Generation Algorithm Research Articles

Development of a dedicated process simulator for the digital twin in apparel manufacturing: a case study

PurposeThe purpose of this study is to introduce a dedicated simulator to automatically generate and simulate a balanced apparel assembly line, which is critical to the digital twin concept in apparel manufacturing. Given the low automation level in apparel manufacturing, this is a first step toward the implementation of a smart factory based on cyber-physical systems.Design/methodology/approachThe mixed task assignment algorithm was implemented to automatically generate a module-based apparel assembly line in the developed simulator. To validate the developed simulator, a case study was conducted using process analysis data of technical jackets obtained from an apparel manufacturer. The case study included three scenarios: calculating the number of workers, selecting orders based on factory capacity and managing unexpected worker absences.FindingsThe developed simulator is approximately 97.2% accurate in assigning appropriate tasks to workstations using the mixed task assignment algorithm. The simulator was also found to be effective in supporting decision-making for production planning, order selection and apparel assembly line management. In addition, the module-based line generation algorithm made it easy to modify the assembly line.Originality/valueThis study contributes a novel approach to address the challenge of low automation levels in apparel manufacturing by introducing a dedicated simulator. This dedicated simulator improves the efficiency of virtual apparel assembly line generation and simulation, which distinguishes it from existing commercial simulation software.

Application of Music Retrieval & Generation

The research explores music generation through LSTM and VAEs neural network architectures, leveraging MIDI representations. LSTM specializes in sequential data processing, while VAEs compress music datasets into low-dimensional representations. Optimization of models is pursued by analyzing the relationship between training loss and epochs. Ultimately, a comparison between LSTM and VAEs determines the most effective algorithm for music generation. Traditional methods face issues like vanishing and exploding gradients, prompting exploration of deep learning approaches. The study aims to advance machine manipulation of music, facilitating new composition generation from existing MIDI files. Keywords: Music generation, LSTM, Variational Autoencoders (VAEs), MIDI representation, Sequential data, Neural network architectures, Training loss, Optimization, Deep learning, Vanishing gradient, Exploding gradient

Dual Dynamic Threshold Adjustment Strategy

Loss functions and sample mining strategies are essential components in deep metric learning algorithms. However, the existing loss function or mining strategy often necessitates the incorporation of additional hyperparameters, notably the threshold, which defines whether the sample pair is informative. The threshold provides a stable numerical standard for determining whether to retain the pairs. It is a vital parameter to reduce the redundant sample pairs participating in training. Nonetheless, finding the optimal threshold can be a time-consuming endeavor, often requiring extensive grid searches. Because the threshold cannot be dynamically adjusted in the training stage, we should conduct plenty of repeated experiments to determine the threshold. Therefore, we introduce a novel approach for adjusting the thresholds associated with both the loss function and the sample mining strategy. We design a static Asymmetric Sample Mining Strategy (ASMS) and its dynamic version, the Adaptive Tolerance ASMS (AT-ASMS), tailored for sample mining methods. ASMS utilizes differentiated thresholds to address the problems (too few positive pairs and too many redundant negative pairs) caused by only applying a single threshold to filter samples. The AT-ASMS can adaptively regulate the ratio of positive and negative pairs during training according to the ratio of the currently mined positive and negative pairs. This meta-learning-based threshold generation algorithm utilizes a single-step gradient descent to obtain new thresholds. We combine these two threshold adjustment algorithms to form the Dual Dynamic Threshold Adjustment Strategy (DDTAS). Experimental results show that our algorithm achieves competitive performance on the CUB200, Cars196, and SOP datasets. Our codes are available at https://github.com/NUST-Machine-Intelligence-Laboratory/DDTAS .

Comparative review of novel model-assisted designs for phase I/II clinical trials.

In recent years, both model-based and model-assisted designs have emerged to efficiently determine the optimal biological dose (OBD) in phase I/II trials for immunotherapy and targeted cellular agents. Model-based designs necessitate repeated model fitting and computationally intensive posterior sampling for each dose-assignment decision, limiting their practical application in real trials. On the other hand, model-assisted designs employ simple statistical models and facilitate the precalculation of a decision table for use throughout the trial, eliminating the need for repeated model fitting. Due to their simplicity and transparency, model-assisted designs are often preferred in phase I/II trials. In this paper, we systematically evaluate and compare the operating characteristics of several recent model-assisted phase I/II designs, including TEPI, PRINTE, Joint i3+3, BOIN-ET, STEIN, uTPI, and BOIN12, in addition to the well-known model-based EffTox design, using comprehensive numerical simulations. To ensure an unbiased comparison, we generated 10,000 dosing scenarios using a random scenario generation algorithm for each predetermined OBD location. We thoroughly assess various performance metrics, such as the selection percentages, average patient allocation to OBD, and overdose percentages across the eight designs. Based on these assessments, we offer design recommendations tailored to different objectives, sample sizes, and starting doselocations.

Distributionally robust disaster relief planning under the Wasserstein set

We study a two-stage natural disaster management problem modeled as a stochastic program, where the first stage consists of a facility location problem, deciding where to open facilities and pre-allocate resources such as medical and food kits, and the second stage is a fixed-charge transportation problem, routing resources to affected areas after observing a disaster. Our model has binary variables present in both stages. Due to the lack of data, classical stochastic programming approaches may be ill-suited, and we propose a two-stage distributionally robust formulation with a Wasserstein ambiguity set, where we consider distributions consistent with historical data and a tunable parameter to control the level of risk aversion. We develop a tailored column-and-constraint generation (CCG) algorithm to solve an extensive reformulation, where scenarios are iteratively generated. We handle the presence of binary variables in the second stage by leveraging the structure of our support set and second-stage problem, and provide conditions under which the optimal value of the latter is concave with respect to the intensity of the disaster, leading to an efficient scenario generation procedure. We also show that our results extend to the case where the second stage is a fixed-charge network flow problem. We perform extensive computational experiments demonstrating the computational advantage of our method over classical CCG implementations on synthetic instances, and illustrate the benefits of our approach on a popular case study from the literature of hurricane threats on the Gulf of Mexico in the United States.

Tracking Water Quality and Macrophyte Changes in Lake Trasimeno (Italy) from Spaceborne Hyperspectral Imagery

This work aims to show the potential of imaging spectroscopy in assessing water quality and aquatic vegetation in Lake Trasimeno, Italy. Hyperspectral reflectance data from the PRISMA, DESIS and EnMAP missions (2019–2022, summer periods) were compared with in situ measurements from WISPStation and used as inputs for water quality product generation algorithms. The bio-optical model BOMBER was run to simultaneously retrieve water quality parameters (Chlorophyll-a (Chl-a) and Total Suspended Matter, (TSM)) and the coverage of submerged and emergent macrophytes (SM, EM); value-added products, such as Phycocyanin concentration maps, were generated through a machine learning approach. The results showed radiometric agreement between satellite and in situ data, with R2 > 0.9, a Spectral Angle < 10° and water quality mapping errors < 30%. Both SM and EM coverage varied significantly from 2019 (135 ha, 0 ha, respectively) to 2022 (2672 ha, 343 ha), likely influenced by changes in rainfall and lake levels. The areas of greatest variability in Chl-a and TSM were identified in the littoral zones in the western side of the lake, while the highest variation in the fractional cover of SM and density of EM were observed in the south-eastern region; this information could support the water authorities’ monitoring activities. To this end, further developments to improve the reference field data for the validation of water quality products are recommended.

Dynamic Playlist Generation using Machine Learning

This study investigates the application of machine learning algorithms for dynamic playlist generation in the context of music recommendation systems. The traditional method of creating playlists frequently depends on immutable standards, like artist or genre, which might not adequately represent the unique and dynamic character of personal preferences. On the other hand, our suggested system makes use of machine learning methods to examine user behavior, preferences, and contextual elements in order to create playlists that are dynamically created and customized to each user’s individual preferences. In order to train machine learning models, the study collects user interaction data, such as listening history, skip patterns, and user feedback. To extract patterns and relationships from the data, a variety of algorithms are used, including hybrid models, content-based filtering, and collaborative filtering. After that, the models are incorporated into a dynamic playlist creation system that can eventually adjust to changing user preferences.Our test findings show how well the suggested strategy works to improve user experience by offering more interesting and customized playlists. With its ability to adjust to changing user preferences and contextual cues, the dynamic playlist generation system provides a smooth and pleasurable music discovery experience. We also talk about possible enhancements, implementation difficulties, and deployment considerations in the real world.This work adds to the ongoing efforts to improve music recommendation systems by demonstrating how machine learning can be used to develop more responsive and intelligent playlist generation systems. The results highlight how crucial customized experiences are in the constantly changing world of digital music consumption. Index Terms—hybrid mode, content-based filtering, intelligent playlist, music

Continual Release of Differentially Private Synthetic Data from Longitudinal Data Collections

Motivated by privacy concerns in long-term longitudinal studies in medical and social science research, we study the problem of continually releasing differentially private synthetic data from longitudinal data collections. We introduce a model where, in every time step, each individual reports a new data element, and the goal of the synthesizer is to incrementally update a synthetic dataset in a consistent way to capture a rich class of statistical properties. We give continual synthetic data generation algorithms that preserve two basic types of queries: fixed time window queries and cumulative time queries. We show nearly tight upper bounds on the error rates of these algorithms and demonstrate their empirical performance on realistically sized datasets from the U.S. Census Bureau's Survey of Income and Program Participation.

Risk-averse electrolyser sizing in industrial parks: An efficient stochastic-robust approach

Hydrogen is called to be one of the most important energy vectors in future energy systems. Nowadays, its use in the industry sector is prominent, finding multiple applications in fertilizer production or oil refining. In this sense, some industry sectors demand a considerable amount of hydrogen for their processes. In many cases, hydrogen must be purchased externally, which supposes a challenge due to hydrogen transportation is costly and few efficient. In this context, local hydrogen production through mature electrolysis technology may suppose an attractive alternative in industrial parks. This paper focuses on this topic, in particular, a risk-averse electrolyser sizing methodology is developed. The new approach accounts for uncertainties in electricity prices as well as local renewable generation and demand through an original hybrid stochastic-robust model. The developed uncertainty modelling is integrated into a novel four-level optimization framework, whose main result is the optimal electrolyser rated power. To efficiently attain the solution, an original hybridization of the Benders' decomposition and the Column and Constraint Generation Algorithm is proposed. The developed methodology results efficient in an illustrative three-industry park, showing that installing local hydrogen generation may reduce the amount of hydrogen purchased externally (by 38%) and project costs by 2.5%. Furthermore, increasing the robustness level leads to increase the project cost by 8%, while assuming unfavourable realization of uncertainties. Moreover, the developed tool is further validated in larger parks, involving an increasing number of industries, showing that the proposed methodology scales well with the size of the park.

Microstructure generation and full-field multi-scale analyses for short fiber reinforced thermoplastics: Application to PA66GF composites

Short Fiber Reinforced Thermoplastics (SFRTs) like PA66GF composites are highly heterogeneous materials with a rather complex microstructure such that the characterization and the prediction of their mechanical behavior remain quite challenging. So far, most of the research efforts have employed phenomenological and mean-field multi-scale models to deal with SFRTs. The present contribution rather focuses on a full-field multi-scale approach that incorporates advanced techniques in terms of microstructural representation and material modeling, allowing a deep insight of the dominating deformation mechanisms occurring in PA66GF composites. The proposed approach is based on an automatic periodic mesh generation algorithm for matrix-inclusion Representative Volume Elements (RVE) with randomly positioned fibers that follow a given Orientation Distribution Function (ODF). At the microscopic scale, while the fibers are assumed to be elastic, the behavior of the thermoplastic matrix is described by a phenomenological multi-mechanism constitutive model accounting for viscoelasticity, viscoplasticity and ductile damage. It results an advanced multi-scale model that enables to visualize the local deformation and degradation mechanisms occurring at the microscopic scale while simultaneously analyzing their influence on the macroscopic response of the composite upon monotonic, persistent and cyclic loading. The potential of the proposed approach is further evaluated by comparing the predicted responses against experimental data.

An enhanced exact algorithm for the multi-trip vehicle routing problem with time windows and capacitated unloading station

This paper introduces a vehicle routing problem that simultaneously considers multiple trips, time windows, and a capacitated unloading station. This problem is a generalization of the multi-trip vehicle routing problem with time windows, which determines a set of least-cost vehicle routes to fulfill all customer demands while respecting the constraints of vehicle capacity and time windows. Due to restricted resources (e.g., equipment and labor force) at the depot, vehicles may need to wait in a queue for being unloaded when they arrive. This unloading capacity constraint significantly complicates the problem, as it causes a trip to involve three stages—traveling, waiting, and unloading. We formulate this problem as an arc flow model and a trip-based set partitioning model, where the latter is solved by a branch-price-and-cut (BPC) algorithm. To improve the computational aspect of the BPC framework, a two-phase column generation (CG) algorithm is designed. First, a bidirectional labeling algorithm is tailored to solve the pricing problem, where two accelerating strategies are employed to speed up the resolution process. Meanwhile, k-path inequalities and limited-memory subset row inequalities are utilized to tighten the linear relaxation of the master problem. Computational results based on the instances adapted from the well-known Solomon’s benchmark show that the developed BPC algorithm can solve most instances within 50 customers to optimality in a short time frame and some instances of 100 customers to optimality within a 3-hour time limit. Moreover, our BPC algorithm performs better than exact algorithms in the literature for similar problem variants in both solution quality and computing time.

Improvement in the Accuracy and Efficiency of Smoothed Particle Hydrodynamics: Point Generation and Adaptive Particle Refinement/Coarsening Algorithms

Improvement in the Accuracy and Efficiency of Smoothed Particle Hydrodynamics: Point Generation and Adaptive Particle Refinement/Coarsening Algorithms

Autoencoder-Based Unsupervised Surface Defect Detection Using Two-Stage Training.

Accurately detecting defects while reconstructing a high-quality normal background in surface defect detection using unsupervised methods remains a significant challenge. This study proposes an unsupervised method that effectively addresses this challenge by achieving both accurate defect detection and a high-quality normal background reconstruction without noise. We propose an adaptive weighted structural similarity (AW-SSIM) loss for focused feature learning. AW-SSIM improves structural similarity (SSIM) loss by assigning different weights to its sub-functions of luminance, contrast, and structure based on their relative importance for a specific training sample. Moreover, it dynamically adjusts the Gaussian window's standard deviation (σ) during loss calculation to balance noise reduction and detail preservation. An artificial defect generation algorithm (ADGA) is proposed to generate an artificial defect closely resembling real ones. We use a two-stage training strategy. In the first stage, the model trains only on normal samples using AW-SSIM loss, allowing it to learn robust representations of normal features. In the second stage of training, the weights obtained from the first stage are used to train the model on both normal and artificially defective training samples. Additionally, the second stage employs a combined learned Perceptual Image Patch Similarity (LPIPS) and AW-SSIM loss. The combined loss helps the model in achieving high-quality normal background reconstruction while maintaining accurate defect detection. Extensive experimental results demonstrate that our proposed method achieves a state-of-the-art defect detection accuracy. The proposed method achieved an average area under the receiver operating characteristic curve (AuROC) of 97.69% on six samples from the MVTec anomaly detection dataset.

Narration with Graphics: An AI Generated Story Teller

Storytelling has always been a powerful tool to convey information, connect with people, and make an impact. The aim of our project is to generate story by using the concept of AI and Machine learning .AI generated storytelling has apotential to transform a variety of industries, for marketing and education to entertainment and beyond. By utilizing the capabilities of ML and NLP, stories generated by artificial intelligence can be tailored to meet the specific need of each industry like personalized narratives, interactive and dynamic storytelling, multimodal storytelling, cross domain storytelling. The introduction of GEN-AI can lead to both opportunities and potential challenges among different creator communities which required collaboration from both academic and industry. This topic gathers and analyse vast amount of data from various sources including literature, movies, and social media we are using natural language processing which understand and process human language enabling them to communicate with the user effectively. To use the facial recognition technology, we are using DALL-E, OpenCV which uses model like SVM, decision tree, and knn etc. The objective of the research is to investigate the power of AI software and automating the process of story generation. This exploration involves utilizing various AI models, such as natural language generation (NLG) algorithms, deep learning architectures, and reinforcement learning frameworks, to create compelling and coherent stories across different genres and themes. We're showcasing an innovative system that empowers users to effortlessly create short stories accompanied by relevant images with minimal input. Our final project is accessible through a user-friendly web page interface, allowing individuals to craft their narratives seamlessly. Key Words: Storytelling, Artificial intelligence, Natural language processing, Ai system, Narratives, Automatic, DALL -E, OpenCV.

Algorithmically Generated Domain Names Detection Using Gated Recurrent Unit Deep Learning

The modern malware increasingly employs domain generation algorithms (DGAs) to evade traditional DNS query detection methods, such as blacklisting or reverse engineering of suspicious domain names. These algorithms generate vast numbers of random domain names to establish communication with Command and Control (C&C) servers, posing significant challenges for detection. Previous research has predominantly relied on classical machine learning algorithms, necessitating manual feature extraction and classification, which is both time-consuming and labour-intensive this paper, we propose a deep learning-based architecture for detecting DGA-generated domain names. Our model utilizes recurrent networks with gated recurrent units (GRUs) for domain name detection. By converting domain names into vectors and employing GRUs, the model autonomously learns features, eliminating the need for manual intervention in feature extraction. Compared to traditional methods, our approach reduces time costs associated with feature extraction. The experimental result demonstrates the effectiveness of our proposed GRU achieving 98% accuracy, 94% recall rate, 93% precision, and an Area Under the Curve (AUC) of 99.6%. The GRUarchitecture outperforms LSTM models in terms of recall rate and accuracy while requiring less computational resources, indicating significant performance enhancement.

Learning to Optimize Contextually Constrained Problems for Real-Time Decision Generation

The topic of learning to solve optimization problems has received interest from both the operations research and machine learning communities. In this paper, we combine ideas from both fields to address the problem of learning to generate decisions to instances of optimization problems with potentially nonlinear or nonconvex constraints where the feasible set varies with contextual features. We propose a novel framework for training a generative model to produce provably optimal decisions by combining interior point methods and adversarial learning, which we further embed within an iterative data generation algorithm. To this end, we first train a classifier to learn feasibility and then train the generative model to produce optimal decisions to an optimization problem using the classifier as a regularizer. We prove that decisions generated by our model satisfy in-sample and out-of-sample optimality guarantees. Furthermore, the learning models are embedded in an active learning loop in which synthetic instances are iteratively added to the training data; this allows us to progressively generate provably tighter optimal decisions. We investigate case studies in portfolio optimization and personalized treatment design, demonstrating that our approach yields advantages over predict-then-optimize and supervised deep learning techniques, respectively. In particular, our framework is more robust to parameter estimation error compared with the predict-then-optimize paradigm and can better adapt to domain shift as compared with supervised learning models. This paper was accepted by Chung Piaw Teo, optimization. Funding: This work was supported in part by the Natural Sciences and Engineering Research Council of Canada. Supplemental Material: The online appendix and data files are available at https://doi.org/10.1287/mnsc.2020.03565 .

A robust optimization method for new distribution systems based on adaptive data-driven polyhedral sets

In order to better describe the uncertainty of renewable energy output, this paper proposed a novel robust optimization method for new distribution systems based on adaptive data-driven polyhedral sets. First, an ellipsoidal uncertainty set was established using historical data on renewable energy output, and a data-driven convex hull polyhedral set was established by connecting high-dimensional ellipsoidal vertices; on this basis, an adaptive data-driven polyhedral set model was established to address the problem of high conservatism in the scaling process of convex hull polyhedral sets. Furthermore, a novel adaptive data-driven robust scheduling model for new distribution systems was established, and a column-and-constraint generation (C&CG) algorithm was used to solve the robust scheduling model. Finally, the improved IEEE-33 bus system simulation verification shows that the robust scheduling model for new distribution systems based on adaptive data-driven polyhedral sets can reduce conservatism and improve the robustness of optimization results.

238: Validation of a cycleGAN deep learning algorithm for synthetic CT generation for female pelvis

238: Validation of a cycleGAN deep learning algorithm for synthetic CT generation for female pelvis

Software implementation of systematic polar encoding based PKC-SPE cryptosystem for quantum cybersecurity

The ever-growing threats in cybersecurity growing with the rapid development of quantum computing, necessitates the development of robust and quantum-resistant cryptographic systems. This paper introduces a novel cryptosystem, Public Key Cryptosystem based on Systematic Polar Encoding (PKC-SPE), based on the combination of systematic polar encoding and public-key cryptographic principles. The Systematic Polar Encoding (SPE), derived from the well-established field of polar codes, serves as the foundation for this proposed cryptographic scheme. Here, we have used MATLAB Software to introduce and implement the PKC-SPE Cryptosystem. The paper examines key generation, encryption, and decryption algorithms, providing insights into the adaptability and efficiency of systematic polar encoding in public-key cryptography. We assess the efficiency of the PKC-SPE Cryptosystem in three aspects: key size, computational complexity, and system implementation timings. In addition, we compare the PKC-SPE Cryptosystem with PKC-PC cryptosystem and find that it has reduced key sizes (Pr\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$P_{r}$$\\end{document} = 0.8436 kbytes). The results obtained through simulations validate the effectiveness of the proposed cryptosystem and highlighting its potential for integration into real-world communication systems. Thus, in the paradigm shift to quantum computing, the PKC-SPE cryptosystem emerges as a promising candidate to secure digital communication in the quantum computing era.

Semantic matching in GUI test reuse

Reusing test cases across apps that share similar functionalities reduces both the effort required to produce useful test cases and the time to offer reliable apps to the market. The main approaches to reuse test cases across apps combine different semantic matching and test generation algorithms to migrate test cases across Android apps. In this paper we define a general framework to evaluate the impact and effectiveness of different choices of semantic matching with Test Reuse approaches on migrating test cases across Android apps. We offer a thorough comparative evaluation of the many possible choices for the components of test migration processes. We propose an approach that combines the most effective choices for each component of the test migration process to obtain an effective approach. We report the results of an experimental evaluation on 8,099 GUI events from 337 test configurations. The results attest the prominent impact of semantic matching on test reuse. They indicate that sentence level perform better than word level embedding techniques. They surprisingly suggest a negligible impact of the corpus of documents used for building the word embedding model for the Semantic Matching Algorithm. They provide evidence that semantic matching of events of selected types perform better than semantic matching of events of all types. They show that the effectiveness of overall Test Reuse approach depends on the characteristics of the test suites and apps. The replication package that we make publicly available online (https://star.inf.usi.ch/#/software-data/11) allows researchers and practitioners to refine the results with additional experiments and evaluate other choices for test reuse components.