Search

Supervised contrastive learning has been explored in making use of label information for multi-label classification, but determining positive samples in multi-label scenario remains challenging. Previous studies have examined strategies for identifying positive samples, considering label overlap proportion between anchors and samples. However, they ignore various relations between given anchors and samples, as well as how to dynamically adjust the weights in contrastive loss functions based on different relations, leading to great ambiguity. In this paper, we introduce five distinct relations between multi-label samples and propose a Similarity-Dissimilarity Loss with contrastive learning for multi-label classification. Our loss function re-weights the loss by computing the similarity and dissimilarity between positive samples and a given anchor based on the introduced relations. We mainly conduct experiments for multi-label text classification on MIMIC datasets, then further extend the evaluation on MS-COCO. The Experimental results show that our proposed loss effectively improves the performance on all encoders under supervised contrastive learning paradigm, demonstrating its effectiveness and robustness.

Deep learning (DL) has substantially enhanced natural language processing (NLP) in healthcare research. However, the increasing complexity of DL-based NLP necessitates transparent model interpretability, or at least explainability, for reliable decision-making. This work presents a thorough scoping review of explainable and interpretable DL in healthcare NLP. The term "eXplainable and Interpretable Artificial Intelligence" (XIAI) is introduced to distinguish XAI from IAI. Different models are further categorized based on their functionality (model-, input-, output-based) and scope (local, global). Our analysis shows that attention mechanisms are the most prevalent emerging IAI technique. The use of IAI is growing, distinguishing it from XAI. The major challenges identified are that most XIAI does not explore "global" modelling processes, the lack of best practices, and the lack of systematic evaluation and benchmarks. One important opportunity is to use attention mechanisms to enhance multi-modal XIAI for personalized medicine. Additionally, combining DL with causal logic holds promise. Our discussion encourages the integration of XIAI in Large Language Models (LLMs) and domain-specific smaller models. In conclusion, XIAI adoption in healthcare requires dedicated in-house expertise. Collaboration with domain experts, end-users, and policymakers can lead to ready-to-use XIAI methods across NLP and medical tasks. While challenges exist, XIAI techniques offer a valuable foundation for interpretable NLP algorithms in healthcare., Comment: This paper has been accepted by Computational and Structural Biotechnology Journal

Pre-trained language models (PLMs) leverage chains-of-thought (CoT) to simulate human reasoning and inference processes, achieving proficient performance in multi-hop QA. However, a gap persists between PLMs' reasoning abilities and those of humans when tackling complex problems. Psychological studies suggest a vital connection between explicit information in passages and human prior knowledge during reading. Nevertheless, current research has given insufficient attention to linking input passages and PLMs' pre-training-based knowledge from the perspective of human cognition studies. In this study, we introduce a Prompting Explicit and Implicit knowledge (PEI) framework, which uses prompts to connect explicit and implicit knowledge, aligning with human reading process for multi-hop QA. We consider the input passages as explicit knowledge, employing them to elicit implicit knowledge through unified prompt reasoning. Furthermore, our model incorporates type-specific reasoning via prompts, a form of implicit knowledge. Experimental results show that PEI performs comparably to the state-of-the-art on HotpotQA. Ablation studies confirm the efficacy of our model in bridging and integrating explicit and implicit knowledge., Comment: This paper has been accepted at COLING 2024

We present the design and test results of two optical data transmission ASICs for the High-Luminosity LHC (HL-LHC) experiments. These ASICs include a two-channel serializer (LOCs2) and a single-channel Vertical Cavity Surface Emitting Laser (VCSEL) driver (LOCld1V2). Both ASICs are fabricated in a commercial 0.25-um Silicon-on-Sapphire (SoS) CMOS technology and operate at a data rate up to 8 Gbps per channel. The power consumption of LOCs2 and LOCld1V2 are 1.25 W and 0.27 W at 8-Gbps data rate, respectively. LOCld1V2 has been verified meeting the radiation-tolerance requirements for HL-LHC experiments., Comment: 9 pages, 12 figures

Pulse timing is an important topic in nuclear instrumentation, with far-reaching applications from high energy physics to radiation imaging. While high-speed analog-to-digital converters become more and more developed and accessible, their potential uses and merits in nuclear detector signal processing are still uncertain, partially due to associated timing algorithms which are not fully understood and utilized. In this paper, we propose a novel method based on deep learning for timing analysis of modularized detectors without explicit needs of labelling event data. By taking advantage of the intrinsic time correlations, a label-free loss function with a specially designed regularizer is formed to supervise the training of neural networks towards a meaningful and accurate mapping function. We mathematically demonstrate the existence of the optimal function desired by the method, and give a systematic algorithm for training and calibration of the model. The proposed method is validated on two experimental datasets based on silicon photomultipliers (SiPM) as main transducers. In the toy experiment, the neural network model achieves the single-channel time resolution of 8.8 ps and exhibits robustness against concept drift in the dataset. In the electromagnetic calorimeter experiment, several neural network models (FC, CNN and LSTM) are tested to show their conformance to the underlying physical constraint and to judge their performance against traditional methods. In total, the proposed method works well in either ideal or noisy experimental condition and recovers the time information from waveform samples successfully and precisely., Comment: 26 pages, 12 figures

The silicon pixel sensor is the core component of the vertex detector for the Circular Electron Positron Collider~(CEPC). The JadePix3 is a full-function large-size CMOS chip designed for the CEPC vertex detector. To test all the functions and the performance of this chip, we designed a test system based on the IPbus framework. The test system controls the parameters and monitors the status of the pixel chip. By integrating the jumbo frame feature into the IPbus suite, the block read/write speed is further extended in order to meet the specifications of the JadePix3. The robustness, scalability, and portability of this system have been verified by pulse test, cosmic test and laser test in the laboratory. This paper summarizes the DAQ and control system of the JadePix3 and presents the first results of the tests.

We present the design and test results of a Drivers and Limiting AmplifierS ASIC operating at 10 Gbps (DLAS10) and three Miniature Optical Transmitter/Receiver/Transceiver modules (MTx+, MRx+, and MTRx+) based on DLAS10. DLAS10 can drive two Transmitter Optical Sub-Assemblies (TOSAs) of Vertical Cavity Surface Emitting Lasers (VCSELs), receive the signals from two Receiver Optical Sub-Assemblies (ROSAs) that have no embedded limiting amplifiers, or drive a VCSEL TOSA and receive the signal from a ROSA, respectively. Each channel of DLAS10 consists of an input Continuous Time Linear Equalizer (CTLE), a four-stage limiting amplifier (LA), and an output driver. The LA amplifies the signals of variable levels to a stable swing. The output driver drives VCSELs or impedance-controlled traces. DLAS10 is fabricated in a 65 nm CMOS technology. The die is 1 mm x 1 mm. DLAS10 is packaged in a 4 mm x 4 mm 24-pin quad-flat no-leads (QFN) package. DLAS10 has been tested in MTx+, MRx+, and MTRx+ modules. Both measured optical and electrical eye diagrams pass the 10 Gbps eye mask test. The input electrical sensitivity is 40 mVp-p, while the input optical sensitivity is -12 dBm. The total jitter of MRx+ is 29 ps (P-P) with a random jitter of 1.6 ps (RMS) and a deterministic jitter of 9.9 ps. Each MTx+/MTRx+ module consumes 82 mW/ch and 174 mW/ch, respectively., Comment: 7 pages, 25 figures, 22nd Virtual IEEE Real Time Conference

In this paper, we present the design and test results of LOCx2, a transmitter ASIC for the ATLAS Liquid Argon Calorimeter trigger upgrade. LOCx2 consists of two channels and each channel encodes ADC data with an overhead of 14.3% and transmits serial data at 5.12 Gbps with a latency of less than 27.2 ns. LOCx2 is fabricated with a commercial 0.25-um Silicon-on-Sapphire CMOS technology and is packaged in a 100-pin QFN package. The power consumption of LOCx2 is about 843 mW.

A Liquid-argon Trigger Digitizer Board (LTDB) is being developed to upgrade the ATLAS Liquid Argon Calorimeter Phase-I trigger electronics. The LTDB located at the front end needs to obtain the clock signals and be configured and monitored remotely from the back end. A clock and control system is being developed for the LTDB and the major functions of the system have been evaluated. The design and evaluation of the clock and control system are presented in this paper.

We report the development of a mid-board, TOSA and ROSA based miniature dual channel optical transmitter (MTx) and a transceiver (MTRx). The design transmission data rate is 5.12 Gbps per channel and receiving data rate 4.8 Gbps. MTx and MTRx are only 6 mm tall and are electrically and optically pluggable. Although the fiber TOSA/ROSA coupling is through a custom latch, the fiber uses the standard LC ferrule, flange and spring. Light coupling is ensured by the TOSA and ROSA with the LC coupling mechanism. With the dual channel serializer LOCx2 sits under MTx, one achieves high data transmission with a small PCB footprint, and enjoys the reliability of the hermetically packaged TOSA. MTx and MTRx are designed for detector front-end readout of the ATLAS Liquid Argon Calorimeter (LAr) trigger upgrade.

In this paper, we present a dual-channel serializer ASIC, LOCx2, and its pin-compatible backup, LOCx2-130, for detector front-end readout. LOCx2 is fabricated in a 0.25-um Silicon-on-Sapphire CMOS process and each channel operates at 5.12 Gbps, while LOCx2-130 is fabricated in a 130-nm bulk CMOS process and each channel operates at 4.8 Gbps. The power consumption and the transmission latency are 900 mW and 27 ns for LOCx2 and the corresponding simulation result of LOCx2-130 are 386 mW and 38 ns, respectively., Comment: 8 pages, 10 figures

We present two prototypes of a gigabit transceiver ASIC, GBCR1 and GBCR2, both designed in a 65-nm CMOS technology for the ATLAS Inner Tracker Pixel Detector readout upgrade. The first prototype, GBCR1, has four upstream receiver channels and one downstream transmitter channel with pre-emphasis. Each upstream channel receives the data at 5.12 Gbps through a 5 meter AWG34 Twinax cable from an ASIC driver located on the pixel module and restores the signal from the high frequency loss due to the low mass cable. The signal is retimed by a recovered clock before it is sent to the optical transmitter VTRx+. The downstream driver is designed to transmit the 2.56 Gbps signal from lpGBT to the electronics on the pixel module over the same cable. The peak-peak jitter (throughout the paper jitter is always peak-peak unless specified) of the restored signal is 35.4 ps at the output of GBCR1, and 138 ps for the downstream channel at the cable ends. GBCR1 consumes 318 mW and is tested. The second prototype, GBCR2, has seven upstream channels and two downstream channels. Each upstream channel works at 1.28 Gbps to recover the data directly from the RD53B ASIC through a 1 meter custom FLEX cable followed by a 6 meter AWG34 Twinax cable. The equalized signal of each upstream channel is retimed by an input 1.28 GHz phase programmable clock. Compared with the signal at the FLEX input, the additional jitter of the equalized signal is about 80 ps when the retiming logic is o . When the retiming logic is on, the jitter is 50 ps at GBCR2 output, assuming the 1.28 GHz retiming clock is from lpGBT. The downstream is designed to transmit the 160 Mbps signal from lpGBT through the same cable connection to RD53B and the jitter is about 157 ps at the cable ends. GBCR2 consumes about 150 mW when the retiming logic is on. This design was submitted in November 2019., Comment: 7 pages, 15 figures

Accurate measuring the location and orientation of individual particles in a beam monitoring system is of particular interest to researchers in multiple disciplines. Among feasible methods, gaseous drift chambers with hybrid pixel sensors have the great potential to realize long-term stable measurement with considerable precision. In this paper, we introduce deep learning to analyze patterns in the beam projection image to facilitate three-dimensional reconstruction of particle tracks. We propose an end-to-end neural network based on segmentation and fitting for feature extraction and regression. Two segmentation branches, named binary segmentation and semantic segmentation, perform initial track determination and pixel-track association. Then pixels are assigned to multiple tracks, and a weighted least squares fitting is implemented with full back-propagation. Besides, we introduce a center-angle measure to judge the precision of location and orientation by combining two separate factors. The initial position resolution achieves 8.8 $\mu m$ for the single track and 11.4 $\mu m$ (15.2 $\mu m$) for the 1-3 tracks (1-5 tracks), and the angle resolution achieves 0.15$^{\circ}$ and 0.21$^{\circ}$ (0.29$^{\circ}$) respectively. These results show a significant improvement in accuracy and multi-track compatibility compared to traditional methods., Comment: 39 pages, 15 figures

Timing systems based on Analog-to-Digital Converters are widely used in the design of previous high energy physics detectors. In this paper, we propose a new method based on deep learning to extract the time information from a finite set of ADC samples. Firstly, a quantitative analysis of the traditional curve fitting method regarding three kinds of variations (long-term drift, short-term change and random noise) is presented with simulation illustrations. Next, a comparative study between curve fitting and the neural networks is made to demonstrate the potential of deep learning in this problem. Simulations show that the dedicated network architecture can greatly suppress the noise RMS and improve timing resolution in non-ideal conditions. Finally, experiments are performed with the ALICE PHOS FEE card. The performance of our method is more than 20% better than curve fitting in the experimental condition., Comment: 24 pages, 9 figures, 4 tables. This is the Accepted Manuscript version of an article accepted for publication in Journal of Instrumentation. Neither SISSA Medialab Srl nor IOP Publishing Ltd is responsible for any errors or omissions in this version of the manuscript or any version derived from it. The Version of Record is available online at https://doi.org/10.1088/1748-0221/14/03/P03002

We present the design and the test results of a dual-channel Vertical-Cavity Surface-Emitting Laser (VCSEL) driver ASIC LOCld65 for detector front-end readout. LOCld65 is designed in a commercial 65-nm CMOS technology with a power supply of 1.2 V. LOCld65 contains two separate channels with the same structure and the two channels share an I2C slave. Each channel consists of an input amplifier, four stages of limiting amplifiers (LAs), a high-current output driver, and a bias-current generator. In order to extend the bandwidth, the input amplifier uses an inductive peaking technique and the LAs use a shared inductive peaking technique. The input amplifier and the output driver each utilize a Continuous-Time Linear Equalizer (CTLE). The LAs employ active feedback. The modulation current, the bias current, the peaking strength of the CTLEs, and the feedback strength of LAs are programmable through an I2C interface. In order to protect from the radiation damage, the I2C slave is implemented with triple modular redundancy. Each channel of LOCld65 is tested to operate up to 14 Gbps with typical power dissipations (the VCSEL included) of 68.3 mW/channel and 62.1 mW/channel at the VCSEL voltages of 3.3 V and 2.5 V, respectively. LOCld65 survives 4.9 kGy(SiO2). LOCld65 is an excellent match for the serializer-deserializer ASIC lpGBT in single- or dual-channel optical transmitters in HL-LHC upgrade applications., Comment: 8 pages, 12 figures, presented at 21st IEEE Real Time Conference, Colonial Williamsburg, VA, USA, 9-15 June 2018

In the search for neutrinoless double-beta decay, the high-pressure gaseous Time Projection Chamber has a distinct advantage, because the ionization charge tracks produced by particle interactions are extended and the detector captures the full three-dimensional charge distribution with appropriate charge readout systems. Such information of tracks provides a crucial extra-handle for discriminating signal events against backgrounds. In this paper, we constructed a toy model to demonstrate where the discrimination power comes from and how much of it the neural network models have already harnessed. Then we adapted 3-dimensional convolutional and residual neural networks on the simulated double-beta and background charge tracks and tested their capabilities in classifying these two types of events. We show that both the 3D structure and the overall depth of the neural networks significantly improve the accuracy of the classifier and lead to results better than previous works. We also studied their performance under various spatial granularities as well as different diffusion and noise conditions. The results indicate that the methods are stable and generalize well despite varying experimental conditions., Comment: 27 pages, 13 figures, 5 tables

We report the design and test results of a beam monitor developed for online monitoring in hadron therapy. The beam monitor uses eight silicon pixel sensors, \textit{Topmetal-${II}^-$}, as the anode array. \textit{Topmetal-${II}^-$} is a charge sensor designed in a CMOS 0.35 $\mu$m technology. Each \textit{Topmetal-${II}^-$} sensor has $72\times72$ pixels and the pixel size is $83\times83$ $\mu$m$^2$. In our design, the beam passes through the beam monitor without hitting the electrodes, making the beam monitor especially suitable for monitoring heavy ion beams. This design also reduces radiation damage to the beam monitor itself. The beam monitor is tested with a carbon ion beam at the Heavy Ion Research Facility in Lanzhou (HIRFL). Results indicate that the beam monitor can measure position, incidence angle and intensity of the beam with a position resolution better than 20 $\mu$m, angular resolution about 0.5$^\circ$ and intensity statistical accuracy better than 2$\%$.

\textit{Topmetal-${II}^-$} is a low noise CMOS pixel direct charge sensor with a pitch of 83$\mu m$. CdZnTe is an excellent semiconductor material for radiation detection. The combination of CdZnTe and the sensor makes it possible to build a detector with high spatial resolution. In our experiments, an epoxy adhesive is used as the conductive medium to connect the sensor and Cadmium Zinc Telluride (CdZnTe). The diffusion coefficient and charge efficiency of electrons are measured at a low bias voltage of -2 Volts, and the image of a single alpha is clear with a reasonable spatial resolution. The detector of such structure has the potential to be applied in X-ray imaging systems with a further improvements of the sensor., Comment: 4 pages,6 figures

We present the detailed study of the digital readout of Topmetal-II- CMOS pixel direct charge sensor. Topmetal-II- is an integrated sensor with an array of 72X72 pixels each capable of directly collecting external charge through exposed metal electrodes in the topmost metal layer. In addition to the time-shared multiplexing readout of the analog output from Charge Sensitive Amplifiers in each pixel, hits are also generated through comparators with individually DAC settable thresholds in each pixel. The hits are read out via a column-based priority logic structure, retaining both hit location and time information. The in-array column-based priority logic is fully combinational hence there is no clock distributed in the pixel array. Sequential logic and clock are placed on the peripheral of the array. We studied the detailed working behavior and performance of this readout, and demonstrated its potential in imaging applications.

Substantial experimental and theoretical efforts worldwide are devoted to explore the phase diagram of strongly interacting matter. At LHC and top RHIC energies, QCD matter is studied at very high temperatures and nearly vanishing net-baryon densities. There is evidence that a Quark-Gluon-Plasma (QGP) was created at experiments at RHIC and LHC. The transition from the QGP back to the hadron gas is found to be a smooth cross over. For larger net-baryon densities and lower temperatures, it is expected that the QCD phase diagram exhibits a rich structure, such as a first-order phase transition between hadronic and partonic matter which terminates in a critical point, or exotic phases like quarkyonic matter. The discovery of these landmarks would be a breakthrough in our understanding of the strong interaction and is therefore in the focus of various high-energy heavy-ion research programs. The Compressed Baryonic Matter (CBM) experiment at FAIR will play a unique role in the exploration of the QCD phase diagram in the region of high net-baryon densities, because it is designed to run at unprecedented interaction rates. High-rate operation is the key prerequisite for high-precision measurements of multi-differential observables and of rare diagnostic probes which are sensitive to the dense phase of the nuclear fireball. The goal of the CBM experiment at SIS100 (sqrt(s_NN) = 2.7 - 4.9 GeV) is to discover fundamental properties of QCD matter: the phase structure at large baryon-chemical potentials (mu_B > 500 MeV), effects of chiral symmetry, and the equation-of-state at high density as it is expected to occur in the core of neutron stars. In this article, we review the motivation for and the physics programme of CBM, including activities before the start of data taking in 2022, in the context of the worldwide efforts to explore high-density QCD matter., Comment: 15 pages, 11 figures. Published in European Physical Journal A

\textit{Topmetal-${II}^-$} is a highly pixelated direct charge sensor that contains a 72${\times}$72 pixel array of 83${\mu}$m pitch size. The key feature of \textit{Topmetal-${II}^-$} is that it can directly collect charges via metal nodes of each pixel to form two-dimensional images of charge cloud distributions. \textit{Topmetal-${II}^-$} was proved to measure charged particles without amplification at room temperature. To measure its performance at cryogenic temperature, a \textit{Topmetal-${II}^-$} sensor is embedded into a liquid nitrogen dewar. The results presented in this paper show that \textit{Topmetal-${II}^-$} can also operate well at this low temperature with a noise (ENC) of 12 e$^-$ lower than that at room temperature (13 e$^-$). From the noise perspective, \textit{Topmetal-${II}^-$} is a promising candidate for the next generation readout of liquid argon and xenon Time Projection Chamber (TPC) used in experiments searching for neutrinoless double beta decay and dark matter., Comment: 5 pages