Episodes

  • How Mobile Apps Use On-Device AI for Real-Time Sleep Apnea Detection

    How Mobile Apps Use On-Device AI for Real-Time Sleep Apnea Detection
    Jun 29 2026
    In this episode of Mobile Development with Fexingo, Lucas and Luna dive into how modern mobile apps use on-device AI to detect sleep apnea in real time. They explore the Apple Watch's 2024 apnea detection feature that led to a flood of third-party apps, the technical challenge of processing blood oxygen and movement data locally on a smartphone or wearable, and the regulatory hurdles that developers face. Lucas breaks down the key sensors—pulse oximetry and accelerometer—and how on-device neural networks distinguish apnea events from normal breathing pauses. Luna raises user privacy concerns and the risk of false positives. The episode also touches on how the 2023 FDA clearance of the first over-the-counter sleep apnea app opened the floodgates. Perfect for mobile developers interested in health tech, edge AI, or sensor fusion. #SleepApnea #OnDeviceAI #HealthTech #MobileDev #AppleWatch #PulseOximetry #SensorFusion #EdgeAI #Privacy #FDAClearance #RealTimeAI #Wearables #iOS #Android #Technology #FexingoBusiness #BusinessPodcast #MobileDevelopment Keep every episode free: buymeacoffee.com/fexingo
    Show More Show Less
    9 mins
  • How Mobile Apps Use On-Device AI for Real-Time Skin Cancer Screening

    How Mobile Apps Use On-Device AI for Real-Time Skin Cancer Screening
    Jun 28 2026
    Episode 79 of Mobile Development with Fexingo dives into how on-device AI is enabling real-time skin cancer screening directly from a smartphone camera. Lucas and Luna explore the technical architecture behind apps like SkinCheck and DermaScan, which use convolutional neural networks (CNNs) trained on dermatoscopic images to classify moles and lesions in under two seconds. They discuss the trade-offs between model size and accuracy, the challenge of dataset diversity, and how Apple's Core ML and Google's ML Kit make deployment feasible on consumer devices. The episode also touches on regulatory hurdles, false positive rates, and why privacy advocates favor on-device processing over cloud-based diagnosis. Specific examples include a 2025 study showing 92% sensitivity for melanoma detection on an iPhone 16 Pro, and the open-source model MobileNetV3-Skin. Perfect for developers interested in medical AI applications. #OnDeviceAI #MobileDevelopment #SkinCancerScreening #CoreML #MLKit #ConvolutionalNeuralNetworks #MedicalAI #Dermatology #AIInHealthcare #iPhone16Pro #MobileNetV3 #PrivacyFirst #DigitalHealth #RealTimeAI #AppDevelopment #Technology #FexingoBusiness #BusinessPodcast Keep every episode free: buymeacoffee.com/fexingo
    Show More Show Less
    9 mins
  • How Mobile Apps Use On-Device AI for Real-Time Music Transcription

    How Mobile Apps Use On-Device AI for Real-Time Music Transcription
    Jun 28 2026
    In this episode of Mobile Development with Fexingo, Lucas and Luna dive into how modern mobile apps are using on-device AI to transcribe music in real time—converting live audio from a guitar, piano, or even a full song into sheet music or MIDI data. They focus on a specific case: the open-source framework Basic Pitch by Spotify, which has been adapted for mobile. Lucas explains how these models run entirely on the phone's neural engine, with latency under 100 milliseconds, and privacy advantages. They compare it to cloud-based solutions like Google's Magenta, discuss the Apple Neural Engine's role in Core ML, and explore trade-offs between accuracy and speed. Luna brings up practical use cases for musicians learning by ear, and they touch on how this technology could integrate with apps like GarageBand or third-party tuners. The episode also includes a brief, natural donation segment supporting ad-free production. Tune in for a focused, technical conversation that leaves you with a concrete understanding of real-time music transcription on mobile. #OnDeviceAI #MusicTranscription #BasicPitch #Spotify #CoreML #AppleNeuralEngine #MobileDevelopment #iOS #Android #RealTimeAudio #MIDI #SheetMusic #MachineLearning #GarageBand #Magenta #Google #Technology #FexingoBusiness Keep every episode free: buymeacoffee.com/fexingo
    Show More Show Less
    9 mins
  • How Mobile Apps Use On-Device AI for Real-Time Handwriting Recognition

    How Mobile Apps Use On-Device AI for Real-Time Handwriting Recognition
    Jun 27 2026
    In this episode of Mobile Development with Fexingo, Lucas and Luna explore how on-device AI is enabling real-time handwriting recognition in mobile apps. They focus on Apple's PencilKit and the MyScript SDK, discussing the shift from cloud-based OCR to on-device neural networks that process strokes as you write. Lucas explains how transformer models now run on the Neural Engine, achieving latency under 10 milliseconds, and why this matters for note-taking apps and form-filling. The hosts also touch on the trade-offs: accuracy versus speed, and the challenge of recognizing cursive handwriting versus print. They briefly mention a recent update to Nebo that uses on-device AI to convert handwritten math equations to LaTeX. A practical episode for developers building apps that need to interpret handwriting without sending data to the cloud. #OnDeviceAI #HandwritingRecognition #ApplePencilKit #MyScriptSDK #NeuralEngine #TransformerModels #RealTimeRecognition #MobileDevelopment #iOS #Android #NoteTakingApps #Nebo #LaTeX #OCR #Technology #FexingoBusiness #BusinessPodcast #MobileAI Keep every episode free: buymeacoffee.com/fexingo
    Show More Show Less
    10 mins
  • How Mobile Apps Use On-Device AI for Real-Time Text-to-Speech on Device

    How Mobile Apps Use On-Device AI for Real-Time Text-to-Speech on Device
    Jun 27 2026
    In this episode, Lucas and Luna explore how on-device AI is transforming text-to-speech in mobile apps, analyzing the case of a popular reading app that replaced cloud-based TTS with a neural engine running entirely on the phone. They discuss the latency improvements—from 500 milliseconds down to 50 milliseconds—and the privacy benefits of keeping audio synthesis local. The conversation also covers the trade-offs in voice quality, the role of custom neural voices trained on small datasets, and how this shift is enabling new use cases like offline audiobook generation and real-time accessibility features. A balanced look at what's gained and what's lost when speech synthesis moves off the cloud. #OnDeviceAI #TextToSpeech #MobileApps #NeuralEngine #Privacy #Accessibility #Latency #SpeechSynthesis #OfflineAI #VoiceCloning #NeuralTTS #MobileDevelopment #iOS #Android #Technology #FexingoBusiness #BusinessPodcast #AIOnEdge Keep every episode free: buymeacoffee.com/fexingo
    Show More Show Less
    8 mins
  • How Mobile Apps Use On-Device AI for Real-Time Sports Pose Analysis

    How Mobile Apps Use On-Device AI for Real-Time Sports Pose Analysis
    Jun 26 2026
    In this episode of Mobile Development with Fexingo, Lucas and Luna dive into how modern mobile apps use on-device AI to analyze sports poses in real time. They break down the technology behind apps like HomeCourt and SwingVision, which track basketball shots and tennis swings without sending video to the cloud. Lucas explains the key role of convolutional neural networks and pose estimation models like MoveNet and PoseNet, and how they run efficiently on smartphone GPUs and neural processing units. The hosts discuss the latency challenges of real-time feedback — how developers optimize for under 30 milliseconds to give athletes immediate corrections. They also touch on data privacy as a major advantage of on-device processing, and how sports analytics is expanding from pro training to casual fitness. A concrete example: a youth soccer app that analyzes kicking form from a phone camera. This episode is perfect for mobile developers and sports tech enthusiasts looking to understand the intersection of computer vision and edge AI. #SportsPoseAnalysis #OnDeviceAI #MobileApps #ComputerVision #PoseEstimation #MoveNet #PoseNet #RealTimeAI #HomeCourt #SwingVision #EdgeAI #NeuralProcessingUnit #GPUMachineLearning #SportsTech #Technology #FexingoBusiness #BusinessPodcast #MobileDevelopment Keep every episode free: buymeacoffee.com/fexingo
    Show More Show Less
    9 mins
  • How Mobile Apps Use On-Device AI for Real-Time Plant Disease Detection

    How Mobile Apps Use On-Device AI for Real-Time Plant Disease Detection
    Jun 26 2026
    Lucas and Luna explore how on-device machine learning on smartphones now identifies plant diseases in real time. They break down the technical pipeline: how models are trained on thousands of leaf images, compressed via quantization and pruning to run inference in under 200 milliseconds on a phone's neural engine, and integrated into camera apps for instant diagnosis. They discuss real-world deployments from a 2025 pilot in Kenya's smallholder farms using the PlantVillage dataset, where detection accuracy hit 94 percent offline. The hosts also touch on the constraints—limited labeled data for rare diseases, the trade-off between model size and precision, and how developers handle false positives. No cloud dependency means rural farmers without connectivity still get results. The episode closes with a look at how Apple's Core ML and Google's MediaPipe are lowering the barrier for integrating custom vision models into any app. Specific, technical, and grounded in real impact. #PlantDiseaseDetection #OnDeviceAI #MobileMachineLearning #CoreML #MediaPipe #AgricultureTech #SmartphoneVision #RealTimeInference #ModelQuantization #EdgeAI #TechForGood #PlantVillage #KenyaFarming #CNN #NeuralEngine #iOSDevelopment #AndroidDevelopment #FexingoBusiness Keep every episode free: buymeacoffee.com/fexingo
    Show More Show Less
    10 mins
  • How Mobile Apps Detect Falls Using On-Device AI

    How Mobile Apps Detect Falls Using On-Device AI
    Jun 25 2026
    In Episode 73 of Mobile Development with Fexingo, Lucas and Luna explore how on-device AI enables real-time fall detection in mobile apps. They break down the sensor fusion pipeline — accelerometer, gyroscope, and machine learning models running locally — using Apple's Fall Detection on Apple Watch and Google's Safety Detection API on Android as concrete examples. They discuss the technical challenges: distinguishing a fall from a sudden drop or a hard sit, preserving battery life while the model listens continuously, and the privacy advantage of keeping all data on device. Lucas shares a stat: Apple reports that its fall detection algorithm triggers an emergency call in under 60 seconds for users over 65 who fall and remain immobile. The episode also touches on how developers can implement fall detection today using Core ML and TensorFlow Lite, and the ethical considerations of always-on sensors. By the end, you'll understand why this is one of the most impactful mobile AI applications in 2026. #OnDeviceAI #FallDetection #MobileApps #AppleWatch #GoogleSafetyDetection #CoreML #TensorFlowLite #MachineLearning #SensorFusion #Accelerometer #Gyroscope #PrivacyFirst #ElderCare #HeathTech #MobileDev #Technology #FexingoBusiness #BusinessPodcast Keep every episode free: buymeacoffee.com/fexingo
    Show More Show Less
    13 mins