Sādhanā最新文献

{"title":"DeepEPhishNet: a deep learning framework for email phishing detection using word embedding algorithms","authors":"M Somesha, Alwyn Roshan Pais","doi":"10.1007/s12046-024-02538-4","DOIUrl":"https://doi.org/10.1007/s12046-024-02538-4","url":null,"abstract":"<p>Email phishing is a social engineering scheme that uses spoofed emails intended to trick the user into disclosing legitimate business and personal credentials. Many phishing email detection techniques exist based on machine learning, deep learning, and word embedding. In this paper, we propose a new technique for the detection of phishing emails using word embedding (Word2Vec, FastText, and TF-IDF) and deep learning techniques (DNN and BiLSTM network). Our proposed technique makes use of only four header based (From, Returnpath, Subject, Message-ID) features of the emails for the email classification. We applied several word embeddings for the evaluation of our models. From the experimental evaluation, we observed that the DNN model with FastText-SkipGram achieved an accuracy of 99.52% and BiLSTM model with FastText-SkipGram achieved an accuracy of 99.42%. Among these two techniques, DNN outperformed BiLSTM using the same word embedding (FastText-SkipGram) techniques with an accuracy of 99.52%.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"21 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141585934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learning compositional capsule networks","authors":"Sai Raam Venkataraman, S Balasubramanian, Ankit Anand, R Raghunatha Sarma","doi":"10.1007/s12046-024-02552-6","DOIUrl":"https://doi.org/10.1007/s12046-024-02552-6","url":null,"abstract":"<p>Objects in the visual field are perceived to have an inherent structure that is seen in the way that they are constructed from their components. For example, a face requires its parts to be arranged in a certain spatial configuration. This property, of having such a structure, is termed as compositionality. For deep neural networks to preserve these structures of their inputs in their representations, the capsule network model was proposed. However, there is no empirical evidence to confirm if capsule networks do indeed learn compositional representations. Here, we propose a novel task for the experimental analysis of this property. This task, termed MeasureComp, tests the unsupervised learning of unannotated part-whole structures in a classification setting. Our results show that capsule networks that use dynamic routing are unable to learn pose-aware representations. In an effort to improve upon this, and as an initial direction towards compositional capsule models, we propose a novel compositional loss-function termed EntrLoss. Experimental results on MeasureComp show that the use of this loss function improves the compositionality of capsule networks. Further, we also present a simple capsule network model that uses our EntrLoss and outperforms several other recent capsule networks. The code for our paper is available at https://github.com/codesubmissionforpaper/entropy_regularised_capsule.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"54 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141588411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization of louver fin geometries for miniature microchannel condenser by Taguchi and CFD method","authors":"S Satheesh Kumar, G Kumaraguruparan, T S Senthilkumar","doi":"10.1007/s12046-024-02558-0","DOIUrl":"https://doi.org/10.1007/s12046-024-02558-0","url":null,"abstract":"<p>In this work, optimization of louver fin geometries is performed to obtain better thermal hydraulic performance of multilouvered microchannel heat exchanger by CFD method. Five louver fin geometries are considered in this work namely fin pitch, fin height, louver pitch, louver angle and louver length. The air side performance is analyzed with the help of airside heat transfer coefficient and pressure drop. These parameters are determined using Colburn-j factor and f factor for Reynolds numbers range of 100–600. In this work, two factors are studied for the effect of individual and combined louver fin geometries. It is observed from the literature study that increase in Reynold number, increases the Colburn-j factor and hence increases the rate of heat transfer favorably. At the same time, increase in Reynold number, increase f factor in term increase the pressure drop which is not desirable. Hence, it is challenging to increase the heat transfer without increase the pressure drop characteristics for heat exchanger design. So, aim of this work is to maximize the heat transfer and minimize the pressure drop. To account for these two contradicting objectives, dimensionless number (JF factor) is considered to determine the thermal hydraulic performance for the heat exchanger and it accounts both Colburn-j factor and f factor simultaneously. Orthogonal array-based Taguchi analysis is performed to obtain optimized louver fin geometries. Taguchi-CFD analysis revealed that fin pitch is the most influencing parameter, that alone accounts for 94.33% of contribution ratio on JF factor. Taguchi-confirmation test showed that the enhancement of JF factor for optimal louver fin is 5.97% higher than that of the initial design parameter. Finally, CFD analysis is performed to compare the performance of optimal louver fin geometry with that of the default louver fin geometry. From this analysis, Colburn-j and JF factor of optimum fin geometry are found to be 24.42% and 18.23% higher than those of default fin geometry. Regression models are developed for optimum fin geometry to predict the Colburn-j, f and JF factor for the Reynolds numbers range of 100–850, whose adj. R² value is 99.05%.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141585937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Monitoring the sulphur-oxidizing bacterial effect of sandstone using the EMI technique","authors":"Kushlendra Lal Kharwar, Anupam Rawat","doi":"10.1007/s12046-024-02546-4","DOIUrl":"https://doi.org/10.1007/s12046-024-02546-4","url":null,"abstract":"<p>Since the dawn of civilization, sandstone has been a fantastic building material. Numerous causes have been observed in the past for sandstone damage or deterioration, one of which is sulphur-oxidizing bacteria (SOB) and cyanobacteria. In general, SOB is present in the soil, air, water, humidity, and human activity. The oxidation of sulphur compounds, such as hydrogen sulphide, thiosulphate, or elements of sulphur, provides energy for SOB. These microorganisms contribute to the decay of buildings materials, especially those made of stone, metal, or concrete. The sulphur oxidizing process affects the mechanical properties of sandstone. Mechanical properties are related to strength. Losses of mechanical properties may be the reason for deflection, cracking, collapse, and catastrophic failure of sandstone. Monitoring and evaluation gives an idea about the behavior of structure and the prevention of catastrophic failure. This research paper contains the application of electromechanical impedance with surface bonded Piezoelectric Lead Zirconate Titanate. The sandstone samples and soil samples have been collected from the historical site. Two sets of cylindrical types of sandstone specimens have been used in experimental work. The conductance signature and susceptance signature have been measured every six months. The variation and shifting of the signature curve have been used to identify the structural behavioral change. Statistical methods like the root mean square deviation have been used for the quantification of damage. An equitation has been generated on the basis of the percentage root mean square deviation to quantify the prediction of damages.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"28 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141585935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An efficient computational model for unequal-area dynamic facility layout problems considering input/output locations under algorithms case","authors":"Seyed Bardia Seyedi, Mahdi Yousefi Nejad Attari, Vahid Abbasgholi Pour Ghadim, Ali Ala","doi":"10.1007/s12046-024-02550-8","DOIUrl":"https://doi.org/10.1007/s12046-024-02550-8","url":null,"abstract":"<p>Recently, the adaptability of production systems is crucial for various facilities or departments, focusing on minimizing the cost associated with material flow in facility layout problems. To address these challenges, an examination of dynamic problems becomes imperative. This paper presents a mathematical model designed explicitly for dynamic facility layout problems (DFLP) characterized by fixed shapes and unequal areas. The model incorporates input and output points, allowing flexibility in their placement within facilities, and treats material handling system input/output (I/O) points as decision variables. The proposed approach utilizes an Improved Particle Swarm Optimization algorithm (IPSO) and an Improved Genetic Algorithm (IGA) to solve the resulting mixed integer nonlinear programming (MINLP) model. Both a theoretical problem and a real-world case are employed to assess the effectiveness of the suggested algorithms. The outcomes demonstrate that the proposed algorithm outperforms the compared algorithms in identifying optimal solutions.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141567197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An approach to characterize cyclic deflection of piles in cohesion less soil media under 1-way and 2-way cyclic loading on sloping ground","authors":"Kiran Rathod, R Siddhardha, Teja Munaga, Kalyan Kumar Gonavaram","doi":"10.1007/s12046-024-02555-3","DOIUrl":"https://doi.org/10.1007/s12046-024-02555-3","url":null,"abstract":"<p>In general, pile foundations are utilized to support structures like tall buildings, bridges, and transmission towers, which are frequently subjected to lateral stresses initiated by wind, action of waves, earthquakes, or traffic loads. Several high-rise structures, highway and railroad overpasses, as well as transmission towers, are constructed near slopes and rely on pile foundations for support. Due to the effects of wind and waves, pile foundations are continuously subjected to cyclic loads. For piles supporting tall buildings, transmission towers, offshore structures, or infrastructure in seismic zones, 1-way or 2-way cyclic lateral loads are commonly applied. Therefore, while designing pile foundations, it is essential to understand how piles behave laterally when they are located near a sloping crest. One of the primary challenges in ensuring the efficient functioning of the superstructure is analyzing how the soil and foundations respond when exposed to long-term lateral loads, such as wind, over an extended period on the piles of offshore platforms. Because of the presence of slope, the pile’s lateral load capacity decreased due to the reduced ability of the soil to provide passive resistance. This paper presents small-scale 1-g model tests conducted on the sand to assess the loss of pile’s lateral capacity when subjected to 100 cycles under 1 and 2-way cyclic loading. The Relative Density (60%) and varying slopes (Horizontal ground, 1V:3H) with varying spacing (5D and 7D) and aspect ratios (L/D) of 25 and 40 were implemented in this study. Cyclic lateral load tests were performed for sloping as well as horizontal ground. A major reduction in lateral capacity, exceeding 60%, was observed due to the application of cyclic loading. Moreover, the transition from horizontal ground (HG) to sloping ground (SG) decreased the maximum bending moment by 25–40%. This study exemplifies the piles’ behaviour when subjected to cyclic lateral loading while resting on a sloping crest, which represents a critical scenario in pile foundation design.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141567368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Investigation of the effect of sintering process parameters on the corrosion, wear and hardness of W–Cu composite","authors":"Ehsan Selahshorrad, Seyyed Amirhossein Alavi, Karim Zangeneh-Madar, Mohammad Reza Samadi, Morteza Yazdanshenas, Mahmoud Afshari","doi":"10.1007/s12046-024-02559-z","DOIUrl":"https://doi.org/10.1007/s12046-024-02559-z","url":null,"abstract":"<p>In this study, tungsten–copper (W–Cu) composite was fabricated using the sintering process to examine the corrosion, wear and hardness of the fabricated samples at three different temperatures of 1050, 1150 and 1300 °C. The potentiodynamic polarization behavior of the composite samples was evaluated in 3.5% NaCl solution containing different benzotriazole inhibitors. Finally, the microstructure of the W–Cu composite was examined by SEM, TEM, XRD and EDS analyses. The XRD results on the milled samples showed that the optimal conditions were obtained with a ball to powder ratio of 16:1 and a milling time of 15 h, so that the crystals with a size of 16.76 nm were obtained. Also, the highest hardness (185 HV) and relative density (97.34%) were obtained in the samples sintered at 1300 °C. With increasing the wear force, the work hardening increased in the mechanically mixed layer, which led to a rise in the wear rate and a decrease in the friction coefficient. The corrosion behavior of the composite indicated that by addition of 200 ppm inhibitor in the corrosion solution, the corrosion current density decreased from 3.73 to 0.59 μA/cm² and the corrosion potential improved from − 630.46 to − 336.28 mV_SCE.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141546528","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Estimation of water quality index using modern-day machine learning algorithms","authors":"Piyush Gupta, Pijush Samui, A. R. Quaff","doi":"10.1007/s12046-024-02545-5","DOIUrl":"https://doi.org/10.1007/s12046-024-02545-5","url":null,"abstract":"<p>Many human-made activities currently pollute groundwater supplies, with mining operations playing a substantial role in this degradation. In this study, water quality index (WQI) was calculated and forecasted for groundwater in gold mining sites of Kolar Gold Fields, Karnataka, using several water quality criteria and modern-day soft computing approaches. Specifically, three sophisticated deep learning models: convolution neural network (CNN), deep neural network (DNN), and recurrent neural network were used to estimate the WQI using various water quality metrics. The outcomes of these models were also compared with three widely used soft computing models namely support vector machine (SVM), least-square support vector machine (LS-SVM), and artificial neural network. Experimental results reveals that the developed CNN model outperform other two models with R² values of 0.9998 and 0.9996 in the training and testing phases, respectively. The RMSE values of the CNN model were determined to be 0.0034 and 0.0038 in the training and testing phases, respectively. As per the results, the developed CNN model can be used as alternate tool for rapid water quality monitoring.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"177 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141506730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A low-complexity transceiver scheme for joint DFT pre-coded DWT SC-FDMA NOMA system under dissimilar power allocation strategies","authors":"M Subha, D Judson","doi":"10.1007/s12046-024-02548-2","DOIUrl":"https://doi.org/10.1007/s12046-024-02548-2","url":null,"abstract":"<p>The competence of Non-Orthogonal Multiple Access (NOMA) to provide improved spectrum efficiency, support massive network elements, and low latency services make it attractive to Multiple Access (MA) technology for next-generation wireless networks. Single-Carrier Frequency Division Multiple Access (SC-FDMA) is an optimal technique in 4G wireless communication to enhance spectrum efficiency and user capacity. The amalgamation of SC-FDMA with NOMA can become a better choice for wireless communication for 5G and Beyond 5G (B5G). Discrete Wavelet Transforms (DWT) have been a better choice for improving the system's performance due to its outstanding orthogonality and spectral confinement characteristics. This study proposes a transceiver architecture that uses joint Discrete Fourier Transform (DFT) and DWT to outperform existing NOMA systems in terms of Bit Error Rate (BER). The transceiver architecture is symbolized as a joint DFT precoded DWT (JDPD) SC-FDMA NOMA System. Furthermore, we propose a Joint Low Complexity Regularized Zero forcing (JLC RZF) for JDPD SC-FDMA NOMA system to enhance the BER with low complexity. In order to illustrate the superiority of the proposed system over multipath channels, the system performance over a range of Carrier Frequency Offset (CFO) values and power allocation scenarios are also examined.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141506727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Additive fault diagnosis techniques in rotor systems: a state-of-the-art review","authors":"Prabhat Kumar, Rajiv Tiwari","doi":"10.1007/s12046-024-02543-7","DOIUrl":"https://doi.org/10.1007/s12046-024-02543-7","url":null,"abstract":"<p>Faults in rotating systems can cause significant damage to the machinery and can result in downtime and production losses. Hence, the timely detection and diagnosis of faults are very important for the smooth running of machines and the assurance of their safety and reliability. In view of this, a review of the literature has been presented in the article on the types of additive faults and their identification using conventional signal-based techniques and automated artificial intelligence techniques. Through a literature survey, the faulty rigid and flexible rotor systems mounted on rolling element bearings, hydrodynamic bearings, and active magnetic bearings have been studied. The faults incorporated in this article are the additive fault types, in which the process is affected by adding process variables. The rotor unbalances, shaft or bearing misalignment, crack, internal damping, bow in the shaft, rotor-to-stator rub, and mechanical looseness are the classifications of additive faults. Additionally, understanding the rotor response through theoretical and experimental investigations influenced by the additive faults and its detection and diagnosis using vibration and current-induced signals is extremely important, and therefore the present paper briefly discusses this. Following the state of the art in the dynamic analysis and identification of multiple hazardous faults, the general remarks and future directions for further research have been suggested at the end of this article.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"187 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141506729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}