strategies to make your mobile apps feel all the feels!

Boost Your Apps' Emotional Intelligence

Jen Looper

Progress

Senior Developer Advocate

Help!

My apps are stupid and boring

"Make Your App Smarter"

Let's build an empathetic recipe app!

• An IoT integration so your app can 'feel' and recommend
• A way for your app to analyze food and suggest recipes to cook
• A way for your app to analyze composed dishes and determine whether they might be easy to prepare

Tools:

Let's talk about NativeScript

NativeScript is…

an open source framework for building truly native mobile apps with JavaScript. Use web skills, like TypeScript, Angular and CSS, and get native UI and performance on iOS and Android.

NativeScript is the best tool for cross-platform native app development 🎉

Rich, animated, “no compromise” native UI

(with shared UI code)

You know JavaScript? You know NativeScript! 

Write once...

Craft the UI with XML

Built plugins with native libraries

...or use the Marketplace for plugins

NativeScript community Slack channel

Presenting: QuickNoms

Powered by Firebase & NativeScript

QuickNoms.com

Algolia search

Firebase Remote Config marquee

Move from a simple master/detail app to...

Make your app 'sensitive'

Build an IoT integration to craft a recipe recommender based on room temperature

Add a sensor

Build the device

wifi-connected Particle Photon + temperature sensor - about $25 total

Flash code to the Photon

Build webhook

Webhook writes to Firebase

app consumes data and reacts

Select recipes tagged as 'hot' or 'cold' - atmosphere type recipes

Observable subscribes to

temperature saved to Firebase

 ngOnInit(): void {
        this.recipesService.getTemperatures(AuthService.deviceId).subscribe((temperature) => {           
            this.temperature$ = temperature[0].temperature;            
            this.getRecommendation(this.mode)                                                  
        })
    }

    getRecommendation(mode){
       
        if (mode == 'F'){
            if (Number(this.temperature$) > 70) {
                this.gradient = this.hotGradient;
                this.recommendation = this.hotRecommendation;            
            } 
            else {
                this.gradient = this.coolGradient;
                this.recommendation = this.coolRecommendation;                           
            }
        }
...

Scale the idea

demo

Machine Learning + Mobile = ❤️

think of the possibilities for photos, video, audio

not

What even is machine learning?

a way to give “computers the ability to learn without being explicitly programmed.”

Machine Learning is:

"A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E.” (Tom Mitchell, 1997).

How to make a machine learn*

Gather a lot of data (images, sounds)

• The training set is categorized (sorted by hand or by machine)
• The test set is uncategorized

*"supervised learning"

ML in the wild

Good uses of ML

Scary uses of ML

good and bad?

MIT students used mapping data and crafted an algorithm to optimize school bus routes

DIY Machine Learning is hard

you need a lot of firepower & skillz

probably not!

might be!

takePhoto() {
        
        const options: camera.CameraOptions = {
            width: 300,
            height: 300,
            keepAspectRatio: true,
            saveToGallery: false
        };

        camera.takePicture(options)
        .then((imageAsset: ImageAsset) => {
            this.processRecipePic(imageAsset);
        }).catch(err => {
            console.log(err.message);
        });
    
    }

    public queryClarifaiAPI(imageAsBase64):Promise<any>{
        return http.request({
            url: AuthService.clarifaiUrl,
            method: "POST",
            headers: {
                "Content-Type": "application/json",
                 "Authorization": "Key " + AuthService.clarifaiKey,
            },
            content: JSON.stringify({
                "inputs": [{
                    "data": {
                        "image": {
                            "base64": imageAsBase64
                        }
                    }
                }]
            })
        })
      .then(function (response) {
          return response
        }
      )}

.then(res => {
   this.loader.hide();
      try {
          let result = res.content.toJSON();
          let tags = result.outputs[0].data.concepts.map( mc => mc.name + '|' + mc.value );
          let ingredients = [];
          tags.forEach(function(entry) {
              let prob = entry.split('|');
              prob = prob[1];
              let ingred = entry.split('|');
                 if(prob > 0.899){
                    ingredients.push(ingred[0])
                 }
                                    
              });
            //there should be between four and eight discernable ingredients                     
            if (ingredients.length >= 4 && ingredients.length <= 8) {
               alert("Yes! This dish might qualify as a QuickNom! It contains "+ingredients)
            }
            else {
               alert("Hmm. This recipe doesn't have the qualifications of a QuickNom. 
                    Try again!")
            }
       }

if between 4 & 8 ingredients are listed with over .899 certainty,

it's a QuickNom!

QuickNom dishes have a few easy-to-see, simple ingredients

Use Google's Vision API to match images with recipes

• Label Detection
• Explicit Content Detection
• Logo Detection
• Landmark Detection
• Face Detection
• Web Detection (search for similar)

takePhoto() {
        
        const options: camera.CameraOptions = {
            width: 300,
            height: 300,
            keepAspectRatio: true,
            saveToGallery: false
        };

        camera.takePicture(options)
        .then((imageAsset: ImageAsset) => {
            this.processItemPic(imageAsset);
        }).catch(err => {
            console.log(err.message);
        });
    
    }

public queryGoogleVisionAPI(imageAsBase64: string):Promise<any>{
        return http.request({
            url: "https://vision.googleapis.com/v1/images:annotate?key="+AuthService.googleKey,
            method: "POST",
            headers: {
                "Content-Type": "application/json",
                "Content-Length": imageAsBase64.length,
            },
            content: JSON.stringify({
                "requests": [{
                "image": {
                "content": imageAsBase64 
                },
                "features" : [
                    {
                        "type":"LABEL_DETECTION",
                        "maxResults":1
                    }
                ]                      
            }]
        })
      })
      .then(function (response) {
          return response
        }
      )}

this.mlService.queryGoogleVisionAPI(imageAsBase64)
    .then(res => {
        let result = res.content.toJSON();
        this.ingredient = result.responses[0].labelAnnotations.map( mc => mc.description );                                                               
        this.ngZone.run(() => {
            this.searchRecipes(this.ingredient)
        })
    });

DIY machine learning

made a little easier!

Now landed in iOS 11: Core ML

Train a model, let Core ML process it for your app on device

TensorFlow Mobile

Designed for low-end Androids, works for iOS and Android

New! Hot! TensorFlow Lite!

next-gen version of TensorFlow for mobile: 11/17 developer release

"on-device machine learning inference with low latency and a small binary size."

Featuring:

• a new model file format, based on "FlatBuffers" - smaller/faster than ProtocolBuffers
• new mobile-optimized interpreter
• an interface to leverage hardware acceleration (Android)
• small footprint! 200-300kb!

TensorFlow on iOS