The corporate decision-making role in the data center, without the decision-making process cannot be imagined. The decision making is based on the decision-making process analytical tools that allow the efficient use of data, information and knowledge. Business Intelligence systems is introduced into the business to improve the availability of existing data that make it easier, faster and broader access to their data, so and in such manner as the work required. Hungarian enterprises often risk analysis, financial analysis, market analysis and controlling territory, rarely making the predictions, the introduction and application of risk analysis used in this system. The key to this new information system for faster spread of reducing the cost of applications, a higher level of data protection and parameter setting can be simple.

When constructed and installed correctly, solid unreinforced pre-cast cement concrete paver bricks are useful, aesthetically pleasing, affordable, and require little to no maintenance. Paver blocks are suitable for application in many traffic scenarios, including light, medium, heavy, and extremely heavy traffic. Using different percentages of nylon fiber (0.1%, 0.2%, 0.3%, 0.4%, and 0.5%) to increase the compressive strength of the cast paver blocks, M-40 grade, 80mm thick, are being employed in the current study project. It is now crucial to hunt for an alternate source for the natural elements used in concrete, such as natural sand and gravel, after determining the ideal ratio of nylon fiber. Sludge from foundries (WFS) is a promising resource that can serve as a replacement.

The increasing prevalence of diabetes poses significant challenges to global healthcare systems, necessitating effective predictive strategies for early diagnosis and intervention. Leveraging advancements in machine learning, this study employs a comprehensive approach integrating the Light Gradient Boosting Method (LGBM), K-Nearest Neighbors (KNN), and a Voting Classifier ensemble technique for diabetes prediction. Through exploratory data analysis (EDA), we discerned critical features and patterns relevant to diabetes prediction, informing model development and interpretation. Our results demonstrate the efficacy of ensemble learning, with the ensemble model surpassing individual methods in accuracy and robustness. Moreover, the EDA phase yielded valuable insights guiding feature selection and enhancing prediction performance. This research underscores the utility of diverse methodologies and data-driven insights in combating the burgeoning diabetes epidemic, offering a promising avenue for improving healthcare outcomes through predictive analytics.

Security is a primary concern for IoT-based environmental parameter monitoring systems that utilize sensors. Humidity significantly influences various chemical and biological properties of the environment, making it essential to monitor humidity and temperature using appropriate sensors. This paper outlines the design of a smart IoT-based secure environmental data monitoring system. A multi-level security system for the transceiver is developed. The proposed system employs secure key-based data encryption standards at the IoT transmitting sensor end. Encrypted data is transmitted via IoT over a private cloud channel. Ensuring data security during cloud server download to receivers is a key focus, addressed by a smart decryption algorithm. A smart IoT-based system for monitoring environmental parameters, specifically humidity and temperature, is designed, with the transceiver at its core. The paper discusses the results of secure encryption and decryption algorithms, presented in two phases: validation of standard AES encryption and implementation of multilevel public and private key decryption at the cloud end. The main focus is on designing a secure key-based AES encryption standard. Data is converted to 16-bit format and encrypted using AES-ECB2 mode before being uploaded to the IoT cloud. Results and timing analysis demonstrate the efficiency of the proposed encryption framework in decrypting data from the cloud. The transceiver employs a NodeMCU-based ESP8266 Wi-Fi module. Additionally, a Base64 AES decoding algorithm is presented in this work.

Liver diseases have become a significant health problem worldwide. As a result of its limited symptoms, it is extremely difficult to detect liver disease until the very last stage. An early diagnosis of liver problems will increase patient’s survival rate. The introduction of Machine Learning Tools in healthcare has opened up a wide spectrum of applications. Early detection by utilizing supervised learning techniques on a diverse data set can help in reducing mortality. This paper reviews some classification algorithms like Logistic Regression, Support Vector Machines (SVM), K Nearest Neighbor (KNN), Random Forest, Decision Tree and Extra tree classifier for comparing their performance based on the liver patient data.