Accurate estimation of production times is critical for effective manufacturing scheduling, yet traditional methods relying on expert analysis or historical data often fall short in dynamic or customized production environments. This paper introduces a data-driven approach that predicts manufacturing steps and their durations directly from 3D models of products with exposed geometries. By rendering the model into multiple 2D images and leveraging a neural network inspired by the Generative Query Network, the method learns to map geometric features into time estimates for predefined production steps with a mean absolute error below 3 seconds making planning across varied product types easier. Introduction Accurate production scheduling is a cornerstone of efficient manufacturing. In practice, schedules are generated based on estimates of processing times required for each step in the production process. However, when these estimates deviate from actual conditions--due to missing or outdated data - the generated schedules quickly become obsolete.

Time perception research has advanced significantly over the years. However, some areas remain largely unexplored. This study addresses two such under-explored areas in timing research: (1) A quantitative analysis of time perception at an individual level, and (2) Time perception in an ecological setting. In this context, we trained a machine learning model to predict the direction of change in an individual's time production. The model's training data was collected using an ecologically valid setup. We moved closer to an ecological setting by conducting an online experiment with 995 participants performing a time production task that used naturalistic videos (no audio) as stimuli. The model achieved an accuracy of 61%. This was 10 percentage points higher than the baseline models derived from cognitive theories of timing. The model performed equally well on new data from a second experiment, providing evidence of its generalization capabilities. The model's output analysis revealed that it also contained information about the magnitude of change in time production. The predictions were further analysed at both population and individual level. It was found that a participant's previous timing performance played a significant role in determining the direction of change in time production. By integrating attentional-gate theories from timing research with feature importance techniques from machine learning, we explained model predictions using cognitive theories of timing. The model and findings from this study have potential applications in systems involving human-computer interactions where understanding and predicting changes in user's time perception can enable better user experience and task performance.

Large language models (LLMs) have exhibited their problem-solving ability in mathematical reasoning. Solving realistic optimization (OPT) problems in industrial application scenarios requires advanced and applied math ability. However, current OPT benchmarks that merely solve linear programming are far from complex realistic situations. In this work, we propose E-OPT, a benchmark for end-to-end optimization problem-solving with human-readable inputs and outputs. E-OPT contains rich optimization problems, including linear/nonlinear programming with/without table data, which can comprehensively evaluate LLMs' solving ability. In our benchmark, LLMs are required to correctly understand the problem in E-OPT and call code solver to get precise numerical answers. Furthermore, to alleviate the data scarcity for optimization problems, and to bridge the gap between open-source LLMs on a small scale (e.g., Llama-2-7b and Llama-3-8b) and closed-source LLMs (e.g., GPT-4), we further propose a novel data synthesis method namely ReSocratic. Unlike general data synthesis methods that proceed from questions to answers, ReSocratic first incrementally synthesizes optimization scenarios with mathematical formulations step by step and then back-translates the generated scenarios into questions. In such a way, we construct the ReSocratic-29k dataset from a small seed sample pool with the powerful open-source large model DeepSeek-V2. To demonstrate the effectiveness of ReSocratic, we conduct supervised fine-tuning with ReSocratic-29k on multiple open-source models. The results show that Llama3-8b is significantly improved from 13.6% to 51.7% on E-OPT, while DeepSeek-V2 reaches 61.0%, approaching 65.5% of GPT-4.

This paper addresses a production scheduling problem derived from an industrial use case, focusing on unrelated parallel machine scheduling with the personnel availability constraint. The proposed model optimizes the production plan over a multi-period scheduling horizon, accommodating variations in personnel shift hours within each time period. It assumes shared personnel among machines, with one personnel required per machine for setup and supervision during job processing. Available personnel are fewer than the machines, thus limiting the number of machines that can operate in parallel. The model aims to minimize the total production time considering machine-dependent processing times and sequence-dependent setup times. The model handles practical scenarios like machine eligibility constraints and production time windows. A Mixed Integer Linear Programming (MILP) model is introduced to formulate the problem, taking into account both continuous and district variables. A two-step solution approach enhances computational speed, first maximizing accepted jobs and then minimizing production time. Validation with synthetic problem instances and a real industrial case study of a food processing plant demonstrates the performance of the model and its usefulness in personnel shift planning. The findings offer valuable insights for practical managerial decision-making in the context of production scheduling.

In the fight to stay competitive, manufacturers will look to AI technologies to fuel a successful operational transformation. With industry 4.0 in full force, manufacturers are pressured to stay competitive. Over the past year, there has been a massive industry-wide shift in the adoption of AI technology to keep up with the demand from customers. We've already seen one-third of IT professionals surveyed globally say their business is now using AI, with 43% saying their company accelerated their AI rollout. By utilizing AI, manufacturers can achieve greater operational efficiency and resilience – while generating cost savings and aiding customer growth, retention, and acquisition.

As a person who is involved in mostly the data related activities such as data processing, data manipulation and model predictions, you are also given an additional task as a data scientist or a machine learning engineer to deploy the product in real-time. After doing the heavy lifting of understanding the right parameters for various models and finally coming up with the best model, deploying the model in real-time can have a significant impact in the way it impresses the business and creates monetary impact. Finally, the model is deployed, and it is able to predict and give its decision based on the historical data at which it was trained. At this point, most people consider that they have completed a large portion of the machine learning tasks. While it is true that a good amount of work has been done so that the models are productionized, there is additional step that is often overlooked in the machine learning lifecycle that is to monitor the models and check if they are performing on the future data or the data that the models have not seen before.

As a marketer, you could use AI in a variety of ways, enhancing customer experiences and evaluating consumer behavior. Over the last few years, its acceptance, impact and widespread popularity have revolutionized how businesses look at everyday processes. Between now and 2024, the global AI space will grow at a 26% Compound Annual Growth Rate (CAGR), reaching a staggering USD 71 billion. It is astonishing how AI is deeply embedded across our daily lives -- play music on your Spotify app, and there's AI to curate a special playlist for you; craving ice cream? Your preferred delivery app will suggest options to order from, and if you back out, it will insist that you proceed with the "sweet deal."

Do Not Reproduce More Than Two Slides or Charts Without Permission Background and context Earlierthis year, a Boston Consulting Group studyfound thatcompanies in the US and Germanyhad implemented the new digitalindustrialtechnologies thatare collectivelyknown as Industry 4.0 at approximatelythe same pace.1 • German companieswere off to a somewhatfasterstartof implementation despite the commonperceptionthat US companieswere the front-runnersin embracing digitaltransformation • German companiesalso appearedto be better prepared foradoptthe new digital technologiesand to have higherambitions To gain further insights aboutthe status of Industry 4.0 adoption byUS manufacturers and the challenges theyface, BCG surveyed 380 US-based manufacturing executives and managers atcompaniesrepresenting a wide range of sizes in various industries (for methodology,see p.13). Do Not Reproduce More Than Two Slides or Charts Without Permission Executive summary Key findings from the research US ...