Explore the vast range of titles available.

Automating the drafting process significantly reduces time and cost, previously dependent on the personal intuition and expertise of pattern makers. Moreover, it has the potential to contribute to the automation of the entire production process. However, the integration of algorithms into the patterns is necessary to automate the drafting of patterns directly on computers based on the pattern maker's intuition. Parametric patterns, which express the silhouette, a formative constraint intimately linked to the pattern, through drafting formulas utilizing key body dimensions as variables, present a promising alternative for the automation of the drafting process. This study develops parametric production patterns for automated garment manufacturing processes by integrating ease allowances and design elements into basic patterns. Leveraging the zero-ease allowance pattern from previous studies, we created basic parametric patterns by incorporating constant values into the ratio formula of parametric nude patterns. Subsequently, the rules for applying design elements were added to develop production patterns of various sizes. The developed patterns were compared with those generated using conventional grading methods. The results indicate that the parametric production patterns closely maintain fit and silhouette, demonstrating their potential as automated alternatives to conventional drafting methods solely based on size specifications and body measurements. Furthermore, we believe that through subsequent studies and analyzing a broader range of garment types and sizes, the methodology of the parametric production pattern developed in this research will contribute to establishing foundational algorithms for automating the process of garment pattern generation.

A novel zero-waste pattern generation system, named SNU-ZWP (Zero-Waste Pattern), has been developed to improve fabric utilization efficiency and minimize textile waste. The system implements the ABCD (Arrangement-Based Conventional pattern Dilation) method, which enables automatic transformation of conventional garment patterns into zero-waste layouts. The ABCD method consists of three processes: dilation, rectangular adjustments, and auxiliary-rectangular adjustments, each supported by specialized algorithms. The system was further enhanced with a 3D garment simulator, enabling two-dimensional zero-waste patterns to be placed onto a virtual human body for realistic visualization. To evaluate its performance, 10 participants were recruited to test the system in generating zero-waste patterns. The results demonstrated that SNU-ZWP is effective across multiple dimensions, providing improved efficiency in zero-waste pattern design, enhanced creative pattern-making capabilities, and potential applications in both educational and industrial contexts. These findings indicate that this study focuses on both developing and evaluating the SNU-ZWP system, demonstrating its potential to advance innovative zero-waste fashion design and sustainable production practices.

The testing process of various electronic design automation tools and the verification process of the manufacturability of a developed Design Rule Check (DRC) deck, particularly in very-large-scale integration designs, is highly dependent on the presence of test data that covers a vast range of the design space in a layout design. However, test data extracted from real designs often lacks the diversity necessary to ensure high coverage during the testing process. This creates a need for a synthetic layout test pattern generator capable of producing diverse test clips to ensure robust testing, where a test clip represents a DRC clean segment of a layout design that encapsulates various layout patterns. This study proposes the use of the advanced Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) to generate a vast and diverse collection of synthetic test clips. The proposed workflow includes WGAN-GP for pattern generation, followed by a legalization process, and ending with generation assessment. Experimental results have shown promising outcomes in terms of the quantity and diversity of the generated patterns. The generated patterns were fully legalized, ensuring they are DRC clean. The diversity of the generated test clips, assessed using Shannon entropy, reached 8.4, while the training clips scored 8.1. This indicates a high diversity ratio between the generated and training datasets, outperforming previous methods and demonstrating the effectiveness of the generation approach.

Camouflage design necessitates region-consistent colour and texture synthesis. However, practical datasets are frequently constrained by scarce paired supervision and cross-source distribution shift, which impede reliable generalisation across heterogeneous environments. To address this problem, we propose a region-feature-driven framework for camouflage generation from unpaired background sequences. The main framework-level contribution lies in constructing a decoupled sequence-conditioned regional representation and using it to drive a fused-background-first camouflage-generation pipeline under unpaired supervision. Specifically, each background sequence is encoded into a continuous region descriptor and combined with a discrete Environment × Season code; under unpaired supervision, this decoupled condition guides StyleGAN2-based fused-background synthesis via style modulation, after which a deterministic digital-camouflage renderer converts the synthesised fused background into a deployable pattern. On a stratified test split, the synthesised backgrounds achieve FID = 15.2 ± 0.5, KID = 4.7 ± 0.3 × 10−3, while also showing stable condition adherence under the tested settings. Auxiliary sequence-consistency proxy measures are PSNR = 34.56 dB, SSIM = 0.776, and LPIPS = 0.134. Under a paired forest-scenario detector protocol, the generated camouflage reduces mean image-best IoU from 0.716 to 0.400 for a one-stage detector and from 0.690 to 0.460 for a two-stage detector. Overall, these results support the effectiveness of the proposed condition design and transfer mechanism under the present experimental setting.

This work presents a new approach for built-in test pattern generation (BIST) based on the variable rate clock-driven linear feedback shift register (LFSR) and twisted-ring counters (TRCs). The proposed technique operates on different operating clocks for generating deterministic test pattern sequence for the circuit under test (CUT). The test vectors generated by LFSR are transformed and reproduced with TRC results. The TRC design constitutes of only flip-flops, which be used as a potential alternative to improved seed storage and complex multi polynomial configurations in LFSR. Moreover, the control logic is simplified with synchronized multi-rate clock generation and can be easily extended for any test cubes among multiple CUTs. The randomness characteristics of LFSR are retained with improved memory efficiency and considerable complexity reduction. Experimental results validate the proposed test pattern generator (TPG) over existing well-known LFSRs models, and its randomness is proved with ISCAS benchmark circuits.

Hardware Trojan (HT) is a severe security threat during the development of an integrated circuit that can deviate the IC from its normal function and/or leak sensitive information during in-field operations. Trojans are often inserted during the fabrication phase, and to have Trojan-free ICs; it is highly desirable to detect them during post-silicon testing. Different test pattern generation-based HT detection techniques are reported in the literature to detect the Trojan during post-silicon testing. The existing methods provide low coverage and require a large number of test patterns. This paper proposes a new test pattern generation-based HT detection technique that provides high coverage while requiring less number of patterns. The proposed technique generates the optimal number of test patterns that activate the rare events by framing the problem as multi-objective optimization and solving it through a non-dominated sorting genetic algorithm (NSGA-II). The Trojans are mostly inserted using rare-triggered nodes (highly vulnerable, low controllable, and low observable). Thus, our technique applies the generated patterns during post-silicon testing to activate Trojans. Further, we also present the use of checker (detection) logic along with a proposed approach to effectively detect the Trojan during testing. The experimental evaluation on ISCAS benchmarks shows that the proposed technique provides 12 times higher trigger coverage with 1/3 fewer test patterns than the best-known existing genetic algorithm-based technique.

Powered exoskeletons for people with complete paraplegia are subject to repetitive large impacts due to the recurrent ground contacts. Those impact forces not only deteriorate the ride comfort but also cause a serious damage to the musculoskeletal system of the human wearing the powered exoskeleton. To address the issue, a mechanism to absorb shock for powered exoskeletons are proposed in this paper. The proposed shock absorption mechanism was integrated into the WalkON Suit, a powered exoskeleton for complete paraplegics. To obtain the desired performance of the proposed mechanism, the gait pattern of the powered exoskeleton was also designed. The mechanism and gait pattern generation algorithm were verified from experiments with a human subject.

The objective is to find a Cellular Automata (CA) rule that can generate “loop patterns”. A loop pattern is given by ones on a zero background showing loops. In order to find out how loop patterns can be locally defined, tentative loop patterns are generated by a genetic algorithm in a preliminary stage. A set of local matching tiles is designed and checked whether they can produce the aimed loop patterns by the genetic algorithm. After having approved a certain set of tiles, a probabilistic CA rule is designed in a methodical way. Templates are derived from the tiles, which then are used in the CA rule for matching. In order to drive the evolution to the desired patterns, noise is injected if the templates do not match or other constraints are not fulfilled. Simulations illustrate that loops and connected loops can be evolved by the CA rule.

Various exoskeleton robots are being developed according to users’ conditions. Lower limb exoskeleton robots have attracted much attention for performing walking motions, a basic exercise for paralyzed patients. In this study, the walking environment of an exoskeleton robot wearer who walks using a crutch is identified as the foot position of the crutch support point and the support leg; therefore, the upcoming foothold location is calculated and sets as a control target. Rather than using preset pedestrian patterns, pedestrian patterns that can match the environment are created using the dynamic movement primitives machine learning technology. We evaluated the exoskeleton robot through an experiment with a healthy 29-year-old male. The experimental results showed that the exoskeleton robot was able to demonstrate the adaptive strides according to the wearer’s intention.

For the central pattern generation inspired biped walking control algorithm, it is hard to coordinate all the degrees of freedom of a robot by regulating the parameters of a neutral network to achieve stable and adaptive walking. In this work, a hybrid rhythmic–reflex control method is presented, which can realize stable and adaptive biped walking. By integrating zero moment position information, the walking stability can be improved on flat terrain. The robot’s body attitude information is used to modulate the control system in real-time to realize sloped terrain adaptive walking. A staged parameter evolution process is used to derive the parameters. Through the entrainment of the oscillatory network and the feedback information, the real-time joint control signals can be regulated to realize adaptive walking. The presented control strategy has been verified by using a biped robot restricted in sagittal plane and the experiments reveal that the robot can successfully achieve changing sloped terrain adaptive walking.