Part Of Representation Research Articles

A novel method based on deep reinforcement learning for machining process route planning

Efficient and high-quality machining process route planning is crucial in the realm of manufacturing. Traditional methods heavily rely on human-computer interaction, which can be inefficient. To enhance the efficiency of machining process route planning, this paper introduces a novel framework based on deep reinforcement learning (DRL), designed to automatically generate machining process routes for designated parts. The framework treats machining process route planning as a Markov decision process, making it amenable to DRL techniques. For effective representations of parts, the framework utilizes directed attributed adjacency graphs, wherein nodes represent machining features and edges represent their relationships. To effectively process the graphs, convolutional graph neural networks are employed as the underlying neural networks in the framework. After training, the framework is able to generate efficient machining process routes while adhering to machining process rules. Experimental studies conducted on a number of aircraft structural parts serve as examples to show the feasibility and effectiveness of the proposed approach. The experimental results underscore the effectiveness of the proposed method in machining processes planning for parts and its ability to overcome limitations in traditional methods. As a result, this study contributes to the enhancement of process planning efficiency within the manufacturing domain, carrying practical implications.

Standardized Representation of Parts and Assembly for Build Planning.

The design and construction of genetic systems, in silico, in vitro, or in vivo, often involve the handling of various pieces of DNA that exist in different forms across an assembly process: as a standalone "part" sequence, as an insert into a carrier vector, as a digested fragment, etc. Communication about these different forms of a part and their relationships is often confusing, however, because of a lack of standardized terms. Here, we present a systematic terminology and an associated set of practices for representing genetic parts at various stages of design, synthesis, and assembly. These practices are intended to represent any of the wide array of approaches based on embedding parts in carrier vectors, such as BioBricks or Type IIS methods (e.g., GoldenGate, MoClo, GoldenBraid, and PhytoBricks), and have been successfully used as a basis for cross-institutional coordination and software tooling in the iGEM Engineering Committee.

Comparing and Evaluating Human and Computationally Derived Representations of Non-Semantic Design Information

Abstract Design artifacts provide a mechanism for illustrating design information and concepts, but their effectiveness relies on alignment across design agents in what these artifacts represent. This work investigates the agreement between multi-modal representations of design artifacts by humans and artificial intelligence (AI). Design artifacts are considered to constitute stimuli designers interact with to become inspired (i.e., inspirational stimuli), for which retrieval often relies on computational methods using AI. To facilitate this process for multi-modal stimuli, a better understanding of human perspectives of non-semantic representations of design information, e.g., by form or function-based features, is motivated. This work compares and evaluates human and AI-based representations of 3D-model parts by visual and functional features. Humans and AI were found to share consistent representations of visual and functional similarities, which aligned well with coarse, but not more granular, levels of similarity. Human–AI alignment was higher for identifying low compared to high similarity parts, suggesting mutual representation of features underlying more obvious than nuanced differences. Human evaluation of part relationships in terms of belonging to the same or different categories revealed that human and AI-derived relationships similarly reflect concepts of “near” and “far.” However, levels of similarity corresponding to “near” and “far” differed depending on the criteria evaluated, where “far” was associated with nearer visually than functionally related stimuli. These findings contribute to a fundamental understanding of human evaluation of information conveyed by AI-represented design artifacts needed for successful human–AI collaboration in design.

Towards a model-based approach: applications to historical demography and palaeodemography

There is a large variety of different kinds of models. However, we think that they all have in common to represent something beyond themselves: they are representations of parts of the world. As scientists, we are driven to select only a few aspects of the phenomena studied. However, these aspects will be characterized with great precision. This explains why models are only considering parts of the world as we are driven to select only a few aspects of the phenomena studied. We will first give a historical presentation of models to show their usefulness in the past. We will then develop agent-based models, which are most used in demography, but also in historical demography. Some of them are not able to solve this incompleteness. Finally, we will show how a deeper philosophical approach to these problems may permit a true scientific treatment of explanation in demography.

Boundary-guided part reasoning network for human parsing

The task of human parsing aims to segment the human body into different semantic regions. Despite advancements in this field, there are still two issues with current works: boundary indistinction and parsing inconsistency. In this paper, we investigate how to utilize structural information and auxiliary information to jointly solve the above two problems. Drawing inspiration from Transformer architecture, a Boundary-guided Part Reasoning Network (BPRNet) is proposed to combine edge information and associated semantics of body parts for human parsing. Specifically, we design a part representation module to represent human body parts as part features. Based on the Transformer decoder, a multi-head self-attention is used to capture the semantic correlation between the human body. Moreover, we propose a boundary-guided module consisting of absolute boundary attention and reinforced boundary attention. They take advantage of edge information and multi-scale image features to jointly constrain cross-attention to extract global features. Experiments and corresponding results on three public datasets show that the proposed method performs favorably against the state-of-the-art methods.

Automatic Multiview Alignment of RGB-D Range Maps of Upper Limb Anatomy.

Digital representations of anatomical parts are crucial for various biomedical applications. This paper presents an automatic alignment procedure for creating accurate 3D models of upper limb anatomy using a low-cost handheld 3D scanner. The goal is to overcome the challenges associated with forearm 3D scanning, such as needing multiple views, stability requirements, and optical undercuts. While bulky and expensive multi-camera systems have been used in previous research, this study explores the feasibility of using multiple consumer RGB-D sensors for scanning human anatomies. The proposed scanner comprises three Intel® RealSenseTM D415 depth cameras assembled on a lightweight circular jig, enabling simultaneous acquisition from three viewpoints. To achieve automatic alignment, the paper introduces a procedure that extracts common key points between acquisitions deriving from different scanner poses. Relevant hand key points are detected using a neural network, which works on the RGB images captured by the depth cameras. A set of forearm key points is meanwhile identified by processing the acquired data through a specifically developed algorithm that seeks the forearm's skeleton line. The alignment process involves automatic, rough 3D alignment and fine registration using an iterative-closest-point (ICP) algorithm expressly developed for this application. The proposed method was tested on forearm scans and compared the results obtained by a manual coarse alignment followed by an ICP algorithm for fine registration using commercial software. Deviations below 5 mm, with a mean value of 1.5 mm, were found. The obtained results are critically discussed and compared with the available implementations of published methods. The results demonstrate significant improvements to the state of the art and the potential of the proposed approach to accelerate the acquisition process and automatically register point clouds from different scanner poses without the intervention of skilled operators. This study contributes to developing effective upper limb rehabilitation frameworks and personalized biomedical applications by addressing these critical challenges.

COMPARISON OF SCALED HYBRID SIMULATIONS AND SHAKING TABLE TESTS ON A 2-SPAN REINFORCED CONCRETE BRIDGE

Hybrid simulation is a testing paradigm combining experimental and computational simulations through a hybrid model which comprises scaled physical and numerical representation of various parts of a structural system. The physical and numerical elements interact within a single model by satisfying the displacement compatibility and the force equilibrium at the common nodes. Hybrid simulation offers numerous advantages, including cost savings and a deeper understanding of complex structures. In this paper, an investigation has been carried out to study the effect of scaling on the accuracy of hybrid simulations of a 2-span reinforced concrete highway bridge. The experimental program included hybrid simulations on 1/10, 1/8 and 1/6 scaled models of a two-span reinforced concrete bridge loaded to failure under seven (7) consecutive seismic events. The seismic motions replicating the 1994 Northridge earthquake in California, were applied with progressively increasing amplitudes. The results of shaking table tests on a 1/4 scaled model of the bridge were used to study the accuracy and reliability of different scales of the hybrid simulations.

Mathematical self-determination theory II: Affine space representation

Self-determination theory is a well-established theory of motivation. This theory provides for fundamental concepts related to human motivation, including self-determination. The mathematization of this theory has been envisaged in a series of two papers by the author. The first paper entitled “Mathematical self-determination theory I: Real representation” addressed the representation of the theory in reals. This second paper is in continuation of it. The representation of the first part allows to abstract the results in more general mathematical structures, namely, affine spaces. The simpler real representation is reobtained as a special instance. We take convexity as the pivotal starting point to generalize the whole exposition and represent self-determination theory in abstract affine spaces. This includes the affine space analogs of the notions of internal locus, external locus, and impersonal locus, of regulated and graded motivation, and self-determination. We also introduce polar coordinates in Euclidean affine motivation spaces to study self-determination on radial and angular line segments. We prove the distributivity of the lattice of general self-determination in the affine space formulation. The representation in an affine space is free in the choice of primitives. However, the different representations, in reals or affine, are shown to be unique up to canonical isomorphism. The aim of this paper is to extend on the results obtained in the first paper, thereby to further lay the mathematical foundations of self-determination motivation theory.

Robust Gait Recognition Based on Deep CNNs With Camera and Radar Sensor Fusion

In recent years, gait recognition has emerged as an important and promising solution for human identification. Generally, gait recognition is based on a single type of sensor, such as a camera or a radar. However, data of a single modality may only capture inadequate gait features of a person, such as camera data lacking the intuitive micro-motion pattern information and radar data lacking the information about gait appearance, making gait-based human identification system vulnerable to complex covariate conditions, e.g. cross-view and cross-walking-condition. To build a robust and reliable gait-based human identification system, in this study, we propose a multi-sensor gait recognition framework with deep convolutional neural networks (CNNs) by fusing camera gait energy images (GEIs) and radar time-Doppler spectrograms. To learn the fine-grained gait appearance features, we propose a body-part spatial attention (BPSA) module to obtain more discriminative body part representations of GEIs. To learn the gait micro-motion pattern, we propose a long-short temporal relation modeling (LSTRM) module to obtain the local and global micro-motion representation of time-Doppler spectrograms. Finally, we fuse the discriminative body part representation and the micro-motion pattern at the multi-scale feature space to obtain richer and more robust gait features for human identification. We provide an extensive empirical evaluation in terms of various complex covariate conditions, namely, cross-view and cross-walking-condition. Experiments on 121 subjects with eight views and three walking conditions of camera and radar data show our proposed method is more robust and accurate.

"A STUDY ON JUDICIAL CUSTODY IN ISLAMIC LAW AND ITS IMPACT ON

This research aims to determine the nature and importance of judicial supervision in the Islamic legal system and its role in enforcing justice in Islamic societies. The significance of this study lies in its representation of an essential part of the Islamic legal system, as it helps achieve security and safety in society and preserves individuals' rights in the face of social, economic, and technological changes experienced by Islamic societies. The research problem is to determine the effectiveness of judicial supervision in meeting the needs of society and establishing trust between citizens and the judiciary system, as well as identifying whether there is a need to develop and update methods of judicial supervision in Islamic societies. Based on previous studies and research, the study found that judicial supervision plays a crucial role in achieving justice and enforcing the law in Islamic societies. It also improves trust between citizens and the judiciary system and protects individuals from injustice and corruption by judicial officials. The study's results include determining the effectiveness of judicial supervision in meeting the needs of society and preserving individuals' rights in the face of social, economic, and technological changes experienced by Islamic societies. Additionally, it is possible to identify various methods of judicial supervision and whether there is a need to develop or reform them to achieve social and economic stability in Islamic societies. In general, achieving social justice in Islamic societies requires considering the role of judicial supervision and developing and updating its methods to achieve security, safety, and justice in these communities.

Late Holocene tule elk (Cervus canadensis nannodes) resource depression and distant patch use in central California: Faunal and isotopic evidence from King Brown and the Emeryville Shellmound

Previous research has documented declines in the abundance of high-return resources including tule elk (Cervus canadensis nannodes) over the past three millennia in central California, suggesting the occurrence of resource depression. We test the hypothesis that hunting depressed tule elk in this setting by articulating stable isotope analyses from 88 directly dated tule elk specimens with data on the age structure and skeletal part representation from the King Brown and Emeryville Shellmound sites. Late Holocene trends in stable isotopes and modeled climatic variation are inconsistent with climate-based population declines. However, at King Brown, located within the Central Valley and vast tule elk freshwater marsh and grassland habitat, increasing isotopic diversity, a decline in mean age, and increasing abundance of high-utility skeletal elements suggest local depression stimulated the increasing use of distant elk patches. Although faunal trends are consistent with the depression of elk at Emeryville, the site is located on the shore of the San Francisco Bay where limited elk habitat existed, and no evidence of distant elk patch use is indicated. This analysis underscores how human behavioral responses to resource depression can vary in relation to the local ecology as they affect patch use economics for specific prey and demonstrates how such responses can be deciphered through stable isotope and faunal data.

PSPDNet: Part-aware shape and pose disentanglement neural network for 3D human animating meshes

Disentangled representations of shape and pose are essential for animating human body meshes in computer animation, computer games, and virtual reality applications. While recent deep neural networks have achieved impressive effectiveness, their performance in terms of interpretability, reconstruction precision, and fine-grained control is not satisfactory. To address these issues, we propose the Part-aware Shape and Pose Disentanglement neural network (PSPDNet), a framework for disentangling the shape and pose of 3D human meshes with the same connectivity. PSPDNet utilizes part mesh autoencoders to learn representations of different human body parts, enhancing the interpretability of the latent codes by corresponding them with local motions. While mesh autoencoders alone can decouple shape and pose information from animated meshes, they fail to control local motions. In addition, PSPDNet employs an additional rotation-translation module to remove global rigid motion, i.e., rotation and translation, from the sequence. Finally, we propose a novel loss function which includes disentanglement loss and alignment loss to train PSPDNet in an unsupervised manner. Our experiments show that PSPDNet greatly improves disentangled representation with strong interpretability, insensitivity to global rigid transformation, and locality of editing and controlling.

Application of oriented methods for computing shortest paths and principal curvatures on triangle surfaces

The paper considers two problems: computation of shortest paths on triangle surfaces and calculation of principal curvatures at vertices of triangle surfaces. A technique that allows us to compute smoother and shorter paths using intermediate admissible directions and linear interpolation of potential functions is proposed. Conventional methods that compute the curvature in nodes of triangle surfaces are based on processing only adjacent vertices. They are non stable because triangle meshes contain frequently oscillating errors in positions of the vertices. We propose a simple practical method that accounts for larger neighborhoods of vertices. The kriging method aimed to the sparse representation of specific surface parts (aesthetic regions) is sketched. Preliminary numerical results are presented.

Learning a Model of Shape Selectivity in V4 Cells Reveals Shape Encoding Mechanisms in the Brain.

The mechanisms involved in transforming early visual signals to curvature representations in V4 are unknown. We propose a hierarchical model that reveals V1/V2 encodings that are essential components for this transformation to the reported curvature representations in V4. Then, by relaxing the often-imposed prior of a single Gaussian, V4 shape selectivity is learned in the last layer of the hierarchy from Macaque V4 responses. We found that V4 cells integrate multiple shape parts from the full spatial extent of their receptive fields with similar excitatory and inhibitory contributions. Our results uncover new details in existing data about shape selectivity in V4 neurons that with additional experiments can enhance our understanding of processing in this area. Accordingly, we propose designs for a stimulus set that allow removing shape parts without disturbing the curvature signal to isolate part contributions to V4 responses.SIGNIFICANCE STATEMENT Selectivity to convex and concave shape parts in V4 neurons has been repeatedly reported. Nonetheless, the mechanisms that yield such selectivities in the ventral stream remain unknown. We propose a hierarchical computational model that incorporates findings of the various visual areas involved in shape processing and suggest mechanisms that transform the shape signal from low-level features to convex/concave part representations. Learning shape selectivity from Macaque V4 responses in the final processing stage in our model, we found that V4 neurons integrate shape parts from the full spatial extent of their receptive field with both facilitatory and inhibitory contributions. These results reveal hidden information in existing V4 data that with additional experiments can enhance our understanding of processing in V4.

HOW METAVERSE EVOLVES THE ARCHITECTURAL DESIGN

Architects have long relied on visualization tools to develop their concepts for specific design problems. From the early traditional drawings to the three-dimensional visualizations and virtual environments, all have enabled architects to demonstrate design outputs relatively early in the process. Real-world projects are similar to what architects imagined from the beginning. In other words, the design process has always started by creating the digital representation of a project and then attempting to replicate it in real life. Once the digital representation of design parts is complete, architects prepare their design for construction. However, the final visualization emerges from actual architectural functions, structure constraints, Gravity, materiality, privacy, and physical laws, meaning that architecture evolves the digitally represented visualizations. With the growth of the metaverse, all physical restrictions are being eliminated, and architects can expand the boundaries of how spaces can be represented regardless of being virtual or physical. As a virtual environment on the internet, the metaverse redefines the rules of architecture and offers endless possibilities for architectural innovation. This article aims to explore the role the metaverse plays in designing architecture. It outlines the fundamental concepts of the metaverse to identify significant elements that could influence architecture design.

Manufacturing Process Classification Based on Distance Rotationally Invariant Convolutions

Abstract Given a part design, the task of manufacturing process classification identifies an appropriate manufacturing process to fabricate it. Our previous research proposed a large dataset for manufacturing process classification and achieved accurate classification results based on a combination of a convolutional neural network (CNN) and the heat kernel signature for triangle meshes. In this paper, we constructed a classification method based on rotation invariant shape descriptors and a neural network, and it achieved better accuracy than all previous methods. This method uses a point cloud part representation, in contrast to the triangle mesh representation used in our previous work. The first step extracted rotation invariant features consisting of a set of distances between points in the point cloud. Then, the extracted shape descriptors were fed into a CNN for the classification of manufacturing processes. In addition, we provide two visualization methods for interpreting the intermediate layers of the neural network. Last, the performance of the method was tested on some ambiguous examples and their performances were consistent with expectations. In this paper, we have considered only shape information, while non-shape information like materials and tolerances were ignored. Additionally, only parts that require one manufacturing process were considered in this research. Our work demonstrates that part shape attributes alone are adequate for discriminating between different manufacturing processes considered.

Taphonomic skeletal disturbances in the Sima de los Huesos postcranial remains.

The postcranial skeleton of fossil hominins is crucial for reconstructing the processes that occurred between the time of death and the recovery of the bones. Thousands of postcranial skeletal fragments from at least 29 hominin individuals have been recovered from the Sima de los Huesos Middle Pleistocene site in Spain. This study's primary objective is to address the main taphonomic features of the postcranial remains from the Sima de los Huesos sample, including antemortem, perimortem, and postmortem skeletal disturbances. We present an updated assessment of the bone surface modification analysis, the fracture pattern analysis, and the skeletal part representation to facilitate interpretation of the biostratinomic and fossil-diagenetic processes in this large paleoanthropological collection. We conclude that carnivores (probably bears) had limited access to the hominin bones and complete bodies were probably placed in the site.

MFANet: A Collar Classification Network Based on Multi-Scale Features and an Attention Mechanism

The collar is an important part of a garment that reflects its style. The collar classification task is to recognize the collar type in the apparel image. In this paper, we design a novel convolutional module called MFA (multi-scale features attention) to address the problems of high noise, small recognition target and unsatisfactory classification effect in collar feature recognition, which first extracts multi-scale features from the input feature map and then encodes them into an attention weight vector to enhance the representation of important parts, thus improving the ability of the convolutional block to combat noise and extract small target object features. It also reduces the computational overhead of the MFA module by using the depth-separable convolution method. Experiments on the collar dataset Collar6 and the apparel dataset DeepFashion6 (a subset of the DeepFashion database) show that MFANet is able to perform at a relatively small number of collars. MFANet can achieve better classification performance than most current mainstream convolutional neural networks for complex collar images with less computational overhead. Experiments on the standard dataset CIFAR-10 show that MFANet also outperforms current mainstream image classification algorithms.

Series of first-order phase shifts correct lattice reduction of fractional K-space indices

Lattice reduction of K-space acquisition at fractional indices refers to reducing the indices to the smallest nearby integer, thereby generating a Cartesian grid, allowing subsequent inverse Fourier Transformation. For band-limited signals, we show that the error in lattice reduction is equivalent to first order phase shifts, which in the infinite limit approaches W∞=φ(cotφ-i), where φ is a first-order phase shift vector. In general, the inverse corrections can be specified from the binary representation of the fractional part of the K-space indices. For non-uniform sparsity, we show how to incorporate the inverse corrections into compressed sensing reconstructions.

Unitarity cuts of the worldsheet

We compute the imaginary parts of genus-one string scattering amplitudes. Following Witten’s i\varepsiloniε prescription for the integration contour on the moduli space of worldsheets, we give a general algorithm for computing unitarity cuts of the annulus, Möbius strip, and torus topologies exactly in \alpha'α′. With the help of tropical analysis, we show how the intricate pattern of thresholds (normal and anomalous) opening up arises from the worldsheet computation. The result is a manifestly-convergent representation of the imaginary parts of amplitudes, which has the analytic form expected from Cutkosky rules in field theory, but bypasses the need for performing laborious sums over the intermediate states. We use this representation to study various physical aspects of string amplitudes, including their behavior in the (s,t)(s,t) plane, exponential suppression, decay widths of massive strings, total cross section, and low-energy expansions. We find that planar annulus amplitudes exhibit a version of low-spin dominance: at any finite energy, only a finite number of low partial-wave spins give an appreciable contribution to the imaginary part.