This paper presents the application of artificial neural networks and decision trees for the prediction of odor properties of post-fermentation sludge from a biological-mechanical wastewater treatment plant. The input parameters were concentrations of popular compounds present in the sludge, such as toluene, p-xylene, and p-cresol, and process parameters including the concentration of volatile fatty acids, pH, and alkalinity in the fermentation sludge. The analyses revealed that the implementation of artificial neural networks allowed the prediction of the values of odor intensity and the hedonic tone of the post-fermentation sludge at the level of 30% mean absolute percentage error. Application of the decision tree made it possible to determine what input parameters the fermentation feed should have in order to arrive at the post-fermentation sludge with an odor intensity −1. It was shown that the aforementioned phenomenon was influenced by the following factors: concentration of p-xylene, pH, concentration of volatile fatty acids, and concentration of p-cresol.

In this paper, we propose a privacy-preserving i-voting system based on the public Stellar Blockchain network. We argue that the proposed system satisfies all requirements stated for a robust i-voting system including transparency, verifiability, and voter anonymity. The practical architecture of the system abstracts a voter from blockchain technology used underneath. To keep user privacy, we propose a privacy-first protocol that protects voter anonymity. Additionally, high throughput and low transaction fees allow handling large scale voting at low costs. As a result we built an open-source, cheap, and secure system for i-voting that uses public blockchain, where everyone can participate and verify the election process without the need to trust a central authority. The main contribution to the field is a method based on a blind signature used to construct reliable voting protocol. The proposed method fulfills all requirements defined for i-voting systems, which is challenging to achieve altogether.

Lack of standardization is highly visible while we use historical data sets or compare our model with others that use IoMT devices from different vendors. The problem also concerns the trust in highly decentralized and anonymous environments where sensitive data are transferred through the Internet and then are analyzed by third-party companies. In our research we propose a standard that has been implemented in the form of framework that allows describing requirements for methods and platforms that collect, manage, share, and perform data analysis form the Internet of Medical Things in order to increase trust. Further, we can distinguish two types of IoMT devices: passive and active. Passive devices measure some parameters of the body and save them in databases. Active devices have the functionality of passive devices and moreover, they can act in a defined way, eg.: inject directly into the patient's body some elements such as a medicament, electric signals to the nervous system, stimulus pacemaker, etc. Nevertheless how to create a safe and transparent environment for using data active sensors, developing safe ML models, performing medical decisions based on the created models and finally deploy this decision to the specified device. While the IoMT devices are used in real-life, professional healthcare the control system should offer tools for backtracking decisions, allowing e.g. to find who made a mistake, or which event caused a particular decision. Our framework provides backtracking in the IoMT environment in which for each medical decision supported by ML models we can prove which sensor sends the data, which data was used to create prediction/recommendation, what prediction was produced, who and when use it, what medical decision was made by who. We propose a vendor transparency framework for each IoMT devices and ML models that will process the medical data in order to increase patient's privacy and prevent for eventual data leaking.

This paper proposes an improved monitoring and measuring system dedicated to industrial infrastructure. Our model achieves security of data by incorporating cryptographical methods and near real-time access by the use of virtual tree structure over records. The currently available blockchain networks are not very well adapted to tasks related to the continuous monitoring of the parameters of industrial installations. In the database systems delivered by default (the so-called world state), only the resultant or the last value recorded by the IoT device is stored. Effective use of measurement values recorded in the past requires each time viewing the entire chain of recorded events for a given IoT device. The solution proposed in the article introduces the concept of dependent wallets, the purpose of which is the aggregation and indexation of changes in machine parameters, recorded in the original wallets. As a result, we can easily get data from a certain sensor or sensors in the specified date range, even if the chain of transactions is very long. Our contribution is a universal mechanism that improves the efficiency of the infrastructure monitoring process, which uses blockchains to record measurements from sensors. The proposed model has been experimentally tested on two types of blockchains: Stellar and Hyperledger Fabric.

This study aims to use the decision-making process in categorizing legal documents by identifying keywords characterizing each legal domain class. The study utilizes the Kohonen Self-Organizing Map method and the Global Vectors for Word Representation (GloVe) model to create an efficient document classification system. As a result, a satisfactory classification accuracy of 71.69% was achieved. The article also discusses alternative approaches implemented to improve classification accuracy, such as the use of Named Entity Recognizer (NER) tools and the RoBERTa model, along with a comparison of their effectiveness. Challenges related to the uneven distribution of categories in the dataset are also mentioned, and potential directions for further research to enhance the classification results of legal documents are presented.