Huge Amount Research Articles

PERFORMANCE OF NATURAL POZZOLAN-BASED GEOPOLYMER REINFORCED WITH BANANA FIBERS

ABSTRACT Türkiye has approximately 50.000 acres of banana plantations. Banana cultivation produces a huge amount of waste that has no commercial value. The main purpose of this study is to investigate the possibilities of using waste banana fiber in natural pozzolan-based geopolymer mortar to increase its ductile fracture behavior. The effects of fiber content and length on physical and mechanical properties were experimentally carried out. The optimum banana fiber content and length were found to be 1.5% and 20 mm, respectively. Above this limit, fibers made it difficult to obtain a workable matrix and generated fiber agglomeration. Although increasing the fiber content from 0.5% to 1.5% and length above 20 mm led to a decrease in the ultrasound pulse velocity, modulus of elasticity and compressive strength due to the higher porosity of the matrix, the increasing ratios of the flexural strength and toughness were consistent. Furthermore, banana fiber-reinforced geopolymer mortars have adequate porosity (22.87%), water absorption ratio (9.25%), swelling thickness (0.58%), saturation coefficient (78%), drying shrinkage (195x10–6), water vapor diffusion resistance index (5.73), flexural strength (6.88 MPa), compressive strength (8.75 MPa), and comply with the performance requirements of the related standards. By considering the adequate physical, mechanical and ductile fracture performance of the material, waste banana fiber can be utilized in the production of geopolymers.

Fake news text detection based on convolutional neural network

The swift evolution of mobile devices and multimedia technology has made the Internet one of the primary means of learning new information today. However, the huge amount of news information is often mixed with erroneous fake news, which can cause bad news events to spread and trigger people's bad emotions, putting the healthy development of society and economy at risk. Addressing the real-world application problem of swiftly and accurately detecting fake news is imperative. To mitigate the aforementioned challenges, we propose a method that uses deep learning to detect fake news and validate it through empirical studies. We begin by collecting a sizeable fake news dataset from domestic social media platforms and use a pre-trained deep learning model to extract textual features. Furthermore, we amalgamate convolutional neural networks and deep learning models to effectively glean and encompass the patterns and attributes of disinformation through an analysis of the text's semantic and structural characteristics. Finally, we experimentally evaluate the effectiveness of the method. The experimental findings demonstrate that the suggested approach exhibits commendable performance in the task of detecting fake news, effectively discerning between authentic and fabricated information. Our deep learning-based approach proves to be both efficient and highly impactful in addressing the issue of fake news within the realm of social media.

Magnetic Shape Memory Nanocomposites Assembled with High Speed High Pressure Torsion.

When a severe plastic deformation (SPD) process is performed at high temperatures, it becomes more versatile. Designed originally for the bulk nanoconstruction of hard-to-deform alloys, high-speed high-pressure torsion (HSHPT) is an SPD method used in this research for assembling multiple layers of shape memory nanocomposites. Three hard-to-deform magnetic alloys in the cast state were used. Soft magnetic shape memory alloys, NiFeGa and FePdMn, and a potentially hard magnetic alloy, CoZr, were assembled in various composites. Both grain refinement and strong layer bonding were achieved in ZrCo/FePdMn and ZrCo/NiFeGa composites in seconds. The very short SPD time is specific to HSHPT because of the intense friction that occurs under high pressures, which generates huge amounts of heat. After SPD, the temperature rises in bulk material like a pulse, being dissipated mostly through heat conduction. The SPD parameters were carefully controlled with an advanced automation system using a programmable logic controller. Nevertheless, the major drawbacks of high-pressure torsion were overcome, and large SPD discs were obtained. Various investigation techniques (optical microscopy, scanning electron microscopy, energy dispersive spectroscopy and atomic force microscopy) show well-defined interfaces as well as a fine and ultrafine structure.

Development of Dual Intake Port Technology in ORC-Based Power Unit Driven by Solar-Assisted Reservoir

The ORC-based micro-cogeneration systems exploiting a solar source to generate electricity and domestic hot water (DHW) simultaneously are a promising solution to reduce CO2 emissions in the residential sector. In recent years, a huge amount of attention was focused on the development of a technological solution allowing improved performance of solar ORC-based systems frequently working under off-design conditions due to the intermittence of the solar source availability and to the variability in domestic hot water demand. The optimization efforts are focused on the improvement of component technology and plant architecture. The expander is retained as the key component of such micro-cogeneration units. Generally, volumetric machines are adopted thanks to their better capability to deal with severe off-design conditions. Among the volumetric expanders, scroll machines are one of the best candidates thanks to their reliability and to their flexibility in managing two-phase working fluid. Their good efficiency adds further interest to place them among the best candidate machines to be considered. Nevertheless, similarly to other volumetric expanders, an additional research effort is needed toward efficiency improvement. The fixed built-in volume ratio, in fact, could produce an unsteady under- or over-expansion during vane filling and emptying, mainly when the operating conditions depart from the designed ones. To overcome this phenomenon, a dual intake port (DIP) technology was also introduced for the scroll expander. Such technology allows widening the angular extension of the intake phase, thus adapting the ratio between the intake and exhaust volume (so called built-in volume ratio) to the operating condition. Moreover, DIP technology allows increasing the permeability of the machine, ensuring a resulting higher mass flow rate for a given pressure difference at the expander side. On the other hand, for a given mass flow rate, the expander intake pressure diminishes with a positive benefit on scroll efficiency. DIP benefits were already proven experimentally and theoretically in previous works by the authors for Sliding Rotary Vane Expanders (SVRE). In the present paper, the impact of the DIP technology was assessed in a solar-assisted ORC-based micro-cogeneration system operating with scroll expanders and being characterized by reduced power (hundreds of W). It was found that the DIP Scroll allows elaboration of a 32% higher mass flow rate for a given pressure difference between intake and expander sides for the application at hand. This leads to an average power increase of 10% and to an improvement of up to 5% of the expander mechanical efficiency. Such results are particularly interesting for micro-cogeneration ORC-based units that are solar-assisted. Indeed, the high variability of hot source and DHW demand makes the operation of the DIP expander at a wide range of operating conditions. The experimental activity conducted confirms the suitability of the DIP expander to exploit as much as possible the thermal power available from a hot source even when at variable temperatures during operation.

Standards for Auctioneers in Vietnam and Alberta (Canada)

Auctioneering as a profession has been in existence for many years. The advantage of selling goods through a public auction compared to a normal willing buyer-willing seller process is that the consignor of the goods is likely to get a better price through a competitive bidding process. A professional consignee known as an auctioneer moderates the competitive bidding process during the sale of goods. However, because of the nature of the business and the frequent huge amounts of money involved in the transactions, there is a need to regulate the auctioneering. Every jurisdiction where auctioneering has specific rules that dictate regulate auctioneer standards. This article looks at the auctioneering standards that have been set and legislated in Alberta (Canada) and Vietnam. The paper has identified the minimum requirements that a prospective auctioneer has to meet in the jurisdictions for them to be given a licence to practice. Also, the paper has identified some regulations that guide the auctioneering process in the said jurisdictions. In the article, the researcher further identified key legal prohibitions that are part of the auctioneering standards.

Feasibility study of a method for tuning wave energy converters

A Wave Energy Converter (WEC) cannot operate efficiently if left alone floating to the mercy of the random sea surface. For a WEC to be efficient, its natural frequency should be close to the peak frequency of the local dominant waves. This paper introduces a method for tuning any natural frequency of a WEC to the peak frequency of a wave spectrum and converting dynamic responses into mechanical power. An innovative lightweight and dual-drag force subsea structure with a huge amount of entrapped seawater can be attached to any vessel using cables. This structure increases the roll mass moment of inertia of a medium size barge, and the mass of a small heaving floater, reducing their natural frequencies. The tension in the cables is converted into mechanical power. The study focuses on the Galápagos Islands, where swells with a typical 13 s peak period and significant wave height between 1 to 3 m dominate the wave climate. For the dynamic systems based on roll and heave responses, annual averages of mechanical power are 178 and 73 kW with efficiencies of 49 and 67% respectively. The method developed in this paper can improve the efficiency of existing and novel WECs.

Wi-AM: Enabling Cross-Domain Gesture Recognition with Commodity Wi-Fi.

RF-based gesture recognition systems outperform computer vision-based systems in terms of user privacy. The integration of Wi-Fi sensing and deep learning has opened new application areas for intelligent multimedia technology. Although promising, existing systems have multiple limitations: (1) they only work well in a fixed domain; (2) when working in a new domain, they require the recollection of a large amount of data. These limitations either lead to a subpar cross-domain performance or require a huge amount of human effort, impeding their widespread adoption in practical scenarios. We propose Wi-AM, a privacy-preserving gesture recognition framework, to address the above limitations. Wi-AM can accurately recognize gestures in a new domain with only one sample. To remove irrelevant disturbances induced by interfering domain factors, we design a multi-domain adversarial scheme to reduce the differences in data distribution between different domains and extract the maximum amount of transferable features related to gestures. Moreover, to quickly adapt to an unseen domain with only a few samples, Wi-AM adopts a meta-learning framework to fine-tune the trained model into a new domain with a one-sample-per-gesture manner while achieving an accurate cross-domain performance. Extensive experiments in a real-world dataset demonstrate that Wi-AM can recognize gestures in an unseen domain with average accuracy of 82.13% and 86.76% for 1 and 3 data samples.

Unlabeled learning algorithms and operations: overview and future trends in defense sector

In the defense sector, artificial intelligence (AI) and machine learning (ML) have been used to analyse and decipher massive volumes of data, namely for target recognition, surveillance, threat detection and cybersecurity, autonomous vehicles and drones guidance, and language translation. However, there are key points that have been identified as barriers or challenges, especially related to data curation. For this reason, and also due to the need for quick response, the defense sector is looking for AI technologies capable of successfully processing and extracting results from huge amounts of unlabelled or very poorly labelled data. This paper presents an in-depth review of AI/ML algorithms for unsupervised or poorly supervised data, and machine learning operations (MLOps) techniques that are suitable for the defense industry. The algorithms are divided according to their nature, meaning that they either focus on techniques, or on applications. Techniques can belong to the supervision spectrum, or focus on explainability. Applications are either focused on text processing or computer vision. MLOps techniques, tools and practices are then discussed, revealing approaches and reporting experiences with the objective of declaring how to make the operationalization of ML integrated systems more efficient. Despite many contributions from several researchers and industry, further efforts are required to construct substantially robust and reliable models and supporting infrastructures for AI systems, which are reliable and suitable for the defense sector. This review brings up-to-date information regarding AI algorithms and MLOps that will be helpful for future research in the field.

OpenEOcubes: an open-source and lightweight R-based RESTful web service for analyzing earth observation data cubes

In recent decades, Earth Observation (EO) systems have seen remarkable technological advancements, leading to a surge in Earth-orbiting satellites capturing EO data. Cloud-based storage solutions have been adopted to manage the increasing data volume. Although numerous EO data management and analysis platforms have emerged to accommodate this growth, many suffer from limitations like closed-source software, leading to platform lock-in and restricted functionalities, restricting the scientific community from conducting open and reproducible research. To tackle these issues, we present OpenEOcubes, a lightweight EO data cubes analysis service that embraces open-source tools, standardized APIs, and containerized deployment, we demonstrate the service’s capabilities in two user scenarios: performing vegetation analysis in Amazonia, Brazil for one year, and detecting changes in a forested area in Brandenburg, Germany based on five years of EO data.OpenEOcubes is an easy-to-deploy service that empowers the scientific community to reproduce small and medium-sized EO scientific analysis while aggregating over a potentially huge amount of data. It enables the extension of functionalities and validation of analysis carried out on different EO data processing platforms.

Improved Performance and Cost Algorithm for Scheduling IoT Tasks in Fog–Cloud Environment Using Gray Wolf Optimization Algorithm

Today, the IoT has become a vital part of our lives because it has entered into the precise details of human life, like smart homes, healthcare, eldercare, vehicles, augmented reality, and industrial robotics. Cloud computing and fog computing give us services to process IoT tasks, and we are seeing a growth in the number of IoT devices every day. This massive increase needs huge amounts of resources to process it, and these vast resources need a lot of power to work because the fog and cloud are based on the term pay-per-use. We make to improve the performance and cost (PC) algorithm to give priority to the high-profit cost and to reduce energy consumption and Makespan; in this paper, we propose the performance and cost–gray wolf optimization (PC-GWO) algorithm, which is the combination of the PCA and GWO algorithms. The results of the trial reveal that the PC-GWO algorithm reduces the average overall energy usage by 12.17%, 11.57%, and 7.19%, and reduces the Makespan by 16.72%, 16.38%, and 14.107%, with the best average resource utilization enhanced by 13.2%, 12.05%, and 10.9% compared with the gray wolf optimization (GWO) algorithm, performance and cost algorithm (PCA), and Particle Swarm Optimization (PSO) algorithm.

Improving the Economic Efficiency of Heat Pump Integration into Distillation Columns of Process Plants Applying Different Pressures of Evaporators and Condensers

The electrification of process industries is one of the main challenges when building a low-carbon society since they consume huge amounts of fossil fuels, generating different emissions. Heat pumps are some of the key players in the industrial sector of the carbon-neutral market. This study proposes an approach to improve the economic feasibility of heat pumps within process plants. Initial energy targeting with grand composite curves was used and supplemented with the detailed design of an evaporator and a compressor for different condensation and evaporation pressures. The trade-off between the capital cost of the heat pump and the electricity cost was investigated, and optimal configurations were selected. This case study investigates the gas fractioning unit of a polymer plant, where three heat pumps are integrated into distillation columns. The results demonstrate that the heat recovery is 174 MW and requires an additional 37.9 MW of electricity to reduce the hot utility by 212 MW. The selection of the evaporation and condensation pressures of heat pumps allows 21.5 M EUR/y to be saved for 7 years of plant operation. The emission-saving potential is estimated at 1.89 ktCO2/y.

Essential Oils from Azorean Cryptomeria japonica Female Cones at Different Developmental Stages: Variations in the Yields and Chemical Compositions

Cryptomeria japonica (Thunb. ex L.f.) D. Don (Cupressaceae) is widely cultivated in the Azores archipelago (Portugal) for landscaping and timber production, generating a huge amount of biomass residues. Among these, female cones (FC) emerge as a source of particularly valuable essential oils (EOs), namely, as promising broad-spectrum antimicrobial agents. However, phytochemical research on C. japonica FC EOs remains scarce. This study evaluated the EO yields and chemical compositions of immature and mature FC (IFC and MFC) from the same batch of Azorean C. japonica. IFC and MFC EOs, obtained via hydrodistillation, presented different yields (0.72% vs. 1.12% w/w, dry weight), and their composition, determined via gas chromatography/mass spectroscopy, revealed that the monoterpenes class was dominant (51.84% vs. 69.13%), followed by the sesquiterpenes (36.44% vs. 26.28%) and diterpenes (10.96% vs. 3.03%) classes. However, the correspondent oxygen-containing terpenes classes were 1.5–2.0 times higher in IFC. Thus, the maturation process revealed an increase in EO yield and α-pinene content (19.5% vs. 41.3%) but a decrease in other important bioactive terpenes/terpenoids (terpinen-4-ol, bornyl acetate, elemol, γ-eudesmol, phyllocladene, and nezukol) content. In conclusion, IFC and MFC EOs, due to their unique composition, may have differential commercial applications and, consequently, contribute to increasing the commercial potential of C. japonica’s EO industry.

Improving Tenebrio molitor Growth and Nutritional Value through Vegetable Waste Supplementation.

Huge amounts of vegetable wastes are generated by the food industry. Their bioconversion into valuable products (e.g., insect flours or biofertilizer) through insect farming is a promising solution to reduce their negative environmental and economic impacts. This study evaluates the growth of Tenebrio molitor larvae and their nutritional profile after supplementing their diets with vegetable wastes. Over a 6-week period, 45-day larvae were fed a diet comprising wheat bran supplemented (1:1) with cucumber or tomato wastes from both conventional and ecological crops. The control diet consisted of wheat bran and an equivalent amount of water to compensate for the waste moisture. Larval weight was measured weekly, and length measures were taken fortnightly. Nutritional composition and fatty acid profile were analyzed at the end of the study in 90-day larvae. Regardless of using vegetable waste from conventional or ecological harvesting, the weight of 6-week supplemented larvae almost doubled that of larvae fed with just wheat bran, and their length was 15% higher. Supplementation also increased larval polyunsaturated fatty acid percentage by 22-37%, with linoleic acid being the most abundant. Likewise, larval protein content reached 50% after supplementation. This study demonstrates that both cucumber and tomato wastes from conventional or ecological crops are excellent supplements for T. molitor's diet, improving their nutritional value and reducing the time necessary for larvae growth.

Leaching Vanadium from the Spent Denitration Catalyst in the Sulfuric Acid/Oxalic Acid Combined Solvent.

Huge amounts of spent denitration catalysts are produced annually as waste from the flue gas denitration process, which will cause resource waste and environmental pollution. It is important to develop an efficient method for the recovery of metals from spent denitration catalysts. In this work, the leaching of vanadium (V) from the spent denitration catalyst by the sulfuric acid/oxalic acid combined solvent was investigated. Factors that influence the leaching rate of V have been studied. Results showed that the optimal leaching rate was 95.65% by 20 wt % sulfuric acid and 0.3 mol·L-1 oxalic acid with a liquid-to-solid ratio of 20 mL·g-1 at 140 °C for 7 h. For further study of the leaching process, the leaching mechanism of V was explored subsequently. Results indicated that sulfuric acid provided a strongly acidic environment, which was beneficial to transformation, complexation, and redox reactions of V in the mixed acid leaching system. Meanwhile, oxalic acid with excellent complexation and reducing-dissolving properties promoted the formation of stable water-soluble VO2+. The "complex effect" generated from the combined acids was greatly favored for leaching V from the spent denitration catalyst.

BIM Data Model Based on Multi-Scale Grids in Civil Engineering Buildings

The construction of digital twin cities is a current research hotspot; GIS technology and BIM technology are widely used in the field of digital twin cities. However, BIM is still subject to major limitations in its applications, mainly due to huge amounts of model data, low query efficiency and accuracy, non-uniform marking systems, etc. The reason is that the BIM model itself focuses more on the expression of visual effects and lacks spatial calculation ability and the utilization of spatial location information. Secondly, the current lightweight processing methods for BIM models are mostly based on geometric transformation and rendering optimization, focusing more on the data compression and visual quality of the model, which essentially does not change the data structure of the BIM model, and it is difficult to establish the mapping relationship between spatial location and spatial data, information, and resources. In addition, current coding methods proposed for BIM models are mostly based on the line classification method, which realizes the identification of components based on the classification of their attributes, and the location information is stored according to the attributes or natural language descriptions, which need to be parsed and translated when they are used, and this procedure ignores the importance of spatial location in daily management and emergency management. The importance of spatial location in daily management and emergency management is also ignored. Based on this kind of identification code, it is impossible to directly analyze and apply spatial location data. Therefore, this paper takes the combination of GIS technology and BIM technology as the starting point and proposes a BIM data modeling method based on the BeiDou grid code, based on the efficiency of its underlying data organization and the accuracy of its real geographic location expression on the one hand and the completeness of the information expression by BIM and fine three-dimensional visualization on the other hand. Finally, a series of experiments are carried out based on the method. Through visualization modeling and efficiency experiments, different feature models are meshed to verify the feasibility and efficiency of the model. Through coding and information query experiments, the model′s data organization capability, data dynamic carrying capability, and efficient spatial computation capability and practical application capability are verified.

Characterization of Thermostable Cellulase Enzyme Isolated from a Hot Spring Bacterium: Bacillus sp.

Cellulase is a complex of enzymes which consists of β-1,4-endoglucanase, cellobiohydrolase, and β-glucosidase. Cellulase contributes a significant share to the world enzyme market and is used in number of industries viz; paper and pulp, food and beverage, bioethanol, detergent and textile. The harsh industrial conditions such as high temperature, extreme pH levels and high substrate concentration etc. which is used in such industries adversely effect on structure and activity of enzymes. Therefore, huge amount of chemical catalysts which cause chemical wastes are used in industrial settings instead of enzymes. Since the chemical wastes adversely affect the ecosystem, isolation and characterization of thermostable cellulase enzyme-producing bacteria and exploring the industrial perspective of thermostable enzymes is a better approach towards green chemistry. The present study focused on characterization of cellulase enzyme produced by Bacillus sp., which shows optimum activity at 60 C under neutral conditions, isolated from Gomarankadavala hot spring in Sri Lanka. The effect of different Carbon sources: glucose and lactose, Nitrogen sources: peptone, tryptone, yeast extract and urea on enzyme production and different Carboxymethylcellulose (CMC) concentrations; 0.5%, 1.5% and 2%, on enzyme activity were measured using the DNS method. Under the optimum conditions, cellulase enzyme activity on different substrates: corn cob, rice bran and raw leaves were measured. The highest enzyme production was recorded in the culture medium which added tryptone as the nitrogen source and adding carbon sources to the culture medium showed an increase of cellulase enzyme production. The optimum CMC concentration for the enzyme activity was recorded as 1% and from all the optimized parameters, the substrate; raw leaves showed the highest enzyme activity of 11.305 U/ml. Further, a considerable amount of enzyme activity was recorded on corn cobs and rice bran as well. Thus, the thermostable cellulase enzyme produced by bacterium identified as Bacillus cereus isolated from Gomarankadavala hot spring could be successfully used in industrial settings such as kitchen/industrial waste management, bioethanol production, paper and pulp industry and textile industry which use high temperatures and cellulosic substrates as raw materials. 
 Keywords: Thermostable enzymes, Cellulase, Industrial applications, Hot springs

Exploring a new criterion to determine the onset of cavitation in centrifugal pumps from energy-saving standpoint; experimental and numerical investigation

This paper proposes a new criterion to determine the cavitation initiation in centrifugal pumps. Because of the importance of saving energy, and the need for specifying a margin for the required net positive suction head (NPSHr) in all centrifugal pumps, a new criterion based on dropping three percent in efficiency (NPSHr,η) was investigated. Extensive experimental and numerical studies were undertaken to assess the effectiveness of the novel criterion from the energy-saving standpoint and its margin compared to the conventional one (NPSHr,Ht). A test bench was employed to conduct numerous experiments on five single-stage centrifugal pumps, generating comprehensive head-drop and efficiency-drop curves under part-load, designed, and over-load conditions. Additionally, simulations were carried out using CFD, employing an appropriate turbulence model and the ZGB cavitation model. Subsequently, dropping curves of total head, hydraulic efficiency, and the torque-rise curve against available NPSH were extracted. Analysis of these simulations revealed that NPSHr,η is consistently higher than NPSHr,Ht. A three-percent total head-drop diminishes the efficiency by an average of 6.04%, ranging from 4.79% to 8.92% depending on the specific case. Using NPSHr,η provides enough distance from the NPSHr,Ht without any need to specify a margin, and a huge amount of energy can be saved annually.

Strategic supplier selection and order allocation for sustainable development of small and medium-sized enterprises: insights from a case study

Purpose Efforts to implement supplier selection and order allocation (SSOA) approaches in small and medium-sized enterprises (SMEs) are quite restricted due to the lack of affordable and simple-to-use strategies. Although there is a huge amount of literature on SSOA techniques, very few studies have attempted to address the issues faced by SMEs and develop strategies from their point of view. The purpose of this study is to provide an effective, practical, and time-tested integrated SSOA framework for evaluating the performance of suppliers and allocating orders to them that can improve the efficiency and competitiveness of SMEs. Design/methodology/approach This study was conducted in two stages. First, an integrated supplier selection approach was designed, which consists of the analytic hierarchy process and newly developed measurement alternatives and ranking using compromise solution to evaluate supplier performance and rank them. Second, the Wagner-Whitin algorithm is used to determine optimal order quantities and optimize inventory carrying and ordering costs. The joint impact of quantity discounts is also evaluated at the end. Findings Insights derived from the case study proved that the proposed approach is capable of assisting purchase managers in the SSOA decision-making process. In addition, this case study resulted in 10.89% total cost savings and fewer stock-out situations. Research limitations/implications Criteria selected in this study are based on the advice of the managers in the selected manufacturing organizations. So the methods applied are limited to manufacturing SMEs. There were some aspects of the supplier selection process that this study could not explore. The development of an effective, reliable supplier selection procedure is a continuous process and it is indeed certainly possible that there are other aspects of supplier selection that are more crucial but are not considered in the proposed approach. Practical implications Purchase managers working in SMEs will be the primary beneficiaries of the developed approach. The suggested integrated approach can make a strategic difference in the working of SMEs. Originality/value A practical SSOA framework is developed for professionals working in SMEs. This approach will help SMEs to manage their operations effectively.

T2FM: A novel hashtable based type-2 fuzzy frequent itemsets mining

Association rule mining (ARM) is an important research issue in the field of data mining that aims to find relations among different items in binary databases. The conventional ARM algorithms consider the frequency of the items in binary databases, which is not sufficient for real time applications. In this paper, a novel hash table based Type-2 fuzzy mining algorithm (T2FM) with an efficient pruning strategy is presented for discovering multiple fuzzy frequent itemsets from quantitative databases. The algorithm employs a hash table based structure for efficient storage and retrieval of item/itemset which reduces the search efficiency to O(1) or constant time. Previously, type-2 based Apriori and FP-growth based fuzzy frequent itemsets mining were proposed, which required large amounts of computation and a greater number of candidate generation and processing. Meanwhile, the proposed approach reduces a huge amount of computation by finding the common keys before the actual intersection operation takes place. An efficient pruning strategy is proposed to avoid unpromising candidates in order to speed up the computations. Several experiments are carried out to verify the efficiency of the approach in terms of runtime and memory for different minimum support threshold and the results show that the designed approach provides better performance compared to the state-of-the-art algorithms.

INCAD: 2D VECTOR DRAWINGS CREATION USING INSTANCE SEGMENTATION

Abstract. Orthoimages are a common product used as a base in CAD software for vectorization purposes. In fact, vectorization of orthoimages constitutes a tedious and labour-intensive process which should be supervised by experts e.g. architects, chemical engineers etc. On the one hand, deep learning algorithms are used extensively nowadays achieving high quality results. On the other hand, deep learning algorithms require a huge amount of manually annotated data to be trained on, which is a very difficult process especially at pixel level applications like semantic segmentation and instance segmentation. However, the transformation of 2D CAD drawings into a suitable deep learning dataset (CAD2DLD) is underexplored ignoring a large source of data, created by experts. In this effort, the InCAD algorithm is proposed, which aims to automatically create 2D vector drawings using the YOLOv8 instance segmentation algorithm which was trained on CAD2DLD data. Additionally, a methodology for transforming 2D CAD drawings into a suitable deep learning dataset for instance segmentation, is presented. Finally, the proposed workflow is evaluated on the creation of 2D vector drawings of stones of a fortification wall achieving promising results (78.34 mIoU).