Digitization of handwritten Devanagari text using CNN transfer learning – A better customer service support

Pande, Sandeep Dwarkanath; Jadhav, Pramod; Joshi, Rahul; Sawant, Amol Dattatray; Muddebihalkar, Vaibhav; Rathod, Suresh; Gurav, Madhuri Navnath; Das, Soumitra

doi:10.1016/j.neuri.2021.100016

Cited by 31 publications

(17 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…) , (10) where k r x,t is the current distance amongst L x and L t . In addition, Δ is a predefined safe physical distance.…”

Section: Update Position With Social Distancingmentioning

confidence: 99%

“…Several aspects can be the cause for disparity in stock market movement. These things made forecasting the stock market a complex task 1,9,10 . The forecasting of the stock market is adopted as an essential part as they considerably bang the global economy 11 .…”

Section: Introductionmentioning

confidence: 99%

“…These things made forecasting the stock market a complex task. 1,9,10 The forecasting of the stock market is adopted as an essential part as they considerably bang the global economy. 11 The majority of stock indices act equally to a random walk.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Hybrid optimization enabled deep learning and spark architecture using big data analytics for stock market forecasting

Kanchanamala

Karnati²,

Reddy

2023

Concurrency and Computation

View full text Add to dashboard Cite

Summary The precise forecasting of stock prices is not possible because of the complexity and uncertainty of stock. The effectual model is needed for the triumphant assessment of upcoming stock prices for several companies. Here, an optimized deep model is utilized to effectively predict the stock market using the spark framework. Here, the data partitioning is done using deep embedded clustering, wherein the tuning of parameters is done using the proposed Jaya Anti Coronavirus Optimization (JACO) algorithm in the master node. The proposed JACO is developed by combining Jaya Algorithm and Anti‐Coronavirus Optimization algorithm. Then, important technical indicators are mined from divided data in slave nodes. Here, the technical indicators are considered features for enhanced processing. Then, data augmentation is done to make data suitable for processing in the master node. At last, the prediction was done in the master node using deep long short‐term memory (Deep LSTM), and training is performed with the proposed JACO. The proposed JACO‐based Deep LSTM attains the smallest mean absolute error of 0.113, mean squared error of 0.095, and root mean squared error of 0.309.

show abstract

“…) , (10) where k r x,t is the current distance amongst L x and L t . In addition, Δ is a predefined safe physical distance.…”

Section: Update Position With Social Distancingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid optimization enabled deep learning and spark architecture using big data analytics for stock market forecasting

Kanchanamala

Karnati²,

Reddy

2023

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Y es que, sin duda, la creciente variedad de tecnología de ventas ha generado que las empresas y los vendedores deban comprender cómo les ayuda cada aplicación para el logro de sus objetivos (Itani, Krush, Agnihotri & Trainor, 2020). Ya que sin duda la digitalización ayuda a facilitar el acceso, la manipulación y el almacenamiento prolongado de datos e información imprescindible para generar una mejor atención al cliente (Pande et al, 2022).…”

Section: Atención Al Clienteunclassified

Gestión logística y atención al cliente en una empresa industrial del rubro alimentos, Lima 2021

Flórez

2022

eyn

View full text Add to dashboard Cite

La presente investigación tuvo como objetivo determinar la relación que existe entre la gestión logística y la atención al cliente en una empresa industrial del rubro alimentos en Lima 2021. Amparado en un método de investigación cuyo método fue hipotético-deductivo, con una tipología aplicada, con nivel investigativo descriptivo y correlacional, bajo el diseño no experimental, de corte transversal y enfoque cuantitativo. La población estuvo circunscrita a 400 colaboradores de la empresa en cuestión y la muestra fue calculada con la fórmula de población finita, arrojando la cifra de 197 personas. La técnica de recolección de datos fue la encuesta y el instrumento un cuestionario de elaboración propia, el mismo que fue sometido a confiabilidad de Alpha de Cronbach. Posterior a la indagación en campo, fueron procesados los datos con el software SPSS considerando la evaluación por cada interrogante y luego por baremos establecidos, cabe precisar que luego de analizar la normalidad de la data y con lo resultante, se procedió a utilizar el estadígrafo de Rho de Spearman cuyos resultados inferenciales demostraron una relación entre las dos variables. Llegándose a la conclusión de que sí existe relación entre la gestión logística y la atención al cliente, al igual que existe relación con cada una de las dimensiones de la gestión logística (gestión de materiales y distribución física) respecto a la variable dependiente.

show abstract

“…As a result, more computation time is needed during training and testing because the design has more parameters. Many deep-learning systems for multiclass classification of skin lesions have been developed since the ImageNet Large Scale Visual Recognition Challenge 24 proved the efficacy of neural networks.…”

Section: Introductionmentioning

confidence: 99%

Fine-grained classification of skin cancer types using deep neural networks on medical images

Kumar

Bebina

Potturu

et al. 2023

Pattern Recognition and Tracking XXXIV

View full text Add to dashboard Cite

Cancer has a tremendous present impact on human existence due to its extremely high global death rate. Malignant melanoma of the skin accounts for 20 daily deaths in the United States. Malignant melanomas (MEL), basal cell carcinomas (BCC), actinic keratoses intraepithelial carcinomas (AKIEC), nevi (melanocytic), keratinocytic lesions (BKL), dermatofibromas (DF), and vascular lesions (VL) are the seven main types of skin cancer (VASC). It might be challenging to recognize and classify different cancer kinds from biomedical imaging, as there are many sub-cancer types that differ significantly from one another. Several researchers and doctors are currently trying to pinpoint the most effective means of spotting skin cancer in its earliest stages. Using multiple residual and sequential convolutional neural networks, we present a learning strategy for cancer classification in this research. An effort is made here to more precisely categorize MEL, BCC, and BKL cancers. F1 score, precision, recall, and accuracy are used to verify the validity of the proposed model. Results show the reliability and validity of the model.

show abstract

Digitization of handwritten Devanagari text using CNN transfer learning – A better customer service support

Cited by 31 publications

References 26 publications

Hybrid optimization enabled deep learning and spark architecture using big data analytics for stock market forecasting

Hybrid optimization enabled deep learning and spark architecture using big data analytics for stock market forecasting

Gestión logística y atención al cliente en una empresa industrial del rubro alimentos, Lima 2021

Fine-grained classification of skin cancer types using deep neural networks on medical images

Contact Info

Product

Resources

About