Search

Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs) for question-answer (QA) tasks. The state-of-the-art RAG approaches often use the graph data as the external data since they capture the rich semantic information and link relationships between entities. However, existing graph-based RAG approaches cannot accurately identify the relevant information from the graph and also consume large numbers of tokens in the online retrieval process. To address these issues, we introduce a novel graph-based RAG approach, called Attributed Community-based Hierarchical RAG (ArchRAG), by augmenting the question using attributed communities, and also introducing a novel LLM-based hierarchical clustering method. To retrieve the most relevant information from the graph for the question, we build a novel hierarchical index structure for the attributed communities and develop an effective online retrieval method. Experimental results demonstrate that ArchRAG outperforms existing methods in terms of both accuracy and token cost.

Repository-level code translation refers to translating an entire code repository from one programming language to another while preserving the functionality of the source repository. Many benchmarks have been proposed to evaluate the performance of such code translators. However, previous benchmarks mostly provide fine-grained samples, focusing at either code snippet, function, or file-level code translation. Such benchmarks do not accurately reflect real-world demands, where entire repositories often need to be translated, involving longer code length and more complex functionalities. To address this gap, we propose a new benchmark, named RepoTransBench, which is a real-world repository-level code translation benchmark with an automatically executable test suite. We conduct experiments on RepoTransBench to evaluate the translation performance of 11 advanced LLMs. We find that the Success@1 score (test success in one attempt) of the best-performing LLM is only 7.33%. To further explore the potential of LLMs for repository-level code translation, we provide LLMs with error-related feedback to perform iterative debugging and observe an average 7.09% improvement on Success@1. However, even with this improvement, the Success@1 score of the best-performing LLM is only 21%, which may not meet the need for reliable automatic repository-level code translation. Finally, we conduct a detailed error analysis and highlight current LLMs' deficiencies in repository-level code translation, which could provide a reference for further improvements.

This report details the design and development of a compact high-voltage functional electrical stimulation (FES) device. Unlike conventional FES systems, the proposed design prioritizes user comfort by leveraging rapid switching times to effectively activate muscles while minimizing stimulation of pain receptors. The device is equipped with a high compliance voltage of up to 135 V, enabling its use across various muscle groups and accommodating users with differing skin conductance levels. At the core of the system is a switched capacitor (SC) stimulator, which facilitates fast switching, and a flyback converter that steps up the battery voltage. The design exclusively utilizes off-the-shelf components, significantly reducing prototyping costs. Initially, a large testing board was developed to evaluate the performance of the SC stimulator in comparison with conventional H-bridge-based current-regulated stimulators. Subsequently, a compact, three-board PCB design was created to enable battery-powered operation, making it suitable for wearable applications. The proposed design methodology is broadly applicable to a wide range of neural rehabilitation applications.

Freezing of gait (FoG) is a debilitating symptom of Parkinson's disease (PD). This work develops flexible wearable sensors that can detect FoG and alert patients and companions to help prevent falls. FoG is detected on the sensors using a deep learning (DL) model with multi-modal sensory inputs collected from distributed wireless sensors. Two types of wireless sensors are developed, including: (1) a C-shape central node placed around the patient's ears, which collects electroencephalogram (EEG), detects FoG using an on-device DL model, and generates auditory alerts when FoG is detected; (2) a stretchable patch-type sensor attached to the patient's legs, which collects electromyography (EMG) and movement information from accelerometers. The patch-type sensors wirelessly send collected data to the central node through low-power ultra-wideband (UWB) transceivers. All sensors are fabricated on flexible printed circuit boards. Adhesive gel-free acetylene carbon black and polydimethylsiloxane electrodes are fabricated on the flexible substrate to allow conformal wear over the long term. Custom integrated circuits (IC) are developed in 180 nm CMOS technology and used in both types of sensors for signal acquisition, digitization, and wireless communication. A novel lightweight DL model is trained using multi-modal sensory data. The inference of the DL model is performed on a low-power microcontroller in the central node. The DL model achieves a high detection sensitivity of 0.81 and a specificity of 0.88. The developed wearable sensors are ready for clinical experiments and hold great promise in improving the quality of life of patients with PD. The proposed design methodologies can be used in wearable medical devices for the monitoring and treatment of a wide range of neurodegenerative diseases.

An ultra-wide-band impulse-radio (UWB-IR) transmitter (TX) for low-energy biomedical microsystems is presented. High power efficiency is achieved by modulating an LC tank that always resonates in the steady state during transmission. A new clipped-sinusoid scheme is proposed for on-off keying (OOK)-modulation, which is implemented by a voltage clipper circuit with on-chip biasing generation. The TX is designed to provide a high data-rate wireless link within the 3-5 GHz band. The chip was fabricated in 130nm CMOS technology and fully characterized. State-of-the-art power efficiency of 21.3% was achieved at a data-rate of 230Mbps and energy consumption of 21pJ/b. A bit-error-rate (BER) of less than 10^-6 was measured at a distance of 1m without pulse averaging. In addition, simultaneous wireless powering and VCO-based data transmission are supported. A potential extension to a VCO-free all-wireless mode to further reduce the power consumption is also discussed.

This paper presents the design of a wireless sensor network for detecting and alerting the freezing of gait (FoG) symptoms in patients with Parkinson's disease. Three sensor nodes, each integrating a 3-axis accelerometer, can be placed on a patient at ankle, thigh, and truck. Each sensor node can independently detect FoG using an on-device deep learning (DL) model, featuring a squeeze and excitation convolutional neural network (CNN). In a validation using a public dataset, the prototype developed achieved a FoG detection sensitivity of 88.8% and an F1 score of 85.34%, using less than 20 k trainable parameters per sensor node. Once FoG is detected, an auditory signal will be generated to alert users, and the alarm signal will also be sent to mobile phones for further actions if needed. The sensor node can be easily recharged wirelessly by inductive coupling. The system is self-contained and processes all user data locally without streaming data to external devices or the cloud, thus eliminating the cybersecurity risks and power penalty associated with wireless data transmission. The developed methodology can be used in a wide range of applications.

This paper proposes a deep learning (DL) model for automatic sleep stage classification based on single-channel EEG data. The DL model features a convolutional neural network (CNN) and transformers. The model was designed to run on energy and memory-constrained devices for real-time operation with local processing. The Fpz-Cz EEG signals from a publicly available Sleep-EDF dataset are used to train and test the model. Four convolutional filter layers were used to extract features and reduce the data dimension. Then, transformers were utilized to learn the time-variant features of the data. To improve performance, we also implemented a subject specific training before the inference (i.e., prediction) stage. With the subject specific training, the F1 score was 0.91, 0.37, 0.84, 0.877, and 0.73 for wake, N1-N3, and rapid eye movement (REM) stages, respectively. The performance of the model was comparable to the state-of-the-art works with significantly greater computational costs. We tested a reduced-sized version of the proposed model on a low-cost Arduino Nano 33 BLE board and it was fully functional and accurate. In the future, a fully integrated wireless EEG sensor with edge DL will be developed for sleep research in pre-clinical and clinical experiments, such as real-time sleep modulation.

Closed-loop sleep modulation is an emerging research paradigm to treat sleep disorders and enhance sleep benefits. However, two major barriers hinder the widespread application of this research paradigm. First, subjects often need to be wire-connected to rack-mount instrumentation for data acquisition, which negatively affects sleep quality. Second, conventional real-time sleep stage classification algorithms give limited performance. In this work, we conquer these two limitations by developing a sleep modulation system that supports closed-loop operations on the device. Sleep stage classification is performed using a lightweight deep learning (DL) model accelerated by a low-power field-programmable gate array (FPGA) device. The DL model uses a single channel electroencephalogram (EEG) as input. Two convolutional neural networks (CNNs) are used to capture general and detailed features, and a bidirectional long-short-term memory (LSTM) network is used to capture time-variant sequence features. An 8-bit quantization is used to reduce the computational cost without compromising performance. The DL model has been validated using a public sleep database containing 81 subjects, achieving a state-of-the-art classification accuracy of 85.8% and a F1-score of 79%. The developed model has also shown the potential to be generalized to different channels and input data lengths. Closed-loop in-phase auditory stimulation has been demonstrated on the test bench.

In this report, methods of wireless power transfer of inside a cage is compared and simulated. Software Ansys Electronics Maxwell was used to simulate magnetic coupling of transmitter(s) and receiver with 10mA winding current in the mouse cage.

Parkinson's disease is a common neurological disease, entailing a multitude of motor deficiency symptoms. In this project, we developed a device with an uploaded edge machine learning algorithm that can detect the onset of freezing of gait symptoms in a Parkinson's patient. The algorithm achieved an accuracy of 83.7% in a validation using data from ten patients. The model was deployed in a microcontroller Arduino Nano 33 BLE Sense Board model and validated in real-time operation with data streamed to the microcontroller from a computer.

Recognizing patterns in lung sounds is crucial to detecting and monitoring respiratory diseases. Current techniques for analyzing respiratory sounds demand domain experts and are subject to interpretation. Hence an accurate and automatic respiratory sound classification system is desired. In this work, we took a data-driven approach to classify abnormal lung sounds. We compared the performance using three different feature extraction techniques, which are short-time Fourier transformation (STFT), Mel spectrograms, and Wav2vec, as well as three different classifiers, including pre-trained ResNet18, LightCNN, and Audio Spectrogram Transformer. Our key contributions include the bench-marking of different audio feature extractors and neural network based classifiers, and the implementation of a complete pipeline using STFT and a fine-tuned ResNet18 network. The proposed method achieved Harmonic Scores of 0.89, 0.80, 0.71, 0.36 for tasks 1-1, 1-2, 2-1 and 2-2, respectively on the testing sets in the IEEE BioCAS 2022 Grand Challenge on Respiratory Sound Classification.

Accurate temperature regulation is critical for amperometric DNA analysis to achieve high fidelity, reliability, and throughput. In this work, a 9x6 cell array of mixed-signal CMOS distributed temperature regulators for on-CMOS multi-modal amperometric DNA analysis is presented. Three DNA analysis methods are supported, including constant potential amperometry (CPA), cyclic voltammetry (CV), and impedance spectroscopy (IS). In-cell heating and temperature sensing elements are implemented in standard CMOS technology without post-processing. Using proportional-integral-derivative (PID) control, the local temperature can be regulated to within +/-0.5C of any desired value between 20C and 90C. The two computationally intensive operations in the PID algorithm, multiplication, and subtraction, are performed by an in-cell dual-slope multiplying ADC in the mixed-signal domain, resulting in a small area and low power consumption. Over 95% of the circuit blocks are synergistically shared among the four operating modes, including CPA, CV, IS, and the proposed temperature regulation mode. A 3mmx3mm CMOS prototype fabricated in a 0.13um CMOS technology has been fully experimentally characterized. Each channel occupies an area of 0.06mm2 and consumes 42uW from a 1.2V supply. The proposed distributed temperature regulation design and the mixed-signal PID implementation can be applied to a wide range of sensory and other applications.

Image semantic segmentation technology is one of the key technologies for intelligent systems to understand natural scenes. As one of the important research directions in the field of visual intelligence, this technology has broad application scenarios in the fields of mobile robots, drones, smart driving, and smart security. However, in the actual application of mobile robots, problems such as inaccurate segmentation semantic label prediction and loss of edge information of segmented objects and background may occur. This paper proposes an improved structure of a semantic segmentation network based on a deep learning network that combines self-attention neural network and neural network architecture search methods. First, a neural network search method NAS (Neural Architecture Search) is used to find a semantic segmentation network with multiple resolution branches. In the search process, combine the self-attention network structure module to adjust the searched neural network structure, and then combine the semantic segmentation network searched by different branches to form a fast semantic segmentation network structure, and input the picture into the network structure to get the final forecast result. The experimental results on the Cityscapes dataset show that the accuracy of the algorithm is 69.8%, and the segmentation speed is 48/s. It achieves a good balance between real-time and accuracy, can optimize edge segmentation, and has a better performance in complex scenes. Good robustness is suitable for practical application.

Stimulation of target neuronal populations using optogenetic techniques during specific sleep stages has begun to elucidate the mechanisms and effects of sleep. To conduct closed-loop optogenetic sleep studies in untethered animals, we designed a fully integrated, low-power system-on-chip (SoC) for real-time sleep stage classification and stage-specific optical stimulation. The SoC consists of a 4-channel analog front-end for recording polysomnography signals, a mixed-signal machine-learning (ML) core, and a 16-channel optical stimulation back-end. A novel ML algorithm and innovative circuit design techniques improved the online classification performance while minimizing power consumption. The SoC was designed and simulated in 180 nm CMOS technology. In an evaluation using an expert labeled sleep database with 20 subjects, the SoC achieves a high sensitivity of 0.806 and a specificity of 0.947 in discriminating 5 sleep stages. Overall power consumption in continuous operation is 97 uW., Comment: 8 pages, 9 figures, 2 tables

Compressive sensing (CS) is a signal processing technique that enables sub-Nyquist sampling and near lossless reconstruction of a sparse signal. The technique is particularly appealing for neural signal processing since it avoids the issues relevant to high sampling rate and large data storage. In this project, different CS reconstruction algorithms were tested on raw action potential signals recorded in our lab. Two numerical criteria were set to evaluate the performance of different CS algorithms: Compression Ratio (CR) and Signal-to-Noise Ratio (SNR). In order to do this, individual CS algorithm testing platforms for the EEG data were constructed within MATLAB scheme. The main considerations for the project were the following. 1) Feasibility of the dictionary 2) Tolerance to non-sparsity 3) Applicability of thresholding or interpolation.

Implanted devices providing real-time neural activity classification and control are increasingly used to treat neurological disorders, such as epilepsy and Parkinson's disease. Classification performance is critical to identifying brain states appropriate for the therapeutic action. However, advanced algorithms that have shown promise in offline studies, in particular deep learning (DL) methods, have not been deployed on resource-restrained neural implants. Here, we designed and optimized three embedded DL models of commonly adopted architectures and evaluated their inference performance in a case study of seizure detection. A deep neural network (DNN), a convolutional neural network (CNN), and a long short-term memory (LSTM) network were designed to classify ictal, preictal, and interictal phases from the CHB-MIT scalp EEG database. After iterative model compression and quantization, the algorithms were deployed on a general-purpose, off-the-shelf microcontroller. Inference sensitivity, false positive rate, execution time, memory size, and power consumption were quantified. For seizure event detection, the sensitivity and FPR (h-1) for the DNN, CNN, and LSTM models were 87.36%/0.169, 96.70%/0.102, and 97.61%/0.071, respectively. Predicting seizures for early warnings was also feasible. The implemented compression and quantization achieved a significant saving of power and memory with an accuracy degradation of less than 0.5%. Edge DL models achieved performance comparable to many prior implementations that had no time or computational resource limitations. Generic microcontrollers can provide the required memory and computational resources, while model designs can be migrated to ASICs for further optimization. The results suggest that edge DL inference is a feasible option for future neural implants to improve classification performance and therapeutic outcomes., Comment: 25 pages, 7 figures, 3 tables

Sensory feedback is critical to the performance of neural prostheses that restore movement control after neurological injury. Recent advances in direct neural control of paralyzed arms present new requirements for miniaturized, low-power sensor systems. To address this challenge, we developed a fully-integrated wireless sensor-brain-machine interface (SBMI) system for communicating key somatosensory signals, fingertip forces and limb joint angles, to the brain. The system consists of a tactile force sensor, an electrogoniometer, and a neural interface. The tactile force sensor features a novel optical waveguide on CMOS design for sensing. The electrogoniometer integrates an ultra low-power digital signal processor (DSP) for real-time joint angle measurement. The neural interface enables bidirectional neural stimulation and recording. Innovative designs of sensors and sensing interfaces, analog-to-digital converters (ADC) and ultra wide-band (UWB) wireless transceivers have been developed. The prototypes have been fabricated in 180nm standard CMOS technology and tested on the bench and in vivo. The developed system provides a novel solution for providing somatosensory feedback to next-generation neural prostheses., Comment: 12 pages, 17 figures

This paper presents a wireless neural recording system featuring energy-efficient data compression and encryption. An ultra-high efficiency is achieved by leveraging compressed sensing (CS) for simultaneous data compression and encryption. CS enables sub-Nyquist sampling of neural signals by taking advantage of its intrinsic sparsity. It simultaneously encrypts the data with the sampling matrix being the cryptographic key. To share the key over an insecure wireless channel, we implement an elliptic-curve cryptography (ECC) based key exchanging protocol. The CS operation is executed in a custom-designed IC fabricated in 180nm CMOS technology. Mixed-signal circuits are designed to optimize the power efficiency of the matrix-vector multiplication (MVM) of the CS operation. The ECC algorithm is implemented in a low-power Cortex-M0 microcontroller (MCU). To be protected from timing and power analysis attacks, the implementation avoids possible data-dependent branches and also employs a randomized ECC initialization. At a compression ratio of 8x, the average correlated coefficient between the reconstructed signals and the uncompressed signals is 0.973, while the ciphertext-only attacks (CoA) achieve no better than 0.054 over 200,000 attacks. The prototype achieves a 35x power saving compared with conventional implementation in low-power MCUs. This work demonstrates a promising solution for future chronic neural recording systems with requirements in high energy efficiency and security., Comment: 10 pages, 10 figures

Off-state current leakage and switching delay has become the main challenge for continued complementary metal-oxide-semiconductor (CMOS) technology scaling. Previous work proposes a "see-saw" relay structure to mimic the operation of CMOS. This paper presents a novel single-pole double-throw (SPDT) switch structure based on AlN piezoelectric cantilever beam to improve the former "see-saw" relay structure. Geometry parameters are given and key switch parameters such as actuation voltage, switching time and contact force have been calculated and compared with previous "see-saw" relay structure. Analysis and design process is shown and micro-fabrication process is described as well.

One of the key challenges in the area of signal processing on graphs is to design transforms and dictionaries methods to identify and exploit structure in signals on weighted graphs. In this paper, we first generalize graph Fourier transform (GFT) to graph fractional Fourier transform (GFRFT), which is then used to define a novel transform named spectral graph fractional wavelet transform (SGFRWT), which is a generalized and extended version of spectral graph wavelet transform (SGWT). A fast algorithm for SGFRWT is also derived and implemented based on Fourier series approximation. The potential applications of SGFRWT are also presented., Comment: 27 pages, 4 figures, 1 table