Sādhanā最新文献

{"title":"Filter based saturated controller design for a class of nonlinear singularly perturbed systems","authors":"Dipak Prasad, S. K. Valluru, M. M. Rayguru","doi":"10.1007/s12046-024-02526-8","DOIUrl":"https://doi.org/10.1007/s12046-024-02526-8","url":null,"abstract":"","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"78 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141114024","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":"Design of PSO controller for real-time non-reversible operation of PMBLDC motor drive system in hot steel rough rolling applications","authors":"N. Mohanraj, R. Balasubramanian, K. Parkavikathirvelu, R. Sankaran, R. Amirtharajan","doi":"10.1007/s12046-024-02533-9","DOIUrl":"https://doi.org/10.1007/s12046-024-02533-9","url":null,"abstract":"","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"126 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141115229","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":"Initial decoding with minimally augmented language model for improved lattice rescoring in low resource ASR","authors":"Savitha Murthy, Dinkar Sitaram","doi":"10.1007/s12046-024-02520-0","DOIUrl":"https://doi.org/10.1007/s12046-024-02520-0","url":null,"abstract":"<p>Automatic speech recognition systems for low-resource languages typically have smaller corpora on which the language model is trained. Decoding with such a language model leads to a high word error rate due to the large number of out-of-vocabulary words in the test data. Larger language models can be used to rescore the lattices generated from initial decoding. This approach, however, gives only a marginal improvement. Decoding with a larger augmented language model, though helpful, is memory intensive and not feasible for low resource system setup. The objective of our research is to perform initial decoding with a minimally augmented language model. The lattices thus generated are then rescored with a larger language model. We thus obtain a significant reduction in error for low-resource Indic languages, namely, Kannada and Telugu. This paper addresses the problem of improving speech recognition accuracy with lattice rescoring in low-resource languages where the baseline language model is not sufficient for generating inclusive lattices. We minimally augment the baseline language model with unigram counts of words that are present in a larger text corpus of the target language but absent in the baseline. The lattices generated after decoding with a minimally augmented baseline language model are more comprehensive for rescoring. We obtain 21.8% (for Telugu) and 41.8% (for Kannada) relative word error reduction with our proposed method. This reduction in word error rate is comparable to 21.5% (for Telugu) and 45.9% (for Kannada) relative word error reduction obtained by decoding with full Wikipedia text augmented language mode while our approach consumes only 1/8th the memory. We demonstrate that our method is comparable with various text selection-based language model augmentation and also consistent for data sets of different sizes. Our approach is applicable for training speech recognition systems under low resource conditions where speech data and compute resources are insufficient, while there is a large text corpus that is available in the target language. Our research involves addressing the issue of out-of-vocabulary words of the baseline in general and does not focus on resolving the absence of named entities. Our proposed method is simple and yet computationally less expensive.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"58 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141149814","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":"Design of optimal controller for static compensator via Hamiltonian formalism for the multimachine system","authors":"A. Halder, Nitai Pal, Debasish Mondal","doi":"10.1007/s12046-024-02462-7","DOIUrl":"https://doi.org/10.1007/s12046-024-02462-7","url":null,"abstract":"","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"90 15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141122736","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":"Enhanced security for IoT networks: a hybrid optimized learning model for intrusion classification","authors":"S Rajarajan, M G Kavitha","doi":"10.1007/s12046-024-02535-7","DOIUrl":"https://doi.org/10.1007/s12046-024-02535-7","url":null,"abstract":"<p>The Internet of Things (IoT) features multiple device connectivity and breaks the conventional network connectivity limitations like limited wireless range, scalability specific communication protocol dependency, etc. Multiple devices can be connected in an IoT network without significant infrastructure changes and the devices can communicate with each other through variety of protocols, which could be more beneficial in many organizations, consumers, and governments. However, the rapid development of IoT technology requires a secure network as it must access different devices and communication methods. This diversity and heterogeneity make network intrusions more convenient for intruders. IoT network complexity and security flaws increase when a large volume of data is transferred through a network. Intrusion detection systems (IDS) are used to monitor the network behavior for detecting unusual behaviors or intrusions. Numerous machine learning models are used in IDS for classifying network traffic. However, these methods lag in detection performances due to limited feature handling abilities. Thus, in selecting optimal features that correctly indicate the intrusions in the network, optimization models are used in IDSs. However, due to the limited exploration and exploitation ability of conventional optimization algorithms, this research presents a hybrid optimization algorithm using Salp Swarm Optimization and Bee Foraging (SSA-BF) optimization approaches for optimal feature selection. The optimal features are classified using a multiplicative Long Short-Term Memory (MLSTM) network. To check the robustness of the proposed IDS, accuracy, recall, f1-score, and precision metrics are considered for analysis. Simulation results of the proposed IDS exhibited a maximum accuracy of 95.8%, better than conventional Auto Encoder, Convolutional Neural Network, Gaussian mixture model with Generative adversarial Network, Multi-CNN, and DeepNet-based IDSs.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"2012 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141064199","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":"Inpainting non-anatomical objects in brain imaging using enhanced deep convolutional autoencoder network","authors":"Puranam Revanth Kumar, B Shilpa, Rajesh Kumar Jha, B Deevena Raju, Thayyaba Khatoon Mohammed","doi":"10.1007/s12046-024-02536-6","DOIUrl":"https://doi.org/10.1007/s12046-024-02536-6","url":null,"abstract":"<p>Medical diagnosis can be severely hindered by distorted medical images, especially in the analysis of Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) images. Therefore, enhancing the accuracy of diagnostic imaging and inpainting damaged areas are essential for medical diagnosis. Over the past decade, image inpainting techniques have advanced due to deep learning and multimedia information. In this paper, we proposed a deep convolutional autoencoder network with improved parameters as a robust method for inpainting non-anatomical objects in MRI and CT images. Traditional approaches based on the exemplar methods are much less effective than deep learning methods in capturing high-level features. However, the inpainted regions would appear blurr and with global inconsistency. To handle the fuzzy problem, we enhanced the network model by introducing skip connections between mirrored layers in the encoder and decoder stacks. This allowed the generative process of the inpainting region to directly use the low-level feature information of the processed image. To provide both pixel-accurate and local-global contents consistency, the proposed model is trained with a combination of the typical pixel-wise reconstruction loss and two adversarial losses, which makes the inpainted output seem more realistic and consistent with its surrounding contexts. As a result, the proposed approach is much faster than existing methods while providing unprecedented qualitative and quantitative evaluation with a high inpainting inception score of 10.58, peak signal-to-noise ratio (PSNR) 52.44, structural similarity index (SSIM) 0.95, universal image quality index (UQI) 0.96, and mean squared error (MSE) 40.73 for CT and MRI images. This offers a promising avenue for enhancing image fidelity, potentially advancing clinical decision-making and patient care in neuroimaging practice.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"22 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141062703","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":"Enhancing quality of services using genetic quantum behaved particle swarm optimization for location dependent services","authors":"C Chaubey, R Khare","doi":"10.1007/s12046-024-02518-8","DOIUrl":"https://doi.org/10.1007/s12046-024-02518-8","url":null,"abstract":"<p>Location Dependent Service (LDS) is a kind of information service that are accessed via mobile devices such as smart phones and other hand held devices that offers the detection of people and object positions. When information gets transmitted from the service provider to the customer, some propagation delay is experienced owing to the quality parameters like bandwidth, jitter, etc. and also there is another challenge corresponding to the location of mobile users that is required to be captured at regular interval. At times, the server handling the location service request has huge overhead with the increase in the number of users. Therefore, it gives rise to a complicated and critical challenge for the correctly performing the task of locating with accuracy and to offer the service demanded in time with no time delay and data. In order to surpass the above challenge, the work proposed a Genetic Quantum Behaved Particle Swarm Optimization (GQPSO) for location based services in medical application. The designed system is used for improving the quality of services (QoS) in LDS that contains three portions namely User, Server, and Wireless Communication. Wireless communication links the user and servers and the server gets the query through the user which is its only responsibility. In the server, the query processing is performed and the server transfers the services over optimal path that is chosen with the help of GQPSO algorithm on the basis of QoS metrics like PDR, E2E Delay, Jitter, throughput and energy. By employing LDSs, the patients can get the neighborhood hospital locations in medical application.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"136 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140936154","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":"Tribo-metallurgical behaviour of high Zn content Al-Zn-Mg-Cu alloy in different homogenization conditions","authors":"Rahul Samanta, Amitava Ghatak","doi":"10.1007/s12046-024-02512-0","DOIUrl":"https://doi.org/10.1007/s12046-024-02512-0","url":null,"abstract":"<p>A significant constraint of aluminum alloys in aircraft and automobile industrial applications is their poor mechanical properties as well as low tribological behavior. In the present study, the correlation between microstructure, hardness, and wear behavior of high Zn (10 wt.%) alloys containing Al-Zn-Mg-Cu was studied. Homogenization treatment at 450°C in the range of 0 to 40 h, followed by an aging process at 120°C/24 h, was applied to the alloy samples. The results show that the alloy homogenized for 16 h exhibits peak hardness due to the presence of precipitates at the grain boundary region as well as in the matrix, which act as intense points for pinning in the Al-matrix to slow the dislocation movement. The wear behavior of the alloy was investigated by a dry sliding wear test. Worn surfaces were investigated to identify the wear mechanism. Archard’s and Fleischer’s wear models were analyzed to correlate with the wear test results of the alloy during homogenization time.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"46 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140941852","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 study on periodic deteriorating linguistic fuzzy inventory model with natural idle time and imprecise demand using GSA","authors":"Sanchita Mahato, Anup Khan, Sujit Kumar De","doi":"10.1007/s12046-024-02523-x","DOIUrl":"https://doi.org/10.1007/s12046-024-02523-x","url":null,"abstract":"<p>The modern global economy is becoming more challenging and it is hardly possible to minimize the inventory cost for inventory practitioners in the coming days. Basically, most of the enterprises deal with deteriorating items having flexible demand rate and follow natural idle time in the entire inventory process. Moreover, traditionally most of the research articles have been made under non-stop time frame, but in reality, in a day–night scenario there exists a natural idle time and hence the time consumed for inventory run time may be viewed as single shift or periodic model. Here we formulate an economic order quantity (EOQ) inventory model considering natural idle time and deterioration under some constraints and minimize the average inventory cost. Then, the model is converted into an equivalent fuzzy model, taking the demand and all the cost parameters as linguistic polynomial fuzzy set (LPFS). To defuzzify the model, we have adopted indexing method as well as <span>(alpha )</span>-cut method. To validate the novelty, numerical experimentations have also been analyzed with the help of metaheuristic and evolutionary algorithms like goat search algorithm (GSA) and particle swarm optimization (PSO). Comparative analysis reveals that GSA approach can give finer optimum (− 10 % cost reduction) than other approaches. The main findings of this research give a new technique of (linguistic term) fuzzification–defuzzification of the proposed model and a new solution procedure to optimize the periodic deteriorating inventory model under GSA. To justify this model, sensitivity analysis and graphical illustration have been done. Scopes of future work have been discussed for further improvement of research on optimization problems using metaheuristic algorithms.</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"17 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140936159","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":"VLSI architecture of stochastic genetic algorithm for real time training of deep neural network","authors":"Anirban Chakraborty, Sayantan Dutta, Indrajit Chakrabarti, Ayan Banerjee","doi":"10.1007/s12046-024-02527-7","DOIUrl":"https://doi.org/10.1007/s12046-024-02527-7","url":null,"abstract":"<p>In this letter, attempt has been made to successfully design a pipelined VLSI architecture for the computation of genetic algorithm (GA). The concept of stochastic computing is uniquely exploited in the proposed pipelined GA architecture to attain significant area and power efficiency with reasonably high speed of operation. The prototype 8-bit fixed point GA architecture is realised using VHDL on Xilinx Vivado 2020.3 and implemented on Zynq Ultrascale+ MPSoC (XCZU7EV-2FFVC1156) to train an arbitrary 4:3:2 fully connected neural network in real-time. The performance of the prototype GA architecture in case of real-time training of the neural network outshines the software and other existing GA architectures. The proposed GA-trained 4:3:2 network exhibits 6<i>X</i> reduction in training time and 720<i>X</i> increase in power efficiency, only at the cost of <span>(0.06%)</span> reduction in accuracy with respect to other existing works and software in case of the image classification of MNIST data-set.\u0000</p>","PeriodicalId":21498,"journal":{"name":"Sādhanā","volume":"71 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140936201","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}