Applied Research最新文献

{"title":"Textile Metamaterials: Design, Fabrication, and Emerging Applications","authors":"Samanta M. de Holanda,&nbsp;Arthur M. da Silva,&nbsp;Thiago F. Santos,&nbsp;Dieter Rahmadiawan,&nbsp;Francisco D. M. Nobre,&nbsp;Jose Heriberto Oliveira do Nascimento,&nbsp;Idalmir de Souza Queiroz Júnior,&nbsp;Antonio Sergio Bezerra Sombra,&nbsp;Humberto D. de Andrade","doi":"10.1002/appl.70184","DOIUrl":"https://doi.org/10.1002/appl.70184","url":null,"abstract":"<p>In recent years, advanced materials have been explored to improve the performance of flexible electronics. As conventional approaches reach their limits, Metamaterials, which are artificially created materials with special electromagnetic properties not found in nature, have emerged as a promising alternative, enabling tunable mechanical behavior and wave control. Textile metamaterials (TMMs) have rarely been reported directly in the literature and, despite having ample potential to be explored, the number of works published in the last 25 years on this type of material represents about 0.3% when compared to general published research on metamaterials in the same period. These materials enable unconventional physical behaviors, including tunable mechanical responses, control of wave propagation, and programmable structural transformations. The TMMs have been integrated into flexible systems, enhancing devices through multi-scale structural engineering. Despite extensive research, textile-based applications remain limited, accounting for only a small fraction of 25 years of metamaterials work, despite their potential. This overview highlights the emerging field, focusing on the intersection of metamaterials and flexible electronics, especially textile-based, covering core concepts, recent advances, and applications such as adaptive deformability, enhanced sensitivity, and multifunctionality for next-generation applications.</p>","PeriodicalId":100109,"journal":{"name":"Applied Research","volume":"5 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/appl.70184","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942721","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experimental Investigation of Electromagnetic Interference Effects on Unmanned Aerial Vehicle Video Transmission Quality","authors":"Nurhakimah Norhashim,&nbsp;Shazril Arfaan Suziandi,&nbsp;Nadhiya Liyana Mohd Kamal,&nbsp;Zulhilmy Sahwee,&nbsp;Norliza Ismail,&nbsp;Shahrul Ahmad Shah,&nbsp;Sabarina Abdul Hamid,&nbsp;Dinesh Sathyamoorthy","doi":"10.1002/appl.70189","DOIUrl":"https://doi.org/10.1002/appl.70189","url":null,"abstract":"<p>Unmanned aerial vehicles (UAVs) are more widely used in industry and are reliant on stable real-time communication and video streaming. These systems can be vulnerable to electromagnetic interference (EMI), which degrades communication performance and may interrupt mission operations. This paper presents an experimental study on the effect of EMI on the video transmission performance of an E88 ProDrone on a 2.4 GHz control and data link. The experiment was conducted in a semi-anechoic chamber, suppressing environmental influence, and the test condition was the controlled variable. Interference signals generated by the signal generator were directed towards the stationary UAV, and the distance between the interference source and the UAV was kept constant at 1 m. The received interference power at the UAV position was computed using free space path loss (FSPL) and verified using a spectrum analyser, and the effect on the UAV video transmission system was recorded. Increasing the received interference power produced a progression from initial blurring and image shaking to freezing, buffering and complete loss of the displayed video feed. This study provides a controlled baseline for assessing the susceptibility of increasingly used low-cost consumer UAV video links to EMI by relating computed and verified received interference levels to observable stages of video degradation.</p>","PeriodicalId":100109,"journal":{"name":"Applied Research","volume":"5 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/appl.70189","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Viability, Storage Stability, Release Kinetics, and Sensory Attributes of Lactiplantibacillus plantarum ATCC 8014 in Synergistic Cryoprotectant-Mediated Puree Blend","authors":"Nur Ainaa Nasuha Mustaffa,&nbsp;Siti Fatimah Ibrahim,&nbsp;Noor Azlina Kamaruding,&nbsp;Mohd Al-Fatihhi Mohd Szali,&nbsp;Shahrulzaman Shaharuddin","doi":"10.1002/appl.70180","DOIUrl":"https://doi.org/10.1002/appl.70180","url":null,"abstract":"<p>Two synergistic cryoprotectants, glycerol and sodium alginate (SA), were evaluated for their impact on survival, simulated gastrointestinal tolerance and sensory quality of the probiotic <i>Lactiplantibacillus plantarum</i> in a frozen fruit puree. <i>L. plantarum</i> was added to purees along with different cryoprotectant mixture combinations and stored at sub-zero temperatures for 4 months. Microbiological, physicochemical and sensory properties were determined during storage. The probiotic viability (6.59–7.33 log₁₀ CFU/mL) of the samples treated with cryoprotectant was higher than that of the controls, indicating good cryoprotection and stability. High resistance and a controlled release in the simulated intestine were achieved through simulated digestion, yielding viable counts between 5.20 and 5.64 log₁₀ CFU/mL after 5 h. In the sensory evaluation, formulations that included cryoprotectants were noted for their overall acceptability, consistency, and taste. The results indicate that both glycerol and sodium alginate are promising candidates for developing functional foods, as they help maintain probiotic stability during frozen storage, facilitate effective gastrointestinal delivery, and enhance consumer acceptance.</p>","PeriodicalId":100109,"journal":{"name":"Applied Research","volume":"5 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/appl.70180","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning-Based Analysis and Prediction of the Influence of Meso-Void Characteristics on Sound Absorption Coefficient of Porous Asphalt Concrete","authors":"Yizhe Han,&nbsp;Xvfeng Wang,&nbsp;Shenxv Wang,&nbsp;Wenhua Wang,&nbsp;Zhan Wei,&nbsp;Jiaxiang Fang,&nbsp;Guangyong Wang","doi":"10.1002/appl.70191","DOIUrl":"https://doi.org/10.1002/appl.70191","url":null,"abstract":"<p>Porous asphalt concrete (PAC) is widely recognized as an effective noise-reducing pavement material due to its interconnected void structure. However, the quantitative relationship between meso-scale void characteristics and the sound absorption coefficient is not well understood, which limits the precision of mixture design for optimal acoustic performance. This study establishes a comprehensive database of PAC specimens, featuring eight meso-void characteristic parameters: computed void ratio, reconstructed void ratio, average equivalent diameter, average void volume, average void surface area, number of voids, total void surface area, and total void volume. A systematic machine learning framework was developed, integrating correlation analysis, multicollinearity diagnosis, stepwise regression, grey relational analysis, and multi-model comparison, to quantify the influence of void features on the average sound absorption coefficient (500–1600 Hz) and to create a high-precision prediction model. Five models, single-factor linear regression, multiple linear regression, random forest (RF), support vector regression (SVR), and Extra Trees (ET), were trained on 139 samples and evaluated against an independent validation set of 22 samples. The results indicate that the computed void ratio and reconstructed void ratio are the dominant factors, with Pearson correlation coefficients of 0.934 and 0.923, respectively. The ET model demonstrated the best predictive performance, achieving an <i>R</i>² of 0.9964 on the independent validation set, significantly outperforming SVR and multiple linear regression. Feature importance analysis revealed that the two void-ratio parameters accounted for 76.08% of the total ET feature importance. Sensitivity analysis confirmed that a ±10% perturbation in the computed void ratio induced the largest fluctuation in the predicted sound absorption coefficient. The proposed methodology and optimal ET model provide a reliable tool for PAC mixture design aimed at achieving targeted noise-reduction performance.</p>","PeriodicalId":100109,"journal":{"name":"Applied Research","volume":"5 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/appl.70191","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization of Production Process Parameters and Anti-Cracking Mechanism of Plant-Mixed Hot Recycling Asphalt Mixture Through SCB-DIC Testing","authors":"Kai Li,&nbsp;Yinghui Zhang,&nbsp;Zhenghao Liu,&nbsp;Zhigang Zhou","doi":"10.1002/appl.70187","DOIUrl":"https://doi.org/10.1002/appl.70187","url":null,"abstract":"<p>Plant-mixed hot recycling technology enables efficient resource utilization of reclaimed asphalt pavement (RAP); However, the resulting mixtures often exhibit inferior anti-cracking stability compared to virgin mixtures, and the cracking evolution mechanisms remain insufficiently understood. This study investigated the effect of six core production parameters: RAP preheating temperature, new aggregate preheating temperature, asphalt preheating temperature, mixing temperature, mixing regime, and RAP content. A mixed-level orthogonal experiment was designed to conduct multi-factor coupling tests. The Semi-Circular Bending (SCB) test combined with Digital Image Correlation (DIC) technology was employed to precisely capture the entire cracking evolution process, including crack initiation, stable propagation, and unstable failure. Three evaluation metrics—Flexibility Index (FI), Crack Initiation Energy (CIE), and Energy Consumption Rate (ECR)—were adopted to systematically analyze the primary and secondary effects of each process parameter on anti-cracking performance. Furthermore, meso-structural uniformity analysis was incorporated to explore the relationship among process parameters, meso-structural characteristics, and macro-scale anti-cracking performance. The results indicated that production process parameters affect the comprehensive performance of recycled mixture in the following descending order: mixing time regime &gt; RAP content &gt; RAP preheating temperature &gt; new aggregate preheating temperature &gt; asphalt preheating temperature &gt; mixing temperature. Notably, mixing regime appeared to be the sole parameter capable of simultaneously controlling both meso-structural uniformity and macro-scale anti-cracking performance, with unequal-step multi-stage mixing proving superior to equal-step mixing. The findings suggested a differentiated control mechanism for crack initiation and propagation: the former was primarily associated with aggregate-asphalt interfacial bonding, while the latter was linked to mastic integrity and aggregate skeleton stability. The optimal process combination balancing both crack initiation and propagation resistance was established as follows: RAP content 40%, RAP preheating temperature 150°C, new aggregate preheating temperature 200°C, asphalt preheating temperature 180°C, mixing temperature 180°C, and 4-min unequal-step staged mixing. These findings offer both theoretical foundations and technical guidance for optimizing production processes and controlling cracking in plant-mixed hot recycling asphalt mixtures.</p>","PeriodicalId":100109,"journal":{"name":"Applied Research","volume":"5 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/appl.70187","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"UniNS: A Neuro-Symbolic Framework for Structure-Regularized Causal Modeling of Catalytic Nanorobot Swarms in Confined Tumor Microenvironments","authors":"Xinyuan Chen,&nbsp;Nurdatillah Hasim,&nbsp;Norliana Muslim,&nbsp;Mohd Nizam Husen","doi":"10.1002/appl.70166","DOIUrl":"https://doi.org/10.1002/appl.70166","url":null,"abstract":"<p>Simulating the behavior of 100 nm catalytic nanorobot swarms in the tumor microenvironment from a multiphysics perspective is extremely challenging: traditional continuum models fail because agent dimensions mirror interstitial pore throats (<i>Kn</i> ~ <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 \u0000 <mrow>\u0000 <mi>O</mi>\u0000 \u0000 <mo>(</mo>\u0000 \u0000 <mn>1</mn>\u0000 \u0000 <mo>)</mo>\u0000 </mrow>\u0000 </mrow>\u0000 <annotation> ${mathscr{O}}{mathscr{(}}1)$</annotation>\u0000 </semantics></math>), and distinguishing genuine causal feedback loops from biological confounders and extracellular matrix remodeling remains an open problem. This paper proposes UniNS, a hybrid neuro-symbolic framework that couples a truncated Rotne-Prager-Yamakawa tensor with the Stokes-Brinkman equations to capture near-field hydrodynamic interactions beyond standard Darcy-Brinkman assumptions, while Michaelis-Menten kinetics bound active driving forces to preserve energy conservation. To counter the tendency of physics-informed neural networks to learn spurious correlations, the framework combines continuous structure regularization with backdoor-criterion marginalization, dynamically refining a structural DAG hypothesis from an expert-knowledge prior; the resulting structure is treated as a statistically reasonable association model rather than an absolute causal claim. Fast multipole acceleration extends the approach to synthetic pore networks with up to <i>N</i> = 10⁴ agents. The discovery phase converges to a structural Hamming distance of 3 from the expert prior (<i>p</i> &lt; 0.01, permutation test), and the refined structure reduces biochemical prediction errors by 27.3% relative to fixed-graph baselines. Together, these results establish a thermodynamically consistent, statistically regularized in silico testbed for nanoscale swarms—one that may help reduce reliance on costly in vitro experimentation and offers a promising direction for sustainable engineering practice in precision medicine.</p>","PeriodicalId":100109,"journal":{"name":"Applied Research","volume":"5 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/appl.70166","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of Eu3+ Doped MoO3 Nanostructures for Emerging Photovoltaic and Photocatalytic Applications","authors":"Boppanahalli Siddegowda Surendra,&nbsp;Harapanahalli Achutha Deepa,&nbsp;Boregowda Roopashree,&nbsp;Kolliganahalli Krishna Murthy Prashanth,&nbsp;Thimmaiah Kiran Kiran,&nbsp;Goppenahalli Nataraj Vikas,&nbsp;Mata Lingaraju Manuja,&nbsp;Neelakantgouda Policepatil,&nbsp;Neralekere Rangaswamaiah Mithun Gowda","doi":"10.1002/appl.70186","DOIUrl":"https://doi.org/10.1002/appl.70186","url":null,"abstract":"<p>Introducing Eu into the host lattice modifies its electronic structure for improving the power conversion efficiency of hetero-junction solar cells and water-purification technologies. The prepared nanomaterials were well characterized by various spectral techniques viz; XRD, SEM-EDX, TEM, XPS and FT-IR analysis. The phase purity and crystalline structure typically confirming the orthorhombic geometry of Eu-MoO₃ nanoparticle using XRD study. XPS characterized the successful incorporation of Eu³⁺ ions into the lattice and exact chemical valence states of Mo⁶⁺/Mo⁵⁺ and Eu³⁺/Eu²⁺, maps the concentration of oxygen vacancies induced by green combustion. Under Sun-light irradiation, the Eu-MoO₃ nanoparticles demonstrated enhanced degradation kinetics against RhB dye than host-MoO₃ nanoparticle, which is attributed to efficient charge separation mediated by the Eu³⁺ dopant states. The degradation efficiencies of host and Eu-MoO₃ nanoparticles were found to be 83% and 95% after 165 min under Sun-light irradiation. The fabricated DSSCs were subjected to J-V analysis under a solar simulator to evaluate their photovoltaic performance. The open-circuit voltage of the DSSC fabricated with Eu³⁺ was found to be 0.687 V, which is higher than host-MoO₃ (0.652 V). Eu doped DSSC showed a higher J_SC of 4.664 mA/cm² than host-MoO₃ (4.0 mA/cm²). As a result, the power conversion efficiency increased from 0.85% to 1.11% for the Eu-doped DSSCs. This research work offers valuable insights into modifying nanomaterial electronic properties for highly efficient photocatalytic and photovoltaic applications.</p>","PeriodicalId":100109,"journal":{"name":"Applied Research","volume":"5 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/appl.70186","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploratory Assessment of Spray-Drying Parameters and Preliminary Machine-Learning Modelling of Plukenetia volubilis Oil-Herbal Extract Emulsions","authors":"Siti Nursyazweena Zul-kharnain,&nbsp;Amiesha Nur Shaheerah Mazlan,&nbsp;Mohamad Syafiq Abdul Wahab,&nbsp;Rasyidah Alrozi,&nbsp;Anca Awal Sembada,&nbsp;Adi Izhar Che Ani,&nbsp;Mohd Othman Halim,&nbsp;Nur Qistina Ariffin,&nbsp;Mohamed Syazwan Osman","doi":"10.1002/appl.70190","DOIUrl":"https://doi.org/10.1002/appl.70190","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 <p>Co-formulating polyunsaturated oils with phytochemical-rich plant extracts presents practical challenges during spray drying, including emulsion instability and wall deposition. This exploratory study examined the effects of oil-to-water ratio, carrier type, carrier loading, and inlet temperature on a <i>Plukenetia volubilis</i> (Sacha Inchi) oil emulsion containing <i>Andrographis paniculata</i> and <i>Moringa oleifera</i> extracts using a sequential one-factor-at-a-time (OFAT) screening approach. Among the conditions investigated, a 1:9 oil-to-water ratio, 25% Arabic gum, and an inlet temperature of 140°C produced the highest powder recovery (93.8%). Scanning electron microscopy showed predominantly spherical particles with generally intact external surfaces, while phytochemical assays of the selected powder gave antioxidant activity of 97.58 mg AAE/g, total phenolic content of 16.15 mg GAE/g, and total flavonoid content of 10.87 mg QE/g. Exploratory Support Vector Machine (SVM) models for these three phytochemical responses produced higher in-domain performance metrics than baseline Decision Tree Regression models (SVM <i>R</i>² = 0.734–0.858; DTR <i>R</i>² = 0.344–0.562). Powder recovery and moisture content were treated only as measured powder characteristics and were not included as machine-learning targets. The small dataset (<i>n</i> = 30), restricted OFAT design, absence of external validation, and lack of measured emulsion and encapsulation descriptors prevent claims of generalisable prediction or confirmed mechanism. The findings identify preliminary formulation trends and define priorities for subsequent multifactorial experimentation and physicochemical validation.</p>\u0000 </section>\u0000 </div>","PeriodicalId":100109,"journal":{"name":"Applied Research","volume":"5 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/appl.70190","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Simulation and Analysis of Stiffened Auxetic Honeycombs Having Enhanced High Impact Velocity Response","authors":"Samy M. Lawaty,&nbsp;Haitham Khalaf,&nbsp;Andrew Alderson,&nbsp;Khaled Zied","doi":"10.1002/appl.70183","DOIUrl":"https://doi.org/10.1002/appl.70183","url":null,"abstract":"<p>This study investigates the ballistic performance of two aluminum-based re-entrant auxetic honeycomb configurations: classic and stiffened structures. Finite element analysis was conducted using ANSYS Explicit Dynamics to evaluate the in-plane response under high-velocity impact conditions. The effects of key geometric parameters, including horizontal cell wall length, wall thickness, and cell wall angle, were examined. The numerical model was validated against published data and showed good agreement. Simulations were performed for impacts in two orthogonal directions, revealing that the <i>X</i>-direction provides higher ballistic resistance. A total of 64 configurations were analyzed under a bullet impact velocity of 450 m/s and rotational speed of 11,771 rad/s. Results showed that increasing horizontal wall thickness significantly enhances ballistic resistance and energy absorption, while reducing wall length further improves impact performance. Cell wall angle exhibited minimal influence on ballistic time. Additionally, incorporating vertical and horizontal stiffening ribs significantly enhanced the ballistic performance, increasing the energy absorption efficiency by up to 119.45% and the projectile velocity reduction by up to 281.36% relative to the baseline specimen, that is, weakest unstiffened structure. The enhanced performance is attributed to structural reinforcement and auxetic-induced densification near the impact zone, which increases local resistance and energy dissipation.</p>","PeriodicalId":100109,"journal":{"name":"Applied Research","volume":"5 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/appl.70183","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942319","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficiency of Machine Learning Methods in Information Security Audit Tasks: A Comparative Analysis","authors":"Z. B. Mukhtarova,&nbsp;K. Е. Izrailov,&nbsp;A. T. Zharkimbekova,&nbsp;A. S. Baitulakov,&nbsp;D. Sagidullauly,&nbsp;А. A. Kyttybek","doi":"10.1002/appl.70182","DOIUrl":"https://doi.org/10.1002/appl.70182","url":null,"abstract":"<p>The automation of information security auditing requires effective software analysis methods, particularly when executable file metadata is missing, corrupted, or intentionally modified. This study presents a comparative analysis of machine learning methods for identifying processor instruction architectures using byte-frequency characteristics of software. Averaged byte-frequency signatures from different architectures were used to evaluate Naïve Bayes models, metric-based methods, linear classifiers, decision trees, random forests, support vector machines, neural networks, and ensemble models. Classification performance was assessed using Accuracy, Precision, Recall, and F1-score metrics. The results demonstrate that machine learning techniques provide satisfactory classification performance even with limited training data and significantly outperform random classification. Among the evaluated approaches, the Linear SVC (Support Vector Classifier) achieved the highest performance across all metrics. Error analysis revealed groups of closely related architectures that differ in endianness, bitness, and floating-point implementation, which represent the primary source of misclassification. The findings confirm the potential of machine learning methods for automating information security audits, software integrity verification, and digital forensic investigations.</p>","PeriodicalId":100109,"journal":{"name":"Applied Research","volume":"5 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/appl.70182","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148942323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}