Fast Alignment Research Articles

Language-Inspired Relation Transfer for Few-Shot Class-Incremental Learning.

Depicting novel classes with language descriptions by observing few-shot samples is inherent in human-learning systems. This lifelong learning capability helps to distinguish new knowledge from old ones through the increase of open-world learning, namely Few-Shot Class-Incremental Learning (FSCIL). Existing works to solve this problem mainly rely on the careful tuning of visual encoders, which shows an evident trade-off between the base knowledge and incremental ones. Motivated by human learning systems, we propose a new Language-inspired Relation Transfer (LRT) paradigm to understand objects by joint visual clues and text depictions, composed of two major steps. We first transfer the pretrained text knowledge to the visual domains by proposing a graph relation transformation module and then fuse the visual and language embedding by a text-vision prototypical fusion module. Second, to mitigate the domain gap caused by visual finetuning, we propose context prompt learning for fast domain alignment and imagined contrastive learning to alleviate the insufficient text data during alignment. With collaborative learning of domain alignments and text-image transfer, our proposed LRT outperforms the state-of-the-art models by over 13% and 7% on the final session of miniImageNet and CIFAR-100 FSCIL benchmarks.

Accurate and Fast Fire Alignment Method Based on a Mono-binocular Vision System

Accurate and Fast Fire Alignment Method Based on a Mono-binocular Vision System

AUTOMATIC COARSE CO-REGISTRATION OF POINT CLOUDS FROM DIVERSE SCAN GEOMETRIES: A TEST OF DETECTORS AND DESCRIPTORS

Abstract. Point clouds are collected nowadays from a plethora of sensors, some having higher accuracies and higher costs, some having lower accuracies but also lower costs. Not only there is a large choice for different sensors, but also these can be transported by different platforms, which can provide different scan geometries. In this work we test the extraction of four different keypoint detectors and three feature descriptors. We benchmark performance in terms of calculation time and we assess their performance in terms of accuracy in their ability in coarse automatic co-registration of two clouds that are collected with different sensors, platforms and scan geometries. One, which we define as having the higher accuracy, and thus will be used as reference, was surveyed via a UAV flight with a Riegl MiniVUX-3, the other on a bicycle with a Livox Horizon over a walking path with un-even ground.The novelty in this work consists in comparing several strategies for fast alignment of point clouds from very different surveying geometries, as the drone has a bird’s eye view and the bicycle a ground-based view. An added challenge is related to the lower cost of the bicycle sensor ensemble that, together with the rough terrain, reasonably results in lower accuracy of the survey. The main idea is to use range images to capture a simplified version of the geometry of the surveyed area and then find the best features to match keypoints. Results show that NARF features detected more keypoints and resulted in a faster co-registration procedure in this scenario whereas the accuracy of the co-registration is similar to all the combinations of keypoint detectors and features.

Optical Fiber Alignment Aid with Image Processing on FPGA-based System

This paper introduces an innovative and efficient solution for achieving precise optical fiber alignment in fiber optic splicing applications. By harnessing the capabilities of FPGA-based real-time image processing, the system surpasses the required frame rate of 20 frames per second, ensuring swift and accurate alignment. With a verified resolution of approximately 1 pixel per µm, the system offers high precision suitable for various applications. Through advanced image processing techniques, the system calculates precise correction values for each frame, resulting in fast and accurate alignment of fiber cores and cladding. This unique feature enhances performance and adaptability, leading to substantial reduction in splice wastage. By integrating motorized alignment stages and guided machine vision, the system provides a robust and automated approach to fiber optic alignment. The FPGA-driven stepper motors enable precise and controlled fiber movements with micrometer-level step resolutions. The calculated correction factors effectively guide the alignment process, with deviations from actual results impressively low – a maximum of 12 µm in the Y correction factor and 7 µm in the X correction factor. This reliability makes the system a crucial component in any optical fiber splicing machine. Furthermore, the paper emphasizes the ability to handle specialty fiber alignment contributes significantly to cost-effective manufacturing of fiber optic components and modules. By ensuring precise and optimal fiber alignment, the system mitigates signal loss, leading to improved performance and reduced production costs.

ESDTW: Extrema-based shape dynamic time warping

As a nonlinear distance measurement, Dynamic time warping (DTW) is widely used to solve the alignment problem of time series. However, due to local distortion of signal, noise interference, and high computational cost, DTW and its variants present some limitations in terms of classification accuracy or speed. In this paper, we develop the extrema-based shape dynamic time warping (ESDTW) for the purpose of fast and accurate alignment of time series. The proposed ESDTW introduces local extrema to represent the original time series, and further uses DTW to align the descriptors of extrema shape. By considering the location information of local extrema, the proposed measure avoids unreliable time series alignment caused by local maxima and minima separately in LEDTW. The experiments on some artificially simulated pairs of aligned sequences demonstrate that ESDTW can obtain more accurate warping paths than comparison methods. Moreover, combining with the nearest neighbor classifier, ESDTW achieves higher classification accuracy than other distance measures on the 84 UCR time series datasets. We also confirm significant computational efficiency gains on long time series.

Fast alignment of mass spectra in large proteomics datasets, capturing dissimilarities arising from multiple complex modifications of peptides

BackgroundIn proteomics, the interpretation of mass spectra representing peptides carrying multiple complex modifications remains challenging, as it is difficult to strike a balance between reasonable execution time, a limited number of false positives, and a huge search space allowing any number of modifications without a priori. The scientific community needs new developments in this area to aid in the discovery of novel post-translational modifications that may play important roles in disease.ResultsTo make progress on this issue, we implemented SpecGlobX (SpecGlob eXTended to eXperimental spectra), a standalone Java application that quickly determines the best spectral alignments of a (possibly very large) list of Peptide-to-Spectrum Matches (PSMs) provided by any open modification search method, or generated by the user. As input, SpecGlobX reads a file containing spectra in MGF or mzML format and a semicolon-delimited spreadsheet describing the PSMs. SpecGlobX returns the best alignment for each PSM as output, splitting the mass difference between the spectrum and the peptide into one or more shifts while considering the possibility of non-aligned masses (a phenomenon resulting from many situations including neutral losses). SpecGlobX is fast, able to align one million PSMs in about 1.5 min on a standard desktop. Firstly, we remind the foundations of the algorithm and detail how we adapted SpecGlob (the method we previously developed following the same aim, but limited to the interpretation of perfect simulated spectra) to the interpretation of imperfect experimental spectra. Then, we highlight the interest of SpecGlobX as a complementary tool downstream to three open modification search methods on a large simulated spectra dataset. Finally, we ran SpecGlobX on a proteome-wide dataset downloaded from PRIDE to demonstrate that SpecGlobX functions just as well on simulated and experimental spectra. We then carefully analyzed a limited set of interpretations.ConclusionsSpecGlobX is helpful as a decision support tool, providing keys to interpret peptides carrying complex modifications still poorly considered by current open modification search software. Better alignment of PSMs enhances confidence in the identification of spectra provided by open modification search methods and should improve the interpretation rate of spectra.

Transfer Learning for P300 Brain-Computer Interfaces by Joint Alignment of Feature Vectors.

This article presents a new transfer learning method named group learning, that jointly aligns multiple domains (many-to-many) and an extension named fast alignment that aligns any further domain to previously aligned group of domains (many-to-one). The proposed group alignment algorithm (GALIA) is evaluated on brain-computer interface (BCI) data and optimal hyper-parameter values of the algorithm are studied for classification performance and computational cost. Six publicly available P300 databases comprising 333 sessions from 177 subjects are used. As compared to the conventional subject-specific train/test pipeline, both group learning and fast alignment significantly improve the classification accuracy except for the database with clinical subjects (average improvement: 2.12±1.88%). GALIA utilizes cyclic approximate joint diagonalization (AJD) to find a set of linear transformations, one for each domain, jointly aligning the feature vectors of all domains. Group learning achieves a many-to-many transfer learning without compromising the classification performance on non-clinical BCI data. Fast alignment further extends the group learning for any unseen domains, allowing a many-to-one transfer learning with the same properties. The former method creates a single machine learning model using data from previous subjects and/or sessions, whereas the latter exploits the trained model for an unseen domain requiring no further training of the classifier.

Qmatey: an automated pipeline for fast exact matching-based alignment and strain-level taxonomic binning and profiling of metagenomes.

Metagenomics is a powerful tool for understanding organismal interactions; however, classification, profiling and detection of interactions at the strain level remain challenging. We present an automated pipeline, quantitative metagenomic alignment and taxonomic exact matching (Qmatey), that performs a fast exact matching-based alignment and integration of taxonomic binning and profiling. It interrogates large databases without using metagenome-assembled genomes, curated pan-genes or k-mer spectra that limit resolution. Qmatey minimizes misclassification and maintains strain level resolution by using only diagnostic reads as shown in the analysis of amplicon, quantitative reduced representation and shotgun sequencing datasets. Using Qmatey to analyze shotgun data from a synthetic community with 35% of the 26 strains at low abundance (0.01-0.06%), we revealed a remarkable 85-96% strain recall and 92-100% species recall while maintaining 100% precision. Benchmarking revealed that the highly ranked Kraken2 and KrakenUniq tools identified 2-4 more taxa (92-100% recall) than Qmatey but produced 315-1752 false positive taxa and high penalty on precision (1-8%). The speed, accuracy and precision of the Qmatey pipeline positions it as a valuable tool for broad-spectrum profiling and for uncovering biologically relevant interactions.

Genetic diversity of Salmonella enterica isolated over 13 years from raw California almonds and from an almond orchard.

A comparative genomic analysis was conducted for 171 Salmonella isolates recovered from raw inshell almonds and raw almond kernels between 2001 and 2013 and for 30 Salmonella Enteritidis phage type (PT) 30 isolates recovered between 2001 and 2006 from a 2001 salmonellosis outbreak-associated almond orchard. Whole genome sequencing was used to measure the genetic distance among isolates by single nucleotide polymorphism (SNP) analyses and to predict the presence of plasmid DNA and of antimicrobial resistance (AMR) and virulence genes. Isolates were classified by serovars with Parsnp, a fast core-genome multi aligner, before being analyzed with the CFSAN SNP Pipeline (U.S. Food and Drug Administration Center for Food Safety and Applied Nutrition). Genetically similar (≤18 SNPs) Salmonella isolates were identified among several serovars isolated years apart. Almond isolates of Salmonella Montevideo (2001 to 2013) and Salmonella Newport (2003 to 2010) differed by ≤9 SNPs. Salmonella Enteritidis PT 30 isolated between 2001 and 2013 from survey, orchard, outbreak, and clinical samples differed by ≤18 SNPs. One to seven plasmids were found in 106 (62%) of the Salmonella isolates. Of the 27 plasmid families that were identified, IncFII and IncFIB plasmids were the most predominant. AMR genes were identified in 16 (9%) of the survey isolates and were plasmid encoded in 11 of 16 cases; 12 isolates (7%) had putative resistance to at least one antibiotic in three or more drug classes. A total of 303 virulence genes were detected among the assembled genomes; a plasmid that harbored a combination of pef, rck, and spv virulence genes was identified in 23% of the isolates. These data provide evidence of long-term survival (years) of Salmonella in agricultural environments.

Deformable medical image registration with global-local transformation network and region similarity constraint.

Deformable medical image registration can achieve fast and accurate alignment between two images, enabling medical professionals to analyze images of different subjects in a unified anatomical space. As such, it plays an important role in many medical image studies. Current deep learning (DL)-based approaches for image registration directly learn spatial transformation from one image to another, relying on a convolutional neural network and ground truth or similarity metrics. However, these methods only use a global similarity energy function to evaluate the similarity of a pair of images, which ignores the similarity of regions of interest (ROIs) within the images. This can limit the accuracy of the image registration and affect the analysis of specific ROIs. Additionally, DL-based methods often estimate global spatial transformations of images directly, without considering local spatial transformations of ROIs within the images. To address this issue, we propose a novel global-local transformation network with a region similarity constraint that maximizes the similarity of ROIs within the images and estimates both global and local spatial transformations simultaneously. Experiments conducted on four public 3D MRI datasets demonstrate that the proposed method achieves the highest registration performance in terms of accuracy and generalization compared to other state-of-the-art methods.

A Novel Application of Polynomial Solvers in mmWave Analog Radio Beamforming

Beamforming is a signal processing technique where an array of antenna elements can be steered to transmit and receive radio signals in a specific direction. The usage of millimeter wave (mmWave) frequencies and multiple input multiple output (MIMO) beamforming are considered as the key innovations of 5 th Generation (5G) and beyond communication systems. The mmWave radio waves enable high capacity and directive communication, but suffer from many challenges such as rapid channel variation, blockage effects, atmospheric attenuations, etc. The technique initially performs beam alignment procedure, followed by data transfer in the aligned directions between the transmitter and the receiver [1]. Traditionally, beam alignment involves periodical and exhaustive beam sweeping at both transmitter and the receiver, which is a slow process causing extra communication overhead with MIMO and massive MIMO radio units. In applications such as beam tracking, angular velocity, beam steering etc. [2], beam alignment procedure is optimized by estimating the beam directions using first order polynomial approximations. Recent learning-based SOTA strategies [3] for fast mmWave beam alignment also require exploration over exhaustive beam pairs during the training procedure, causing overhead to learning strategies for higher antenna configurations. Therefore, our goal is to optimize the beam alignment cost functions e.g. , data rate, to reduce the beam sweeping overhead by applying polynomial approximations of its partial derivatives which can then be solved as a system of polynomial equations. Specifically, we aim to reduce the beam search space by estimating approximate beam directions using the polynomial solvers. Here, we assume both transmitter (TX) and receiver (RX) to be equipped with uniform linear array (ULA) configuration, each having only one degree of freedom (d.o.f.) with N t and N r antennas, respectively.

Strong Tracking UKF-Based Hybrid Algorithm and Its Application to Initial Alignment of Rotating SINS With Large Misalignment Angles

In this paper, the fast and precise initial alignment of the low-cost rotary strapdown inertial navigation system under mooring conditions is investigated. The unscented Kalman filter (UKF) is used to address model nonlinearity and to achieve fast alignment for large misalignment angles. A generalized multi-fading strong tracking UKF (GSTUKF) is proposed to effectively compensate for the kinematic model errors caused by mooring and rotary motions. The performance of the standard strong tracking UKF cannot be optimal because only a portion of the fading factors associated with the directly observable state variables can be obtained approximately using the analytical method. By contrast, using the iteration method to calculate the full-dimension fading factors precisely, the GSTUKF has greater robustness and adaptability. To find out the optimal fading factors in real time, the multivariate nonlinear optimization model is first designed, and then the iteration approach based on a hybrid algorithm consisting of particle swarm optimization and beetle antennae search is developed, which has no risk of falling into a local minimum. Simulations and experiments are conducted to validate the GSTUKF's effectiveness. The experiments demonstrate that the proposed method reduces the yaw error by 47.2% compared with the standard strong tracking UKF.

Deep learning-based registration of two-dimensional dental images with edge specific loss.

Image registration is a very common procedure in dental applications for aligning images. Registration between pairs of images taken from different angles can improve diagnosis. Our study presents an edge-enhanced unsupervised deep learning (DL)-based deformable registration framework for aligning two-dimensional (2D) pairs of dental x-ray images. The proposed neural network is based on the combination of a U-Net like structure, which produces a displacement field, combined with spatial transformer networks, which produce the transformed image. The proposed structure is trained end-to-end by minimizing a weighted loss function consisting of three parts corresponding to image similarity, edge similarity, and registration restrictions. In this regard, the proposed edge specific loss enhances the unsupervised training of the registration framework without the need of supervision through anatomical structures. The proposed framework was applied to two datasets, a set of 104 x-ray images of mandibles, arranged in 2600 pairs for training and testing and a set of 17 pairs of pre- and post-operative reconstructed panoramic images. The proposed model outperformed both conventional registration methods and DL-based techniques for both qualitative and quantitative assessment, in most of the compared metrics concerning intensity similarity and edge distances. The proposed framework achieved accurate and fast deformable alignment of pairs of 2D dental radiographic images. The edge-based module of the loss function enhances the unsupervised learning by directing the network toward deformations that take into consideration the edges of the depicted objects (teeth, bone, and tissue), which are crucial in diagnosis.

Beam Alignment for Analog Arrays Based on Gaussian Approximation

Beam alignment is a process for receive and transmit antenna arrays to find the correct beamforming directions. It is typically based on beam scanning and peak-energy searching, which lead to time-consuming beam training process in communication protocols, such as 802.11ad for vehicular networks. In this correspondence, we propose a fast beam alignment method for analog arrays, based on directly estimating the angle-of-arrival (AoA) of the incoming signals. We propose simple and highly efficient AoA estimators, by approximating the power of the array response as a Gaussian function. One estimator is based on the power ratio and can coherently combine multiple measurements scanned at arbitrary intervals and with different beam widths. The other two are based on an innovative idea of Gaussian curve fitting with weighted least square techniques, and one of them can even work without knowing the beam width. Simulation results validate the effectiveness of the proposed scheme.

Eliminating Space Scanning: Fast mmWave Beam Alignment with UWB Radios

Due to their large bandwidth and impressive data speed, millimeter-wave (mmWave) radios are expected to play a key role in the 5G and beyond (e.g., 6G) communication networks. Yet, to release mmWave’s true power, the highly directional mmWave beams need to be aligned perfectly. Most existing beam alignment methods adopt an exhaustive or semi-exhaustive space scanning, which introduces up to seconds of delays. To eliminate the need for complex space scanning, this article presents an Ultra-wideband (UWB)-assisted mmWave communication framework, which leverages the co-located UWB antennas to estimate the best angles for mmWave beam alignment. One major challenge of applying this idea in the real world is the barrier of limited antenna numbers. Commercial-Off-The-Shelf (COTS) devices are usually equipped with only a small number of UWB antennas, which are not enough for the existing algorithms to provide an accurate angle estimation. To solve this challenge, we design a novel Multi-Frequency MUltiple SIgnal Classification (MF-MUSIC) algorithm, which extends the classic MUltiple SIgnal Classification (MUSIC) algorithm to the frequency domain and overcomes the antenna limitation barrier in the spatial domain. Extensive real-world experiments and numerical simulations illustrate the advantage of the proposed MF-MUSIC algorithm. MF-MUSIC uses only three antennas to achieve an accurate angle estimation, which is a mere 0.15° (or a relative difference of 3.6%) different from the state-of-the-art 16-antenna-based angle estimation method.

Temporal characteristics of child-adult conversations: utterances and turn-taking

Since its inception, conversation analysis has focused on the question of how participants achieve a fast and smooth alignment between two turns. Most research has analyzed adults’ conversations, but much less has been known about child-adult interactions. The aim of this study is to analyze the temporal patterns of children’s utterances and turn-taking (TT). Twenty adult-child conversations (ages 5 and 7) were selected from the GABI database. Articulation rate, duration of interpausal units, pauses, and FTO-value (Floor Transfer Offset) of turn-taking launched by the children were analyzed. Temporal patterns did not differ between the two age groups, but individual differences were found within both groups. TT mostly occurred with a gap, but children were also able to take the floor immediately. TTs after a gap were significantly longer than after overlapping speech. The results provide new information on the communicative competence in childhood, particularly regarding timing patterns and organization of child-adult dialogues.

Fast Beam Alignment via Pure Exploration in Multi-Armed Bandits

The beam alignment (BA) problem consists in accurately aligning the transmitter and receiver beams to establish a reliable communication link in wireless communication systems. Existing BA methods search the entire beam space to identify the optimal transmit-receive beam pair. This incurs a significant latency when the number of antennas is large. In this work, we develop a bandit-based fast BA algorithm to reduce BA latency for millimeter-wave (mmWave) communications. Our algorithm is named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Two-Phase Heteroscedastic Track-and-Stop</i> (2PHT&S). We first formulate the BA problem as a pure exploration problem in multi-armed bandits in which the objective is to minimize the required number of time steps given a certain fixed confidence level. By taking advantage of the correlation structure among beams that the information from nearby beams is similar and the heteroscedastic property that the variance of the reward of an arm (beam) is related to its mean, the proposed algorithm groups all beams into several beam sets such that the optimal beam set is first selected and the optimal beam is identified in this set after that. Theoretical analysis and simulation results on synthetic and semi-practical channel data demonstrate the clear superiority of the proposed algorithm vis-à-vis other baseline competitors.

Inter-fraction deformable image registration using unsupervised deep learning for CBCT-guided abdominal radiotherapy

Objective. CBCTs in image-guided radiotherapy provide crucial anatomy information for patient setup and plan evaluation. Longitudinal CBCT image registration could quantify the inter-fractional anatomic changes, e.g. tumor shrinkage, and daily OAR variation throughout the course of treatment. The purpose of this study is to propose an unsupervised deep learning-based CBCT-CBCT deformable image registration which enables quantitative anatomic variation analysis. Approach. The proposed deformable registration workflow consists of training and inference stages that share the same feed-forward path through a spatial transformation-based network (STN). The STN consists of a global generative adversarial network (GlobalGAN) and a local GAN (LocalGAN) to predict the coarse- and fine-scale motions, respectively. The network was trained by minimizing the image similarity loss and the deformable vector field (DVF) regularization loss without the supervision of ground truth DVFs. During the inference stage, patches of local DVF were predicted by the trained LocalGAN and fused to form a whole-image DVF. The local whole-image DVF was subsequently combined with the GlobalGAN generated DVF to obtain the final DVF. The proposed method was evaluated using 100 fractional CBCTs from 20 abdominal cancer patients in the experiments and 105 fractional CBCTs from a cohort of 21 different abdominal cancer patients in a holdout test. Main Results. Qualitatively, the registration results show good alignment between the deformed CBCT images and the target CBCT image. Quantitatively, the average target registration error calculated on the fiducial markers and manually identified landmarks was 1.91 ± 1.18 mm. The average mean absolute error, normalized cross correlation between the deformed CBCT and target CBCT were 33.42 ± 7.48 HU, 0.94 ± 0.04, respectively. Significance. In summary, an unsupervised deep learning-based CBCT-CBCT registration method is proposed and its feasibility and performance in fractionated image-guided radiotherapy is investigated. This promising registration method could provide fast and accurate longitudinal CBCT alignment to facilitate inter-fractional anatomic changes analysis and prediction.

Scrooge: A Fast and Memory-Frugal Genomic Sequence Aligner for CPUs, GPUs, and ASICs.

Pairwise sequence alignment is a very time-consuming step in common bioinformatics pipelines. Speeding up this step requires heuristics, efficient implementations, and/or hardware acceleration. A promising candidate for all of the above is the recently proposed GenASM algorithm. We identify and address three inefficiencies in the GenASM algorithm: it has a high amount of data movement, a large memory footprint, and does some unnecessary work. We propose Scrooge, a fast and memory-frugal genomic sequence aligner. Scrooge includes three novel algorithmic improvements which reduce the data movement, memory footprint, and the number of operations in the GenASM algorithm. We provide efficient open-source implementations of the Scrooge algorithm for CPUs and GPUs, which demonstrate the significant benefits of our algorithmic improvements. For long reads, the CPU version of Scrooge achieves a 20.1×, 1.7×, and 2.1× speedup over KSW2, Edlib, and a CPU implementation of GenASM, respectively. The GPU version of Scrooge achieves a 4.0× 80.4×, 6.8×, 12.6× and 5.9× speedup over the CPU version of Scrooge, KSW2, Edlib, Darwin-GPU, and a GPU implementation of GenASM, respectively. We estimate an ASIC implementation of Scrooge to use 3.6× less chip area and 2.1× less power than a GenASM ASIC while maintaining the same throughput. Further, we systematically analyze the throughput and accuracy behavior of GenASM and Scrooge under various configurations. As the best configuration of Scrooge depends on the computing platform, we make several observations that can help guide future implementations of Scrooge. https://github.com/CMU-SAFARI/Scrooge.

Fast Two-position Initial Alignment of SINS Based on CKF

In practical vehicle applications, the initial alignment environment of SINS is more complicated, and the coarse alignment accuracy is not high due to carrier sloshing, which leads to the filtering problem of nonlinear system in fine alignment. The traditional two-position alignment method based on EKF is no longer applicable. In this paper, a fast two-position alignment method of SINS based on CKF is proposed. Use two CKFs for state estimation at two locations respectively, then the error parameters are solved through the spatial relationship between the two positions. The simulation shows that using CKF improves accuracy compared to EKF. Verified by experiment, the two-position alignment method based on CKF can better adapt to the nonlinear system, which can be applied in practical engineering.