Abstracts

Demystifying the Bayesian Optimization Platform in JMP Pro (2026-US-30MP-2942) While the JMP Bayesian Optimization platform’s Auto Mode conveniently automates the sequential experimentation process for the most common applications, working directly with candidate sets and the Augmented Acquisition Functions Profiler in Custom Mode opens the possibility of more user-driven Bayesian optimization. We explain the meaning of the different acquisition functions, along with how and ...

Skill level: intermediate

Kasia Dobrzycka JMP

Data-driven Coral Reef Conservation (2026-US-30MP-2890) If you want to be a leading scientist in your field, it has historically paid to have a myopic vision; that's how most Nobel Prizes are won. However, if you want to save the world, your outlook must instead become more holistic.Coral reefs are in jeopardy across the globe due to the rising seawater temperatures associated with climate change, not to mention more local insults. However, in our field...

Skill level: intermediate

Anderson Mayfield Coral Reef Diagnostics

Moving from Dashboards to Decisions: Using Modeling to Improve Your Metrics (2026-US-30MP-2918) In manufacturing, more operational data is being collected than ever before. Metrics are being calculated for availability, performance, quality, etc., and are broken down by days, product line, and shift. All of this is widely available in dashboards, often throughout the manufacturing floor. Production managers are able to slice the data so they can see exactly how and why production performed go...

Skill level: intermediate

Brad Foulkes Gapz Analytics

Batch Weighing Methodology Using Machine Learning & Monte Carlo Simulation (2026-US-30MP-2982) Batch weighing is a common practice in the manufacture, research, development, and handling of product. Counting individual parts can be a time-consuming and inefficient process, and the ability to batch weigh can save time and money. The main downside of batch weighing is the potential risk of error in the estimated quantity due to tolerance and noise stacking.The methodology highlighted in this p...

Skill level: intermediate

Christopher Drake US Army Futures Command

Using JMP Profiler and Simulation to Characterize Installed Process Valves (2026-US-PO-2935) A challenge with controls – specifically, with advanced control systems – is the installed characterizations of control valves. Often times the actual installed characteristics are different from what the published characteristics state, or, frankly, the information is no longer available. Additionally, a common practice is to manipulate the valve from 0 to 100% while watching the flow, but this is...

Skill level: beginner

Drew Luebe and others

JMP and AI: Where LLM Integration Meets the Analytic Workflow (2026-US-30MP-2955) Scientists and engineers are being told to incorporate artificial intelligence (AI)-integrated strategies into their workflows. While there are many options available to do this, no one wants to sacrifice rigor or trust in the results just to say they're using AI.JMP’s value proposition remains unchanged: an interactive, end‑to‑end analytic workflow that supports exploration, modeling, and reportin...

Skill level: beginner

Daniel Valente and others

Experimental Design Training Meets Bayesian Optimization: A PPG Case Study (2026-US-30MP-2944) Balancing multiple performance properties while minimizing experimental effort is a common challenge in industrial R&D. Bayesian optimization provides a powerful framework for adaptive, sequential experimentation in complex, nonlinear response spaces. This presentation evaluates the Bayesian Optimization platform in JMP Pro using a realistic formulation simulation developed for PPG’s Sigma Logi...

Skill level: beginner

David Fenn and others

Application-based Empirical Modeling of Semiconductor Circuit Reliability (2026-US-30MP-2921) With aggressive technology scaling and novel device architectures in modern semiconductor technologies, it has become challenging to make input/output (I/O) transistors that can support higher voltages (e.g., 3.3 V). However, I/O operation at higher voltages is needed to allow the chip to communicate with other devices on the board, which may have been fabricated with older-generation technologies ...

Skill level: intermediate

Mehul Shroff and others

Practical Bayesian Optimization in the Fab (2026-US-30MP-2920) Modern semiconductor experiments are constrained by more than statistics. Lot sizes, review cycles, and operational risk all limit how much experimentation can realistically happen in production. At the same time, practitioners are often asked to choose between two powerful – but imperfect – approaches: design of experiments (DOE), which is efficient but model-dependent, and Bayesian optimization, ...

Skill level: intermediate

Mike Anderson JMP

LLM‑Style Issue Prediction Using JMP Neural Modeling (2026-US-30MP-2970) Manufacturing-fleet issue resolution often relies on manual interpretation of unstructured engineering logs, where outcomes are influenced by inconsistent descriptions or subjective categorization. This study demonstrates how neural predictive modeling in JMP 19 can be applied as an LLM‑style inference framework to improve issue prediction consistency.Rather than generating free‑text responses, thi...

Skill level: intermediate

Paulo Herrera Applied Materials

Will BayesOpt Transform Industrial Experimentation? My Bayesian Optimization Journey (2026-EU-30MP-2842) Bayesian optimization seems to be the rising star on the stage of industrial experimentation, but how does it fit alongside traditional DOE approaches? Its adaptive, goal-oriented strategy can dramatically improve efficiency and insight generation in complex systems, yet DOE remains a cornerstone in industry. In this talk, I share learnings from my research and discussions with practitioners, outli...

Skill level: beginner

Florian Vogt

Temporal Profile Predictions for Cell Culture Using FDE and PLS (2026-EU-30MP-2778) Managing cell culture operations during bioreactor experiments is demanding, requiring constant adjustment. Coordination with downstream purification and analytics adds complexity, where misalignment drives inefficiency and delays. These challenges are magnified during technology transfer, where scale, equipment, and operational differences introduce additional uncertainty.To mitigate these ch...

Skill level: advanced

Per Vase and others

Modeling Synthetic Chromatograms in JMP 19: Updates and New Applications (2026-EU-PO-2745) Chromatographic techniques such as HPLC, GC, and CGE are essential for analytical workflows across industries. However, optimizing these methods remains challenging due to numerous parameters and the complexity of chromatograms. Traditionally, performance metrics such as resolution or peak-to-valley ratios are extracted and modeled, but linking these metrics back to the full chromatogram is often d...

Skill level: advanced

Marco Kunzelmann

From DOE to Predictive Modeling: Utilizing JMP to Customize Powder Coating Properties (2026-EU-PO-2759) The gel time and cure time are important properties of powder coatings. The rate of the curing reaction inherently affects both of these characteristics. Consequently, it is often challenging to modify one of these properties without compromising the other. The curing rate can be controlled by varying the amount of catalyst used. We found that using two specific catalysts, A and B, produces interes...

Piotr Dudzinski

Smart Subsampling for Predictive Modeling: A Decade of Progress in Material Science (2026-EU-30MP-2798) Even in the age of powerful machine learning, handling large data sets still comes with its share of challenges. Going brute force – processing everything just because we can – sometimes leads to inefficiencies, overfitting, noise, and rapidly diminishing returns. Smarter doesn’t always mean bigger. Intelligent subsampling, where only a representative fraction of data is used, often revea...

Damien Perret and others

Bayesian Optimization for Formulations Involving Complex Constraints with JMP 19 (2026-EU-30MP-2816) The production of many products involves mixing or blending multiple ingredients. Finding optimal formulations for these products can be challenging, expensive, and time-consuming, especially if the formulation is subject to complex constraints. The ability to innovate new high-quality products quickly is becoming increasingly more important as technologies advance and competition increas...

Christopher Gotwalt and others

Assistant, A Natural Language Interface to JMP LearnBot의 성공을 기반으로, 우리는 Assistant라는 새로운 마켓플레이스 애드인을 소개합니다. 이 애드인을 활용하면 프롬프트를 통해 JMP 메뉴를 거치지 않고도 자신의 데이터로 직접 다양한 작업을 수행할 수 있습니다. Assistant는 Claude, GPT, Gemini 등 사용자가 원하는 어떤 대규모 언어 모델(LLM)과도 연동할 수 있습니다. 아직 완벽하지는 않지만, 단순한 데이터 시각화부터 복잡한 워크플로우까지 더 효율적이고 자신 있게 작업할 수 있도록 돕습니다. 이번 세션에서는 JMP 메뉴를 전혀 사용하지 않고도 실행할 수 있는 여러 가지 실용적인 예시를 시연할 예정입니다.

Russ Wolfinger and others

딥블루 대 알파고, 그리고 설명가능한 인공지능 고대 그리스 탈로스에서 시작된 인공지능의 꿈은 챗지피티를 통해 현실이 되었습니다. 이제 인공지능 특이점 이후 발전 방향에 대한 예측이 필요한 시점입니다. 발전 방향은 벡터이기에 변화의 관성을 파악하려면 과거를 알아야 합니다. 컴퓨터 탄생 이래 인공지능 발전은 기호주의와 연결주의 대결이 이끌어왔습니다. 이 대결의 본질은 데이터에 대한 관점의 차이입니다. 이번 강연에서는 의학 통계 관점에서 인공지능의 발전 과정을 되짚어 볼 것입니다. 이를 통해 미래의 화두인 설명가능한 인공지능에서 왜 통계적 통찰이 요구되는지 확인할 수 있을 것입니다.

Skill level: beginner

주철현 울산대학교

Hop to It: Crafting Paper Frogs with Easy DOE (2025-JA-25MP-2620) JMPのナビ付きDOE (Easy DOE) が持つ強力な機能と、父娘チームの創造的なエネルギーが融合する、活気あふれるセッションを体験しませんか。本発表では、研究開発マネージャーである父親Ryanと10歳の娘Roryが、ナビ付 DOE（Easy DOE）を使った魅力的な実験を通して、さまざまな紙製のカエル作りに挑戦します。ナビ付 DOE（Easy DOE）のユーザーフレンドリーなアプローチは、異なる紙製のカエルがさまざまな条件下でどのように振る舞うかを、実験計画法を駆使して簡単に設定し、実行する方法をご紹介します。

Skill level: beginner

Rory Lekivetz and others

応答曲面計画の立案における A最適化基準の活用　～I-最適性とG-最適性の両立～ JMPのカスタム計画で応答曲面計画を立案するときにI-最適化基準が良く用いられている(カスタム計画でRSMをクリックしたときのデフォルト)．I-最適化基準は計画領域内の予測分散の平均値が最小となる計画を探索する基準であり，最適条件を探索するフェーズで有用ではあるものの，意図せずG-最適性が悪い計画が立案されてしまう場合がある．これは最適であると選ばれた条件の精度があまりよくない可能性があるという点で問題である．この問題への対処法としてA-最適化基準の活用を考えた．応答曲面計画を立案する場合にA-最適化基準を使用した場合にかなりI-最適化基準で立案した計画に近い計画が得られることに加えて，"A最適でのパラメータの重み"を利用して計画の性質をかなり柔軟にコントロールできることが理由である．実際にパラメータの重みを活用することでG-最適性を改善した応答曲面計画の立案が可能であり，また，I-最適化基...

山本達郎 日本ゴア合同会社

素敵なスマイル：SMILES記法から化学特性を予測する (2025-JA-25MP-2678) 近年の定量的構造活性相関（Quantitative Structure–Activity Relationship, QSAR）では、機械学習を活用して高度なモデルを構築し、新しい分子の特性を予測する手法が用いられています。これにより、実験にかかる時間やコストの削減が期待されています。本発表では、JMP Marketplaceから Materials Informatics ToolkitとTorch Deep Learningのエクステンションを紹介します。これらのアドインでは、化学物質のSMILES文字列を処理するために、広く使われているオープンソースのRDKitパッケージを活用し、化学者がQSARを実行するための対話的で強力なワークフローを提供しています。本発表では、このエクステンションを使ったいくつかの例をご紹介します。

Skill level: advanced

Russ Wolfinger and others

超微小粒子の個人曝露評価にも適用可能な地理空間情報を用いた空間分布推測モデルの構築 (2025-JA-25MP-2695) 一般大気中に存在する大気汚染物質のヒトへの曝露と健康影響を評価する大気環境疫学では、調査対象者個人に対して大気汚染物質の曝露量がどの程度か評価（個人曝露評価）することが極めて重要であり、かつ難しい課題である。超微小粒子（ultrafine particle: UFP）は粒子径が100nm 以下と極めて小さく、環境濃度は重量濃度ではなく、個数濃度（particles/cm3）で表現されることが多い。また、UFPの曝露は心血管や中枢神経への影響が疑われている。近年、大気汚染物質の個人曝露評価では、地理空間情報を目的変数に用いるLand Use Regression Model（LURモデル）がよく用いられ、UFPについても報告がある。しかしながら、日本ではUFPの個人曝露評価に適用できるUFP空間分布に関する情報は十分ではない。そこで本研究では、横浜市を対象地域として、UFPの個人曝露評価に適用...

Skill level: beginner

堺温哉 一般財団法人日本自動車研究所

市販ヨーグルトの物性・味覚評価と物性値モデリング (2025-JA-PO-2762) 【背景】近年の健康志向の高まりにより、ヨーグルト市場は大きく成長している。消費者ニーズの多様化に伴い、市場には食感や機能性の異なる幅広い商品が展開されている。本研究では、市販ヨーグルトを対象に官能評価および物性・味覚評価を行い、得られたデータを統計解析することで、その官能的特徴を明らかにすることを目的とした。さらに、物性値を用いた予測モデルを構築し、官能特性に寄与すると考えられる特徴量の探索を試みた。【方法】物性評価は、動的粘弾性測定、粘度測定、粒子径分布測定を行い、特徴量を抽出した。味覚評価には味覚センサによる分析および官能評価を行った。これらのデータを多変量解析することで市販品ポジショニングマップを作成した。官能評価を表す物性値モデルはPLS回帰を用いて構築した。【結果】ポジショニングマップにより、食感や味覚の類似性に基づき各サンプルが位置付けられ、関係性や特徴が可視化された。さらに、P...

Skill level: beginner

樋口侑夏 and others

開会のご挨拶／基調講演：イノベーションの拡大：エンジニアリング・ワークフローへのデータサイエンス統合 10:00～10:15：開会のご挨拶10:15～11:15：基調講演今日のエンジニアリングにおける課題は、もはや局所的な解決策だけでは不十分です。データサイエンスの手法をデータ分析のワークフローに組み込むための、拡張性が高く柔軟なツールが求められています。JMPの製品群は、統計解析、プロセス最適化、データ視覚化のための強力なプラットフォームを提供し、エンジニアが日々の問題解決を超えて活躍できる環境を創造します。このセッションでは、複雑で大規模な問題への取り組みに焦点を当て、JMPがどのようにエンジニアリング・データサイエンスを支援するかを深掘りします。あわせて、データアクセス、プロセススクリーニング、環境モニタリング、グループ別分析、モデル・応答スクリーニング、そしてJMP Liveとの統合といったツールに焦点を当て、JMPが多様なニーズにどのように対応するかを解説します。具体的な事例やデモ...

Skill level: beginner

Jules Parris and others

Exploring Global Trends in Coral Reef Health with JMP Pro (2025-US-30MP-2478) Coral reefs across the planet are threatened by the rising temperatures associated with climate change. Not only do we simply need to better understand what we have to lose, but we must exploit unbiased approaches for ensuring that the optimal conservation or restoration approach deployed is actually the one that maximixes cost/benefit: greatest positive impact for corals and other reef-dwelli...

Anderson Mayfield Coral Reef Diagnostics

Presentations

Filter By

Analytic Capabilities

Abstract Type

Regions

Year

Skill Level