Mobile cellular networks have evolved into both data producers and data carriers. Big data analytics can enhance the operation of mobile cellular networks while increasing operator income. We present a unified data model based on random matrix theory and machine learning in this study. Following that, we provide an architectural framework for implementing big data analytics in mobile cellular networks. Furthermore, we discuss numerous illustrative cases in mobile cellular networks, such as huge signalling data, big traffic data, big location data, big radio waveforms data, and big heterogeneous data. Finally, we outline many open research problems in big data analytics in mobile cellular networks.

Education and computer science are both involved in the burgeoning inter-disciplinary research field known as Educational Data Mining (EDM). EDM uses data mining software and ways to extract meaningful and practical data from big educational databases. EDM introduces better and more efficient learning techniques in an effort to enhance educational processes. The term "EDM methods" refers to a group of techniques for creating models and applications. This page provides a thorough literature review on EDM techniques. The essay also covers EDM research problems and trends.This EDM insight aims to provide researchers interested in furthering the field of EDM with useful and valuable information.

The Message Queue Telemetry Transport (MQTT) protocol for publish/subscribe middleware is proposed in this paper as a way to secure messages. In which the end-to-end method employs the Advanced Encryption System (AES) and Secure Hash Algorithm (SHA), and analyses the overhead associated with the usage of digital signatures Because there is no encryption method applied to the payload, MQTT has this drawback. Which enables one to discover the payload content that results in no data privacy. MQTT also has issues with data integrity. This digital signature's function is to confirm the payload's authenticity, that it doesn't alter during transmission, and that the payload is secret.The proposed solution can be evaluated and tested after which the programme can secure the MQTT payload. The addition of a security mechanism to MQTT, such as the encryption and decryption processes and verification outcomes, results in overhead in many areas. The overhead employed in this study is used to calculate the payload size, message sending time, process of digital signature security mechanism, memory consumption, and CPU utilisation. In an overhead analysis, overhead is performed by looking at many AES key types and numerous SHA key types. Upon closer inspection, it is seen that the digital signature system has resulted in a size increase for a number of the previously listed elements.

At present the Computer automated Face recognition systems are used for personal identification, but the Age variations of an individual poses a serious problem for it. Designing an appropriate feature representation and an effective matching framework for age invariant face recognition remains an open problem. To classify person age using faces author using combination of two CNN where one CNN will extract face features which can help in identify changes in face over time and second CNN helps in predicting/ classifying age. Face aging causes intra-subject variations (such as geometric changes during childhood & adolescence, wrinkles and saggy skin in old age) which negatively affects the accuracy of face recognition systems. Therefore, this paper proposes a unified, multi-task framework to jointly handle these two tasks, termed MTLFace, which can learn age-invariant identity-related representation while achieving pleasing face synthesis. Specifically, we first decompose the mixed face features into two uncorrelated components—identity- and age-related features—through an attention mechanism, and then decorrelate these two components using multi-task training and continuous domain adaption. d. This system will decrease the crimes and ensure the security in our society.

In a country where farming is still the most common vocation and conventional agricultural practises are still used, farmers can only expect a limited amount of crop yields, which is ultimately less advantageous for them than the inputs they provide. So, in order to maximise crop yields for a given input, we are demonstrating various techniques that will be helpful to create a recommendation system for smart farming. Agriculture has never been a lucrative industry in India despite being a big industry and major occupation there. We suggest a system that would evaluate soil properties (pH value, soil type, and nutrient concentration) as well as environmental factors (temperature, rainfall, and geographic location in terms of state) before advising the user on the best crop to plant. The numerous data mining approaches are discussed inthis work along with how they relate to soil fertility, nutrient analysis, and rainfall forecasting. Using decision trees, classification can be accomplished in data mining. One of the major problems that farmers confront is diseases that are affected on plant leaves, especially rice leaves. As a result, it is very challenging to deliver the amount of food required to feed the world's expanding population.Diseases affecting rice have reduced production and cost the agricultural industry money. Image acquisition, picture pre-processing, image segmentation, feature extraction, and classification are processes in the disease detection process. The techniques for identifying plant diseases using photographs of their leaves were covered in this essay. The segmentation and feature extraction algorithms utilised in the identification of plant diseases were also covered in this research.