Real-time Search Research Articles

Wide-Area and Real-Time Object Search System of UAV

The method of collecting aerial images or videos by unmanned aerial vehicles (UAVs) for object search has the advantages of high flexibility and low cost, and has been widely used in various fields, such as pipeline inspection, disaster rescue, and forest fire prevention. However, in the case of object search in a wide area, the scanning efficiency and real-time performance of UAV are often difficult to satisfy at the same time, which may lead to missing the best time to perform the task. In this paper, we design a wide-area and real-time object search system of UAV based on deep learning for this problem. The system first solves the problem of area scanning efficiency by controlling the high-resolution camera in order to collect aerial images with a large field of view. For real-time requirements, we adopted three strategies to accelerate the system, as follows: design a parallel system, simplify the object detection algorithm, and use TensorRT on the edge device to optimize the object detection model. We selected the NVIDIA Jetson AGX Xavier edge device as the central processor and verified the feasibility and practicability of the system through the actual application of suspicious vehicle search in the grazing area of the prairie. Experiments have proved that the parallel design of the system can effectively meet the real-time requirements. For the most time-consuming image object detection link, with a slight loss of precision, most algorithms can reach the 400% inference speed of the benchmark in total, after algorithm simplification, and corresponding model’s deployment by TensorRT.

Application of Key Technologies of Distributed Storage Based on the Internet of Things in Urban Fire Protection

Due to the rapid development of science and technology in the current era, fires occur more frequently, and the relationship between various economic activities and things is becoming more and more frequent. The need for real-time monitoring and remote monitoring of various firefighting facilities in buildings has become very urgent; this is a task that must be put on the agenda. The existing urban fire remote monitoring system has fewer intelligent networks, so it has high requirements for the firefighters on duty in the fire control room, which is no longer sufficient for the firefighting needs of the modern society. This paper proposes a wireless city fire remote monitoring system based on Internet of Things technology, NB-IoT technology, and cloud computing technology and studies core technologies such as designing wireless monitoring nodes at the perception layer. In the urban fire protection environment of distributed storage, several important theories, key technologies, and related algorithms are being studied in detail. After a variety of experimental verification results, the spatial data engine and adaptive spatial data model of the metadata database are developed. This provides a distributed storage virtual city geographic environment, multilevel, multiregional design and development of a simulated prototype platform and storage, management, sharing, and visualization of urban geospatial data. After technical analysis, a visualization framework was installed, which has the characteristics of global vector grid integration and distributed spatial data. Through the research on the key technology of distributed storage of the Internet of Things, this paper applies it to urban fire protection and promotes the intelligent development of urban fire protection. The application of IoT storage technology in urban fire protection can solve the shortcomings of the current urban fire remote monitoring system and automatic fire alarm system. Wireless city fire remote monitoring system, real-time collection, and transmission and storage of working status information of various fire facilities in the building are provided. The functions of real-time monitoring, real-time alarm, real-time search query, record query, maintenance management, route guidance, and user management are also realized.

Real-Time Search-Assisted Acquisition on a Tribrid Mass Spectrometer Improves Coverage in Multiplexed Single-Cell Proteomics

In the young field of single-cell proteomics (scMS), there is a great need for improved global proteome characterization, both in terms of proteins quantified per cell and quantitative performance thereof. The recently introduced real-time search (RTS) on the Orbitrap Eclipse Tribrid mass spectrometer in combination with SPS-MS3 acquisition has been shown to be beneficial for the measurement of samples that are multiplexed using isobaric tags. Multiplexed scMS requires high ion injection times and high-resolution spectra to quantify the single-cell signal; however, the carrier channel facilitates peptide identification and thus offers the opportunity for fast on-the-fly precursor filtering before committing to the time-intensive quantification scan. Here, we compared classical MS2 acquisition against RTS-SPS-MS3, both using the Orbitrap Eclipse Tribrid MS with the FAIMS Pro ion mobility interface and present a new acquisition strategy termed RETICLE (RTS enhanced quant of single cell spectra) that makes use of fast real-time searched linear ion trap scans to preselect MS1 peptide precursors for quantitative MS2 Orbitrap acquisition. We show that classical MS2 acquisition is outperformed by both RTS-SPS-MS3 through increased quantitative accuracy at similar proteome coverage, and RETICLE through higher proteome coverage, with the latter enabling the quantification of over 1000 proteins per cell at an MS2 injection time of 750 ms using a 2 h gradient.

Live Streaming Speech Recognition Using Deep Bidirectional LSTM Acoustic Models and Interpolated Language Models

Although Long-Short Term Memory (LSTM) networks and deep Transformers are now extensively used in offline ASR, it is unclear how best offline systems can be adapted to work with them under the streaming setup. After gaining considerable experience on this regard in recent years, in this paper we show how an optimized, low-latency streaming decoder can be built in which bidirectional LSTM acoustic models, together with general interpolated language models, can be nicely integrated with minimal perfomance degradation. In brief, our streaming decoder consists of a one-pass, real-time search engine relying on a limited-duration window sliding over time and a number of ad hoc acoustic and language model pruning techniques. Extensive empirical assessment is provided on truly streaming tasks derived from the well-known LibriSpeech and TED talks datasets, as well as from TV shows on a main Spanish broadcasting station.

Volatility of Public Interest in Orthopaedics during the COVID-19 Pandemic

Background: Several studies have demonstrated the decrease of public interest in elective orthopaedic surgeries throughout the beginning and middle of the COVID-19 pandemic, but none have assessed the return, if any, of public interest as the pandemic has progressed. Questions/Purpose: Apply a user-friendly tool and replicable methodology to (1) determine differential impacts of COVID-19 on search frequencies for exploratory and interventional search terms; (2) evaluate if public interest towards some common orthopaedic symptoms and their respective elective procedures have returned to pre-pandemic baseline. Method: Google search frequencies for common orthopaedic procedures and symptoms were extracted from Google Extended Trends for Health (GETH) between January 7th, 2018, and January 15th, 2022, using the Google Trends Information Extraction Tool. Queried terms were split into two categories: exploratory and interventional. Control limit analysis was performed for each search term to determine special cause variations and assess any recovery. Results: All search terms saw significant decreases the week of March 15th, 2020, and five of the six saw at least one more drop during the 2020 holiday season. Search volumes for exploratory terms initially fell less and recovered nearly four times faster compared to search volumes for interventional terms, but volatility of public interest was seen until the end of the study window. Conclusions: Public interest in elective orthopaedic procedures continues to be chaotic during this pandemic. This study is the first to assess the initial recovery of public interest in elective orthopaedic procedures in the COVID-19 era using a novel application of the Google Trends Information Extraction Tool and provides a timely update on changes in public perception as the pandemic has progressed. These results can be used to better understand, quantify, and potentially anticipate the interests of the national patient population and tailor care, public outreach programs, or policy based on real-time search trends.

Pemanfaatan Packages Pada R Programming Untuk Crawling Data Pada Social Media

Social media is one of the many sources of data that can be extracted to obtain various information. In R Programming, there are thousands of packages that can be used to crawl social media data, both the default packages and the developer versions. Difficulty in extracting data will result in less than optimal research, so there is a need for adequate tools to support research. R Programming is able to become a bridge for researchers to explore existing tools, both by utilizing packages and building simple algorithms in R programming. Twitter data crawling is done through an API connection on Twitter with R Programming, so that we can get data by entering keywords according to the desired search both in realtime and at certain times as needed. With these packages it makes it easy to research in crawling social media data such as Twitter and other social media

Real-time Search for Compact Binary Mergers in Advanced LIGO and Virgo's Third Observing Run Using PyCBC Live

Abstract The third observing run of Advanced LIGO and Advanced Virgo took place between 2019 April and 2020 March and resulted in dozens of gravitational-wave candidates, many of which are now published as confident detections. A crucial requirement of the third observing run was the rapid identification and public reporting of compact binary mergers, which enabled massive follow-up observation campaigns with electromagnetic and neutrino observatories. PyCBC Live is a low-latency search for compact binary mergers based on frequency-domain matched filtering, which was used during the second and third observing runs, together with other low-latency analyses, to generate these rapid alerts from the data acquired by LIGO and Virgo. This paper describes and evaluates the improvements made to PyCBC Live after the second observing run, which defined its operation and performance during the third observing run.

Anytime versus Real-Time Heuristic Search for On-Line Planning

Many AI systems, such as robots, must plan under time constraints. The most popular search approach applied in robotics so far is anytime search, in which the algorithm quickly finds a suboptimal plan, and then continues to find better and better plans as time passes, until eventually converging on an optimal plan. However, the time until the first plan is returned is not controllable, so such methods inherently involve idling the system's operation before `real' execution can begin. Real-time search methods provide hard real-time bounds on action selection time, yet to our knowledge, they have not yet been demonstrated for robotic systems. In this work, we compare anytime and real-time heuristic search methods in their ability to allow agents to achieve goals quickly.Our results suggest that real-time search is more broadly applicable and often achieves goals faster than anytime search, while anytime search finds shorter plans and does not suffer from dead-ends.

Real-time multi-messenger analysis framework for KM3NeT

KM3NeT is a multi-purpose cubic-kilometer neutrino observatory under construction in the Mediterranean Sea. It consists of ORCA and ARCA (for Oscillation and Astroparticle Research with Cosmics in the Abyss, respectively), currently both have a few detection lines in operation. Although having different primary goals, both detectors can be used for neutrino astronomy over a wide energy range, from a few tens of MeVs to a few tens of PeV. In view of the growing field of time-domain astronomy, it is crucial to be able to identify neutrino candidates in real-time. This online neutrino sample will allow triggered neutrino alerts that will be sent to the astronomy community and to look for time/space coincidences around external electromagnetic and multi-messenger triggers. These real-time searches can significantly increase the discovery potential of transient cosmic accelerators and refine the pointing directions in the case of poorly localized triggers, such as gravitational waves. In the field of core-collapse supernovae (CCSN), the detection of the MeV-scale CCSN neutrinos is crucial as an early warning of the electromagnetic follow-up. KM3NeT's digital optical modules act as good detectors for these supernovae neutrinos. This proceeding presents the status of KM3NeT's real-time multi-messenger activities, including online event reconstruction, event classification and selection, alert distribution, and supernova monitoring.

Improved Safe Real-Time Heuristic Search

A fundamental concern in real-time planning is the presence of dead ends in the state space, from which no goal is reachable. Recently, the SafeRTS algorithm was proposed for searching in such spaces. SafeRTS exploits a user-provided predicate to identify safe states, from which a goal is likely reachable, and attempts to maintain a backup plan for reaching such a state at all times. In this paper, we study the SafeRTS approach, identify certain properties of its behavior, and design an improved framework for safe real-time search. We prove that the new approach performs at least as well as SafeRTS and present experimental results showing that its promise is fulfilled in practice.

A Neural Network for Decision Making in Real-Time Heuristic Search

Most real-time heuristic search algorithms solve search problems by executing a series of episodes. During each episode the algorithm decides an action for execution. Such a decision is usually made using information gathered by running a bounded, heuristic-search algorithm. In this paper we report on a real-time search algorithm that does not use a search algorithm to choose the next action to be applied. Rather, it uses a neural network whose input is local information about the search graph, comparable to the information that would be used by a bounded search algorithm. We describe a supervised learning approach to training such a network. Our three types of maps from the Moving AI benchmarks, shows that our algorithm is, in some cases, substantially superior to algorithms that have access to the same information about the graph. One of our most important conclusions is that our extended set of features important: indeed, using features beyond the heuristic seems key to achieving good performance.

Fast-transient Searches in Real Time with ZTFReST: Identification of Three Optically Discovered Gamma-Ray Burst Afterglows and New Constraints on the Kilonova Rate

Abstract The most common way to discover extragalactic fast transients, which fade within a few nights in the optical, is via follow-up of gamma-ray burst and gravitational-wave triggers. However, wide-field surveys have the potential to identify rapidly fading transients independently of such external triggers. The volumetric survey speed of the Zwicky Transient Facility (ZTF) makes it sensitive to objects as faint and fast fading as kilonovae, the optical counterparts to binary neutron star mergers, out to almost 200 Mpc. We introduce an open-source software infrastructure, the ZTF REaltime Search and Triggering, ZTFReST, designed to identify kilonovae and fast transients in ZTF data. Using the ZTF alert stream combined with forced point-spread-function photometry, we have implemented automated candidate ranking based on their photometric evolution and fitting to kilonova models. Automated triggering, with a human in the loop for monitoring, of follow-up systems has also been implemented. In 13 months of science validation, we found several extragalactic fast transients independently of any external trigger, including two supernovae with post-shock cooling emission, two known afterglows with an associated gamma-ray burst (ZTF20abbiixp, ZTF20abwysqy), two known afterglows without any known gamma-ray counterpart (ZTF20aajnksq, ZTF21aaeyldq), and three new fast-declining sources (ZTF20abtxwfx, ZTF20acozryr, ZTF21aagwbjr) that are likely associated with GRB200817A, GRB201103B, and GRB210204A. However, we have not found any objects that appear to be kilonovae. We constrain the rate of GW170817-like kilonovae to R < 900 Gpc−3 yr−1 (95% confidence). A framework such as ZTFReST could become a prime tool for kilonova and fast-transient discovery with the Vera Rubin Observatory.

Real-Time Heuristic Search in Dynamic Environments

In dynamic environments, agents often do not have time to find a complete plan to reach a goal state, but rather must act quickly under changing circumstances. Real-time heuristic search models this setting by requiring that the agent's next action must be selected within a prespecified time bound. In this paper, we study real-time search algorithms that can tolerate a dynamic environment, in which action costs are not fully predictable. We propose a combination of two previously-proposed methods and study its behavior both theoretically and empirically on several different benchmark domains.

Reconnecting with the Ideal Tree: An Alternative to Heuristic Learning in Real-Time Search

In this paper, we present a conceptually simple, easy-to-implement real-time search algorithm suitable for a priori partially known environments. Instead of performing a series of searches towards the goal, like most Real-Time Heuristic Search Algorithms do, our algorithm follows the arcs of a tree T rooted in the goal state that is built initially using the heuristic h. When the agent observes that an arc in the tree cannot be traversed in the actual environment, it removes such an arc from T and our algorithm carries out a reconnection search whose objective is to find a path between the current state and any node in T. The reconnection search need not be guided by $h$, since the search objective is not to encounter the goal. Furthermore, h need not be updated. We implemented versions of our algorithm that utilize various blind search algorithms for reconnection. We show experimentally that these implementations significantly outperform state-of-the-art real-time heuristic search algorithms for the task of pathfinding in grids. In grids, our algorithms, which do not incorporate any geometrical knowledge, naturally behaves similarly to a bug algorithm, moving around obstacles, and never returning to areas that have been visited in the past. In addition, we prove theoretical properties of the algorithm.

Experimental Real-Time Heuristic Search Results in a Video Game

In real-time domains such as video games, a planning algo- rithm has a strictly bounded time before it must return the next action for the agent to execute. We introduce a realistic video game benchmark domain that is useful for evaluating real-time heuristic search algorithms. Unlike previous bench- marks such as grid pathfinding and the sliding tile puzzle, this new domain includes dynamics and induces a directed graph. Using both the previous and new domains, we investigate sev- eral enhancements to a leading real-time search algorithm, LSS-LRTA*. We show experimentally that 1) it is not dif- ficult to outperform A* when optimizing goal achievement time, 2) it is better to plan after each action than to commit to multiple actions or to use a dynamically sized lookahead, 3) A*-based lookahead can cause undesirable actions to be selected, and 4) on-line de-biasing of the heuristic can lead to improved performance. We hope that this new domain and results will stimulate further research on applying real-time search to dynamic real-time domains.

Paper Summary: Time-Bounded Adaptive A*

This paper summarizes our AAMAS 2012 paper on "Time-Bounded Adaptive A*," which introduces the game time model to evaluate search algorithms in real-time settings, such as video games. It then extends the existing real-time search algorithm TBA* to path planning with the freespace assumption in initially partially or completely unknown terrain, resulting in Time-Bounded Adaptive A* (TBAA*). TBAA* needs fewer time intervals in the game time model than several state-of-the-art complete and real-time search algorithms and about the same number of time intervals as the best compared complete search algorithm, even though it has the advantage over complete search algorithms that the agent starts to move right away.

Real-Time Adaptive A* with Depression Avoidance

Real-time search is a well known approach to solving search problems under tight time constraints. Recently, it has been shown that LSS-LRTA∗ , a well-known real-time search algorithm, can be improved when search is actively guided away of depressions. In this paper we investigate whether or not RTAA∗ can be improved in the same manner. We propose aRTAA∗ and daRTAA∗ , two algorithms based on RTAA∗ that avoid heuristic depressions. Both algorithms outperform RTAA∗ on standard path-finding tasks, obtaining better-quality solutions when the same time deadline is imposed on the duration of the planning episode. We prove, in addition, that both algorithms have good theoretical properties.

Evaluating Real-Time Search over Tweets

Twitter offers a phenomenal platform for the social sharing of information. We describe new resources that have been created in the context of the Text Retrieval Conference (TREC) to support the academic study of Twitter as a real-time information source. We formalize an information seeking task — real-time search — and offer a methodology for measuring system effectiveness. At the TREC 2011 Microblog Track, 58 research groups participated in the first ever evaluation of this task. We present data from the effort to illustrate and support our methodology.

A Study of "Churn" in Tweets and Real-Time Search Queries

The real-time nature of Twitter means that term distributions in tweets and in search queries change rapidly: the most frequent terms in one hour may look very different from those in the next. Informally, we call this phenomenon "churn". Our interest in analyzing churn stems from the perspective of real-time search. How do we "correctly" compute term statistics, considering that the underlying distributions change rapidly? In this paper, we present an analysis of tweet and query churn on Twitter, as a first step to answering this question. Analyses reveal interesting insights on the temporal dynamics of term distributions on Twitter and hold implications for the design of search systems.

Event Summarization Using Tweets

Twitter has become exceedingly popular, with hundreds of millions of tweets being posted every day on a wide variety of topics. This has helped make real-time search applications possible with leading search engines routinely displaying relevant tweets in response to user queries. Recent research has shown that a considerable fraction of these tweets are about "events," and the detection of novel events in the tweet-stream has attracted a lot of research interest. However, very little research has focused on properly displaying this real-time information about events. For instance, the leading search engines simply display all tweets matching the queries in reverse chronological order. In this paper we argue that for some highly structured and recurring events, such as sports, it is better to use more sophisticated techniques to summarize the relevant tweets. We formalize the problem of summarizing event-tweets and give a solution based on learning the underlying hidden state representation of the event via Hidden Markov Models. In addition, through extensive experiments on real-world data we show that our model significantly outperforms some intuitive and competitive baselines.