DFTerNet improves human activity recognition on portable devices with 2-bit quantization and dynamic fusion.
problem Resource constraints and unequal fusion strategies limit practical human activity recognition on portable devices.
method 2-bit Convolutional Neural Networks with dynamic fusion strategies for different activity types.
result Exceeds baseline model performance by up to ~5% on OPPORTUNITY and PAMAP2 datasets.
A method distills GANs for mobile devices, reducing computation and storage.
problem Heavy computation and storage cost of GANs on mobile devices.
method Knowledge distillation to train a smaller generator with inherited information from a larger teacher generator, including a discriminator.
result Portable GAN models with strong performance achieved.
This paper proposes a method to embed teacher knowledge into a student network without increasing parameters.
problem The need for portable neural networks on mobile devices with limited resources.
method Feature embedding approach to distill knowledge from a teacher network to a student network without introducing new parameters.
result The proposed method maintains the performance of the teacher network while significantly reducing computational and storage complexity.
Paper analyzes GPS data to identify POIs and user similarities.
problem Analyzing GPS data for meaningful places and user profiles.
method Data mining algorithms applied to raw GPS data.
result Steps to identify POIs and user similarities are satisfactory.
Relay simplifies deep learning compilation across diverse hardware.
problem Challenges in extending DL frameworks to diverse models and hardware.
method Relay introduces a unified, expressive intermediate representation and extension mechanisms for hardware portability.
result Relay achieves competitive performance across various hardware platforms.
A low-cost, robust, and simple mechanism to measure hemoglobin would play a critical role in the modern health infrastructure. Consistent sample acquisition has been a long-standing technical hurdle for photometer-based portable hemoglobin detectors which rely on micro cuvettes and dry chemistry. Any particulates (e.g.…
Deep learning detects pneumonia with 36x compression on low-power devices.
problem High accuracy pneumonia detection on low-power embedded devices.
method Structured weight pruning method for compression and maintaining accuracy.
result Up to 36x compression ratio with no accuracy loss.
CodeReef enables sharing ML models across platforms efficiently.
problem Sharing and deploying ML models across different systems efficiently.
method Developed an open platform to share ML components, automate deployment, and benchmark models.
result Demonstrated efficient deployment and benchmarking of ML models across diverse platforms.
Simplified EEG analysis improves Parkinson's disease detection.
problem Improving accuracy in EEG-based Parkinson's disease diagnosis.
method Binary electrode grouping, Tsallis Entropy, and dual ec/eo EEG states.
result Binary grouping retains enough information for HC vs PD discrimination.
Proposes privacy-preserving sensor data transformations to prevent user re-identification and sensitive activity inference.
problem Privacy threats from shared sensor data and potential user re-identification.
method Mechanisms to transform sensor data to eliminate patterns for re-identification and sensitive activity inference, while maintaining minor utility loss.
result Reduced user re-identification accuracy to random guess level and prevented inference of sensitive activities.
DataLearner simplifies data mining on Android devices.
problem Lack of general-purpose data-mining tools for mobile devices.
method Augments Weka engine with Charles Sturt University algorithms, providing 40 mining algorithms.
result Delivers classification accuracy similar to PCs/laptops with acceptable speed and battery life.
Anonymizes sensor data to protect user privacy.
problem Protecting user privacy from motion sensor data.
method Information-theoretic approach and multi-objective loss function for deep autoencoders.
result Anonymized sensor data preserves activity recognition accuracy above 92% while keeping user identification accuracy below 7%.
We design, conduct and present the results of a highly personalized baseline emotion recognition experiment, which aims to set reliable ground-truth estimates for the subject's emotional state for real-life prediction under similar conditions using a small number of physiological sensors. We also propose an adaptive st…
New method quantizes neural networks for mobile devices.
problem High computational and memory costs of deep neural networks.
method Formulates quantization as a differentiable function.
result Quantization networks outperform state-of-the-art methods.
Automated VOC classification using embedded machine learning.
problem Classifying volatile organic compounds (VOCs) from electronic nose data.
method Embedded machine learning algorithm on Arduino Uno for VOC detection.
result 99% classification accuracy achieved in embedded solution.
Framework learns portable representations for diverse tasks.
problem Creating task-independent abstract representations for diverse environments.
method Autonomously learns portable representations in egocentric space.
result Portable representations enable task-independent planning and transfer.
Hand-held system translates foreign menus for diet management.
problem Translation ambiguities and context-specific information for diet management.
method Portable multimedia device, machine translation, context-specific corpora, pre-processing steps, multimedia information.
result Higher accuracy and instant translations compared to Google Translate.
Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems. However, training models directly with coarsely quantized weights is a key step towa…
A framework uses deep learning for activity recognition in IoT devices.
problem Activity recognition in IoT devices without physical contact.
method Background subtraction followed by 3D-Convolutional Neural Networks.
result Enhanced activity recognition using small IoT devices.
DAFL learns efficient neural networks without training data.
problem Training data unavailable for deep networks.
method Generative adversarial networks (GANs) to create training samples.
result Achieves high accuracy (92.22%) on CIFAR-10 dataset.
swTVM optimizes deep learning code for Sunway processors.
problem Efficiently compiling deep learning models for Sunway processors.
method Extends TVM to support Sunway, leveraging architecture features.
result 1.79x improvement on average across benchmarks.
New attacks exploit neural network energy and latency, increasing costs by 10-200x.
problem Energy and latency vulnerabilities in neural networks.
method Crafted sponge examples to maximize energy and latency.
result Adversaries can increase energy consumption by 10-200x and delay decisions.
ECC compresses DNNs for energy-constrained devices like UAVs and smartphones.
problem Energy-constrained deep neural networks in vision applications.
method ECC uses a bilinear regression model to estimate DNN energy consumption and optimizes compression to meet energy constraints.
result ECC achieves higher accuracy under the same or lower energy budget compared to state-of-the-art techniques.
Recurrent neural networks have achieved excellent performance in many applications. However, on portable devices with limited resources, the models are often too large to deploy. For applications on the server with large scale concurrent requests, the latency during inference can also be very critical for costly comput…
A simple encoder and complex decoder for secure image encryption and decryption.
problem Secure and efficient image encryption and decryption.
method Uses a shallow encoder neural network for encryption and a deep decoder for decryption, trained independently.
result Decrypted images are nearly identical to the original, demonstrating the effectiveness of the framework.
Paper proposes a capsule attention mechanism for EEG-EOG vigilance estimation.
problem Driver vigilance estimation for safer transportation.
method Capsule attention mechanism following LSTM network for multimodal EEG-EOG analysis.
result Capsule attention improves vigilance estimation robustness and accuracy.
Paper proposes a method to compress deep learning models using PU setting and cloud data.
problem Compression and acceleration of deep learning models on portable devices.
method Positive-Unlabeled (PU) setting, attention-based multi-scale feature extractor, robust knowledge distillation.
result An efficient model can be obtained using only 8% of ImageNet data.
We investigated publicly reported security breaches of internal controls in corporate systems to determine whether SOX assessments are information bearing with respect to breaches which can lead to materially significant losses and misstatements. SOX Section 404 adverse decisions on effectiveness of controls occurred i…
Mosquitoes are a major vector for malaria, causing hundreds of thousands of deaths in the developing world each year. Not only is the prevention of mosquito bites of paramount importance to the reduction of malaria transmission cases, but understanding in more forensic detail the interplay between malaria, mosquito vec…
We provide complete source code for building a fundamental industry classification based on publically available and freely downloadable data. We compare various fundamental industry classifications by running a horserace of short-horizon trading signals (alphas) utilizing open source heterotic risk models (https://ssr…
FedZKT enables resource-constrained devices to participate in federated learning with heterogeneous models.
problem Inequality in resource allocation hinders participation from resource-constrained devices in federated learning.
method Zero-shot knowledge transfer through a server-assigned distillation process.
result FedZKT effectively transfers knowledge across heterogeneous on-device models without requiring comparable local training efforts.
On-device federated learning updates edge models by exchanging trained results.
problem Limited training data at edge devices due to model drift.
method OS-ELM for sequential training and autoencoder for anomaly detection, combined with federated learning.
result The proposed approach produces a merged model as accurately as traditional methods with lower costs.
Deep learning identifies unknown IoT devices in network traffic.
problem Unauthorized IoT devices pose security risks in BYOD environments.
method Deep learning applied to network traffic images for IoT device identification.
result Over 99% accuracy in identifying 10 IoT devices and non-white-listed devices.
A method for trust evaluation of devices in human-device coexistence systems.
problem Efficient trust evaluation of devices in systems with diverse physical and social attributes.
method Canonical correlation analysis-enhanced hypergraph self-supervised learning (HSLCCA).
result The proposed HSLCCA method significantly outperforms baseline algorithms in identifying trusted devices.
Two approaches scale up DNN optimization for diverse edge devices.
problem Optimizing DNNs for edge devices with varying performance requirements.
method Reuse performance predictors on proxy devices and build scalable predictors.
result Optimized DNN designs for many different edge devices without lengthy optimization.
This paper optimizes how deep learning models are distributed across different devices.
problem Optimizing how large, complex neural networks are split across multiple devices.
method Identified and solved an optimization problem for device placement of DNN operators.
result Automated algorithms that solve the device placement problem for modern pipelined settings.
Survey on-device ML challenges and future directions.
problem Training machine learning models on-device with limited resources.
method Reformulated as resource constrained learning, comparing techniques from various AI areas.
result Identification of open challenges and future research directions.
This work proposes a complete 8-bit quantization framework for large-scale deep neural networks.
problem Training large-scale deep neural networks with high performance and low memory footprint.
method WAGEUBN framework that quantizes all data paths including weights, activations, gradients, errors, updates, and batch normalization.
result Achieves competitive accuracy on the ImageNet dataset using only 8-bit integers.
Distributed learning adapts to diverse devices, improving performance.
problem Training neural networks on devices with varying capabilities and resources.
method Each device trains a customized neural network, sharing parameters with others.
result Achieves higher rewards on more powerful devices without sacrificing weaker ones.
Flexible device participation improves federated learning convergence.
problem Strict device participation limits federated learning reach.
method Analytical results and new aggregation scheme for flexible participation.
result Convergence improved with flexible device participation.
New method reduces fine-tuning cost for reused models.
problem Repeating fine-tuning costs with outdated foundation models.
method Portable Reward Tuning (PRT) trains a reward model to maximize the same loss function as fine-tuning.
result PRT achieves comparable accuracy to inference-time tuning with less inference cost.
ProGraML uses graph-based machine learning to improve program optimization and analysis.
problem Improving program optimization and analysis with machine learning.
method Low-level, language agnostic graph representation and message passing neural networks.
result ProGraML achieves an average 94.0 F1 score on a benchmark dataset, significantly outperforming state-of-the-art approaches.
A real-time context-aware system for IoT using mobile devices.
problem Challenges in running machine learning on mobile devices.
method Developed a context-learning algorithm for mobile devices that updates itself periodically from the server.
result Achieved mean accuracy of 97.51% with only 11ms execution time.
Paper optimizes neural architectures for multiple device constraints.
problem NAS ignores device constraints like latency and energy.
method Developed MONAS and DPP-Net for multi-objective optimization.
result Found Pareto-optimal architectures for various devices.
Framework simplifies AI access for all.
problem AI's concentration of power leads to inequalities.
method Develops a Python framework for democratizing AI.
result Single interface for various AI solutions.
The paper optimizes neural network inference on mobile GPUs.
problem Limited computing power and thermal constraints on mobile CPUs.
method Leverage mobile GPUs for neural network inference.
result Real-time inference of deep neural networks on Android and iOS devices.
Semi-decentralized federated learning combines device-to-server and device-to-device communications for faster convergence.
problem Faster convergence in federated learning with decentralized model training.
method Two timescale hybrid federated learning (TT-HF) with cooperative D2D model aggregations.
result Achieves sublinear convergence rate of O(1/t) with adaptive control algorithm.
This paper optimizes AI inference on edge devices with reduced communication and computation costs.
problem Efficiently performing AI inference on resource-constrained edge devices with reduced communication and computation costs.
method A three-step framework for effective inference: model split point selection, communication-aware model compression, and task-oriented encoding of intermediate features.
result Our proposed framework achieves a better trade-off and significantly reduces inference latency compared to baseline methods.