An Analogy between Various Machine-learning Techniques for Detecting Construction Materials in Digital Images

Abbas Rashidi,Mohamad Hoseyn Sigari,Marcel Maghiar,David Citrin 대한토목학회 2016 KSCE JOURNAL OF CIVIL ENGINEERING Vol.20 No.4

Digital images and video clips collected at construction jobsites are commonly used for extracting useful information. Exploring new applications for image processing techniques within the area of construction engineering and management is a steady growing field of research. One of the initial steps for various image processing applications is automatically detecting various types of construction materials on construction images. In this paper, the authors conducted a comparison study to evaluate the performance of different machine learning techniques for detection of three common categorists of building materials: Concrete, red brick, and OSB boards. The employed classifiers in this research are: Multilayer Perceptron (MLP), Radial Basis Function (RBF), and Support Vector Machine (SVM). To achieve this goal, the feature vectors extracted from image blocks are classified to perform a comparison between the efficiency of these methods for building material detection. The results indicate that for all three types of materials, SVM outperformed the other two techniques in terms of accurately detecting the material textures in images. The results also reveals that the common material detection algorithms perform very well in cases of detecting materials with distinct color and appearance (e.g., red brick); while their performance for detecting materials with color and texture variance (e.g., concrete) as well as materials containing similar color and appearance properties with other elements of the scene (e.g., ORB boards) might be less accurate.

Preparation of nanoporous activated carbon and its application as nano adsorbent for CO2 storage

Alimorad Rashidi,Davood Kazemi,Nosrat Izadi,Mahnaz Pourkhalil,Abbas Jorsaraei,Enseyeh Ganji,Roghayeh Lotfi 한국화학공학회 2016 Korean Journal of Chemical Engineering Vol.33 No.2

Nanoporous activated carbons, as adsorbent for CO2 storage, were prepared from walnut shells via two chemical processes including phosphoric acid treatment and KOH activation at high temperature. Specific surface area and porosities were controlled by KOH concentration and activation temperature. The obtained adsorbents were characterized by N2 adsorption at 77.3 K. Their carbon dioxide adsorption capacities were measured at different pressures at 290 K by using volumetric adsorption equipment. The KOH-treated nanoporous carbons typically led to the production of high specific surface areas and high micropore volumes and showed better performance for CO2 adsorptions. The maximum experimental value for adsorption capacity happened when pressure increased from 5 to 10 bar (1.861- 2.873mmol·g−1). It was found that in order to improve the highest capacity of CO2 adsorption for KOH-modified carbon (9.830-18.208mmol·g−1), a KOH: C weight ratio of 3.5 and activation temperature of 973 K were more suitable for pore development and micro-mesopore volume enhancement.

A Markov Decision Process Workflow for Automating Interior Design

Ebrahim Karan,Sadegh Asgari,Abbas Rashidi 대한토목학회 2021 KSCE JOURNAL OF CIVIL ENGINEERING Vol.25 No.9

We present a novel workflow based on artificial intelligence (AI) techniques to automate interior design processes. We discuss the essential steps for creating an intelligent agent that can automatically perceive the design environment (perception) and produce design ideas (action). In the first step, we use photographs or video images to model three-dimensional coordinates and exact positions of surface points on objects inside the interior space. We then convert the collected spatial data to a set or cloud of points. To fully model the interior space, we create either a triangulated surface or a mesh from the points and then transform it into a detailed building information model (BIM). Last, we apply texture data to either the 3D surface/mesh or the building information model. In the second step, we develop a sequential decision-making model based on Markov decision process for the intelligent agent to make design decisions in the BIM environment. We apply the proposed workflow to a case study with 512 possible design options, conduct experiments with 20 participants where design decisions are made based on AI insights, and perform statistical analysis on the experiment results. Our findings show the proposed workflow is capable of improving participants’ satisfaction by only searching through on average 5.1% of all possible design options. Also, across all performance measures, design decisions proposed by the AI system outperform designs made randomly.

Response of Triple Negative Breast Cancer to Neoadjuvant Chemotherapy: Correlation between Ki-67 Expression and Pathological Response

Elnemr, Gamal M,El-Rashidy, Ahmed H,Osman, Ahmed H,Issa, Lotfi F,Abbas, Osama A,Al-Zahrani, Abdullah S,El-Seman, Sheriff M,Mohammed, Amrallah A,Hassan, Abdelghani A Asian Pacific Journal of Cancer Prevention 2016 Asian Pacific journal of cancer prevention Vol.17 No.2

Triple-negative breast cancers constitute about 15% of all cases, but despite their higher response to neoadjuvant chemotherapy, the tumors are very aggressive and associated with a poor prognosis as well as a higher risk of early recurrence. This study was retrospectively performed on 101 patients with stage II and III invasive breast cancer who received 6-8 cycles of neo-adjuvant chemotherapy. Out of the total, 23 were in the triple negative breast cancer subgroup. Nuclear Ki-67 expression in both the large cohort group (n=101) and triple negative breast cancer subgroup (n=23) and its relation to the pathological response were evaluated. The purpose of the study was to identify the predictive value of nuclear protein Ki-67 expression among patients with invasive breast cancers, involving the triple negative breast cancer subgroup, treated with neoadjuvant chemotherapy in correlation to the rate of pathological complete response. The proliferation marker Ki-67 expression was highest in the triple negative breast cancer subgroup. No appreciable difference in the rate of Ki-67 expression in triple negative breast cancer subgroup using either a cutoff of 14% or 35%. Triple negative breast cancer subgroup showed lower rates of pathological complete response. Achievement of pathological complete response was significantly correlated with smaller tumor size and higher Ki-67 expression. The majority of triple negative breast cancer cases achieved pathological partial response. The study concluded that Ki-67 is a useful tool to predict chemosensitivity in the setting of neoadjuvant chemotherapy for invasive breast cancer but not for the triple negative breast cancer subgroup.

Effects of Sucrose and Trehalose on the Freezability of Markhoz Goat Spermatozoa

Khalili, B.,Farshad, Abbas,Zamiri, M.J.,Rashidi, A.,Fazeli, P. Asian Australasian Association of Animal Productio 2009 Animal Bioscience Vol.22 No.12

The present study was conducted to observe the effect of increased osmolality of basic tris extender supplemented with trehalose and sucrose on post-thawing quality (motility, progressive motility, viability, the rate of acrosome abnormality, total abnormality and membrane integrity) of Markhoz goat spermatozoa. Fresh semen samples were evaluated for motility and sperm concentration. Only semen samples with motility more than 70% and sperm concentration higher than $3{\times}10^{9}$ sperm/ml were used for cryopreservation. In Exp. 1, trehalose (50, 75 or 100 mM) and sucrose (40, 60 or 80 mM) were added to a basic tris diluent. Based on the results of experiment 1, the goal of Exp. 2 was to investigate the combinational effects of the highest and lowest concentrations ($T_{100}+S_{80}$ or $T_{50}+S_{40}$) of trehalose and sucrose. As the control, semen was diluted and frozen in the tris diluent without trehalose or sucrose. The results in Exp. 1 showed that all evaluated spermatozoa characteristics improved significantly after freezing and thawing (p<0.05) and at the same time the increase of trehalose and sucrose concentrations in basic extenders was seen, with the best results obtained for extenders containing 70 and 100 mM trehalose and 80 mM sucrose. Comparing these results with those of control diluents, the effects of supplementation were significantly (p<0.05) better. In Exp. 2, the results showed no significant differences (p>0.05) between $T_{100}+S_{80}$ and $T_{50}+S_{40}$ extenders, but the results of $T_{50}+S_{40}$were slightly better than obtained with $T_{100}+S_{80}$ diluents. Furthermore, the results of this experiment indicated that the sperm characteristics in the isotonic control extender were significantly (p<0.05) lower than examined extenders. In conclusion, the results of this study indicated that goat sperm can tolerate hypertonic trehalose and sucrose solutions better than isotonic control diluents in the freezing period. In particular, these positive effects have been shown for acrosome integrity, which is very important for the fertilization capacity of sperm. The data indicated that addition of trehalose plus sucrose to the freezing extender can be recommended for cryopreservation of goat spermatozoa, but more data is needed on pregnancy rate, acrosome reaction and IVF to ascertain the real effect.

Optimization of lithium separation conditions from Caspian seawater using fuzzy logic combined with dispersive liquid–liquid extraction

Romina Pourhassan Motlagh Sharemi,Abbas Rashidi,Mohammad Hassan Mallah,Jaber Safdari 한국자원공학회 2019 Geosystem engineering Vol.22 No.3

For optimization of separation conditions of lithium from the Caspian seawater, a new combination technique of liquid–liquid extraction and fuzzy logic is being used. In this research, disperser and extraction solvents, and ligand of benzo15-crown-5, have been quickly injected. It went to cloudy form solution contain small extraction solvent drops. The impact of different parameters such as the kind and concentration of benzo15-crown-5, the volume of disperser and extraction solvents, pH and extraction time have been optimized on the extraction percentage and analyzed using fuzzy logic. The effect of other metal ion on extraction percentage was also investigated. Under the optimized conditions (volume of tetrachloroethylene: 1.5 mL, volume of acetone: 120 mL, volume of benzo15-crown-5: 0.1 mL, concentration of benzo15-crown-5: 0.001 mol/L, and pH: 1), the extraction has increased to 74% for the synthesis sample and 31% for the real sample from Caspian seawater.

Numerical Study of Entropy Generation with Nonlinear Thermal Radiation on Magnetohydrodynamics non-Newtonian Nanofluid Through a Porous Shrinking Sheet

M. M. Bhatti,T. Abbas,M. M. Rashidi 한국자기학회 2016 Journal of Magnetics Vol.21 No.3

In this article, entropy generation on MHD Williamson nanofluid over a porous shrinking sheet has been analyzed. Nonlinear thermal radiation and chemical reaction effects are also taken into account with the help of energy and concentration equation. The fluid is electrically conducting by an external applied magnetic field while the induced magnetic field is assumed to be negligible due to small magnetic Reynolds number. The governing equations are first converted into the dimensionless expression with the help of similarity transformation variables. The solution of the highly nonlinear coupled ordinary differential equation has been obtained with the combination of Successive linearization method (SLM) and Chebyshev spectral collocation method. Influence of all the emerging parameters on entropy profile, temperature profile and concentration profile are plotted and discussed. Nusselt number and Sherwood number are also computed and analyzed. It is observed that entropy profile increases for all the physical parameters. Moreover, it is found that when the fluid depicts non-Newtonian (Williamson fluid) behavior then it causes reduction in the velocity of fluid, however, non-Newtonian behavior enhances the temperature and nanoparticle concentration profile.

Optimization of Microphone Placement for Audio-based Modeling of Construction Jobsites

Maria Vitoria Bini Farias,Yinhu Wang,Abbas Rashidi,Nikola Marković 대한토목학회 2024 KSCE Journal of Civil Engineering Vol.28 No.5

Heavy equipment is a crucial resource in the construction industry. Recent studies have shown that analyzing the sound patterns generated by construction machinery can be an effective way to monitor their performance and detect potential operational issues. However, construction jobsites are complex environments that require consideration of multiple factors when creating an audio-based model. To perform efficient audio-based modeling of jobsites, it is essential to optimize the number and placement of microphones to capture the sound emitted by all the operating machines and achieve optimal sound quality. To address this challenge, we developed two optimization methods: (a) an integer programming model that guarantees finding the optimal placement of microphones, and (b) an evolutionary programming model, a heuristic approach more suited to larger problem instances. We evaluated the effectiveness of these models in five different case studies from construction jobsites. Our results showed that the developed models require a reasonable number of microphones to achieve the desired sound quality, demonstrating their satisfactory performance. Notably, both approaches exhibited similar performance in terms of the required number of microphones needed to cover all the machinery.