Category:Semester Thesis
From iis-projects
The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.
Semester thesis at the IIS is for 1-3 students for a duration of 14 weeks and should take 50% of the time of the students. The available projects in this category are meant primarily for a semester thesis. However if you are interested in the topic, you can discuss with the supervisor, in most cases the content of the project can be expanded to fit a master thesis as well.
Pages in category "Semester Thesis"
The following 200 pages are in this category, out of 524 total.
(previous page) (next page)F
- Fast Simulation of Manycore Systems (1S)
- Fast Wakeup From Deep Sleep State
- Feature Extraction and Architecture Clustering for Keyword Spotting (1S)
- Feature Extraction for Speech Recognition (1S)
- Feature Extraction with Binarized Descriptors: ASIC Implementation and FPGA Environment
- FFT-based Convolutional Network Accelerator
- Finalizing and Releasing Our Open-source AXI4 IPs (1-3S/B/2-3G)
- Fitting Power Consumption of an IP-based HLS Approach to Real Hardware (1-3S)
- Flexfloat DL Training Framework
- Floating-Point Divide & Square Root Unit for Transprecision
- FPGA mapping of RPC DRAM
- FPGA System Design for Computer Vision with Convolutional Neural Networks
- Freedom from Interference in Heterogeneous COTS SoCs
G
H
- Hardware Accelerator for Model Predictive Controller
- Hardware Accelerators for Lossless Quantized Deep Neural Networks
- Hardware Constrained Neural Architechture Search
- Hardware Support for IDE in Multicore Environment
- Hardware/software codesign neural decoding algorithm for “neural dust”
- HERO: TLB Invalidation
- Heroino: Design of the next CORE-V Microcontroller
- High Performance Digitally-Assisted Time Domain ADC Design for DPLL used in Cellular IOT
- High Power Efficient Digitally Controlled Oscillator Design for Cellular IOT
- High-Speed Digital-to-Analog Converter (DAC) for massive MIMO testing in 65nm CMOS
- High-Speed SAR ADC for next generation wireless communication in 12nm FinFET
- High-speed Scene Labeling on FPGA
- High-throughput Embedded System For Neurotechnology in collaboration with INI
- High-Throughput Hardware Implementations of Authenticated Encryption Algorithms
- Huawei Research
- Human Intranet
- Hybrid Analog/Digital Leveling Loop for Very-Low-Distortion Oscillator
- Hyper Meccano: Acceleration of Hyperdimensional Computing
- Hyper-Dimensional Computing Based Predictive Maintenance
- Hypervisor Extension for Ariane (M)
I
- Ibex: Bit-Manipulation Extension
- Ibex: FPGA Optimizations
- Ibex: Tightly-Coupled Accelerators and ISA Extensions
- IBM Research
- Image and Video Processing
- Image Sensor Interface and Pre-processing
- Implementation of a Cache Reliability Mechanism (1S/M)
- Implementation of a Coherent Application-Class Multicore System (1-2S)
- Implementation of a Heterogeneous System for Image Processing on an FPGA (S)
- Implementation of an Accelerator for Retentive Networks (1-2S)
- Implementation of an AES Hardware Processing Engine (B/S)
- Implementation of the RISC-V Bit Manipulation (RVB) extensions for our RI5CY core
- Implementation of the RISC-V Bit Manipulation (RVB) extensions for our RISC-V core
- Implementing A Low-Power Sensor Node Network
- Implementing Configurable Dual-Core Redundancy
- Implementing DSP Instructions in Banshee (1S)
- Implementing Hibernation on the ARM Cortex M0
- Improved Collision Avoidance for Nano-drones
- Improved Reacquisition for the 5G Cellular IoT
- Improved State Estimation on PULP-based Nano-UAVs
- Improving Cold-Start in Batteryless And Energy Harvesting Systems
- Improving datarate and efficiency of ultra low power wearable ultrasound
- Improving our Smart Camera System
- Improving Resiliency of Hyperdimensional Computing
- Improving Scene Labeling with Hyperspectral Data
- Improving SystemVerilog Support for Free And Open-Source EDA Tools (1-3S/B)
- In-ear EEG signal acquisition
- Indoor Positioning with Bluetooth
- Indoor Smart Tracking of Hospital instrumentation
- Inductive Charging Circuit for Implantable Devices
- Infrared Wake Up Radio
- Integrating an Open-Source Double-Precision Floating-Point DivSqrt Unit into CVFPU (1S)
- Integrating Hardware Accelerators into Snitch (1S)
- Integrating Ultrasound Technology into a Fitness Tracking Device (1M, 2 B/S)
- Integration Of A Smart Vision System
- Intelligent Disaster Early-Warning System (1-2S/M)
- Intelligent Power Management Unit (iPMU)
- Interference Cancellation for EC-GSM-IoT
- Investigating the Cost of Special-Case Handling in Low-Precision Floating-Point Dot Product Units (1S)
- Investigation of Quantization Strategies for Retentive Networks (1S)
- Investigation of the high-performance multi-threaded OoO IBM A2O Core (1-3S)
- IoT Turbo Decoder
- IP-Based SoC Generation and Configuration (1-3S/B)
L
- Learning at the Edge with Hardware-Aware Algorithms
- Learning Image Compression with Convolutional Networks
- Learning Image Decompression with Convolutional Networks
- Level Crossing ADC For a Many Channels Neural Recording Interface
- LightProbe
- LightProbe - 192cha Multiplexer Stage (Rigid-Flex-PCB Project)
- LightProbe - 200G Remote DMA for GPU FPGA Data Transfers
- LightProbe - CNN-Based-Image-Reconstruction
- LightProbe - Design of a High-Speed Optical Link
- LightProbe - Frontend Firmware and Control Side Channel
- LightProbe - Implementation of compressed-sensing algorithms
- LightProbe - Thermal-Power aware on-head Beamforming
- LightProbe - Ultracompact Power Supply PCB
- LightProbe - WIFI extension (PCB)
- Linux Driver for built-in ADC using DMA and Programmable Real-Time Unit (PRU) support on Beaglebone Black used as embedded HPC-performance-monitoring device
- Linux Driver for fine-grain and low overhead access to on-chip performance counters
- LLVM and DaCe for Snitch (1-2S)
- Low Latency Brain-Machine Interfaces
- Low Power Geolocalization And Indoor Localization
- Low Power Neural Network For Multi Sensors Wearable Devices
- Low Power One bit Microphone for Acoustic Imaging Using A Parallel Processor
- Low Precision Ara for ML
- Low-Dropout Regulators for Magnetic Resonance Imaging
- Low-Energy Cluster-Coupled Vector Coprocessor for Special-Purpose PULP Acceleration
- Low-power Temperature-insensitive Timer
- LTE IoT Network Synchronization
- LTE-Advanced RF Front-end Design in 28nm CMOS Technology
M
- Machine Learning for extracting Muscle features from Ultrasound raw data
- Machine Learning for extracting Muscle features using Ultrasound
- Machine Learning for extracting Muscle features using Ultrasound 2
- Machine Learning on Ultrasound Images
- Manycore System on FPGA (M/S/G)
- Mapping Networks on Reconfigurable Binary Engine Accelerator
- Memory Augmented Neural Networks in Brain-Computer Interfaces
- MemPool on HERO (1S)
- Minimal Cost RISC-V core
- Minimum Variance Beamforming for Wearable Ultrasound Probes
- Mixed-Precision Neural Networks for Brain-Computer Interface Applications
- ML based Quantitative Movement Analysis on a Portable IoT Camera (1-2S/B)
- Model Complexity of Electromagnetic Systems
- Modeling FlooNoC in GVSoC (S/M)
- Modeling High Bandwidth Memory for Rapid Design Space Exploration (1-3S/B)
- Modular Distributed Data Collection Platform
- Monocular Vision-based Object Following on Nano-size Robotic Blimp
- Multi issue OoO Ariane Backend (M)
- Multi-Modal Environmental Sensing With GAP9 (1-2S)
- Multisensory system for performance analysis in ski jumping (M/1-2S/B)
N
- Nanoelectrode array biosensors - programmable non-overlapping clocks generator project
- Neural Architecture Search using Reinforcement Learning and Search Space Reduction
- Neural Network Algorithms and Interfaces with Accelerators for Embedded Platforms with Real World Applications
- Neural Networks Framwork for Embedded Plattforms
- Neuromorphic Intelligence In An Embedded System in Collaboration with AiCTX
- NeuroSoC RISC-V Component (M/1-2S)
- New RVV 1.0 Vector Instructions for Ara
- Next Generation Channel Decoder
- Next Generation Synchronization Signals
- Next-Gen Ultrasound Imaging Systems (Industry Student Projects & PhD Opportunity)
- Noise Figure Measurement for Cryogenic System
- Non-binary LDPC Decoder for Deep-Space Optical Communications
- Non-blocking Algorithms in Real-Time Operating Systems
- NORX - an AEAD algorithm for the CAESAR competition
- Novel Metastability Mitigation Technique
O
- Object Detection and Tracking on the Edge
- On-Board Software for PULP on a Satellite
- On-chip clock synthesizer design and porting
- On-Device Federated Continual Learning on Nano-Drone Swarms
- On-Device Learnable Embeddings for Acoustic Environments
- Online Learning of User Features (1S)
- Open Power-On Chip Controller Study and Integration
- OpenRISC SoC for Sensor Applications
- Optimal routing for 2D Mesh-based Analog Compute-In-Memory Accelerator Architecture (IBM-Zurich)
- Optimizing the Pipeline in our Floating Point Architectures (1S)
- Optogenetics And Game Theory Applied To Small Side Bird Using Smart Sensing
- OTDOA Positioning for LTE Cat-M
- Outdoor Precision Object Tracking for Rockfall Experiments
P
- Passive and Self Sustaining Receivers For On and Intra Body Communication For Wearable Sensors Networks
- Peripheral Event Linking System for Real-time Capable Energy Efficient SoCs
- Physical Implementation of Ara, PULP's Vector Machine (1-2S)
- Physical Implementation of ITA (2S)
- Physical Implementation of MemPool, PULP's Manycore System (1M/1-2S)
- Physics is looking for PULP
- Power Optimization in Multipliers
- Praxisgerechte Berechnung von Switching Noise in VLSI-Schaltungen
- Precise Ultra-low-power Timer
- Predictable Execution on GPU Caches
- PREM Intervals and Loop Tiling
- PREM on PULP
- PREM Runtime Scheduling Policies
- Pressure and acoustic Smart Sensors Network for Wind Turbines Monitoring
- Probing the limits of fake-quantised neural networks
- PULP Freertos with LLVM
- PULP in space - Fault Tolerant PULP System for Critical Space Applications
- PULP-Shield for Autonomous UAV
- PULPonFPGA: Hardware L2 Cache
- PULPonFPGA: Lightweight Virtual Memory Support - Coherency Extensions
- PULPonFPGA: Lightweight Virtual Memory Support - Page Table Walker
- PULPonFPGA: Lightweight Virtual Memory Support - Physically Contiguous Memory
- PULPonFPGA: Lightweight Virtual Memory Support - Software Cache
- PULP’s CLIC extensions for fast interrupt handling
- Pulse Oximetry Fachpraktikum
- PVT Dynamic Adaptation in PULPv3
R
- Radiation Testing of a PULP ASIC
- Radio Signal Direction Detection For Smart Glasses For Augmented Reality Applications
- Reading The GSM Beacon Carrier with OsmocomBB and stoneEDGE
- Real-Time ECG Contractions Classification
- Real-Time Embedded Classification of Neural Activity in Rat Barrel Cortex
- Real-time eye movement analysis on a tablet computer
- Real-time Linux on RISC-V
- Real-Time Motor-Imagery Classification Using Neuromorphic Processor
- Real-Time Optical Flow Using Neural Networks
- Real-Time Pedestrian Detection For Privacy Enhancement
- Realtime Gaze Tracking on Siracusa
- Receiver design for the DigRF 4G high speed serial link
- Reconfigurability of SHA-3 candidates
- RedCap-5G for IOT application on prototype taped-out silicon
- Reliability by Switching the Embedded ISA in Ibex (1-2S/B/1M)
- Resilient Brain-Inspired Hyperdimensional Computing Architectures
- Resource Partitioning of Caches
- Resource Partitioning of RPC DRAM