This study uses a Long Short-Term Memory (LSTM) network to predict the remaining useful life (RUL) of jet engines from time-series data, crucial for aircraft maintenance and safety. The LSTM model's performance is compared with a Multilayer Perceptron (MLP) on the C-MAPSS dataset from NASA, which contains jet engine run-to-failure events. The LSTM learns from temporal sequences of sensor data, while the MLP learns from static data snapshots. The LSTM model consistently outperforms the MLP in prediction accuracy, demonstrating its superior ability to capture temporal dependencies in jet engine degradation patterns. The software for this project is in https://github.com/AneesPeringal/rul-prediction.git.
In this paper, we present ECAPA2, a novel hybrid neural network architecture and training strategy to produce robust speaker embeddings. Most speaker verification models are based on either the 1D- or 2D-convolutional operation, often manifested as Time Delay Neural Networks or ResNets, respectively. Hybrid models are relatively unexplored without an intuitive explanation what constitutes best practices in regard to its architectural choices. We motivate the proposed ECAPA2 model in this paper with an analysis of current speaker verification architectures. In addition, we propose a training strategy which makes the speaker embeddings more robust against overlapping speech and short utterance lengths. The presented ECAPA2 architecture and training strategy attains state-of-the-art performance on the VoxCeleb1 test sets with significantly less parameters than current models. Finally, we make a pre-trained model publicly available to promote research on downstream tasks.
Representation learning plays a critical role in the analysis of time series data and has high practical value across a wide range of applications. including trend analysis, time series data retrieval and forecasting. In practice, data confusion is a significant issue as it can considerably impact the effectiveness and accuracy of data analysis, machine learning models and decision-making processes. In general, previous studies did not consider the variability at various levels of granularity, thus resulting in inadequate information utilization, which further exacerbated the issue of data confusion. This paper proposes an unsupervised framework to realize multi-granularity representation learning for time series. Specifically, we employed a cross-granularity transformer to develop an association between fine- and coarse-grained representations. In addition, we introduced a retrieval task as an unsupervised training task to learn the multi-granularity representation of time series. Moreover, a novel loss function was designed to obtain the comprehensive multi-granularity representation of the time series via unsupervised learning. The experimental results revealed that the proposed framework demonstrates significant advantages over alternative representation learning models.
Shapley values, originating in game theory and increasingly prominent in explainable AI, have been proposed to assess the contribution of facts in query answering over databases, along with other similar power indices such as Banzhaf values. In this work we adapt these Shapley-like scores to probabilistic settings, the objective being to compute their expected value. We show that the computations of expected Shapley values and of the expected values of Boolean functions are interreducible in polynomial time, thus obtaining the same tractability landscape. We investigate the specific tractable case where Boolean functions are represented as deterministic decomposable circuits, designing a polynomial-time algorithm for this setting. We present applications to probabilistic databases through database provenance, and an effective implementation of this algorithm within the ProvSQL system, which experimentally validates its feasibility over a standard benchmark.
Systematic reviews are crucial for evidence-based medicine as they comprehensively analyse published research findings on specific questions. Conducting such reviews is often resource- and time-intensive, especially in the screening phase, where abstracts of publications are assessed for inclusion in a review. This study investigates the effectiveness of using zero-shot large language models~(LLMs) for automatic screening. We evaluate the effectiveness of eight different LLMs and investigate a calibration technique that uses a predefined recall threshold to determine whether a publication should be included in a systematic review. Our comprehensive evaluation using five standard test collections shows that instruction fine-tuning plays an important role in screening, that calibration renders LLMs practical for achieving a targeted recall, and that combining both with an ensemble of zero-shot models saves significant screening time compared to state-of-the-art approaches.
We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation. Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction. This limitation becomes particularly evident in scenarios involving continuous input, such as Metaverse, live video streaming, and broadcasting, where high throughput is imperative. To address this, we present a novel approach that transforms the original sequential denoising into the batching denoising process. Stream Batch eliminates the conventional wait-and-interact approach and enables fluid and high throughput streams. To handle the frequency disparity between data input and model throughput, we design a novel input-output queue for parallelizing the streaming process. Moreover, the existing diffusion pipeline uses classifier-free guidance(CFG), which requires additional U-Net computation. To mitigate the redundant computations, we propose a novel residual classifier-free guidance (RCFG) algorithm that reduces the number of negative conditional denoising steps to only one or even zero. Besides, we introduce a stochastic similarity filter(SSF) to optimize power consumption. Our Stream Batch achieves around 1.5x speedup compared to the sequential denoising method at different denoising levels. The proposed RCFG leads to speeds up to 2.05x higher than the conventional CFG. Combining the proposed strategies and existing mature acceleration tools makes the image-to-image generation achieve up-to 91.07fps on one RTX4090, improving the throughputs of AutoPipline developed by Diffusers over 59.56x. Furthermore, our proposed StreamDiffusion also significantly reduces the energy consumption by 2.39x on one RTX3060 and 1.99x on one RTX4090, respectively.
Planning and reasoning about actions and processes, in addition to reasoning about propositions, are important issues in recent logical and computer science studies. The widespread use of actions in everyday life such as IoT, semantic web services, etc., and the limitations and issues in the action formalisms are two factors that lead us to study about how actions are represented. Since 2007, there was some ideas to integrate Description Logic (DL) and action formalisms for representing both static and dynamic knowledge. In meanwhile, time is an important factor in dynamic situations, and actions change states over time. In this study, on the one hand, we examined related logical structures such as extensions of description logics (DLs), temporal formalisms, and action formalisms. On the other hand, we analyzed possible tools for designing and developing the Knowledge and Action Base (KAB). For representation and reasoning about actions, we embedded actions into DLs (such as Dynamic-ALC and its extensions). We propose a terminable algorithm for action projection, planning, checking the satisfiability, consistency, realizability, and executability, and also querying from KAB. Actions in this framework were modeled with SPIN and added to state space. This framework has also been implemented as a plugin for the Prot\'eg\'e ontology editor. During the last two decades, various algorithms have been presented, but due to the high computational complexity, we face many problems in implementing dynamic ontologies. In addition, an algorithm to detect the inconsistency of actions' effects was not explicitly stated. In the proposed strategy, the interactions of actions with other parts of modeled knowledge, and a method to check consistency between the effects of actions are presented. With this framework, the ramification problem can be well handled in future works.
With the wide adoption of AI applications, there is a pressing need of enabling real-time neural network (NN) inference on small embedded devices, but deploying NNs and achieving high performance of NN inference on these small devices is challenging due to their extremely weak capabilities. Although NN partitioning and offloading can contribute to such deployment, they are incapable of minimizing the local costs at embedded devices. Instead, we suggest to address this challenge via agile NN offloading, which migrates the required computations in NN offloading from online inference to offline learning. In this paper, we present AgileNN, a new NN offloading technique that achieves real-time NN inference on weak embedded devices by leveraging eXplainable AI techniques, so as to explicitly enforce feature sparsity during the training phase and minimize the online computation and communication costs. Experiment results show that AgileNN's inference latency is >6x lower than the existing schemes, ensuring that sensory data on embedded devices can be timely consumed. It also reduces the local device's resource consumption by >8x, without impairing the inference accuracy.
Natural Language Video Localization (NLVL), grounding phrases from natural language descriptions to corresponding video segments, is a complex yet critical task in video understanding. Despite ongoing advancements, many existing solutions lack the capability to globally capture temporal dynamics of the video data. In this study, we present a novel approach to NLVL that aims to address this issue. Our method involves the direct generation of a global 2D temporal map via a conditional denoising diffusion process, based on the input video and language query. The main challenges are the inherent sparsity and discontinuity of a 2D temporal map in devising the diffusion decoder. To address these challenges, we introduce a multi-scale technique and develop an innovative diffusion decoder. Our approach effectively encapsulates the interaction between the query and video data across various time scales. Experiments on the Charades and DiDeMo datasets underscore the potency of our design.
Event cameras are neuromorphic sensors that capture asynchronous and sparse event stream when per-pixel brightness changes. The state-of-the-art processing methods for event signals typically aggregate events into a frame or a grid. However, events are dense in time, these works are limited to local information of events due to the stacking. In this paper, we present a novel spatiotemporal representation learning method which can capture the global correlations of all events in the event stream simultaneously by tensor decomposition. In addition, with the events are sparse in space, we propose an Elastic Net-incorporated tensor network (ENTN) model to obtain more spatial and temporal details about event stream. Empirically, the results indicate that our method can represent the spatiotemporal correlation of events with high quality, and can achieve effective results in applications like filtering noise compared with the state-of-the-art methods.