Lead scoring is an essential process in sales and marketing that prioritizes prospective customers based on their potential to convert. In this study, we present a robust machine learning framework for lead scoring using the publicly available X Education dataset, which comprises 9240 leads described by 37 diverse features including online behavior, engagement metrics, and demographic details. Our approach begins with thorough data preprocessing removing irrelevant identifiers, handling missing values, and converting categorical variables followed by normalization and dimensionality reduction using Principal Component Analysis (PCA). We evaluated several PCA configurations (with 3–30 components) to capture the intrinsic variance in the dataset. Four classifiers, namely K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree, and Random Forest, were then trained with optimal hyperparameters determined through GridSearchCV and stratified cross validation. Specifically, KNN achieved its best performance with 15 principal components and n_neighbors=9, while SVM attained an accuracy of 91.8% at 25 components with C=10, γ=0.01, and an RBF kernel. The Decision Tree and Random Forest models also demonstrated competitive results. Moreover, ensemble methods—namely a soft voting ensemble and a stacking ensemble using Logistic Regression as a meta-classifier—were implemented to integrate the strengths of individual models. The stacking ensemble delivered the highest performance, with an overall accuracy of 92% and an AUC of 0.967. This study underscores the potential of machine learning, particularly ensemble approaches, to significantly enhance the precision of lead scoring and thereby optimize resource allocation in marketing strategies.

Saliency detection is finding the visually significant and attention grabbing objects present in an image. The present work is about finding saliency detection methods using Multi-Stream Convolution Neural Network. The main aim of this is to train a CNN model which captures the contextual information and multiscale features. Different metrics like f-measure, recall, precision and MAE are used to know how our model is performing with respect to other models. We also used cross dataset evaluation to know how our model is performing with unknown data to know the generalization capabilities. We compared our results with other well-known methods such as IT, MZ and SR which proves the efficacy of our work.

In the present study, we report the green synthesis of novel magnetically separable MgFe2O4 nanoparticles using Cajanus cajan (L.) Millsp leafs via combustion method. The MgFe2O4 were characterized by powder X-ray diffraction (XRD), Fourier transform infrared spectroscopy (FTIR), scanning electron microscopy (SEM), transmission electron microscopy (TEM), vibrating sample magnetometer (VSM), and UV-diffuse reflectance (UV-DRS) spectroscopy. The crystalline structure of MgFe2O4 was confirmed via XRD studies and TEM showed that the MgFe2O4 NPs were distorted spherical particles with particle size ranging between 5 and 15 nm. UV-DRS study showed the optical band gap of MgFe2O4 NPs to be 1.8 eV. Microwave-assisted (MW) degradation of PCM-dolo drug using MgFe2O4 as catalyst was performed at different operating parameters such as time (30 min), drug concentration (PCM-dolo 50 mg/L), initial concentration of MgFe2O4 (0–110 mg/L), and microwave power (100–600 W) to obtained the degraded fragments of the drug. Experimental data was used to compute the degradation efficiency of PCM-dolo on MgFe2O4. The enhanced catalytic performance could be ascribed to the production of MW-induced active species, such as holes (h+), superoxide radicals (⋅O2−) and hydroxyl radicals (⋅OH) in the degradation process. A possible degradation mechanism and pathway was proposed.

Fetal brain age prediction is crucial for assessing brain development and diagnosing congenital anomalies. Accurate gestational age estimation using imaging can enhance prenatal evaluation and understanding of brain maturity. The prediction of continuous values using deep learning remains a challenging task, despite the impressive application of convolutional neural networks (CNNs) for classification problems. The present study addresses this issue and uses transfer learning for such types of problem. The authors fine-Tuned ResNet50, DenseNet201, and MobileNetV2 by adding custom regression layers and selectively freezing pretrained layers to enhance training efficiency. Image resizing, normalization, and various data augmentation strategies were employed to avoid overfitting. Results show that fine-Tuning significantly improved regression accuracy, with further enhancement when the models were combined in an ensemble.

Joint spectral-spatial feature extraction has been proven to be the most effective part of hyperspectral image (HSI) classification. But, due to the mixing of informative and noisy bands in HSI, joint spectral-spatial feature extraction using convolutional neural network (CNN) may lead to information loss and high computational cost. More specifically, joint spectral-spatial feature extraction from excessive bands may cause loss of spectral information due to the involvement of convolution operation on non-informative spectral bands. Therefore, we propose a simple yet effective deep learning model, named deep hierarchical spectral-spatial feature fusion (DHSSFF), where spectral-spatial features are exploited separately to reduce the information loss and fuse the deep features to learn the semantic information. It makes use of abundant spectral bands and few informative bands of HSI for spectral and spatial feature extraction, respectively. The spectral and spatial features are extracted through 1D CNN and 3D CNN, respectively. To validate the effectiveness of our model, the experiments have been performed on five well-known HSI datasets. Experimental results demonstrate that the proposed method outperforms other state-of-the-art methods and achieved 99.17%, 98.84%, 98.70%, 99.18%, and 99.24% overall accuracy on Kennedy Space Center, Botswana, Indian Pines, University of Pavia, and Salinas datasets, respectively.

In recent years, there has been an enormous increase in the number of companies and of customers for almost every industry. The increment in the number of companies has also provided the choices to the customer but in turn it has also created new challenges. Thus, the companies must work not only to improve their products or services but to sustain customers in the competitive world. Churn prediction is the prediction of customers who are at a potential risk of discontinuing the product or service of the company. Thus, in today's competitive world, churn prediction is more relevant. In the present work, we have employed various machine learning models for an early prediction of churns, to mitigate the potential risk of losing the customers. The authors have chosen ensemble models for this task. Finally, the models are trained on the dataset. The results for various models are compared using accuracy, precision, recall, and F1 score. Moreover, it is also observed that for our dataset XGBoost outperformed over other models.

Blockchain technology is in fact a public ledger that gathers data in a chain of blocks, which gradually improves security, trust, transparency, quality, decentralization, and immutability while operating businesses. In the present scenario of business, the organization is not only concentrating on improving the activities related to operational aspects, but it also needs to meet the expectations of various stakeholders. Corporate social responsibility (CSR) is such a concept which facilitates the organization to cater the information related to various social and environmental concerns arising out of the business operations. It is now the liability on the part of the organization to communicate these CSR-related concerns in such a way that they effectively meet the expectations of stakeholders. CSR communication has become an integral part of the organization’s marketing strategy not only through the rise of public awareness on environmental and social issues but also because there is a demand for the correct use of CSR communication. However, organizations face difficulties in their CSR activities and actions, and due to this challenging situation, there is a rampant need for a solution. Blockchain is one of the most rewarding technology because it stores and records information in such a way that it makes it practically impossible to change or cheat the system. In fact, blockchain provides the desire transparency, traceability, decentralization, and accountability that CSR communication lacks recently. Therefore, this study identifies those common difficulties of CSR communication based on a literature review and proposes implementing blockchain as a solution for these problems. Finally, the objective of this study is to investigate what are the common problems or difficulties in CSR communication, and furthermore, what are the usefulness and benefits of blockchain, and could these benefits really overcome the identified difficulties?.

The present work develops a method for identity authentication and verification of static signatures stored in the database employing artificial neural network. The present method uses mathematical moments for feature extraction such as mean, variance, skewness and kurtosis. First of all, the method suggests to scan the signature images, then after a sequence of preprocessing steps the resulting images are subjected to feature extraction, however, at present already existing standard databases have been used. Subsequently, the system is trained from the genuine signature of individuals, and then an ANN is used to classify the signature images. The suggested method’s effectiveness has been demonstrated by comparison with the four current methodologies and experimental findings.

Skin Melanoma is a lethal type of cancer. The early diagnosis of which is crucial to improve the survival rate of the patients. Convolution neural networks are at the heart of the deep learning algorithms. In the present work authors have experimentally compared 2D and 3D Convolution Neural Network (CNN) models to identify the melanoma. We have employed three different types of datasets namely PH2, ISIC archive, and ISIC skin cancer datasets. We applied the two models on each of the datasets to determine their accuracy, precision, recall, f1 score and ROC curves. The experimental results provide the insights about the advantages and limitations of using 2D and 3D CNN models for the identification of skin melanoma. The authors have observed that 2D CNN model shows enhanced capabilities to detect skin lesion structures compared to 3D CNN. Moreover, the classification accuracy of the 2D CNN is also found better than 3D CNN.

Mobile Ad hoc Network (MANET) is a frameless, wireless network with no central access point. The network consists of migrant nodes. Topology is highly dynamic, unpredictable, and its probability of link failure is high due to continuous mobility of the nodes. As a result, we find that the nodes are no longer reachable and it moves away from the mobile or active path. This maximizes the dropping estimate, end-to-end delay and also undergoes cut in packet delivery rate thereby leading to degradation of network efficiency. In order to conquer such consequences, our work proposes designing of a route repairing mechanism in MANET. The basic idea of our proposed routing protocol is to find an optimal path based on the minimum hop count in the multipath scenario. Based on the widespread simulation of the proposed mechanism, done by adopting NS2 and by relative study of the same with existing protocol AODV, it was found that the projected routing mechanism helps in enhancing the performance and brings about improvement in ratio of packet delivery, packet loss as well as end-to-end delay.

Exemplar-based texture synthesis is a process of generating perceptually equivalent textures with the exemplar. The present work proposes a novel patch-based synthesis algorithm for synthesizing new textures that employs the powerful concept of gray-level co-occurrence matrix coupled with restricted cross-correlation. Furthermore, a simple and peculiar blending mechanism has been devised which avoids the necessity of retracing the path after ascertaining the minimum cut within the overlap region between the two neighboring patches. The method has been tested and executed for the samples derived from Brodatz album, the widely acceptable benchmark dataset for texture processing. The results are found to be comparable to Efros and Freeman for stochastic texture while outperforms the Efros and Freeman algorithm for semistructured texture.

In image processing, segmentation of textural regions from non-textural background has not been given a significant attention, however, considered to be an important problem in texture analysis and segmentation task. In this paper, we have proposed a new method, which fits under the framework of mathematical morphology. The entire procedure is based on recently developed textural descriptor termed as Morphological Texture Contrast (MTC). In this work authors have employed the bright and dark top-hat transformations to handle the bright and dark features separately. Both bright and dark features so extracted are subjected to MTC operator for identification of the texture components which in turn are used to enhance the textured parts of the original input image. Subsequently, our method is employed to segment the bright and dark textured regions separately from the two enhanced versions of the input image. Finally, the partial segmentation results so obtained are combined to constitute the final segmentation result. The method has been formulated, implemented and tested on benchmark textured images. The experimental results along with the performance measures have established the efficacy of the proposed method.

Saliency in a scene describes those facets of any stimulus that makes it stand out from the masses. Saliency detection has attracted numerous algorithms in recent past and proved to be an important aspect in object recognition, image compression, classification and retrieval tasks. The present method makes two complementary saliency maps namely color and texture. The method employs superpixel segmentation using Simple Linear Iterative Clustering (SLIC). The tiny regions obtained are further clustered on the basis of homogeneity using DBSCAN. The method also employs two levels of quantization of color that makes the saliency computation easier. Basically, it is an adaptation to the property of the human visual system by which it discards the less frequent colors in detecting the salient objects. Furthermore, color saliency map is computed using the center surround principle. For texture saliency map, Gabor filter is employed as it is proved to be one of the appropriate mechanisms for texture characterization. Finally, the color and texture saliency maps are combined in a non-linear manner to obtain the final saliency map. The experimental results along with the performance measures have established the efficacy of the proposed method.

Texture is the collective repetitive pattern that characterizes the surface of real world objects. The main challenge in the texture description is its application specific definition. The present work aims at bringing the definition of textures under a generalized framework and propose some texture descriptors. In order to accomplish this, authors have extensively studied the properties of texture, drawn four observations and used some of them to devise two texture descriptors under the framework of multi-scale mathematical morphology and co-occurrence matrices. Thereafter, the descriptors are used for texture classification and tested on three benchmark datasets. Before applying the descriptors to texture classification, a dependence between number of decomposition levels (scales) and classification percentage is established using hypothesis testing. Once the dependence is established, the corresponding scale and distance parameter is chosen for each dataset. The classification results are compared with a number of existing methods. The efficacy of results prove the supremacy of the proposed methods over the existing ones.

Texture segmentation refers to splitting of an image into homogeneous textured regions. The proposed approach is influenced by the multi-channel filtering theory of the human visual system. Authors have used gabor filter as a means of decomposing the textured mosaics into constituent magnitude response images which are subjected to non-linear function, in addition to this the results thus obtained are used in computing the texture energy as proposed by Jain et al. Subsequently, maximum texture energy is selected pixel wise out of these obtained feature images. The resultant image is normalized and smoothened for unnecessary perturbation and subjected to K-means clustering meanwhile pixel co-ordinates are also used as additional features. The method has been devised, enforced and tested on the benchmark texture mosaics. The empirical data along with performance measures have entrenched the efficacy of the proposed approach.