In this paper we propose adaptive brain tumor detection, Image processing is used in the medical tools for detection of tumor, only MRI images are not able to identify the tumorous region in this paper we are using K-Means segmentation with preprocessing of image. Which contains de-noising by Median filter and skull masking is used. Also we are using object labeling for more detailed information of tumor region. To make this system an adaptive we are using SVM (Support Vector Machine), SVM is used in unsupervised manner which will use to create and maintain the pattern for future use. Also for patterns we have to find out the feature to train SVM. For that here we have find out the texture feature and color features. It is expected that the experimental results of the proposed system will give better result in comparison to other existing systems.

A novel, portable deep learning-assisted smartphone-based electrochemiluminescence (ECL) cost-effective (~10$) sensing platform was developed and used for selective detection of lactate. Low-cost, fast prototyping screen printing and wax printing methods with paper-based substrate were used to fabricate miniaturized single-pair electrode ECL platforms. The lab-made 3D-printed portable black box served as a reaction chamber. This portable platform was integrated with a smartphone and a buck-boost converter, eliminating the need for expensive CCD cameras, photomultiplier tubes, and bulky power supplies. This advancement makes this platform ideal for point-of-care testing applications. Foremost, the integration of a deep learning approach served to enhance not just the accuracy of the ECL sensors, but also to expedite the diagnostic procedure. The deep learning models were trained (3600 ECL images) and tested (900 ECL images) using ECL images obtained from experimentation. Herein, for user convenience, an Android application with a graphical user interface was developed. This app performs several tasks, which include capturing real-time images, cropping them, and predicting the concentration of required bioanalytes through deep learning. The device’s capability to work in a real environment was tested by performing lactate sensing. The fabricated ECL device shows a good liner range (from 50 µM to 2000 µM) with an acceptable limit of detection value of 5.14 µM. Finally, various rigorous analyses, including stability, reproducibility, and unknown sample analysis, were conducted to check device durability and stability. Therefore, the developed platform becomes versatile and applicable across various domains by harnessing deep learning as a cutting-edge technology and integrating it with a smartphone.

The rapid escalation in global COVID-19 cases has engendered profound emotions of fear, agitation, and despondency within society. It is evident from COVID-19-related tweets that spark panic and elevate stress among individuals. Analyzing the sentiment expressed in online comments aids various stakeholders in monitoring the situation. This research aims to improve the performance of pre-trained bidirectional encoder representations from transformers (BERT) by employing transfer learning (TL) and fine hyper-parameter tuning (FT). The model is applied to three distinct COVID-19-related datasets, and each of the datasets belongs to a different class. The evaluation of the model’s performance involves six different machine learning (ML) classification models. This model is trained and evaluated using metrics such as accuracy, precision, recall, and F1-score. Heat maps are generated for each model to visualize the results. The performance of the model demonstrates accuracies of 83%, 97%, and 98% for Class-5, Class-3, and binary classifications, respectively.

Sentiment analysis (SA) has become an essential component of natural language processing (NLP) with numerous practical applications to understanding “what other people think”. Various techniques have been developed to tackle SA using deep learning (DL); however, current research lacks comprehensive strategies incorporating multiple-word embeddings. This study proposes a self-attention mechanism that leverages DL and involves the contextual integration of word embedding with a time-dispersed bidirectional gated recurrent unit (Bi-GRU). This work employs word embedding approaches GloVe, word2vec, and fastText to achieve better predictive capabilities. By integrating these techniques, the study aims to improve the classifier’s capability to precisely analyze and categorize sentiments in textual data from the domain of movies. The investigation seeks to enhance the classifier’s performance in NLP tasks by addressing the challenges of underfitting and overfitting in DL. To evaluate the model’s effectiveness, an openly available IMDb dataset was utilized, achieving a remarkable testing accuracy of 99.70%.

The digital era presents both opportunities and challenges for women's empowerment. Traditional safety paradigms often prove inadequate in addressing these concerns, creating a pressing need for novel approaches to anticipate and mitigate risks proactively. Addressing these disparities necessitates a two-pronged approach: fostering equitable access to technology and cultivating digital skills, enabling women to navigate online spaces safely and confidently. Empowering women in the digital era will unlock their full potential, driving innovation, economic growth, and sustainable development. AI-driven predictive safety mechanisms hold the key to anticipating potential threats and creating a safer, more inclusive digital world for all women. This chapter's overarching mission is to illuminate the transformative potential of harnessing AI alongside data analytics to revolutionize women's safety, fostering empowerment, inclusivity, and societal progress. Request access from your librarian to read this chapter's full text.