Search Results (21)

With artificial intelligence (AI) rapidly increasing in popularity and presence in everyday life, new applications utilizing AI are being explored across virtually all domains, from banking and healthcare to cybersecurity to generative AI for images, voice, and video content creation. With that trend comes an inherent need for increased AI capabilities. One cornerstone of AI applications is the ability of generative AI to consume documents and utilize their content to answer questions, generate new content, correlate it with other data sources, and more. No longer constrained to text alone, we now leverage multimodal AI models to help us understand visual elements within documents, such as images, tables, figures, and charts. Within this realm, capabilities have expanded exponentially from traditional Optical Character Recognition (OCR) approaches towards increasingly utilizing complex AI models for visual content analysis and understanding. Modern approaches, especially those leveraging AI, are now focusing on interpreting more complex diagrams such as flowcharts, block diagrams, Unified Modeling Language (UML) diagrams, electrical schematics, and timing diagrams. These diagram types combine text, symbols, and structured layout, making them challenging to parse and comprehend using conventional techniques. This paper presents a historical analysis and comprehensive survey of scientific literature exploring this domain of visual understanding of complex technical illustrations and diagrams. We explore the use of deep learning models, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer-based architectures. These models, along with OCR, enable the extraction of both textual and structural information from visually complex sources. Despite these advancements, numerous challenges remain, however. These range from hallucinations, where the content extraction system produces outputs not grounded in the source image, which leads to misinterpretations, to a lack of contextual understanding of diagrammatic elements, such as arrows, grouping, and spatial hierarchy. This survey focuses on five key diagram types: flowcharts, block diagrams, UML diagrams, electrical schematics, and timing diagrams. It evaluates the effectiveness, limitations, and practical solutions—both traditional and AI-driven—that aim to enable the extraction of accurate and meaningful information from complex diagrams in a way that is trustworthy and suitable for real-world, high-accuracy AI applications. This survey reveals that virtually all approaches struggle with accurately extracting technical diagram information. It also illustrates a path forward. Pursuing research to further improve their accuracy is crucial for supporting and enabling various applications, including complex document question answering and Retrieval Augmented Generation (RAG), document-driven AI agents, accessibility applications, and automation. Full article

The subject of the present work is the study of the phenomena of the interaction between wave motion and coastal defense structures for a new type of reinforcement unit in concrete armor blocks (C.A.U.)—named “MAYA”. The performance of single-layer MAYA armor, reproduced in a 1:20 Froude-scaled physical model, has been investigated in terms of hydraulic behavior and wave run-up, reflection, and overtopping. The results have been compared to classic literature formulations, numerical results of the same type of structure reproduced at full scale, and other artificial blocks. A new approach for the prediction of the reflection coefficient based on dimensional analysis was proposed in a previous study, and a newly derived empirical equation was also tested for numerical result validation. The structures were numerically modeled and reproduced using an innovative approach by overlapping individual three-dimensional elements of a new type of block “Maya”, Accropode and Tetrapod and a fine computational grid was fitted to provide enough computational nodes within the flow paths. The hydraulic behavior of the novel block was numerically evaluated, and its potential was assessed in comparison to other existing blocks. This was achieved by reproducing and analyzing the structures using a RANS approach. The numerical approach, which was validated by experimental results, enables the analysis of various design solutions in a shorter amount of time while ensuring the accuracy of the results. Additionally, the preliminary analysis showed the potential of the novel block, which allows for a reduction in construction and manufacturing costs while also demonstrating superior hydrodynamic performance in some cases. Full article

Conventional inspections in car damage assessments depend on visual judgments by human inspectors, which are labor-intensive and prone to fraudulent practices through manipulating damages. Recent advancements in artificial intelligence have given rise to a state-of-the-art object detection algorithm, the You Only Look Once algorithm (YOLO), that sets a new standard in smart and automated damage assessment. This study proposes an enhanced YOLOv9 network tailored to detect six types of car damage. The enhancements include the convolutional block attention module (CBAM), applied to the backbone layer to enhance the model’s ability to focus on key damaged regions, and the SCYLLA-IoU (SIoU) loss function, introduced for bounding box regression. To be able to assess the damage severity comprehensively, we propose a novel formula named damage severity index (DSI) for quantifying damage severity directly from images, integrating multiple factors such as the number of detected damages, the ratio of damage to the image size, object detection confidence, and the type of damage. Experimental results on the CarDD dataset show that the proposed model outperforms state-of-the-art YOLO algorithms by 1.75% and that the proposed DSI demonstrates intuitive assessment of damage severity with numbers, aiding repair decisions. Full article

Fifth-generation mobile networks (5G) are designed to support enhanced Mobile Broadband, Ultra-Reliable Low-Latency Communications, and massive Machine-Type Communications. To meet these diverse needs, 5G uses technologies like network softwarization, network slicing, and artificial intelligence. Multi-connectivity is crucial for boosting mobile device performance by using different Wireless Access Technologies (WATs) simultaneously, enhancing throughput, reducing latency, and improving reliability. This paper presents a multi-connectivity testbed from the 5G-CLARITY project for performance evaluation. MultiPath TCP (MPTCP) was employed to enable mobile devices to send data through various WATs simultaneously. A new MPTCP scheduler was developed, allowing operators to better control traffic distribution across different technologies and maximize aggregated throughput. Our proposal mitigates the impact of limitations on one path affecting others, avoiding the Head-of-Line blocking problem. Performance was tested with real equipment using 5GNR, Wi-Fi, and LiFi —complementary WATs in the 5G-CLARITY project—in both static and dynamic scenarios. The results demonstrate that the proposed scheduler can manage the traffic distribution across different WATs and achieve the combined capacities of these technologies, approximately 1.4 Gbps in our tests, outperforming the other MPTCP schedulers. Recovery times after interruptions, such as coverage loss in one technology, were also measured, with values ranging from 400 to 500 ms. Full article

Polymer self-assembly can prepare various shapes and sizes of pores, making it widely used. The complexity and diversity of biomolecules make them a unique class of building blocks for precise assembly. They are particularly suitable for the new generation of biomaterials integrated with life systems as they possess inherent characteristics such as accurate identification, self-organization, and adaptability. Therefore, many excellent methods developed have led to various practical results. At the same time, the development of advanced science and technology has also expanded the application scope of self-assembly of synthetic polymers. By utilizing this technology, materials with unique shapes and properties can be prepared and applied in the field of tissue engineering. Nanomaterials with transparent and conductive properties can be prepared and applied in fields such as electronic displays and smart glass. Multi-dimensional, controllable, and multi-level self-assembly between nanostructures has been achieved through quantitative control of polymer dosage and combination, chemical modification, and composite methods. Here, we list the classic applications of natural- and artificially synthesized polymer self-assembly in the fields of biomedicine and materials, introduce the cutting-edge technologies involved in these applications, and discuss in-depth the advantages, disadvantages, and future development directions of each type of polymer self-assembly. Full article

Glass fiber-reinforced polymer (GFRP) anchor bolts are a new type of high-performance nonmetallic anchor with significantly higher tensile strength, a lighter weight, better corrosion resistance, and a lower cost than steel bars. Therefore, exploring the durability and bonding performance of GFRP anchor systems is of great importance for the structural design of protective engineering, especially in coastal environments. However, insufficient research has been conducted on the durability of GFRP resin bolts in seawater conditions, with no universal standard on the pullout testing of GFRP bolts. To study the durability and bonding performance of GFRP resin bolts, durability experiments were conducted in this work using artificial seawater, and the pullout tests were conducted using a large-scale concrete platform with different compressive strengths (21.2, 40.8, and 61.3 MPa). The results of the durability experiments indicated that the strength variations of the GFRP rods and epoxy resin materials in artificial seawater environments were less than 5%. Subsequently, indoor pullout tests using steel tubes filled with epoxy resin were conducted, and the test results indicated a critical anchor length value. Pullout tests of the GFRP resin bolts embedded in large-scale concrete blocks were also conducted with different strengths. According to the test results, all GFRP resin bolts embedded in the three concrete blocks with different compressive strengths exhibited rod fracture failure. The failure mode was not controlled via the compressive strength of the concrete blocks due to the high bonding strength between the resin and the rod, as well as between the resin and the concrete. Therefore, this GFRP resin anchor system could fully utilize the tensile strength of GFRP rods. This research offers significant practical value in verifying the safety and reliability of GFRP resin bolts in corrosive marine service environments, and it contributes to the application and development of GFRP materials in the engineering field, serving as a valuable reference for the structural design and further study of GFRP bolts. Full article

Fracturing hard roofs by ground hydraulic action is an important control technology for the strong mine pressure in the stope. In this paper, a new simulation method, “separate + interface,” is proposed, and two physical simulation experiments are conducted; the phenomenon of increased goaf pressure and decreased front abutment pressure is discovered after fracturing in the key strata, and then the influence of different fractured crack shapes on the front abutment pressure and the goaf stress is revealed. The results are as follows: Firstly, the separation under the high-level hard strata blocks the transmission of overburden load to the goaf, leading to the high-stress concentration of the coal seam, which is the main reason for the large deformation of roadways and the breakage of a single hydraulic prop in the roadway. Secondly, the weakening effect of mine pressure differs when hard rock strata are fractured artificially with different types of cracks. The peak value of abutment pressure is reduced from 24.91 to 20.60 MPa, 17.80 MPa, and 16.13 MPa with the vertical crack spacing of 20 m, 15 m, and 10 m, respectively, and the related goaf pressure is increased from 2.61 to 3.54 MPa, 3.91 MPa, and 4.34 MPa, respectively. The peak value of abutment pressure decreased from 24.79 to 22.08 MPa, 19.88 MPa, and 17.73 MPa. The related goaf pressure increased from 2.61 to 3.39 MPa, 3.81 MPa, and 4.43 MPa, respectively, with the key strata also fractured into two horizontal layers, three horizontal layers, and four horizontal layers with horizontal fractures. Thirdly, after the hard roof is fractured above the No. 8202 working face, the first breaking step distance of the main roof decreased from 112.6 to 90.32 cm, while the first breaking step distances of KS2 and KS3 decreased from 106.3 and 135.8 cm to 93.5 cm and 104.8 cm, respectively, and the goaf pressure also increased. Compared to the adjacent unfractured No. 8203 working face, the mine pressure intensity of the No. 8202 working face is significantly reduced. The research results can provide useful guidance for the treatment of strong mine pressure. Full article

The rapid development of cloud–fog–edge computing and mobile devices has led to massive amounts of data being generated. Also, artificial intelligence technology, like machine learning and deep learning, is widely used to mine the value of the data. Specifically, detecting attacks on the cloud–fog–edge computing system using mobile devices is essential. External attacks on network press organizations led to anomaly flow in network traffic. The network intrusion detection system (NIDS) has been an effective method for detecting anomaly flow. However, the NIDS is hard to deploy in distributed networks because network flow data are kept private. Existing methods cannot obtain an accurate NIDS under such a federated scenario. To construct an NIDS while preserving data privacy, we propose a combined model that integrates binary classifiers into a whole network based on simple classifier networks to specify the type of attack on anomalous data and offer instruction to other security system components. We also introduce federated learning (FL) methods into our system and design a new aggregation algorithm named vertical blocking aggregation (FedVB) according to our model structure. Our experiments demonstrate that our system can be more effective than simple multi-classifiers in terms of accuracy and significantly reduce communication and computation overhead when applying FedVB. Full article

In the blockchain system, mining pools are popular for miners to work collectively and obtain more revenue. Nowadays, there are consensus attacks that threaten the efficiency and security of mining pools. As a new type of consensus attack, the Fork After Withholding (FAW) attack can cause huge economic losses to mining pools. Currently, there are a few evaluation tools for FAW attacks, but it is still difficult to evaluate the FAW attack protection capability of target mining pools. To address the above problem, this paper proposes a novel evaluation framework for FAW attack protection of the target mining pools in blockchain systems. In this framework, we establish the revenue model for mining pools, including honest consensus revenue, block withholding revenue, successful fork revenue, and consensus cost. We also establish the revenue functions of target mining pools and other mining pools, respectively. In particular, we propose an efficient computing power allocation optimization algorithm (CPAOA) for FAW attacks against multiple target mining pools. We propose a model-solving algorithm based on improved Aquila optimization by improving the selection mechanism in different optimization stages, which can increase the convergence speed of the model solution and help find the optimal solution in computing power allocation. Furthermore, to greatly reduce the possibility of falling into local optimal solutions, we propose a solution update mechanism that combines the idea of scout bees in an artificial bee colony optimization algorithm and the constraint of allocating computing power. The experimental results show that the framework can effectively evaluate the revenue of various mining pools. CPAOA can quickly and accurately allocate the computing power of FAW attacks according to the computing power of the target mining pool. Thus, the proposed evaluation framework can effectively help evaluate the FAW attack protection capability of multiple target mining pools and ensure the security of the blockchain system. Full article

The resolution of complex medical diagnoses using pattern recognition requires an artificial neural network-based expert system to automate autoimmune disease diagnosis in blood samples. This process is done using image-based computer-aided diagnosis (CAD) to reduce errors in the diagnosis process. This paper describes a Multistage Classification Scheme (MSCS), which uses antinuclear antibody (ANA) tests to identify and classify the existence of autoantibodies in the blood serum that bind to antigens found in the nuclei of mammalian cells. The MSCS classified HEp-2 cells into three stages by using Binary Tree (BT), Artificial Neural Network (ANN), and Support Vector Machine (SVM) as basic blocks. The Indirect Immunofluorescence (IIF) technique is used in the ANA test with Human Epithelial type-2 (HEp-2) cells as substrates. The efficiency of the proposed methodology is assessed using the dataset of ICPR 2016. The intermediate cells (IMC) and positive cells (PC) were separated in Stage 1 prior to preprocessing based on their total strength, and special preprocessing is applied to intermediate cells for improved output, and positive cells are subjected to mild preprocessing. The mean class accuracy (MCA) was 84.9% for intermediate cells and 95.8% for positive cells, although the carefully picked 24 features and SVM classifier were applied. ANN showed better performance by adjusting the weights using the SCGBP algorithm. So, the MCA is 88.4% and 97.1% for intermediate and positive cells, respectively. BT had an MCA of 95.3% for intermediate and 98.6% for positive. In Stage 2, the meta learners BT2, ANN2, and SVM2 were trained for an augmented feature set (24 + 3 results from base learners). Therefore, the performance of BT2, ANN2, and SV M2 was increased by 1.8%, 4.5%, and 4.1% as compared to Stage 1. In Stage 3, the final prediction was performed by majority voting among the results of the three meta learners to achieve 99.1% MCA. The proposed algorithm can be embedded into a CAD framework built for the ANA examination. The proposed model will improve operational efficiency, decrease medical expenses, expand accessibility to healthcare, and improve patient safety in the sector, enabling enterprises to lower unplanned downtime, develop new products or services, increase operational effectiveness, and enhance risk management. Full article

Based on the open-source code DualSPHysics, a numerical model was conducted to simulate the regular wave transformation on the slope breakwater with artificial block, and the simulation results were verified according to the measured data from the physical experiment. The deviation between the numerical model and the measured data was less than 6% and 9% in wave run-up and overtopping, respectively, which demonstrated the model can reliably capture the wave evolution on the breakwater with an artificial block. Based on this verified model, the size of the artificial block was adjusted to obtain optimal wave-damping effects. Once obtained, the hydrodynamic characteristics of the optimized new artificial block TB-CUBE were further studied, and the effects of the breakwater slope, water depth in front of the breakwater, incident wave period, and the height on wave run-up were all analyzed. Finally, an empirical formula for wave run-up on this type of article block was suggested through data-fitting, for which the correlation coefficient is 0.981. Full article

In this study, a methodology for automatic recognition of multiple simultaneous types of partial discharges (PDs) in hydro-generator stator windings was proposed. All the seven PD sources typical in rotating machines were considered, and up to three simultaneous sources could be identified. The functionality of identifying samples with no valid PDs was also incorporated using a new technique. The data set was composed of phase-resolved partial discharge (PRPD) patterns obtained from on-line measurements of hydro-generators. From an input PRPD, noise and interference were removed with an improved version of an image-based denoising algorithm previously proposed by the authors. Then, a novel image-based algorithm that separates partially superposed PD clouds was proposed, by decomposing the input pattern into two sub-PRPDs containing discharges of different natures. From the sub-PRPDs, one extracts features quantifying the PD distribution over amplitudes and the contour of PD clouds. Those features are fed as inputs to several artificial neural networks (ANNs), each of which solves a part of the classification problem and acts as a block of a larger system. Once trained, ANNs work collaboratively to identify an unknown sample. Good results were obtained, with overall accuracies ranging from 88% to 94.8% for all the considered PD sources. Full article

The discovery of new carbon allotropes with different building blocks and crystal symmetries has long been of great interest to broad materials science fields. Herein, we report several hundred new carbon allotropes predicted by the state-of-the-art ${\mathrm{RG}}^2$ code and first-principles calculations. The types of new carbon allotropes that were identified in this work span pure ${\mathrm{sp}}^2$, hybrid ${\mathrm{sp}}^2$/${\mathrm{sp}}^3$, and pure sp³ C–C bonding. All structures were globally optimized at the first-principles level. The thermodynamic stability of some selected carbon allotropes was further validated by computing their phonon dispersions. The predicted carbon allotropes possess a broad range of Vickers’ hardness. This wide range of Vickers’ hardness is explained in detail in terms of both atomic descriptors such as density, volume per atom, packing fraction, and local potential energy throughout the unit cell, and global descriptors such as elastic modulus, shear modulus, and bulk modulus, universal anisotropy, Pugh’s ratio, and Poisson’s ratio. For the first time, we found strong correlation between Vickers’ hardness and average local potentials in the unit cell. This work provides deep insight into the identification of novel carbon materials with high Vickers’ hardness for modern applications in which ultrahigh hardness is desired. Moreover, the local potential averaged over the entire unit cell of an atomic structure, an easy-to-evaluate atomic descriptor, could serve as a new atomic descriptor for efficient screening of the mechanical properties of unexplored structures in future high-throughput computing and artificial-intelligence-accelerated materials discovery methods. Full article

To avoid serious diabetic complications, people with type 1 diabetes must keep their blood glucose levels (BGLs) as close to normal as possible. Insulin dosages and carbohydrate consumption are important considerations in managing BGLs. Since the 1960s, models have been developed to forecast blood glucose levels based on the history of BGLs, insulin dosages, carbohydrate intake, and other physiological and lifestyle factors. Such predictions can be used to alert people of impending unsafe BGLs or to control insulin flow in an artificial pancreas. In past work, we have introduced an LSTM-based approach to blood glucose level prediction aimed at “what-if” scenarios, in which people could enter foods they might eat or insulin amounts they might take and then see the effect on future BGLs. In this work, we invert the “what-if” scenario and introduce a similar architecture based on chaining two LSTMs that can be trained to make either insulin or carbohydrate recommendations aimed at reaching a desired BG level in the future. Leveraging a recent state-of-the-art model for time series forecasting, we then derive a novel architecture for the same recommendation task, in which the two LSTM chain is used as a repeating block inside a deep residual architecture. Experimental evaluations using real patient data from the OhioT1DM dataset show that the new integrated architecture compares favorably with the previous LSTM-based approach, substantially outperforming the baselines. The promising results suggest that this novel approach could potentially be of practical use to people with type 1 diabetes for self-management of BGLs. Full article

Affected by high ground stress, the surrounding rock control of a roadway is one of the most important factors restricting the utilization of deep resources. Therefore, it is necessary to propose a method to improve the stress environment of the deep-buried roadway and reduce its deformation. The article focuses on the 121,302 machine roadway in Kouzidong coal mine to analyze the large deformations of roadways near goafs (RNGs) in deep coal mines and reveal the mechanisms related to pressure relief via roof cutting. Through physical simulation, overburdened structures and the migration laws of RNGs in deep coal mines are studied, and the overburdened RNGs will eventually have a double short-arm “F”-type suspended roof structure. The superposition movement of the structure is the prime cause for the large deformation of the RNGs considered here. Artificial roof cutting can weaken the superposition effect of the double “F” structure and induce the roof to produce a new fracture. Meanwhile, sliding deformation along the fault line releases greater stress, and the cut roof can better fill the goaf. The stress distribution ratio between goafs and the coal pillar is improved. Here, a mechanical model of key block B’ (KBB’) is considered and the stability criterion of KBB’ is obtained. According to the theoretical calculation here, the stress of a coal pillar could be reduced by 19.14% when KBB’ is cut along the edge of the coal pillar in the 121,302 machine roadway. After engineering verification, the field observation result shows that the deformation of the 121,302 machine roadway is reduced by more than 50% after roof cutting. Full article