arXiv subjects

Julius Kusuma

Publications and source records attributed to Julius Kusuma.

10 recordsLinked to original sources

arXiv2026

BOxCrete: A Bayesian Optimization Open-Source AI Model for Concrete Strength Forecasting and Mix Optimization

Modern concrete must simultaneously satisfy evolving demands for mechanical performance, workability, durability, and sustainability, making mix designs increasingly complex. Recent studies leveraging Artificial Intelligence (AI) and Machine Learning (ML) models show promise for predicting compressive strength and guiding mix optimization, but most existing efforts are based on proprietary industrial datasets and closed-source implementations. Here we introduce BOxCrete, an open-source probabilistic modeling and optimization framework trained on a new open-access dataset of over 500 strength measurements (1-15 ksi) from 123 mixtures - 69 mortar and 54 concrete mixes tested at five curing ages (1, 3, 5, 14, and 28 days). BOxCrete leverages Gaussian Process (GP) regression to predict strength development, achieving average R$^2$ = 0.94 and RMSE = 0.69 ksi, quantify uncertainty, and carry out multi-objective optimization of compressive strength and embodied carbon. The dataset and model establish a reproducible open-source foundation for data-driven development of AI-based optimized mix designs.

cs.LG↗

arXiv2023

Sustainability assessment of 4G and 5G universal mobile broadband strategies

With infrastructure systems lasting for decades, even centuries, there is growing need to assess sustainability impacts. However, compared to energy or transportation networks (which each contribute roughly one third of global emissions), broadband networks have arguably received less attention due to their much smaller footprint (~1.8-3.9% of global emissions). Nevertheless, many countries are looking to provide universal mobile broadband over the next decade to meet Goal 9 of the Sustainable Development Goals (SDGs). Therefore, this paper evaluates the future sustainability impacts of providing either 4G or 5G mobile broadband, quantifying the carbon and other environmental emissions associated with each universal broadband strategy. This paper contributes the first ex ante sustainability assessment of global universal mobile broadband strategies aimed at delivering SDG Goal 9.

stat.AP↗

arXiv2023

Sustainable Concrete via Bayesian Optimization

Eight percent of global carbon dioxide emissions can be attributed to the production of cement, the main component of concrete, which is also the dominant source of CO2 emissions in the construction of data centers. The discovery of lower-carbon concrete formulae is therefore of high significance for sustainability. However, experimenting with new concrete formulae is time consuming and labor intensive, as one usually has to wait to record the concrete's 28-day compressive strength, a quantity whose measurement can by its definition not be accelerated. This provides an opportunity for experimental design methodology like Bayesian Optimization (BO) to accelerate the search for strong and sustainable concrete formulae. Herein, we 1) propose modeling steps that make concrete strength amenable to be predicted accurately by a Gaussian process model with relatively few measurements, 2) formulate the search for sustainable concrete as a multi-objective optimization problem, and 3) leverage the proposed model to carry out multi-objective BO with real-world strength measurements of the algorithmically proposed mixes. Our experimental results show improved trade-offs between the mixtures' global warming potential (GWP) and their associated compressive strengths, compared to mixes based on current industry practices. Our methods are open-sourced at github.com/facebookresearch/SustainableConcrete.

cs.LG↗

arXiv2022

Accelerated Design and Deployment of Low-Carbon Concrete for Data Centers

Concrete is the most widely used engineered material in the world with more than 10 billion tons produced annually. Unfortunately, with that scale comes a significant burden in terms of energy, water, and release of greenhouse gases and other pollutants; indeed 8% of worldwide carbon emissions are attributed to the production of cement, a key ingredient in concrete. As such, there is interest in creating concrete formulas that minimize this environmental burden, while satisfying engineering performance requirements including compressive strength. Specifically for computing, concrete is a major ingredient in the construction of data centers. In this work, we use conditional variational autoencoders (CVAEs), a type of semi-supervised generative artificial intelligence (AI) model, to discover concrete formulas with desired properties. Our model is trained just using a small open dataset from the UCI Machine Learning Repository joined with environmental impact data from standard lifecycle analysis. Computational predictions demonstrate CVAEs can design concrete formulas with much lower carbon requirements than existing formulations while meeting design requirements. Next we report laboratory-based compressive strength experiments for five AI-generated formulations, which demonstrate that the formulations exceed design requirements. The resulting formulations were then used by Ozinga Ready Mix -- a concrete supplier -- to generate field-ready concrete formulations, based on local conditions and their expertise in concrete design. Finally, we report on how these formulations were used in the construction of buildings and structures in a Meta data center in DeKalb, IL, USA. Results from field experiments as part of this real-world deployment corroborate the efficacy of AI-generated low-carbon concrete mixes.

cs.AI↗

arXiv2021

Engineering-Economic Evaluation of Diffractive Non-Line-Of-Sight Backhaul (e3nb): A Techno-economic Model for 3D Wireless Backhaul Assessment

Developing ways to affordably deliver broadband connectivity is one of the major issues of our time. In challenging deployment locations with irregular terrain, traditional Clear-Line-Of-Sight (CLOS) wireless links can be uneconomical to deploy, as the number of required towers make infrastructure investment unviable. With new research focusing on developing wireless diffractive backhaul technologies to provide Non-Line-Of-Sight (NLOS) links, this paper evaluates the engineering-economic implications. A Three-Dimensional (3D) techno-economic assessment framework is developed, utilizing a combination of remote sensing and viewshed geospatial techniques, in order to quantify the impact of different wireless backhaul strategies. This framework is applied to assess both Clear-Line-Of-Sight and diffractive Non-Line-Of-Sight strategies for deployment in Peru, as well as the islands of Kalimantan and Papua, in Indonesia. The results find that a hybrid strategy combining the use of Clear-Line-Of-Sight and diffractive Non-Line-Of-Sight links produces a 9-45 percent cost-efficiency saving, relative to only using traditional Clear-Line-Of-Sight wireless backhaul links.

cs.NI↗

arXiv2021

Wi-Fi Wardriving Studies Must Account for Important Statistical Issues

Knowledge of Wi-Fi networks helps to guide future engineering and spectrum policy decisions. However, due to its unlicensed nature, the deployment of Wi-Fi Access Points is undocumented meaning researchers are left making educated guesses as to the prevalence of these assets through remotely collected or passively sensed measurements. One commonly used method is referred to as `wardriving` essentially where a vehicle is used to collect geospatial statistical data on wireless networks to inform mobile computing and networking security research. Surprisingly, there has been very little examination of the statistical issues with wardriving data, despite the vast number of analyses being published in the literature using this approach. In this paper, a sample of publicly collected wardriving data is compared to a predictive model for Wi-Fi Access Points. The results demonstrate several statistical issues which future wardriving studies must account for, including selection bias, sample representativeness and the modifiable areal unit problem.

cs.NI↗

arXiv2020

SuperCell: A Wide-Area Coverage Solution Using High-Gain, High-Order Sectorized Antennas on Tall Towers

In this article we introduce a novel solution called SuperCell, which can improve the return on investment (ROI) for rural area network coverage. SuperCell offers two key technical features: it uses tall towers with high-gain antennas for wide coverage and high-order sectorization for high capacity. We show that a solution encompassing a high-elevation platform in excess of 200 meters increases coverage by 5x. Combined with dense frequency reuse by using as many as 36 azimuthal sectors from a single location, our solution can adequately serve the rural coverage and capacity demands. We validate this through propagation analysis, modeling, and experiments. The article gives a design perspective using different classes of antennas: Luneburg lens, active/passive phased array, and spatial multiplexing solutions. For each class, the corresponding analytical model of the resulting signal-to-interference plus noise ratio (SINR) based range and capacity prediction is presented. The spatial multiplexing solution is also validated through field measurements and additional 3D ray-tracing simulation. Finally, in this article we also shed light on two recent SuperCell field trials performed using a Luneburg lens antenna system. The trials took place in rural New Mexico and Mississippi. In the trials, we quantified the coverage and capacity of SuperCell in barren land and in a densely forested location, respectively. In the article, we demonstrate the results obtained in the trials and share the lessons learned regarding green-field and brown-field deployments.

eess.SY↗

arXiv2020

Revisiting Wireless Internet Connectivity: 5G vs Wi-Fi 6

In recent years, significant attention has been directed toward the fifth generation of wireless broadband connectivity known as `5G`, currently being deployed by Mobile Network Operators. Surprisingly, there has been considerably less attention paid to `Wi-Fi 6`, the new IEEE 802.1ax standard in the family of Wireless Local Area Network technologies with features targeting private, edge-networks. This paper revisits the suitability of cellular and Wi-Fi in delivering high-speed wireless Internet connectivity. Both technologies aspire to deliver significantly enhanced performance, enabling each to deliver much faster wireless broadband connectivity, and provide further support for the Internet of Things and Machine-to-Machine communications, positioning the two technologies as technical substitutes in many usage scenarios. We conclude that both are likely to play important roles in the future, and simultaneously serve as competitors and complements. We anticipate that 5G will remain the preferred technology for wide-area coverage, while Wi-Fi 6 will remain the preferred technology for indoor use, thanks to its much lower deployment costs. However, the traditional boundaries that differentiated earlier generations of cellular and Wi-Fi are blurring. Proponents of one technology may argue for the benefits of their chosen technology displacing the other, requesting regulatory policies that would serve to tilt the marketplace in their favour. We believe such efforts need to be resisted, and that both technologies have important roles to play in the marketplace, based on the needs of heterogeneous use cases. Both technologies should contribute to achieving the goal of providing affordable, reliable, and ubiquitously available high-capacity wireless broadband connectivity.

cs.NI↗

arXiv2011

Malleable Coding with Fixed Reuse

In cloud computing, storage area networks, remote backup storage, and similar settings, stored data is modified with updates from new versions. Representing information and modifying the representation are both expensive. Therefore it is desirable for the data to not only be compressed but to also be easily modified during updates. A malleable coding scheme considers both compression efficiency and ease of alteration, promoting codeword reuse. We examine the trade-off between compression efficiency and malleability cost-the difficulty of synchronizing compressed versions-measured as the length of a reused prefix portion. Through a coding theorem, the region of achievable rates and malleability is expressed as a single-letter optimization. Relationships to common information problems are also described.

cs.IT↗

arXiv2008

Malleable Coding: Compressed Palimpsests

A malleable coding scheme considers not only compression efficiency but also the ease of alteration, thus encouraging some form of recycling of an old compressed version in the formation of a new one. Malleability cost is the difficulty of synchronizing compressed versions, and malleable codes are of particular interest when representing information and modifying the representation are both expensive. We examine the trade-off between compression efficiency and malleability cost under a malleability metric defined with respect to a string edit distance. This problem introduces a metric topology to the compressed domain. We characterize the achievable rates and malleability as the solution of a subgraph isomorphism problem. This can be used to argue that allowing conditional entropy of the edited message given the original message to grow linearly with block length creates an exponential increase in code length.

cs.IT↗