Nof Nathansohn, Elisheva Gillis, Gitit Linker et al.

3D Printing and Additive Manufacturing • 2025

Imagine a world in which architecture will be 3D printed from living materials. That buildings will germinate, bloom, wither, produce new kinds of materials, and return back to the soil. This article introduces an innovative approach to sustainable architecture, through the utilization of 3D-printed structures crafted from locally sourced soil and plant seeds. After printing, the seeds germinate over time, forming load-bearing designs with interwoven root systems, which exhibit remarkable strength and resilience, reducing reliance on conventional construction materials. The research evaluates the mechanical properties of 3D-printed living structures through a set of material experiments to find a material combination that will allow maximum growth within 3D-printed architectural scale objects. The successful pilot project demonstrated their strength and capacity to support plant growth. The study also addresses the esthetic, cultural, and social dimensions of this novel fabrication technique, offering personalized, native plant-based patterns, and fostering community engagement. In conclusion, this research underscores the transformative potential of 3D-printed root-built structures as a sustainable architectural solution. By harnessing local soil and plant roots, these living constructions offer an eco-friendly alternative to conventional materials, with diverse environmental and social benefits. This study contributes to the evolving knowledge base of eco-conscious building practices, encouraging further exploration and adoption of nature-based solutions in architecture. With ongoing development, root-built buildings hold the promise of revolutionizing design, construction, and habitation, promoting a harmonious coexistence between humans and the natural environment.

Andong Wang, Junhao Guo, Chenkang Shao et al.

3D Printing and Additive Manufacturing • 2024

Currently, there is great demand for flexible three-dimensional (3D) printable thermoplastic polyurethane (TPU) wires with excellent ultraviolet (UV) resistance, which have broad application prospects in wearable products. In this study, UV-resistant TPU composites were obtained using a blending modification method. The relationship between the optimized parameters of fused deposition modeling 3D printing and mechanical properties of the TPU composite is discussed using an orthogonal test. This study observed that the UV absorption properties of TPU composites were enhanced, and the TiO 2 and TiO 2 /ZnO fillers improved the tensile strength of TPU composites. After UV aging, the tensile strength and elongation of the TPU composite slightly decreased, but were still much higher than those of pure TPU. Among the printing parameters, printing speed had the greatest influence on the mechanical properties of TPU composites. When the printing speed was 80 mm/s, printing layer thickness was 0.25 mm, nozzle temperature was 220°C, and hot bed temperature was 50°C, the TPU composites exhibited the best elongation at break and tensile strength. After regression analysis, two regression models for the elongation at break and tensile strength of TPU composites were obtained and verified, which provide a reference for predicting the relationship between the printing parameters and mechanical properties of flexible TPU composites.

Bora Uzun

3D Printing and Additive Manufacturing • 2024

Scaffolds' designs and physical properties have an important place in tissue engineering. Using different biomaterials, scaffolds with other structures can be developed. The thermal and mechanical properties of biomaterials used in producing scaffolds with the fused deposition modeling method are significant for the application's success. The material must be suitable for both the production method and to be used as a scaffold. Therefore, this study designed three different scaffolds made of the same polylactic acid (PLA) material, but with different lattice structures. To determine the mechanical properties of PLA scaffolds formed, 800 N axial compression load at a 20 mm/min velocity was applied to the samples, with n = 3 in each group. To determine the stiffness of scaffolds, the stress-strain values were calculated by measuring the maximum displacement data under load in each group. Also, finite element analysis was performed on PLA scaffold models. At the same time, scanning electron microscope, differential thermal analysis-thermogravimetric analysis, differential scanning calorimetry, and X-ray powder diffraction pattern analyses were carried out. As a result, it has been concluded that the design significantly affects mechanical properties. Besides the material, the scaffold design is the most important parameter in tissue engineering studies.

Hussain S

Bioequivalence & Bioavailability International Journal • 2020

The pharmaceutical industry is advancing at an incredible rate. Novel drug formulations for targeted therapy have been developed all thanks to advances in modern sciences. Even so, the manufacturing sector of novel dosage forms is minimal, and the industry continues to rely on traditional drug delivery systems, particularly modified tablets. The use of 3D printing technologies in pharma companies has opened up new possibilities for printed products and device research and production. 3D Printing has slowly progressed from its original use as pre-surgical imaging templates and tooling molds to produce one-of-a-kind instruments, implants, tissue engineering scaffolds, testing platforms, and drug delivery systems. The most significant advantages of 3D printing technologies include the ability to produce small batches of drugs with custom dosages, forms, weights, and drug release profiles. The production of medicines in this manner could eventually contribute to the realization of the principle of personalized medicine. The biomedical industry and academia have also embraced 3D printing in recent years. It offers commercially available medical devices as well as a forum for cutting-edge studies in fields such as tissue and organ printing. This mini-review provides an overview of 3D printed technology in medicines.

Maxwell Lohss, Elliott Hammersley, Anish Ghodadra

3D Printing in Medicine • 2023

Abstract Background The rapid expansion and anticipated U.S Food and Drug Administration regulation of 3D printing at the point-of-care necessitates the creation of robust quality management systems. A critical component of any quality management system is a document control system for the organization, tracking, signature collection, and distribution of manufacturing documentation. While off-the-shelf solutions for document control exist, external programs are costly and come with network security concerns. Here, we present our internally developed, cost-effective solution for an electronic document control system for 3D printing at the point-of-care. Methods We created a hybrid document control system by linking two commercially available platforms, Microsoft SharePoint and Adobe Sign, using a customized document approval workflow. Results Our platform meets all Code of Federal Regulations Title 21, Part 11 guidances. Conclusion Our hybrid solution for document control provides an affordable system for users to sort, manage, store, edit, and sign documents. The system can serve as a framework for other 3D printing programs to prepare for future U.S Food and Drug Administration regulation, improve the efficiency of 3D printing at the point-of-care, and enhance the quality of work produced by their respective program.

Xiaomei Zheng, Yongqing Wang, Guohong Du et al.

3D Printing and Additive Manufacturing • 2024

3D printing is an indispensable technology in modern life and is widely used in aerospace, exoskeleton, and architecture. The increasing accuracy requirements of 3D printed objects in these fields require high-precision measurement methods to obtain accurate data. Based on the precision measurement requirements, in this study, a fast multifrequency phase unwrapping method based on 3D printing object appearance acquisition is proposed. By performing standard image acquisition of 3D printed objects that are not limited to materials and sampling locations, the surface shape and texture details of the objects can be accurately reconstructed using this method, independent of ambient light, with high robustness. Compared with the conventional multifrequency method, the required projection pattern is reduced from 12 to 9 and the overall measurement efficiency is improved by 25%, while maintaining the advantages of the independent pixel calculation method of the multifrequency method. In addition, the effectiveness of the method is experimentally verified by complex surface reconstruction experiments and plaster model experiments, which provide accurate measurement accuracy with high efficiency and precision. Therefore, the method can provide accurate measurements for 3D printed objects.

Giovanni Biglino, Carina Hopfner, Joakim Lindhardt et al.

3D Printing in Medicine • 2023

Abstract This editorial presents the vision for the newly formed (2022) European 3D Special Interest Group (EU3DSIG) in the landscape of medical 3D printing. There are four areas of work identified by the EU3DSIG in the current landscape, namely: 1) creating and fostering communication channels among researches, clinicians and industry, 2) generating awareness of hospitals point-of-care 3D technologies; 3) knowledge sharing and education; 4) regulation, registry and reimbursement models.

Maria Mavri, Vangelis Mennis

3D Printing and Additive Manufacturing • 2022

The contribution of the fight against COVID-19 to the incorporation of 3D printing technology into the manufacturing industry is the research question of this study. By observing the structure of initiatives of hobbyists and enterprises in the 3D printing industry that are printing health care equipment for nursing staff, we conclude that 3D printing technology could be used for mass production under a different production model. We propose two different typologies of a factory's structure, calling them “Adjust-Semi Cloud Factory 1” and “Semi-Cloud Factory 2.” To measure the effectiveness of these new types of factories, we propose a framework based on characteristics and aspects of knowledge management.

Grace M. Thiong’o, Mark Bernstein, James M. Drake

3D Printing in Medicine • 2021

Abstract Objectives The objectives of this manuscript were to review the literature concerning 3D printing of brain and cranial vault pathology and use these data to define the gaps in global utilization of 3D printing technology for neurosurgical education. Methods Using specified criteria, literature searching was conducted to identify publications describing engineered neurosurgical simulators. Included in the study were manuscripts highlighting designs validated for neurosurgical skill transfer. Purely anatomical designs, lacking aspects of surgical simulation, were excluded. Eligible manuscripts were analyzed. Data on the types of simulators, representing the various modelled neurosurgical pathologies, were recorded. Authors’ countries of affiliation were also recorded. Results A total of thirty-six articles, representing ten countries in five continents were identified. Geographically, Africa as a continent was not represented in any of the publications. The simulation-modelling encompassed a variety of neurosurgical subspecialties including: vascular, skull base, ventriculoscopy / ventriculostomy, craniosynostosis, skull lesions / skull defects, intrinsic brain tumor and other. Finally, the vascular and skull base categories together accounted for over half (52.8 %) of the 3D printed simulated neurosurgical pathology. Conclusions Despite the growing body of literature supporting 3D printing in neurosurgical education, its full potential has not been maximized. Unexplored areas of 3D printing for neurosurgical simulation include models simulating the resection of intrinsic brain tumors or of epilepsy surgery lesions, as these require complex models to accurately simulate fine dissection techniques. 3D printed surgical phantoms offer an avenue for the advancement of global-surgery education initiatives.

Maxwell W. Walker, Christodoulos Kaoutzanis, Nicholas M. Jacobson

3D Printing in Medicine • 2023

Abstract Background Phalloplasty procedures are performed to create a phallus, typically as a gender-affirming surgery for treating gender dysphoria. Due to the controversial nature of this specific procedure, more innovation is needed to directly assist surgical teams in this field. As a result, surgeons are left to improvise and adapt tools created for other procedures to improve surgical outcomes. This study developed a patient-specific 3D printed model from segmented computed tomography (CT) scans to accurately represent the relevant vasculature necessary for anterolateral thigh (ALT) flap phalloplasty. The surgical procedure seeks to maintain intact vessels that derive from the descending branch of the lateral circumflex femoral artery, typically found traveling within the intermuscular septum between the rectus femoris and vastus lateralis. Methods In this study, we created and printed 3D models of the leg and vasculature using two techniques: (1) a standard segmentation technique with the addition of a reference grid and (2) a bitmap method in which the total CT volume is colorized and printed. Results The results gathered included the physician’s view on the model’s accuracy and visualization of relevant anatomy. Bitmap-printed models resulted in a high amount of detail, eliciting surgeons’ undesirable reactions due to the excess of information. The hybrid method produced favorable results, indicating positive feasibility. Conclusions This study tested the ability to accurately print a patient-specific 3D model that could represent the vasculature necessary for ALT flap procedures and potentially be used in surgical reference and planning in the future. A surgeon performing phalloplasty procedures discussed their approval of both models and their preference for grid creation and application.

Yanlu Wang

3D Printing in Medicine • 2024

Abstract Background 3D printers have gained prominence in rapid prototyping and viable in creating dimensionally accurate objects that are both safe within a Magnetic Resonance Imaging (MRI) environment and visible in MRI scans. A challenge when making MRI-visible objects using 3D printing is that hard plastics are invisible in standard MRI scans, while fluids are not. So typically, a hollow object will be printed and filled with a liquid that will be visible in MRI scans. This poses an engineering challenge however since objects created using traditional Fused Deposition Modeling (FDM) 3D-printing techniques are prone to leakage. Digital Light Processing (DLP) is a relatively modern and affordable 3D-printing technique using UV-hardened resin, capable of creating objects that are inherently liquid-tight. When printing hollow parts using DLP printers, one typically requires adding drainage holes for uncured liquid resin to escape during the printing process. If this is not done liquid resin will remain inside the object, which in our application is the desired outcome. Purpose We devised a method to produce an inherently MRI-visible accessory using DLP technology with low dimensional tolerance to facilitate MRI-guided breast biopsies. Methods By hollowing out the object without adding drainage holes and tuning printing parameters such as z-lift distance to retain as much uncured liquid resin inside as possible through surface tension, objects that are inherently visible in MRI scans can be created without further post-processing treatment. Results Objects created through our method are simple and inexpensive to recreate, have minimal manufacturing steps, and are shown to be dimensionally exact and inherently MRI visible to be directly used in various applications without further treatment. Conclusion Our proposed method of manufacturing objects that are inherently both MRI safe, and MRI visible. The proposed process is simple and does not require additional materials and tools beyond a DLP 3D-printer. With only an inexpensive DLP 3D-printer kit and basic cleaning and sanitation materials found in the hospital, we have demonstrated the viability of our process by successfully creating an object containing fine structures with low spatial tolerances used for MRI-guided breast biopsies.

Unknown Author

Fuel Cells Bulletin • 2021

Danish companies Blue World Technologies and Clayton Power are collaborating to develop a small-scale mobile methanol fuel cell solution for stationary and auxiliary power. The aim is to develop a solution in the 5–15 kW power range, that can be applied to heavy-duty trucks for powering air-conditioning and onboard appliances.

Jingwei Qi, Ming Hu, Pengcheng Xu et al.

Fuel • 2023

Arshia Fathima, Yong Zheng Liam, IMSK Ilankoon et al.

Bioresource Technology • 2022

Mathematical modelling of microbial fuel cells (MFC) facilitates their scale-up by maintaining dimensionless parameters across reactor volumes for consistent performance. This study developed data-driven correlations to predict areal power density for a batch-fed dual-chamber MFC using hybridised first-principle mechanistic model and Buckingham's Pi theorem. The established correlations were validated using experimentally-derived data for pre-enriched electroactive biofilm from mixed cultures. The biochemical model parameters are infilled with stoichiometric and thermodynamics estimations. Results showed that the correlations using logistic kinetics (Nash-Sutcliffe Efficiency, NSE = 0.59) outperformed Monod kinetics (NSE = 0.52) as the latter was not suitable for representing the first-order biochemical kinetics under limited substrate conditions. Sensitivity analysis on varying pH and bicarbonate concentration improved model predictions by ± 50%, though relative absolute error was ± 20% due to inherent error of estimated biochemical parameters. The application of hybridised approach for modelling MFC provides renewed perspectives for their rational design and scale-up applications.

Jiao Meng, Shufan Liu, Le Gao et al.

Microbial Cell Factories • 2023

Abstract Background Methanol, synthesized from CO 2 , is a potentially sustainable one-carbon (C1) resource for biomanufacturing. The use of methanol as a feedstock to produce single cell protein (SCP) has been investigated for decades as an alternative to alleviate the high global demand for animal-derived proteins. The methylotrophic yeast Pichia pastoris is an ideal host for methanol-based SCP synthesis due to its natural methanol assimilation ability. However, improving methanol utilization, tolerance to higher temperature, and the protein content of P. pastoris are also current challenges, which are of great significance to the economical industrial application using methanol as a feedstock for SCP production. Results In the present work, adaptive laboratory evolution (ALE) has been employed to overcome the low methanol utilization efficiency and intolerance to a higher temperature of 33 °C in P. pastoris , associated with reduced carbon loss due to the lessened detoxification of intracellular formaldehyde through the dissimilation pathway and cell wall rearrangement to temperature stress resistance following long-term evolution as revealed by transcriptomic and phenotypic analysis. By strengthening nitrogen metabolism and impairing cell wall synthesis, metabolic engineering further increased protein content. Finally, the engineered strain via multi-strategy produced high levels of SCP from methanol in a pilot-scale fed-batch culture at 33 °C with a biomass of 63.37 g DCW/L, methanol conversion rate of 0.43 g DCW/g, and protein content of 0.506 g/g DCW. SCP obtained from P. pastoris contains a higher percentage of protein compared to conventional foods like soy, fish, meat, whole milk, and is a source of essential amino acids, including methionine, lysine, and branched-chain amino acids (BCAAs: valine, isoleucine, leucine). Conclusions This study clarified the unique mechanism of P. pastoris for efficient methanol utilization, higher temperature resistance, and high protein synthesis, providing a P. pastoris cell factory for SCP production with environmental, economic, and nutritional benefits.

Prince Atta Opoku, Huang Jingyu, Li Yi et al.

Renewable Energy • 2023

Unknown Author

Fuel Cells Bulletin • 2021

Performance verification is nearing completion on new fuel cell electric terminal tractors, as the Zero Emissions for California Ports (ZECAP) project prepares to launch. GTI [see also page 6] and its partners have spent 16 months designing and assembling the tractors, which will now be assessed in a demanding, real-world cargo handling application. The hydrogen refueling equipment is in final assembly and scheduled for installation this spring, alongside delivery of the trucks.

Ruggero Rossi, Andy Y. Hur, Martin A. Page et al.

Water Research • 2022

Luis Caballero-Sanchez, Pedro E. Lázaro-Mixteco, Alejandra Vargas-Tah et al.

Microbial Cell Factories • 2023

Abstract Background A processing methodology of raw starch extraction from avocado seeds (ASs) and a sequential hydrolysis and fermentation bioprocess in just a few steps was successfully obtained for the bioethanol production by a single yeast Saccharomyces cerevisiae strain and this research was also to investigate the optimum conditions for the pretreatment of biomass and technical procedures for the production of bioethanol. It successfully resulted in high yields and productivity of all the experiments from the laboratory scale and the pilot plant. Ethanol yields from pretreated starch are comparable with those in commercial industries that use molasses and hydrolyzed starch as raw materials. Results Before the pilot-scale bioethanol production, studies of starch extraction and dilute sulfuric acid-based pretreatment was carefully conducted. The amount of starch extracted from dry and fresh avocado seed was 16.85 g ± 0.34 g and 29.79 ± 3.18 g of dry starch, representing a yield of ∼17% and 30%, respectively. After a dilute sulfuric acid pretreatment of starch, the released reducing sugars (RRS) were obtained and the hydrolysate slurries containing glucose (109.79 ± 1.14 g/L), xylose (0.99 ± 0.06 g/L), and arabinose (0.38 ± 0.01 g/L). The efficiency of total sugar conversion was 73.40%, with a productivity of 9.26 g/L/h. The ethanol fermentation in a 125 mL flask fermenter showed that Saccharomyces cerevisiae (Fali, active dry yeast) produced the maximum ethanol concentration, p max at 49.05 g/L (6.22% v/v) with a yield coefficient, Y p/s of 0.44 g Ethanol/ g Glucose , a productivity or production rate, r p at 2.01 g/L/h and an efficiency, Ef of 85.37%. The pilot scale experiments of the ethanol fermentation using the 40-L fermenter were also successfully achieved with essentially good results. The values of p max, Y p/s , r p , and Ef of the 40-L scale were at 50.94 g/L (6.46% v/v), 0.45 g Ethanol/ g Glucose , 2.11 g/L/h, and 88.74%, respectively. Because of using raw starch, major by-products, i.e., acetic acid in the two scales were very low, in ranges of 0.88–2.45 g/L, and lactic acid was not produced, which are less than those values in the industries. Conclusions The sequential hydrolysis and fermentation process of two scales for ethanol production using the combination of hydrolysis by utilizing dilute sulfuric acid-based pretreatment and fermentation by a single yeast Saccharomyces cerevisiae strain is practicable and feasible for realistic and effective scale-up strategies of bioethanol production from the starch of avocado seeds.

Isabel Thiele, Lara Santolin, Svea Detels et al.

Microbial Biotechnology • 2024

Abstract The transition towards a sustainable bioeconomy requires the development of highly efficient bioprocesses that enable the production of bulk materials at a competitive price. This is particularly crucial for driving the commercialization of polyhydroxyalkanoates (PHAs) as biobased and biodegradable plastic substitutes. Among these, the copolymer poly(hydroxybutyrate‐ co ‐hydroxyhexanoate) (P(HB‐ co ‐HHx)) shows excellent material properties that can be tuned by regulating its monomer composition. In this study, we developed a high‐cell‐density fed‐batch strategy using mixtures of fructose and canola oil to modulate the molar composition of P(HB‐ co ‐HHx) produced by Ralstonia eutropha Re2058/pCB113 at 1‐L laboratory scale up to 150‐L pilot scale. With cell densities >100 g L −1 containing 70–80 wt% of PHA with tunable HHx contents in the range of 9.0–14.6 mol% and productivities of up to 1.5 g L −1 h −1 , we demonstrate the tailor‐made production of P(HB‐ co ‐HHx) at an industrially relevant scale. Ultimately, this strategy enables the production of PHA bioplastics with defined material properties on the kilogram scale, which is often required for testing and adapting manufacturing processes to target diverse applications.

Sima Malekmohammadi, Seyed Ahmad Mirbagheri

Environmental Technology • 2023

Despite the high efficiency of microbial fuel cells (MFCs), MFCs cannot be a suitable alternative for treatment plants because of insufficient power generation and tiny reactors. Additionally, the increased reactor size and MFC stack result in a reduction in production power and reverse voltage. In this study, a larger MFC with a volume of 1.5 L has been designed called LMFC. A conventional MFC, called SMFC, with a volume of 0.157 L, was constructed and compared with LMFC. Moreover, the designed LMFC can be integrated with other treatment systems and generate significant electricity. In order to evaluate MFC's ability to integrate with other treatment systems, the LMFC reactor was converted into MFC-MBBR by adding sponge biocarriers. A 9.5 percent increase in reactor volume resulted in a 60 percent increase in power density from 290 (SMFC) to 530 (LMFC). An agitator effect was also investigated for better mixing and circulating substrate, which positively affected the power density by about 18%. Compared with LMFCs, the reactor with biocarriers generated a 28% higher power density. The COD removal efficiency of SMFC, LMFC, and MFC-MBBR reactors after 24 h was 85, 66, and 83%, respectively. After 80 h of operation, the Coulombic efficiency of the SMFC, LMFC, and MFC-MBBR reactors was 20.9, 45.43, and 47.28%, respectively. The doubling of coulombic efficiency from SMFC to LMFC reactor shows the design's success. The reduction of COD removal efficiency in LMFC is the reason for integrating this reactor with other systems, which was compensated by adding biocarriers.

Dishant Patel, Sweta L. Bapodra, Datta Madamwar et al.

Bioresource Technology • 2021

Pim de Jager, Daniel Groen, David P.B.T.B. Strik

Renewable Energy • 2023

Mouna Mothey

Kuwait Journal of Machine Learning • 2023

Software testing is one of the most critical processes toward achieving software quality and reliability. However, this is a time-consuming and resource-intensive process. Integration of Machine Learning into such a process in software testing could be seen as promising for automating or optimising such processes. This report discusses how ML techniques can assist in streamlining some of these testing activities, such as test case generation, fault detection, and test prioritization. Predictive analytics and ML algorithms make testing better in terms of effectiveness, accuracy, and adaptability. Although much has been accomplished, there are many issues related to fully implementing ML in traditional testing frameworks that still need research.

Karthika Balasubramani, Uma Maheswari Natarajan

Babylonian Journal of Machine Learning • 2024

Traffic go with the flow forecasting is essential in urban planning and management, optimizing transportation structures and resource allocation. However, accurately predicting visitors glide is tough because of its inherent complexity, nonlinearity, and diverse uncertain factors. The trouble declaration underscores the issue in as it should be forecasting site visitors flow, mainly in urban environments characterized through dynamic and complex site visitor’s styles. In the existing paintings there are numerous traditional devices getting to know models used for visitors flow prediction, however those conventional strategies show off barriers in reaching excessive prediction accuracy. Therefore, the proposed work targets to put into effect hybrid optimization techniques for correct prediction in shipping machine. Here fuzzy wavelet neural community (FWNN) is used to address complicated nonlinear structures with uncertain conditions and hybrid optimization method called hybrid firefly and particle swarm optimization (HFO-PSO) which combines the exploration and exploitation talents of firefly and this fusion allows the version to capture intricate visitor’s styles efficiently and optimize the prediction technique, improving accuracy and efficiency. Moreover, the prediction performance of the proposed model is established and compared by means of the usage of distinct measures.

Kavita Rajora, Nazar salih Abdulhussein

Babylonian Journal of Machine Learning • 2023

High false positive rates impede the adoption of anomaly detection methods, which have promise for detecting novel cyber threats. Techniques reviewed include Extreme Learning Machine (ELM), Hidden Markov Models (HMM), situation awareness frameworks, ensemble methods, and feature selection algorithms when applied to contemporary benchmark datasets. Findings show combinations of ELM, HMMs, and ensemble classifiers can achieve reduced false positive rates. However, gaps still exist in research using current representative data.

Mahdi Salah Mahdi AL-Inizi

Babylonian Journal of Machine Learning • 2025

Government bodies around the world are going digital and slowly starting to make use of data driven technologies to make better, faster and more transparent decisions. From these technologies, machine learning (ML) has become one of the most significantly employed tools, especially via its ability to predict. Predictive analytics allows governments to identify obscure trends that previously were hidden, predict potential future scenarios with an acceptable level of certainty and better inform decision-making in important areas, such as public finance, healthcare planning, emergency management, and resource allocation. In this work we explore the use of predictive modeling (implemented as our own Linear Regression, Decision Trees, Random Forests and Artificial Neural Networks) in the context of governmental decision models. The models were tested on real-world cases such as quarterly budget planning or estimation of healthcare service demand or emergency resource allocation using publicly available data from open government data platforms. Performance was evaluated based on the well-known RMSE, MAE and R² score. Results show that Artificial Neural Network always leads the highest in predictive accuracy, especially in dense or complex data setting, and there is no significant difference between Random Forest and Neural Network (the Random Forest has more generalization between interpretability and predictive power. On the other hand, Linear Regression and Decision Trees are more interpretable but have restrictions in using non-linear or high-dimensional datasets. In addition, the paper covers practical challenges including algorithmic bias, data quality considerations, and infrastructure capabilities, and ethical implications of automated decision making. This study has implications for the growing smart governance by proposing an integrated machine learning framework suitable for evidence-based policymaking. Future work involves improving the accuracy of prediction by incorporating explainable AI methodologies and customizing the model locally to enhance transparency, accountability, and generalization across different regional offices.

Sumana Sharma Poudel, Suresh Pokharel, Mohan Timilsina

Machine Learning with Applications • 2024

Akeel Shaker Mahmoud, Olfa Lamouchi, Safya Belghith

Babylonian Journal of Machine Learning • 2024

Chronic kidney disease (CKD) is a prevalent and debilitating condition worldwide, characterized by progressive loss of kidney function over time. Early detection plays a crucial role in mitigating its impact on patient health and healthcare systems. In recent years, there has been a burgeoning interest in leveraging machine learning (ML) and deep learning (DL) techniques to enhance the early diagnosis of CKD. This comprehensive review explores the advancements in ML and DL models applied to CKD diagnosis, focusing on their ability to integrate diverse data sources including clinical biomarkers, imaging modalities, and patient demographics. Key ML algorithms such as Support Vector Machines (SVM), Random Forests (RF), and neural network architectures like Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs) are examined in the context of their performance in predicting CKD progression, classifying disease stages, and identifying at-risk populations. Furthermore, the review discusses challenges such as data quality, model interpretability, and integration into clinical practice, alongside emerging trends in explainable AI, transfer learning, federated learning, and integration with electronic health records (EHRs). By synthesizing findings from recent literature, this paper aims to provide insights into current methodologies, identify gaps for future research, and underscore the transformative potential of ML and DL in revolutionizing early CKD diagnosis and management..

Rana Khalid Hamad

Babylonian Journal of Machine Learning • 2025

In bioinformatics, the classification of gene-disease associations is crucial. It directly affects whether we can untangle the genetic roots of various disease as well as if we will find some justifiable therapy for these cured diseases.Using XBNet to construct genetic algorithms for higher accuracy and speeds of gene-disease classification--this is the method developed in the book.Consisting of gene expression profiles for six diseases--Alzheimer's, Asthma, Cancer, Diabetes, Fabry and Down syndrome--our research has applied a comprehensive pre-processing technique to this data set from Kaggle. This has included such things as eliminating stop-words and punctuation marks and tokenization. Using the terms of Frequency (TF) and of Term Frequency-Inverse Document Frequency (TF-IDF method) for features extraction, our text data on genes are transformed into numerical axes fit for input to machine learning models.

Waseem Ghafori Yass, Mohammad Faris

Babylonian Journal of Machine Learning • 2023

This research focuses on the advancements in car detection techniques, particularly targeting wrong-way driving vehicles, using deep learning and machine learning methodologies. In recent years, numerous techniques have been proposed to address vehicle detection in real-time scenarios, leveraging algorithms such as YOLO (You Only Look Once) and centroid tracking to detect vehicles in various traffic situations. Additionally, methods involving UAV imagery, infrared imaging, and frame differencing approaches have enhanced the capabilities of real-time vehicle detection systems. Despite achieving significant milestones in accuracy and efficiency, existing methods still face limitations, such as high false-positive rates, imbalanced datasets, and challenges in complex environments like poor lighting and diverse road conditions. This study provides a comprehensive review of recent car detection approaches, comparing various algorithms including YOLO variants, CTAD, CNN, and DLMTD, and evaluating their strengths and limitations. A critical analysis of these methods reveals areas for improvement, particularly in terms of enhancing robustness, optimizing real-time response, and expanding detection capabilities to accommodate complex traffic patterns. The findings underscore the potential of hybrid approaches that combine object detection, tracking, and feature extraction techniques to achieve higher accuracy and adaptability in real-time applications. The study concludes by proposing a framework that addresses the observed limitations, suggesting pathways for future research in developing efficient, AI-powered car detection systems tailored for real-world applications.

Sahar Yousif Mohammed

Babylonian Journal of Machine Learning • 2024

Language learning has changed in recent years with the inclusion of ArtificialIntelligence (AI) bots. This paper discusses how AI bots have changed languageacquisition, paying more attention on how they improve language learningexperience. The Article looks at what prominent AI bots such as Gemini,ChatGPT and Cloud can do to make personalized feedback a reality as well asenhance interactivity and convenience in language learning.This article examinesthe functionality of adaptive learning algorithms which correct errors in real time,along with immersive environments that demonstrate the importance of artificialintelligence bots in achieving effective language acquisition. AI Bots are enablingbetter tutoring, increased cultural awareness and expanded learning choices.The fieldof foreign language education has been revolutionized thanks to tailored supportprovided by AI bots that promote cultural understanding and also offer flexible waysfor studying.

Unknown Author

Advances in Machine Learning & Artificial Intelligence • 2021

An important diagnostic method for diagnosing abnormalities in the human heart is the electrocardiogram (ECG). A large number of heart patients increase the assignment of physicians. To reduce their assignment, an automatic computer detection system is needed. In this study, a computer system for classifying ECG signals is presented. The MIT-BIH, ECG arrhythmia database is used for analysis. After the ECG signal is noisy in the preprocessing stage, the data feature is extracted. In the feature extraction step, the decision tree is used and the support vector machine (SVM) is constructed to classify the ECG signal into two categories. It is normal or abnormal. The results show that the system classifies the given ECG signal with 90% sensitivity.

Unknown Author

Advances in Machine Learning & Artificial Intelligence • 2024

This paper analyzes a dataset containing radio frequency (RF) measurements and Key Performance Indicators (KPIs) captured at 1876.6MHz with a bandwidth of 10MHz from an operational 4G LTE network in Nigeria. The dataset includes metrics such as RSRP (Reference Signal Received Power), which measures the power level of reference signals; RSRQ (Reference Signal Received Quality), an indicator of signal quality that provides insight into the number of users sharing the same resources; RSSI (Received Signal Strength Indicator), which gauges the total received power in a bandwidth; SINR (Signal to Interference plus Noise Ratio), a measure of signal quality considering both interference and noise; and other KPIs, all derived from three evolved node base stations (eNodeBs). After meticulous data cleaning, a subset of measurements from one serving eNB, spanning a 20-minute duration, was selected for deeper analysis. The PDCP DL Throughput, as a vital KPI metric, plays a paramount role in evaluating network quality and resource allocation strategies. Leveraging the high granularity of the data, the primary aim was to predict throughput. For this purpose, I compared the predictive capabilities of two machine learning models: Linear Regression and Random Forest. Metrics such as Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) were used to examine the models as they offer a comprehensive insight into the models’ accuracies. The comparative analysis highlighted the superior performance of the Random Forest model in predicting the PDCP DL Throughput. The insights derived from this research can potentially guide network engineers and data scientists in optimizing network performance, ensuring a seamless user experience. Furthermore, as the telecommunication industry advances towards the integration of 5G and beyond, the methodologies explored in this paper will be invaluable in addressing the increasingly complex challenges of future wireless networks.

Abdulazeez Alsajri, Amani Steiti

Babylonian Journal of Machine Learning • 2023

The widespread utilization of the internet and computer systems has resulted in notable security concerns, characterized by a surge in intrusions and vulnerabilities. Malicious users manipulate internal systems, resulting in the exploitation of software flaws and default setups. With the integration of the internet into society, there is an emergence of new risks such as viruses and worms, which highlights the importance of implementing robust security measures. Intrusion detection systems (IDS) are security technologies utilized to monitor and analyze network traffic or system activity with the purpose of identifying hostile behavior. This article presents a proposed method for detecting intrusion in network traffic using a hybrid approach, which combines a genetic algorithm and an SVM algorithm. The model underwent training and testing on the KDDCup99 dataset, with a reduction in features from 42 to 29 using the hybrid approach. The results demonstrated that throughout the system testing, it exhibited a remarkable accuracy of 0.999. Additionally, it achieved a true positive value of 0.9987 and a false negative rate of 0.012.

Hadeel M Saleh, Abdulrahman Kareem Oleiwi, Ahmed Abed Hwaidi Abed

Babylonian Journal of Machine Learning • 2023

Human Immunodeficiency Virus (HIV) is a global health issue that can progress to Acquired Immunodeficiency Syndrome (HIV) if not diagnosed and treated early. The advent of Artificial Intelligence (AI), particularly in machine learning and deep learning, presents new opportunities for improving the accuracy and efficiency of HIV diagnosis. This research explores the application of AI techniques in diagnosing HIV by reviewing previous studies and proposing a novel AI-based approach. The proposed methodology leverages deep learning algorithms, such as convolutional neural networks (CNNs), along with advanced data preprocessing techniques to enhance diagnostic accuracy, sensitivity, and specificity. The results of the proposed CNN-based model show an accuracy of 96.2%, sensitivity of 95.8%, specificity of 96.8%, and an AUC-ROC score of 0.965. Compared to Random Forest (accuracy: 92.1%), SVM (accuracy: 91.5%), and traditional methods (accuracy: 89.0%), the CNN model outperforms existing techniques significantly in terms of accuracy, sensitivity, and specificity. This demonstrates the effectiveness of the proposed AI approach for enhancing early and accurate HIV detection.

Alok Singh Chauhan, H Mary Henrietta

Babylonian Journal of Machine Learning • 2023

The domain of machine learning has experienced an unparalleled increase in attention and implementation, becoming an essential component of diverse businesses. This review paper provides a thorough analysis of the comprehensive handbook named "Machine Learning Basics: A Comprehensive Guide." Written by [Dr. Jane Doe], this guide has become a vital reference for those at all levels of expertise seeking to comprehend and traverse the intricate realm of machine learning.

Unknown Author

Advances in Machine Learning & Artificial Intelligence • 2021

Software defect prediction is a significant activity in every software firm. It helps in producing quality software by reliable defect prediction, defect elimination, and prediction of modules that are susceptible to defect. Several researchers have proposed different software prediction approaches in the past. However, these conventional software defect predictions are prone to low classification accuracy, time-consuming, and tasking. This paper aims to develop a novel multi-model ensemble machine-learning for software defect prediction. The ensemble technique can reduce inconsistency among training and test datasets and eliminate bias in the training and testing phase of the model, thereby overcoming the downsides that have characterized the existing techniques used for the prediction of a software defect. To address these shortcomings, this paper proposes a new ensemble machine-learning model for software defect prediction using k Nearest Neighbour (kNN), Generalized Linear Model with Elastic Net Regularization (GLMNet), and Linear Discriminant Analysis (LDA) with Random Forest as base learner. Experiments were conducted using the proposed model on CM1, JM1, KC3, and PC3 datasets from the NASA PROMISE repository using the RStudio simulation tool. The ensemble technique achieved 87.69% for CM1 dataset, 81.11% for JM1 dataset, 90.70% for PC3 dataset, and 94.74% for KC3 dataset. The performance of the proposed system was compared with that of other existing techniques in literature in terms of AUC. The ensemble technique achieved 87%, which is better than the other seven state-of-the-art techniques under consideration. On average, the proposed model achieved an overall prediction accuracy of 88.56% for all datasets used for experiments. The results demonstrated that the ensemble model succeeded in effectively predicting the defects in PROMISE datasets that are notorious for their noisy features and high dimensions. This shows that ensemble machine learning is promising and the future of software defect prediction.

Abdulazeez Alsajri

Babylonian Journal of Machine Learning • 2023

As we enter the Industry 5.0 era, enormous volumes of data are being created across digital systems. Machine learning techniques have recently achieved immense success in areas such as intelligent control, decision-making, speech recognition, natural language processing, computer graphics, and computer vision. This despite the significant challenge of analyzing and interpreting massive datasets. Owing to their strong performance, deep learning and machine learning algorithms have become widely deployed across various real-time engineering applications. Developing working knowledge of machine learning is now critical for building automated, smart systems that can process data in domains like healthcare, cybersecurity, and intelligent transportation. There exist multiple strategies in machine learning, including reinforcement learning, semi-supervised learning, unsupervised learning, and supervised learning algorithms. This research provides a comprehensive examination of leveraging machine learning for managing real-time engineering systems, with the goal of augmenting their capabilities and intelligence. It contributes to the understanding of how different machine learning approaches can be applied in real-world use cases like cybersecurity, healthcare, and intelligent transportation. Additionally, it highlights ongoing research objectives and difficulties that machine learning techniques encounter while tackling real-world systems. This research serves both industry professionals and academics as a reference, while technically benchmarking decision-making across different application areas and real-world scenarios.

Ashima Tyagi, Vibhav Prakash Singh, Manoj Madhava Gore

Neuroinformatics • 2024