The application overlays on a map the locations of all “dark” vessels, that have disconnected from the Automatic Identification System (AIS), in addition to those using AIS.
Kategorie: Programming
Kategorien
🦇BigBAT⚡
First completely free bioacoustic analysis tool with included Auto-ID powered by deep neural net BigBAT
Neuroinformatics Project, graded 1.0 (best grade)
The automatic identification of bat species from their echolocation calls is a difficult but crucial task for monitoring bats and the ecosystems they live in. One of the main challenge is the lack of annotated data, since annotating echolocation data requires exceptional expertise and is very time consuming. Here, we experimented with different methods to incorporate unlabeled data to improve the performance of an existing model. We were able to improve performance of mixed macro-F1 by 2.73%, single accuracy by 10.69% and single F1 by 4.96% on a dataset of South African bats from the university of free state (UFS). We also proposed a method called „genus smoothing“, which was able to increase the macro-F1 by 0.47%, single test accuracy by 0.42% and single F1-score
by 4.73%. In addition, we have developed a free bioacoustics analysis tool, including automated identification.
Kategorien
🦇BAT – BioAcoustic Transformer
Bachelor Thesis, graded 1.0 (best grade)
Automatically identifying bat species from their echolocation calls is a difficult but crucial task for monitoring bats and the ecosystem they live in. The main issues are high call variability, similarities between species, interfering calls and lack of annotated data. This thesis proposes a deep learning approach that attempts to tackle these issues by using a Transformer-hybrid architecture that utilizes temporal information and artificially generated interfering calls for multi-label classification. Our method is more efficient than previous methods and has potential for applications in real-time classification scenarios. We were able to achieve a single species accuracy of 88.92% (F1-score of 84.23%) and a multi species macro F1-score of 74.40% on our test set. We compared our method to three other tools on an independent and publicly available dataset, which showed that our method achieved at least 25.82% better accuracy for single species classification and at least 6.9% better macro F1-score for multi species classification. We created a web-demo version with visualization for the multi-label classification and example files on https://bat.hadros.de/. We also created a command-line tool for fast inference on large amounts of data. The entirety of the implementation is opensource.
Kategorien
TachoAnalytics
Mit TachoAnalytics informieren Sie Ihre Fahrer über Verstöße und Fehlbedienungen des Fahrtenschreibers. Sie erhalten eine statistische Auswertung und senden Ihre Belehrung unmittelbar an den betroffenen Fahrer – per SMS, WhatsApp oder App. Die Annahme-Bestätigung durch den Fahrer garantiert Ihnen, dass Sie Ihrer Belehrungs-Pflicht nachgekommen sind.
Kategorien
Talking Timmy
A virtual avatar which face movements are created from an AI.
This was part of a University project. You have to connect to the python server that can be downloaded from github. You then control the avatar using the python GUI. The python program also includes a AIML parser, text to speech and is rasa compatbile.
Kategorien
SoundSquad
Create playlists out of mixed streaming services like Spotify, SoundCloud, YouTube and even your own Storage. Download them and hear them offline. You can create servers and hear music with people who share the same taste. Rate songs, chat and collect points to level up. Create your own playlists and check out playlists of others.
Kategorien
PursuitOfHappiness
Learn about the source of happiness, how to be more thankful, get better sleep and much more. Meditation, inner peace and graditude are key factors for a happy life. Journal your week, create reoccuring events and track your progress over time.
Kategorien
Smart Home Device
Building a prototype smart home device using a ESP32 developement board. For that use I built a library for communication between the ESP32 and the OpenHome server. Using the OpenHome App you can then add your custom smart home device and control the billboard text, turn the LEDs on/off and read the temperature and humidity.
Kategorien
OpenHome
Mit OpenHome ist es möglich einfach eigene Smart Home Geräte zu entwickeln z.B. mit einem Arduino, Raspberry Pi oder ESP32. Mit einer umfangreichen WebSocket und HTTP Schnittstelle ist es sehr einfach ihr Gerät Smart zu machen. Geräte können per App, Alexa oder HomeKit gesteuert werden.