Search

Many nations are promoting the green transition in the energy sector to attain neutral carbon emissions by 2050. Smart Grid 2.0 (SG2) is expected to explore data-driven analytics and enhance communication technologies to improve the efficiency and sustainability of distributed renewable energy systems. These features are beyond smart metering and electric surplus distribution in conventional smart grids. Given the high dependence on communication networks to connect distributed microgrids in SG2, potential cascading failures of connectivity can cause disruption to data synchronization to the remote control systems. This paper reviews security threats and defense tactics for three stakeholders: power grid operators, communication network providers, and consumers. Through the survey, we found that SG2's stakeholders are particularly vulnerable to substation attacks/vandalism, malware/ransomware threats, blockchain vulnerabilities and supply chain breakdowns. Furthermore, incorporating artificial intelligence (AI) into autonomous energy management in distributed energy resources of SG2 creates new challenges. Accordingly, adversarial samples and false data injection on electricity reading and measurement sensors at power plants can fool AI-powered control functions and cause messy error-checking operations in energy storage, wrong energy estimation in electric vehicle charging, and even fraudulent transactions in peer-to-peer energy trading models. Scalable blockchain-based models, physical unclonable function, interoperable security protocols, and trustworthy AI models designed for managing distributed microgrids in SG2 are typical promising protection models for future research., Comment: 30 pages, 21 figures, 5 tables, accepted to appear in IEEE COMST

Pre-training foundation models has become the de-facto procedure for deep learning approaches, yet its application remains limited in the geological studies, where in needs of the model transferability to break the shackle of data scarcity. Here we target on the X-ray fluorescence (XRF) scanning data, a standard high-resolution measurement in extensive scientific drilling projects. We propose a scalable self-supervised learner, masked autoencoders on XRF spectra (MAX), to pre-train a foundation model covering geological records from multiple regions of the Pacific and Southern Ocean. In pre-training, we find that masking a high proportion of the input spectrum (50\%) yields a nontrivial and meaningful self-supervisory task. For downstream tasks, we select the quantification of XRF spectra into two costly geochemical measurements, CaCO$_3$ and total organic carbon, due to their importance in understanding the paleo-oceanic carbon system. Our results show that MAX, requiring only one-third of the data, outperforms models without pre-training in terms of quantification accuracy. Additionally, the model's generalizability improves by more than 60\% in zero-shot tests on new materials, with explainability further ensuring its robustness. Thus, our approach offers a promising pathway to overcome data scarcity in geological discovery by leveraging the self-supervised foundation model and fast-acquired XRF scanning data.

We leverage best response dynamics to solve monotone variational inequalities on compact and convex sets. Specialization of the method to variational inequalities in game theory recovers convergence results to Nash equilibria when agents select the best response to the current distribution of strategies. We apply the method to generalize population games with additional convex constraints. Furthermore, we explore the robustness of the method by introducing various types of time-varying disturbances.

The case-control sampling design serves as a pivotal strategy in mitigating the imbalanced structure observed in binary data. We consider the estimation of a non-parametric logistic model with the case-control data supplemented by external summary information. The incorporation of external summary information ensures the identifiability of the model. We propose a two-step estimation procedure. In the first step, the external information is utilized to estimate the marginal case proportion. In the second step, the estimated proportion is used to construct a weighted objective function for parameter training. A deep neural network architecture is employed for functional approximation. We further derive the non-asymptotic error bound of the proposed estimator. Following this the convergence rate is obtained and is shown to reach the optimal speed of the non-parametric regression estimation. Simulation studies are conducted to evaluate the theoretical findings of the proposed method. A real data example is analyzed for illustration., Comment: 26 pages, 2 figures, 3 tables

Noise robustness is critical when applying automatic speech recognition (ASR) in real-world scenarios. One solution involves the used of speech enhancement (SE) models as the front end of ASR. However, neural network-based (NN-based) SE often introduces artifacts into the enhanced signals and harms ASR performance, particularly when SE and ASR are independently trained. Therefore, this study introduces a simple yet effective SE post-processing technique to address the gap between various pre-trained SE and ASR models. A bridge module, which is a lightweight NN, is proposed to evaluate the signal-level information of the speech signal. Subsequently, using the signal-level information, the observation addition technique is applied to effectively reduce the shortcomings of SE. The experimental results demonstrate the success of our method in integrating diverse pre-trained SE and ASR models, considerably boosting the ASR robustness. Crucially, no prior knowledge of the ASR or speech contents is required during the training or inference stages. Moreover, the effectiveness of this approach extends to different datasets without necessitating the fine-tuning of the bridge module, ensuring efficiency and improved generalization.

Local feature extractors are the cornerstone of many computer vision tasks. However, their vulnerability to adversarial attacks can significantly compromise their effectiveness. This paper discusses approaches to attack sophisticated local feature extraction algorithms and models to achieve two distinct goals: (1) forcing a match between originally non-matching image regions, and (2) preventing a match between originally matching regions. At the end of the paper, we discuss the performance and drawbacks of different patch generation methods.

Despite notable advancements in the field of computer vision, the precise detection of tiny objects continues to pose a significant challenge, largely owing to the minuscule pixel representation allocated to these objects in imagery data. This challenge resonates profoundly in the domain of geoscience and remote sensing, where high-fidelity detection of tiny objects can facilitate a myriad of applications ranging from urban planning to environmental monitoring. In this paper, we propose a new framework, namely, DeNoising FPN with Trans R-CNN (DNTR), to improve the performance of tiny object detection. DNTR consists of an easy plug-in design, DeNoising FPN (DN-FPN), and an effective Transformer-based detector, Trans R-CNN. Specifically, feature fusion in the feature pyramid network is important for detecting multiscale objects. However, noisy features may be produced during the fusion process since there is no regularization between the features of different scales. Therefore, we introduce a DN-FPN module that utilizes contrastive learning to suppress noise in each level's features in the top-down path of FPN. Second, based on the two-stage framework, we replace the obsolete R-CNN detector with a novel Trans R-CNN detector to focus on the representation of tiny objects with self-attention. Experimental results manifest that our DNTR outperforms the baselines by at least 17.4% in terms of APvt on the AI-TOD dataset and 9.6% in terms of AP on the VisDrone dataset, respectively. Our code will be available at https://github.com/hoiliu-0801/DNTR., Comment: The article is accepted by IEEE Transactions on Geoscience and Remote Sensing. Our code will be available at https://github.com/hoiliu-0801/DNTR

In this work, we propose a novel pipeline that combines AdaIN and NeRF for the task of stylized Novel View Synthesis. Compared to previous works, we make the following contributions: 1) We simplify the pipeline. 2) We extend the capabilities of model to handle the multi-style task. 3) We modify the model architecture to perform well on styles with strong brush strokes. 4) We implement style interpolation on the multi-style model, allowing us to control the style between any two styles and the style intensity between the stylized output and the original scene, providing better control over the stylization strength.

Summarizing medical conversations poses unique challenges due to the specialized domain and the difficulty of collecting in-domain training data. In this study, we investigate the performance of state-of-the-art doctor-patient conversation generative summarization models on the out-of-domain data. We divide the summarization model of doctor-patient conversation into two configurations: (1) a general model, without specifying subjective (S), objective (O), and assessment (A) and plan (P) notes; (2) a SOAP-oriented model that generates a summary with SOAP sections. We analyzed the limitations and strengths of the fine-tuning language model-based methods and GPTs on both configurations. We also conducted a Linguistic Inquiry and Word Count analysis to compare the SOAP notes from different datasets. The results exhibit a strong correlation for reference notes across different datasets, indicating that format mismatch (i.e., discrepancies in word distribution) is not the main cause of performance decline on out-of-domain data. Lastly, a detailed analysis of SOAP notes is included to provide insights into missing information and hallucinations introduced by the models., Comment: Clinical NLP Workshop 2024

Jersey number recognition (JNR) has always been an important task in sports analytics. Improving recognition accuracy remains an ongoing challenge because images are subject to blurring, occlusion, deformity, and low resolution. Recent research has addressed these problems using number localization and optical character recognition. Some approaches apply player identification schemes to image sequences, ignoring the impact of human body rotation angles on jersey digit identification. Accurately predicting the number of jersey digits by using a multi-task scheme to recognize each individual digit enables more robust results. Based on the above considerations, this paper proposes a multi-task learning method called the angle-digit refine scheme (ADRS), which combines human body orientation angles and digit number clues to recognize athletic jersey numbers. Based on our experimental results, our approach increases inference information, significantly improving prediction accuracy. Compared to state-of-the-art methods, which can only handle a single type of sport, the proposed method produces a more diverse and practical JNR application. The incorporation of diverse types of team sports such as soccer, football, basketball, volleyball, and baseball into our dataset contributes greatly to generalized JNR in sports analytics. Our accuracy achieves 64.07% on Top-1 and 89.97% on Top-2, with corresponding F1 scores of 67.46% and 90.64%, respectively., Comment: 10 pages, 6 figures, 5 tables

Temporal point process (TPP) is an important tool for modeling and predicting irregularly timed events across various domains. Recently, the recurrent neural network (RNN)-based TPPs have shown practical advantages over traditional parametric TPP models. However, in the current literature, it remains nascent in understanding neural TPPs from theoretical viewpoints. In this paper, we establish the excess risk bounds of RNN-TPPs under many well-known TPP settings. We especially show that an RNN-TPP with no more than four layers can achieve vanishing generalization errors. Our technical contributions include the characterization of the complexity of the multi-layer RNN class, the construction of $\tanh$ neural networks for approximating dynamic event intensity functions, and the truncation technique for alleviating the issue of unbounded event sequences. Our results bridge the gap between TPP's application and neural network theory.

Case-control sampling is a commonly used retrospective sampling design to alleviate imbalanced structure of binary data. When fitting the logistic regression model with case-control data, although the slope parameter of the model can be consistently estimated, the intercept parameter is not identifiable, and the marginal case proportion is not estimatable, either. We consider the situations in which besides the case-control data from the main study, called internal study, there also exists summary-level information from related external studies. An empirical likelihood based approach is proposed to make inference for the logistic model by incorporating the internal case-control data and external information. We show that the intercept parameter is identifiable with the help of external information, and then all the regression parameters as well as the marginal case proportion can be estimated consistently. The proposed method also accounts for the possible variability in external studies. The resultant estimators are shown to be asymptotically normally distributed. The asymptotic variance-covariance matrix can be consistently estimated by the case-control data. The optimal way to utilized external information is discussed. Simulation studies are conducted to verify the theoretical findings. A real data set is analyzed for illustration.

Clustering of event stream data is of great importance in many application scenarios, including but not limited to, e-commerce, electronic health, online testing, mobile music service, etc. Existing clustering algorithms fail to take outlier data into consideration and are implemented without theoretical guarantees. In this paper, we propose a robust temporal point processes clustering framework which works under mild assumptions and meanwhile addresses several important issues in the event stream clustering problem.Specifically, we introduce a computationally efficient model-free distance function to quantify the dissimilarity between different event streams so that the outliers can be detected and the good initial clusters could be obtained. We further consider an expectation-maximization-type algorithm incorporated with a Catoni's influence function for robust estimation and fine-tuning of clusters. We also establish the theoretical results including algorithmic convergence, estimation error bound, outlier detection, etc. Simulation results corroborate our theoretical findings and real data applications show the effectiveness of our proposed methodology.

This paper addresses the problem of predicting the energy consumption for the drivers of Battery electric vehicles (BEVs). Several external factors (e.g., weather) are shown to have huge impacts on the energy consumption of a vehicle besides the vehicle or powertrain dynamics. Thus, it is challenging to take all of those influencing variables into consideration. The proposed approach is based on a hybrid model which improves the prediction accuracy of energy consumption of BEVs. The novelty of this approach is to combine a physics-based simulation model, which captures the basic vehicle and powertrain dynamics, with a data-driven model. The latter accounts for other external influencing factors neglected by the physical simulation model, using machine learning techniques, such as generalized additive mixed models, random forests and boosting. The hybrid modeling method is evaluated with a real data set from TUM and the hybrid models were shown that decrease the average prediction error from 40% of the pure physics model to 10%., Comment: 15 pages, 9 figures, 3 tables, published in EAI INTSYS 2022

Visual Instruction Tuning represents a novel learning paradigm involving the fine-tuning of pre-trained language models using task-specific instructions. This paradigm shows promising zero-shot results in various natural language processing tasks but is still unexplored in vision emotion understanding. In this work, we focus on enhancing the model's proficiency in understanding and adhering to instructions related to emotional contexts. Initially, we identify key visual clues critical to visual emotion recognition. Subsequently, we introduce a novel GPT-assisted pipeline for generating emotion visual instruction data, effectively addressing the scarcity of annotated instruction data in this domain. Expanding on the groundwork established by InstructBLIP, our proposed EmoVIT architecture incorporates emotion-specific instruction data, leveraging the powerful capabilities of Large Language Models to enhance performance. Through extensive experiments, our model showcases its proficiency in emotion classification, adeptness in affective reasoning, and competence in comprehending humor. The comparative analysis provides a robust benchmark for Emotion Visual Instruction Tuning in the era of LLMs, providing valuable insights and opening avenues for future exploration in this domain. Our code is available at \url{https://github.com/aimmemotion/EmoVIT}., Comment: Accepted by CVPR 2024

In recent years, radicalization is being increasingly attempted on video-sharing platforms. Previous studies have been proposed to identify online radicalization using generic social context analysis, without taking into account comprehensive viewer traits and how those can affect viewers' perception of radicalizing content. To address the challenge, we examine QAnon, a conspiracy-based radicalizing group, and have designed a comprehensive questionnaire aiming to understand viewers' perceptions of QAnon videos. We outline the traits of viewers that QAnon videos are the most appealing to, and identify influential factors that impact viewers' perception of the videos.

Semi-supervised learning has received increasingly attention in statistics and machine learning. In semi-supervised learning settings, a labeled data set with both outcomes and covariates and an unlabeled data set with covariates only are collected. We consider an inference problem in semi-supervised settings where the outcome in the labeled data is binary and the labeled data is collected by case-control sampling. Case-control sampling is an effective sampling scheme for alleviating imbalance structure in binary data. Under the logistic model assumption, case-control data can still provide consistent estimator for the slope parameter of the regression model. However, the intercept parameter is not identifiable. Consequently, the marginal case proportion cannot be estimated from case-control data. We find out that with the availability of the unlabeled data, the intercept parameter can be identified in semi-supervised learning setting. We construct the likelihood function of the observed labeled and unlabeled data and obtain the maximum likelihood estimator via an iterative algorithm. The proposed estimator is shown to be consistent, asymptotically normal, and semiparametrically efficient. Extensive simulation studies are conducted to show the finite sample performance of the proposed method. The results imply that the unlabeled data not only helps to identify the intercept but also improves the estimation efficiency of the slope parameter. Meanwhile, the marginal case proportion can be estimated accurately by the proposed method.

With the measurements of the decay $D^+_s \rightarrow K^0_S K^0_S \pi^+$ by the BESIII Collaboration, we investigate this three-body weak decay via the chiral unitary approach for the final state interaction, where the resonances $S(980)$ and $S(1710)$ are dynamically reproduced with the interaction of eleven coupled channels, and the $W$-external and -internal emission mechanisms are considered at the quark level. Besides, we also take into account the contribution from the $P$-wave resonance $K^*(892)^+$ and make a combined fit of the $K^0_S K^0_S$ and $K^0_S \pi^+$ invariant mass spectra measured by the BESIII Collaboration. The fitted results show that the enhancement around 1.7 GeV in $K^0_S K^0_S$ mass spectrum is overlapped with two visible peaks, indicating the mixing signal originated from the resonances $a_0(1710)$ and $f_0(1710)$ due to their different poles (masses). Thus, the decay $D^+_s \rightarrow K^0_S K^0_S \pi^+$ is helpful to reveal their molecular nature with the mixing signal, which can be more precisely measured in the future., Comment: 17 pages, 7 figures, 2 tables

The prompt emission, X-ray plateau, and X-ray flares of Gamma-ray bursts (GRB) are thought to be from internal dissipation, and the magnetar as the central engine with propeller fallback accretion is proposed to interpret the observed phenomena of GRBs. In this paper, by systematically searching for X-ray emission observed by Swift/Xry Telescope, we find that seven robust GRBs include both X-ray flares and plateau emissions with measured redshift. More interestingly, the X-ray flares/bumps for those seven GRBs are simultaneously observed in the gamma-ray band. By adopting the propeller fallback accretion model to fit the observed data, it is found that the free parameters of two GRBs (140512A and 180329B) can be constrained very well, while in the other five cases, more or less, they are not all sufficiently constrained. On the other hand, this requires that the conversion efficiency of the propeller is to be two or three times higher than that of the spindown dipole radiation of the magnetar. If this is the case, it is contradictory to the expectation from the propeller model: namely, a dirtier ejecta should be less efficient in producing gamma-ray emissions. Our results hint that at least the magnetar central engine with propeller fallback accretion model cannot interpret very well both the GRB X-ray flares simultaneously observed in the gamma-ray band and the X-ray flares of GRBs with a high Lorentz factor., Comment: 13 pages, 5 figures, 1 table, updated references, match with published version

A physics-driven generative adversarial network (GAN) was established here for single-pixel hyperspectral imaging (HSI) in the infrared spectrum, to eliminate the extensive data training work required by traditional data-driven model. Within the GAN framework, the physical process of single-pixel imaging (SPI) was integrated into the generator, and the actual and estimated one-dimensional (1D) bucket signals were employed as constraints in the objective function to update the network's parameters and optimize the generator with the assistance of the discriminator. In comparison to single-pixel infrared HSI methods based on compressed sensing and physics-driven convolution neural networks, our physics-driven GAN-based single-pixel infrared HSI can achieve higher imaging performance but with fewer measurements. We believe that this physics-driven GAN will promote practical applications of computational imaging, especially various SPI-based techniques., Comment: 14 pages, 8 figures

This research introduces an enhanced version of the multi-objective speech assessment model--MOSA-Net+, by leveraging the acoustic features from Whisper, a large-scaled weakly supervised model. We first investigate the effectiveness of Whisper in deploying a more robust speech assessment model. After that, we explore combining representations from Whisper and SSL models. The experimental results reveal that Whisper's embedding features can contribute to more accurate prediction performance. Moreover, combining the embedding features from Whisper and SSL models only leads to marginal improvement. As compared to intrusive methods, MOSA-Net, and other SSL-based speech assessment models, MOSA-Net+ yields notable improvements in estimating subjective quality and intelligibility scores across all evaluation metrics in Taiwan Mandarin Hearing In Noise test - Quality & Intelligibility (TMHINT-QI) dataset. To further validate its robustness, MOSA-Net+ was tested in the noisy-and-enhanced track of the VoiceMOS Challenge 2023, where it obtained the top-ranked performance among nine systems., Comment: Accepted to IEEE ICME 2024

Two quantum key agreement protocols using Bell states and Bell measurement were recently proposed by Shukla et al.(Quantum Inf. Process. 13(11), 2391-2405, 2014). However, Zhu et al. pointed out that there are some security flaws and proposed an improved version (Quantum Inf. Process. 14(11), 4245-4254, 2015). In this study, we will show Zhu et al.'s improvement still exists some security problems, and its efficiency is not high enough. For solving these problems, we utilize four Pauli operations {I, Z, X, Y } to encode two bits instead of the original two operations {I,X} to encode one bit, and then propose an efficient and secure arbitrary N-party quantum key agreement protocol. In the protocol, the channel checking with decoy single photons is introduced to avoid the eavesdropper's flip attack, and a post-measurement mechanism is used to prevent against the collusion attack. The security analysis shows the present protocol can guarantee the correctness, security, privacy and fairness of quantum key agreement., Comment: 13 pages, 5 figures

Privacy-preserving computational geometry is the research area on the intersection of the domains of secure multi-party computation (SMC) and computational geometry. As an important field, the privacy-preserving geometric intersection (PGI) problem is when each of the multiple parties has a private geometric graph and seeks to determine whether their graphs intersect or not without revealing their private information. In this study, through representing Alice's (Bob's) private geometric graph G_A (G_B) as the set of numbered grids S_A (S_B), an efficient privacy-preserving quantum two-party geometric intersection (PQGI) protocol is proposed. In the protocol, the oracle operation O_A (O_B) is firstly utilized to encode the private elements of S_A=(a_0, a_1, ..., a_(M-1)) (S_B=(b_0, b_1, ..., b_(N-1))) into the quantum states, and then the oracle operation O_f is applied to obtain a new quantum state which includes the XOR results between each element of S_A and S_B. Finally, the quantum counting is introduced to get the amount (t) of the states |a_i+b_j> equaling to |0>, and the intersection result can be obtained by judging t>0 or not. Compared with classical PGI protocols, our proposed protocol not only has higher security, but also holds lower communication complexity.

Speech emotion recognition (SER) often experiences reduced performance due to background noise. In addition, making a prediction on signals with only background noise could undermine user trust in the system. In this study, we propose a Noise Robust Speech Emotion Recognition system, NRSER. NRSER employs speech enhancement (SE) to effectively reduce the noise in input signals. Then, the signal-to-noise-ratio (SNR)-level detection structure and waveform reconstitution strategy are introduced to reduce the negative impact of SE on speech signals with no or little background noise. Our experimental results show that NRSER can effectively improve the noise robustness of the SER system, including preventing the system from making emotion recognition on signals consisting solely of background noise. Moreover, the proposed SNR-level detection structure can be used individually for tasks such as data selection.