Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: What problem are you close to solving and how can we help?

news.ycombinator.com

Post reply on HN
Print view View original

471–480 of 486 posts

Re: Ask HN: What problem are you close to solving and how can we help?

#471

Post by sthatipamala »

lonk11 wrote: post #121
jordwest wrote: post #88

I want to bring back old school distributed forum communities but modernise them in a way that respects attention and isn’t a notification factory. Mastodon is a pretty inspirational project but the Twitter influence shows, I miss the long form writing that was encouraged before our attention spans were eroded. Not at all close to solving it, but it’s been on my mind for a long time. Would love to hear if there are o…

I am building a project ( https://linklonk.com ) that does information discovery in a way that respects your attention. In short, when you upvote content you connect to other people upvoted that content and to feeds that posted that content. So to get your attention other users need to prove to be a good curator of content for you. I'm planning to do a "Show HN" post next week for it and would appreciate any feedback…

Hmm... did you happen to work at Google? The concept and the UI seems very familiar.

Re: Ask HN: What problem are you close to solving and how can we help?

#472

Post by motyar »

bogwog wrote: post #261
motyar wrote: post #46

Problem: Create image with text. Solution: https://img.bruzu.com?a.t=Text You can help by trying the API and giving honest feedback. https://bruzu.com

Seems like it would be a lot easier and a lot more powerful to use SVG instead of a giant string of URL parameters. Your service could provide pre-made templates and an editor, and expose textfields, images, fonts, etc options via URL parameters. Then your service just has to render the SVG and return it as an image with the requested dimensions/format. Example: ` https://img.bruzu.com?s= ID>&title=Hello&font=arial&w…

Problem with svgs is that the text don't auto scale.

Re: Ask HN: What problem are you close to solving and how can we help?

#473

Post by chubot »

jtolmar wrote: post #174
chubot wrote: post #119

These are statistics/math problems that 2 medical professionals I'm seeing are working on, not my own work. But they got me curious. FWIW I worked in "data science" as a software engineer for many years, and did some machine learning, so I have some adjacent experience, but I could use help conceptualizing the problems. Does anyone know of any books or surveys about statistics and medicine, or specifically mechanics…

> One therapist is taking measurements of say your arm motion and making inferences about the motion of other muscles. This seems like a sequential Bayesian filtering problem. Probably high enough dimension that you should just use a particle filter. The big seminal background text in this area is Bishop: Pattern Recognition and Machine Learning. If the "motion of other muscles" is inferring pose, you could also look…

Thanks, I will follow these references.

I've heard of inverse kinematics but I think it's more focused on "modeling" than statistics/probability? That is, you would have to model each muscle?

I think he is doing something that is more "invariant" across human variation? (strength, body dimensions, age, etc.) I'm not sure which is why my question was vague, but this is helpful.

Re: Ask HN: What problem are you close to solving and how can we help?

#474

Post by chubot »

jpeloquin wrote: post #250
chubot wrote: post #119

These are statistics/math problems that 2 medical professionals I'm seeing are working on, not my own work. But they got me curious. FWIW I worked in "data science" as a software engineer for many years, and did some machine learning, so I have some adjacent experience, but I could use help conceptualizing the problems. Does anyone know of any books or surveys about statistics and medicine, or specifically mechanics…

My research specialty is in orthopedic biomechanics. For the arm motion thing, it sounds like you might want inverse kinematics or inverse dynamics. Take a look at OpenSim: https://simtk.org/projects/opensim For the oral appliance adjustment, I'm not sure what your output measures of interest are. If they're mechanical maybe you want to do a sensitivity analysis using FEA. Maybe look at FEBio: https://febio.org/ As f…

Thank you for the references, I will follow these!

I think the basic idea is that when you're doing physical therapy that targets certain muscles, you have to find the muscle(s) that are limiting the motion! This is not obvious because they all interact.

Like if you have a back problem, you can try to exercise your back all you want, and that may not actually fix the problem. Because the real issue could be with your leg, which causes 16 hours a day of "bad" motion against your pelvis, which in turn messes up your back.

All the muscles in the body are interlinked and they often compensate for each other. When people have a problem in one area, they compensate in other ways.

So I have the same question as above: I think inverse kinematics is more about "modeling"? You would need to model every muscle, which is hard, and it is specific to a person?

I think his intuition is partly based on a mental model, but it's also probablistic. I think the model has to capture the things that are "invariant" across humans (i.e. basic knowledge of anatomy), and the variation between humans is the probablistic part. It's also based on variation in your personal health history / observed behavior, e.g. how you walk, how often you're sitting at a computer, etc.

So it does feel like an "inference" problem in that sense -- many factors/observations that result in multiple weighted guesses of the cause / effective therapies.

Re: Ask HN: What problem are you close to solving and how can we help?

#475

Post by trevcanhuman »

adriangrigore wrote: post #232

Web site building complexity, for now I started with a simple static site generator https://mkws.sh/ . Right now, I'm not using any package manager, no config files, only one language for templates (sh), and obviously HTML, CSS, Js. I eventually plan to develop a simple CMS based on the same ideas. Ideas and code are welcome!

Hey there, how can I download/install this? I've been meaning to but I couldn't find another way besides https://mkws.sh/mkws@4.0.11.tgz which currently throws a 404 not found error. Any ideas?

Re: Ask HN: What problem are you close to solving and how can we help?

#476

Post by jtolmar »

chubot wrote: post #473
jtolmar wrote: post #174

Earlier quoted context omitted.

> One therapist is taking measurements of say your arm motion and making inferences about the motion of other muscles. This seems like a sequential Bayesian filtering problem. Probably high enough dimension that you should just use a particle filter. The big seminal background text in this area is Bishop: Pattern Recognition and Machine Learning. If the "motion of other muscles" is inferring pose, you could also look…

Thanks, I will follow these references. I've heard of inverse kinematics but I think it's more focused on "modeling" than statistics/probability? That is, you would have to model each muscle? I think he is doing something that is more "invariant" across human variation? (strength, body dimensions, age, etc.) I'm not sure which is why my question was vague, but this is helpful.

Yeah, IK is about pose and motion modeling. But you can put any state+motion model inside sequential Bayes, and get the probability that the model is in a particular configuration out.

Hard to know whether that's relevant without knowing what he's trying to predict though.

Re: Ask HN: What problem are you close to solving and how can we help?

#477

Post by MaurizioPz »

bambax wrote: post #159
dbancajas wrote: post #129

How to find motivation/energy to do a long-term creative project when having a full time jobs + other responsibilities?

The brain hates to start things and loves to finish things. This can be hacked in that a working session should always leave something unfinished. Say you're writing a novel. Every writing session (but the first, obviously) should cover the end of the last scene and the beginning of a new one, AND THEN STOP, i.e. not finish the new scene. Your brain will want to come back to the work to finish it, which overcomes the…

I've adopted this sort of trick ending my programming session with a failing unit test. I works quite well (When I remember to do it)

Re: Ask HN: What problem are you close to solving and how can we help?

#478

Post by qPM9l3XJrF »

davehcker wrote: post #48

I have posted this here before- hexafarms.com. I am trying to use ML to discover optimal phenotype for growing plants in vertical indoor farms to a. have the higest quality produce b. to lower the cost of producing leafy green/med plants, etc. within cities itself. Basically, every leafy green (and herbs, and even mushrooms), can grow in a range of climatic condition (phenotype, roughly) ie temperature, humidity, wat…

I think you'd be better off using a Gaussian process than reinforcement learning

Re: Ask HN: What problem are you close to solving and how can we help?

#479

Post by jpeloquin »

chubot wrote: post #474
jpeloquin wrote: post #250

Earlier quoted context omitted.

My research specialty is in orthopedic biomechanics. For the arm motion thing, it sounds like you might want inverse kinematics or inverse dynamics. Take a look at OpenSim: https://simtk.org/projects/opensim For the oral appliance adjustment, I'm not sure what your output measures of interest are. If they're mechanical maybe you want to do a sensitivity analysis using FEA. Maybe look at FEBio: https://febio.org/ As f…

Thank you for the references, I will follow these! I think the basic idea is that when you're doing physical therapy that targets certain muscles, you have to find the muscle(s) that are limiting the motion! This is not obvious because they all interact. Like if you have a back problem, you can try to exercise your back all you want, and that may not actually fix the problem. Because the real issue could be with your…

Inverse kinematics is about reconstructing body motion from position marker data, not really about modeling. For example, glue some tennis balls to a person's arms and legs, track their position from video of the person walking around, and use inverse kinematics to reconstruct their joint angles (their skeletal pose) across time. It's also possible to do this with marker-free methods.

Inverse dynamics takes the kinematics data from above and, in combination with ground reaction forces measured from a force plate (or instrumented footwear, etc.), calculates the forces and moments on each joint. Since control of the human musculoskeletal system is over-determined (the same motion, forces, and moments can be produced by multiple muscle activation patterns), EEG data or even ultrasound elastography is sometimes used to better constrain estimates of muscle activation patterns.

In your example the usual approach would be to use (elements of) the above methods to find out if a patient had unusual motion patterns, like the suspected abnormal leg motion in your back pain patient. Statistics comes into play once you have population data to classify as "good" or "bad", and when you're trying to determine if the hypothesized relationships between symptoms and particular motion / muscle activation patterns genuinely exist. Of course, it's fine to try different approaches (but don't forget to obtain IRB review and comply with the various regulations on human subjects research).

Re: Ask HN: What problem are you close to solving and how can we help?

#480

Post by flir »

jordwest wrote: post #430
flir wrote: post #325

Earlier quoted context omitted.

The people I want to talk to are on facebook groups (my hobbies seem to be "old people" hobbies). I think you're suffering from network effects. Sooooo..... StackOverflow solved it by starting with a vertical the founders had a lot of social juice in, and spreading in to other verticals. Possibly also by focusing very tightly on "questions and answers". So my suggestion is "overfocus". If the big platforms have a wea…

Great point about starting with a specific vertical. Creator communities (youtubers etc) is an area I had been thinking to focus on, though this space is mostly dominated by Discord at the moment. > Centralised always wins My dream isn’t necessarily to win in a financial/monopolistic sense, but rather to build a compelling enough alternative to the centralised systems that have lost their way thanks to incentives tha…

I've thoguht about this for a couple of days, and I want you to understand I'm coming from a place of kindness - I want you to succeed.

Ok, so. The problem you're trying to solve is "build a community that is prepared to contribute financially to the running of the site" (correct me if I'm wrong).

Distributed is one possible solution to this problem. You're in love with that solution and its time to murder your darlings. Sit down, brainstorm five other possible solutions, and honestly assess which one solves your problem best.

I think you'll have a hard time beating a subscription model.

Post reply on HN