Techno Press
Tp_Editing System.E (TES.E)
Login Search
You logged in as

acc
 
CONTENTS
Volume 18, Number 1, July 2024 (Special Issue)
 

Abstract


Key Words


Address


Abstract
The construction industry has not benefited greatly from current research on AI and IoT-driven sensor technologies, which has mostly concentrated on smart cities, manufacturing, and healthcare. Research currently being conducted tends to focus more on data gathering and simple automation than on incorporating sophisticated AI for real-time decision-making and predictive analytics. There is a research gap because stronger systems are required to manage the unstable and dynamic environment found on building sites. By creating a cutting-edge AI and IoT-based system specifically designed for real-time monitoring and control in the construction industry, our study fills this gap. This framework offers a considerable advantage over present technologies by improving not just data accuracy and sensor dependability but also safety, optimization of resource allocation, and predictive maintenance. The purpose of the project was to develop sensor technologies powered by AI and IoT for real-time construction monitoring and control. There were 1,198 street images and 330,165 individuals that comprise the ShanghaiTech dataset were gathered from the campus of Shanghai Jiao Tong University. In order to ensure consistency and reliability, the raw data prior to processing has been adjusted using the min-max normalization technique. We presented the Deep Deterministic Policy Gradient Algorithm with support vector machine (DDPGA-SVM) to provide real-time monitoring and control of construction-related sensors powered by AI and the IoT-driven. To evaluate the suggested solution works in terms of accuracy, prediction rate, loss function, F1-score and Cohen kappa score. As a result, real-time monitoring and control in construction demonstrated by the suggested superior performance over other similar models in terms of accuracy (99%), MAE (28%), F1-score (90), and recall (96) and loss function achieving 80% in training and 92% in validation.

Key Words
AI and IoT-Driven; Deep Deterministic Policy Gradient Algorithm with support vector machine (DDPGASVM); min-max normalization; real time; sensor technologies

Address
Shandong University, School of Mechanical, Electrical & Information Engineering, Weihai, Shandong Province, 264200, China.

Abstract
Despite tremendous progress in the field of landscape design, there is still a lack of artificial intelligence (AI) integration in order to maximize the utilization of recovered waste materials for sustainable practices. The majority of recent study examines AI in landscape design for practical and esthetic reasons, with a few studies focusing on sustainability. In a similar vein, research on recycled waste materials in landscape design highlights the advantages for the environment but falls short of AI's level of accuracy and optimization. Our study closes this gap by utilizing AI to improve the efficacy and efficiency of recycled waste materials in landscape design. By providing scalable and repeatable solutions, this interdisciplinary approach has the potential to raise the bar for sustainable landscape design. This study was to use recycled waste materials and AI in sustainable landscape design. According to data gathered from Guangzhou, as land use stockpile enters a new phase, it is imperative to unleash this potential through urban ruins (URs) reuse. To determine which features have the greatest influence on the landscape design process make sure it is appropriate for evaluating index. We proposed the spider monkey dove swarm optimized generative adversarial network (SMDSO-GAN) for sustainable landscape design utilizing recycled waste materials. To evaluate the suggested solution works in terms of accuracy rate, R2 and MAE. As a result, recycled waste materials demonstrated by the suggested superior performance over other similar models in terms of accuracy rate (98%), recycle management (93%), MAE (25%), and R2 32%.

Key Words
Artificial Intelligence (AI); evaluating index; landscape; recycled waste materials; spider monkey dove swarm optimized generative adversarial network (SMDSO-GAN); urban ruins (URs)

Address
(1) Changqiang Sui, Qianrong Deng:
Department of Design & Manufacturing Engineering, Jeonbuk National University, Jeonju, Jeonbuk, 54896, Korea;
(2) Qianrong Deng:
College of Literature Art, Shihezi University, Shihezi, Xinjiang, 832000, China.

Abstract
Fiber-reinforced materials have shown promise in recent decades as long-lasting materials with a wide range of applications. Instead of relying solely on widely used steel fiber, various reinforcements, such as carbon fiber and basalt fiber, have been introduced as alternatives. This study utilizes split tensile testing and flexural strength testing to examine how incorporating basalt fiber and carbon fiber impacts reinforced concrete. Six unique concrete samples, incorporating carbon fiber and basalt fiber reinforcement, are developed using the M25 and M35 control mixtures determined by compressive strength test outcomes. The research evaluates the Tensile Strength (TS), Flexural Strength (FS), deflection, and Modulus of Elasticity concerning stress and strain characteristics in cube, beam, and cylinder specimens for both carbon fiber and basalt fiberreinforced concrete. The findings indicate that carbon fiber-reinforced concrete surpasses basalt fiber-reinforced concrete in terms of TS, flexural strength, and modulus of elasticity. Additionally, it is noted that the carbon-reinforced fiber based on the M35 mix demonstrates superior performance compared to the M25 mix-based carbon-reinforced fiber.

Key Words
basalt fiber; carbon fiber; fiber-reinforced concrete; flexural strength; modulus of elasticity; split tensile strength

Address
(1) S. Kavitha:
Department of Civil Engineering, Noorul Islam Centre for Higher Education, Kumaracoil, India;
(2) M.S. Ravikumar:
Department of Civil Engineering, PSN Engineering College, Tirunelveli, India.

Abstract
Alloy AZ31 Mg exhibits great potential as an implant metallic material for restoring human body hard tissues. Yet, it is prone to deterioration in physiological fluid environments. Enhancing the ability of magnesium alloys to resist corrosion and last longer can be efficiently achieved through the application of a nano-material coating. This investigation involved coating the magnesium alloy AZ31 with carbon nanopowder and Poly-Ether-Ether-Ketone (PEEK). This analysis employs Box-Behnken experimental designs to model the response surface. Further, scanning electron microscopy, and electrochemical corrosion testing are performed. In addition, the regression and reliability analysis are executed. The histogram studies are employed to represent the descriptive variables. The test findings indicate that incorporating carbon nanopowder and PEEK into the magnesium alloy can enhance its corrosion resistance.

Key Words
Box-Behnken design; carbon nanopowder; magnesium alloy; PEEK; scanning electron microscopy

Address
Department of Mechanical Engineering, Noorul Islam Centre for Higher Education, Kumaracoil, India.

Abstract
According to major part of the energy-intensive manufacture of cement clinker, the cement sector contributes significantly to global CO2 emissions. Previous experiments that have already been done on the subject of reducing CO2 emissions and conserving energy during the production of cement clinker typically overlook the possibility of improving aggregate composition as a means of achieving these goals. While process efficiency is the main focus of current techniques, a thorough investigation of how raw material composition can further boost sustainability is lacking. This work presents a novel strategy for enhancing energy efficiency and lowering CO2 emissions at the same time through aggregate composition optimization. This double gain has the potential to greatly advance cement industry sustainability initiatives. We examined the data set of cement the clinkers. Recycling cement was thought to use as little as 60%-76% of the energy used to produce clinker and emit less carbon dioxide. We proposed an optimal strategy based on the genetic programming with dynamic fuzzy system ensemble and Convolutional Neural networks (GP-DMFSE-CNN) are used to construct prediction models, which are subsequently refined through the application of one-year operation data, focusing attention to a cement clinker production process. To evaluate the suggested solution works in terms of efficiency, employee

Key Words
aggregate composition; cement clinker production; CO2 emission; energy conservation; genetic programming with dynamic fuzzy system ensemble and convolutional neural networks (GP-DMFSE-CNN)

Address
Energy Conservation Office of Nantong First People's Hospital, Nantong, 226006, Jiangshu, China.


Abstract
The enormous volumes of waste produced by the building sector, particularly by the ceramics industry, which releases large amounts of CWP-wates of ceramic, through polishing and cutting procedures, causes serious environmental issues. Traditional methods of concrete production increase pollutions and create a severe burden on waste capacity. CWP usage in concrete mixtures as a responsible option, but however, accurate prediction is a one of the major problems. Current predictive models commonly create issues regarding accuracy, particularly by capturing the difficult, interactions among the mechanical features of concrete based CWP content. These drawbacks highlight the urgent need for an advanced predictive analytics model that can able to handle both environmental issues related to CWP concrete's manufacture also accurately predict the material's qualities. By considering this as a background, this study presents an effective novel hybrid solution for sustainable construction, which combines Deep convolutional particle filtering techniques (CNN-PF) with attention based Bi-LSM based predictive analytics on CWP for concrete. The proposed model combines the benefits of CNN-PF to extract important features in input data like composition details or microstructural images. Where the particle filtering improves the model's efficacy by handling abnormalities in the data. Additionally, attention based Bi-LSTM helps to capture long term dependencies in sequential data to improve prediction accuracy. The experimental investigation is performed with 54 different concrete mixes with two existing articles, in different Molds, using CWP. The outcomes highlight that our proposed model marks its remarkable outcomes than the existing models by achieving a notable result in both model-based prediction and Mold based prediction.

Key Words
cement; ceramic wate powder; deep learning algorithms; environmental impacts; predictive analytics; sustainable concrete

Address
China Construction Fifth Engineering Bureau Haixi Investment and Construction Co., Ltd, Xiamen, Fujian, 36100, China.

Abstract
The current study was not created with a specific goal in view, which addresses many applications in the field of building and construction. It provides a variety of goals that must be addressed immediately for construction applications. This means that we approach the situation from different angles. The present paper approaches the title in two distinct ways. With regard to "building," we concentrated on damage detection (crack and spall). At the same time, for "construction site application," we mainly depend on worker safety. Since this study is a novel concept with two distinct domains, with one solution. We design an advanced deep learning strategy to address both of the study's objectives. Most previous studies specifically deal with this type of application with various approaches, but the present study gives one solution to address both the objectives. Guaranteeing stable structure of buildings and worker safety are important in the quickly developing field of construction management. By creating an edge-enhanced multi-drone system that makes use of advanced deep learning algorithms, this work provides a novel solution. The chief objectives of this research are to: (1) detect crack damage at building sites; and (2) Focused on employees' compliance by using drone technology. According to this, the proposed model combines two effective strengths called YOLOv3 and Bayesian optimization, an Intelligent Deep Learning (INDEED) model which helps to meet the dual challenges was handled by the study. The system's integration of edge computing principles guarantees real-time processing and decision-making abilities, and providing quick response to abnormalities occurred. Due to this combined ability, the model able to solve both damage detection and safety enhancement procedures in single hand. The evaluation of the study is conducted through two distinct datasets: Crack damage detection was assessed using CSIR-CEERI, Pilani. And the workers safety procedures were evaluated using the UAE based local site samples. The proposed model uses the hardware environment of Jetson-TX2. A multi-drone system, which helps to capture the surroundings of construction and buildings stability. The experiment proves the suggested model efficacy with two distinct validations.

Key Words
Bayesian optimization; construction site management; crack damage detection; DL algorithms; edge intelligence; multi-drone system; YOLO v3; workers safety monitoring

Address
School of Architecture and Engineering, Shanghai Zhongqiao Vocational and Technical University, Jinshan, 201514 Shanghai, China.

Abstract
AI-driven optimization for sustainable landscape design has so far mostly concentrated on site analysis, plant selection, and design automation. Recycled waste materials have not received much attention as a central component of this approach. The area that needs more research is the application of AI algorithms specifically for selecting, processing, and using these recycled materials in a way that maximizes sustainability and minimizes waste. Our research is valuable because it closes this gap by creating AI-driven processes that prioritize the usage of recovered waste materials and improve landscape design, supporting both creative design and environmental sustainability. The goal of this study was to optimize recycled waste materials using artificial intelligence for sustainable landscape design. Direct data collection from the case study plant was done for the three recycled materials. To make sure the gathered data is appropriate for AI model training and analysis, Z-score uses preprocessing. Using AI-driven planning and operation, genetic programming (GP) is used to evaluate the characteristics of recycled materials and match them with the specifications of energy system landscape design optimization. We examined the operational data from energy producing machinery in real time. In order to ensure sustainability and durability, MLP used predictive modeling to simulate the long-term performance of various materials in varied environmental situations. CNN will develop a range of design alternatives that integrate recycled materials, considering aspects including environmental impact, cost-effectiveness, and resource efficiency. As a result, recycled waste materials demonstrated by the suggested superior performance over other similar models in terms of AUC, accuracy (training has 83% and validation has 90%), energy consumption (38J), precision (98%), RMSE (3.24), MAE (2.73) and R2 (0.88). Through the result overcoming sustainable design principles, this effort hopes to open up new avenues for ecologically conscious landscape architecture.

Key Words
AI-driven; genetic programming (GP); MLP- CNN; recycled waste materials; sustainable landscape

Address
School of Architectural Engineering, Zhejiang Industry Polytechnic College, Shaoxing, 312000, Zhejiang, China.

Techno-Press: Publishers of international journals and conference proceedings.       Copyright © 2024 Techno-Press ALL RIGHTS RESERVED.
P.O. Box 33, Yuseong, Daejeon 34186 Korea, Email: admin@techno-press.com