event that involves an organized gathering of people.
这个系统的设计决定了它可以适用于任何需要管理聚集人群的场合。
And my new dream is to improve, adapt and deploy the system all over the world
我的新梦想是在全球各地去提升、调整和部署这个系统，
to prevent loss of life and ensure a safe flow of people,
避免伤亡，确保人流安全，
because every human soul is precious, whether at concerts or sporting events,
因为每个人的灵魂都是珍贵的，不管在演唱会还是体育赛事，
the Maha Kumbh Mela in Allahabad, the Hajj in Mecca, the Shia procession to Karbala or at the Vatican City.
不管在阿拉哈巴德的的大壶节，还是在麦加的朝圣，亦或是卡尔巴拉，或者梵蒂冈城的什叶派游行。
So what do you all think, can we do it? Yes! Thank you.
所以你们怎么想，我们能做到吗？能！谢谢。