The classification of statements provided by individuals during police interviews is a complex and significant task within the domain of natural language processing (NLP) and legal informatics. The lack of extensive domain-specific datasets raises challenges to the advancement of NLP methods in the field. This paper aims to address some of the present challenges by introducing a novel dataset tailored for classification of statements made during police interviews, prior to court proceedings. Utilising the curated dataset for training and evaluation, we introduce a fine-tuned DistilBERT model that achieves state-of-the-art performance in distinguishing truthful from deceptive statements. To enhance interpretability, we employ explainable artificial intelligence (XAI) methods to offer explainability through saliency maps, that interpret the model’s decision-making process. Lastly, we present an XAI interface that empowers both legal professionals and non-specialists to interact with and benefit from our system. Our model achieves an accuracy of 86%, and is shown to outperform a custom transformer architecture in a comparative study. This holistic approach advances the accessibility, transparency, and effectiveness of statement analysis, with promising implications for both legal practice and research.
Background: With global food demand increasing, novel agricultural practices are critical for increasing productivity and minimising waste. Water, a crucial agricultural resource, must be used efficiently, which needs modern irrigation systems.Objective: The article investigates the possibility of 5G networks in changing conventional irrigation systems into intelligent, highly responsive, and managed infrastructures. The research integrates Internet of Things (IoT) sensors and machine learning algorithms to construct an intelligent irrigation model that uses 5G technology’s quick data transfer, low latency, and widespread connection.Methodology: The study included year-long field tests that monitored soil moisture, rainfall, and crop health across various plants with varying water requirements. Data was gathered and delivered over a 5G network to a centralised control system that used machine learning techniques to change watering schedules dynamically.Results: Compared to traditional irrigation systems, the intelligent irrigation model resulted in a 30% reduction in water use, a 15% increase in crop output, and a 25% reduction in energy consumption.Conclusions: According to the study, 5G-enabled intelligent irrigation systems have the potential to revolutionise agricultural practises by providing more efficient, sustainable, and flexible water management solutions. This breakthrough is becoming more critical as climate change exacerbates water shortage issues. The article discusses how 5G networks might help to achieve global sustainability objectives by revolutionizing the agricultural industry and laying the groundwork for future research and development in intelligent farming technology.
Background: Technology in education has given birth to online examination systems (OES), which provide a simple and risk-free testing technique across several networks. The OES overcomes concerns inherent in manual check techniques, such as processing delays, registration, and record filtering issues.Objective: This article introduces an automated, web-based Open Educational System (OES) that is adaptable to any educational level or discipline, explaining its essential features, functions, and the technology that underpins it. The current study investigates how the OES improves test administration efficiency while protecting the privacy and security of students’ scores.Methods: The OES has a client-server architecture, leveraging PHP and MySQL, and functions across many networks, allowing for remote access and exam management. It includes features such as automatic test production, an analytical system, and configurable tests, all while maintaining safe and reliable test administration.Results: The OES implementation has considerably decreased the time and effort necessary for giving exams and reporting results. The system’s flexibility in test customisation and quick result tabulation underlines its efficiency, while its security features protect the examination process’s integrity.Conclusion: The OES provides a disruptive approach to digital exams, providing educational institutions with a safe, trustworthy, and efficient alternative to conventional testing techniques. The system’s flexibility and automation capabilities highlight its promise to transform testing operations by solving difficulties related to dependability, productivity, and security inherent in manual testing methods.
In the domain of character-based approximate string matching, edit distances such as Levenshtein have remained predominant despite their quadratic time complexity. This reality has prompted the adoption of more efficient metrics like Jaro and Jaro-Winkler. However, these methods often overlook the significance of character order within the matching window, which can adversely affect accuracy.For the first time, we introduce a novel class of character-based approximate string matching algorithms that leverage a convolutional kernel, surpassing the performance of existing state-of-the-art unsupervised character-based approximate string matching algorithms. This paper presents Convolutional Jaro (ConvJ) and Convolutional Jaro-Winkler (ConvJW), innovative similarity metrics designed to overcome these shortcomings. ConvJ and ConvJW utilize a convolutional approach with Gaussian weighting to effectively capture the positional proximity of matching characters, resulting in a more precise similarity evaluation. This method not only achieves computational efficiency comparable to that of Jaro and Jaro-Winkler but also surpasses the state-of-the-art in terms of F1-score, demonstrating faster execution times compared to the conventional Jaro and Jaro-Winkler implementations across various datasets.Our extensive experimental analysis highlights the exceptional performance of ConvJ and ConvJW across a range of datasets. Remarkably, ConvJ exhibits a 7x faster execution time than the fast Jaro implementation and exceeds the state-of-the-art F1-score by a significant margin of 10% more than Jaro. By setting a new benchmark in unsupervised character-based approximate string matching, our research shows the new way for future exploration and development in this field. The ConvJ and ConvJW algorithms, characterized by their quasilinear time complexity and improved accuracy, provide a solid foundation for the advancement of string matching techniques. These developments hold promise for a broad spectrum of applications in data mining, bioinformatics, and related areas.
Background: As wireless communication systems progress, there is a more significant requirement for high data transmission rates, requiring the investigation of practical multicarrier modulation approaches.Objective: The article’s objective is to develop and compare two popular multicarrier modulation algorithms, Coded Orthogonal Frequency Division Multiplexing (COFDM) and Orthogonal Frequency Division Multiplexing (OFDM), utilising the TMS320C6713 digital signal processor and the MATLAB Simulink platform.Methods: The article goes deeply into the theoretical and practical aspects of COFDM and OFDM. We assess both methods’ spectrum and energy efficiency using MATLAB Simulink simulations, considering the real-world constraints they may encounter.Results: The results show that COFDM has improved spectral efficiency, particularly in frequency-selective fading channels, and higher resistance to interference. As a result, COFDM is an excellent choice for applications requiring high data rates and continuous transmission under challenging situations. On the other hand, OFDM has higher energy efficiency, making it the modulation of choice for situations with strict power limits.Conclusion: The current study provides critical insights into the practical performance of COFDM and OFDM, supporting stakeholders in identifying the best modulation approach for various communication applications. The insights reached are critical in pushing the creation of digital communication systems adapted to individual needs.
Design patterns play a crucial role in modern software engineering, providing reusable solutions to common design challenges. Among the most influential collections of design patterns is the Gang of Four (GoF) patterns, which offer a timeless framework for addressing recurring design problems. This article investigates the enduring impact of GoF design patterns on software development practices, examining their utilization in contemporary software projects and frameworks. Additionally, this study conducts a thorough analysis of various design pattern detection approaches, evaluating their effectiveness and implications in real-world software development contexts. By combining theoretical frameworks with empirical studies, we aim to provide valuable insights into the role of design patterns in software engineering and offer guidance on selecting appropriate detection methods for software project.
Background: Image processing is crucial in different scientific fields and is at the core of digital technology owing to its diverse uses. Due to the extensive usage of digital image processing, user-friendly, efficient picture processing and editing software is needed. Due to the popularity of commercial software like Microsoft's Digital Image Suite and Adobe Photoshop, similar alternatives have emerged. Objective: This project aims to create a robust and adaptable picture editor utilising MATLAB capabilities with an intuitive GUI for users of varied competence levels. The article seeks to provide a viable alternative to commercial image processing software that is simple to use and has many features. Methods: MATLAB's image processing tools and unique methodologies created an image editor with extensive capabilities. The editor's development concentrated on supporting RGB, monochrome, and binary image formats and allowing users to manipulate them. The software's layout, design, message, usability, and cultural appropriateness were considered to improve user experience. Results: The image editor effectively enhances digital picture quality for medical image restoration and satellite image reconstruction. The program is user-friendly due to its minimal download size, easy setup, and straightforward UI. It shows how digital technology evolves, offering a flexible tool for beginners and experts. Conclusion: This study successfully developed a user-friendly MATLAB-based picture editor for varied digital image processing demands. The tool improves data analysis success and accuracy in engineering, research, and finance due to its simplicity and powerful features.
Background: As the number of automobiles on the road has increased, parking-related events have become a significant worry. Blind zones, or regions surrounding the car that are not visible to the driver, play a significant role in these incidents. Addressing these blind spots with technology may dramatically improve traffic safety. Objective: Using the Arduino microcontroller, this study attempts to create a low-cost, dependable blind spot monitoring system. Recognizing adjacent barriers aims to aid drivers in parking and lessen the probability of parking-related accidents. Methods: Methodology: The article comprises creating a car blind spot detection system using an Arduino Nano as the primary CPU. This system combines ultrasonic sensors for obstacle detection with infrared sensors for improved accuracy. The method uses threshold-based logic for object identification, significantly reducing false positives. Data from these sensors is transferred via a Bluetooth module, allowing for real-time monitoring. Results: After extensive testing in multiple parking circumstances, the blind spot detection system displayed consistent and reliable identification and warning of adjacent impediments. It was clear that it could significantly improve traffic and parking safety. Conclusion: The suggested Arduino-based blind spot sensor system is cost-effective, customizable, and efficient for improving parking safety. Combined with current automotive technology, it promises improved driving safety and provides a platform for DIY enthusiasts to develop further.
Contemporary advancements in NLP and neural network techniques are paving the way to enhance and harness traditional linguistic resources and corpora, as well as expand the methods of applying neural networks for complex language material. Thus, a weak point for both theoretical and applied linguistic tasks is the processing of spontaneous everyday speech. Two experiments described in this article are dedicated to the analysis of how successfully modern neural models cope with the recognition and generation of everyday Russian speech. The material for the experiments is the well-known ORD speech corpus, the largest collection of professional and mundane dialogues in Russian. The first experiment targets the pressing issue of increasing the volume of transcribed speech data through state-of-the-art automatic speech recognition techniques. Experimental recognition was conducted using two diverse methods – the NTR Acoustic Model and OpenAI’s Whisper system. The second experiment zeroes in on refining generative language models tailored for Russian using a conversational dataset. A prototype dialogue system, derived from the enhanced ruGPT-3 Small model, exemplifies the transformative potential of fine-tuning in dialogue generation tasks. The acquired results are utilized to enrich datasets for recognizing everyday Russian speech and for constructing chatbots that emulate spontaneous Russian conversations.
This paper outlines the creation of a multidisciplinary NordPlus competence network aimed at integrating the best teaching-oriented, technology-driven engineering education practices to support the green transition in the Baltic and Nordic regions. The network focuses on a comprehensive initiative to integrate electrical engineering and automation, mechatronics, information and communication technologies (ICT), informatics engineering, and cybersecurity, tailored to meet the evolving needs of the green industry. Methodologically, this interdisciplinary collaboration across the Baltic and Nordic regions addresses the specific challenges within these areas, such as optimizing energy efficiency, enhancing sustainable manufacturing processes, securing green technology from cyber threats, and innovating in smart infrastructure development. The outcomes of the NordPlus network's initiatives are instrumental in cultivating engineers equipped with not only technical knowledge and skills but also a profound dedication to sustainability principles. This preparation ensures they are more than ready to tackle the complex challenges associated with transitioning towards a sustainable future.
Background: Medical diagnostic and imaging technology has been fundamentally impacted by the twenty-first-century increase in internet technology, computers, wireless communication, and data storage. However, like with other imaging modalities, medical imaging may be hampered by noise and artefacts, compromising practical diagnostic analysis and potentially posing health hazards. Objective: The study focuses on the BM3D (Block Matching and 3D Filtering) technique, a state-of-the-art method, to combat the noise in medical images. Denoising these images aims to improve the quality of medical diagnoses and reduce associated risks. Methods: Building upon the foundation set by the Non-Local Means (NLM) filtering method, the BM3D technique utilises a patch-based denoising mechanism. Instead of denoising individual pixels, clusters or blocks of pixels are processed collectively to improve the overall image quality. Results: BM3D will exhibit strong performance against impartial thoroughness criteria, making it a prospective stalwart in the denoising realm for medical images. However, certain limitations are identified, like user-supplied noise levels and potential artefacts due to hard thresholding. Conclusion: While BM3D emerges as a powerful denoising tool for medical images, it is imperative to address its limitations further to bolster its efficacy and applicability in real-time diagnostic imaging systems.
Background: Because of signal attenuation, multipath fading, and Doppler phenomena, the underwater environment provides unique obstacles for communication channels. Traditional approaches often need to address these issues appropriately. Objective: This article aims to investigate the possibility of combining polar codes with OFDM (Orthogonal Frequency Division Multiplexing) methods to improve the performance and reliability of underwater communication systems. Methods: The suggested models combine polar codes’ capacity-achieving and error-correcting qualities with the robustness of OFDM against impairments such as impulsive noise. Key parameters such as bit error rate (BER), signal-to-noise ratio (SNR), and channel capacity were examined to assess the model’s efficacy. Results: Compared to traditional communication systems, simulations and tests show a 30% reduction in BER, a 20% increase in SNR, and a 25% increase in channel capacity. These measures highlight the tremendous advances in underwater channel performance that polar code-OFDM models provide. Conclusion: The combination of polar codes with OFDM is a viable method for improving the capabilities of underwater communication systems. The significant gains in performance indicators suggest potential applications in underwater sensor networks, oceanographic data transmission, underwater robotics, and deep-sea research. This study makes an important contribution to the advancement and dependability of underwater communication systems.
Background: Keeping people and things safe involves the constant development of novel firefighting technologies. Robots have emerged as viable assets in firefighting, capable of performing dangerous duties and reducing hazards to human life, particularly in enclosed spaces.Objective: The purpose of this study is to investigate the feasibility of deploying robots capable of autonomously detecting and extinguishing fires in buildings, thereby improving safety in various indoor settings such as factories, hospitals, schools, and government buildings.Methods: The robot, constructed modularly with omnidirectional wheels for agility, incorporates several sensors such as thermal imaging cameras, gas sensors, and obstacle detection sensors. The implementation entails rigorous testing in simulated interior environments to examine the robot’s capacity to detect and extinguish flames, manoeuvre around obstacles, and function effectively within a restricted period. The architecture of the robot also allows for future upgrades and component replacements.Results: The trials show that the robot can identify and extinguish flames and traverse obstacles in simulated situations. The robot’s modular design emphasises its versatility and application across various interior situations, demonstrating its potential for reducing fire damage and improving safety.Conclusion: This article demonstrates the feasibility and promise of using robots for firefighting in hazardous indoor situations. The results highlight the developed robot’s flexibility and adaptability, paving the way for future advances in robotics and firefighting methods, with implications for boosting safety and lowering hazards in various indoor applications.
Anomaly detection in multivariate time series (MVTS) is a significant research domain across several industries, including cybersecurity and industrial systems. There have been several deep learning-based methods proposed within this research domain. The development of high capacity frameworks has received the majority of attention in recent years due to the availability of large open-source datasets and improvement in computer processing power. However, there has not been much attention in investigating the importance of how the data is presented to these techniques during training. Curriculum learning (CL), a technique based on ordered learning, was proposed for machine learning. In CL, the model first learns from easy data and is progressively trained with increasingly difficult data. In this paper, we propose data-based CL for MVTS anomaly detection. We further introduce the CL concept to the learner (model), in which we first train a simple model and then utilize a complex model in the final training round. To the best of our knowledge, we are the first to investigate these approaches in MVTS anomaly detection. We evaluate the proposed designs on the SWaT dataset using the F1 score and the results show an improvement in performance.
Background: Medical labs play an important role in healthcare by delivering critical diagnostic services. Previously dependent on article records, many hospitals have switched to electronic systems, increasing efficiency and security in patient data management. Implementing electronic systems in healthcare has had a distinct effect on medical laboratories, which play a crucial role in diagnostic procedures and patient data management. This article explicitly examines the distinctions between digitalisation in laboratories and other healthcare sectors, such as clinics and hospitals, concerning document flow and data processing problems. Objective: This study aims to evaluate the deployment and effectiveness of electronic health records and laboratory information management systems in medical laboratories. The objective is to emphasise the technological elements and operational difficulties, explicitly focusing on the dangers and preventive measures related to data management without extensively discussing the direct consequences on patient care and hospital operations. Methods: This study systematically evaluates electronic health records and laboratory management software in healthcare settings. The main objective is to identify the primary variables that lead to data loss and analyse the different preventive techniques used to reduce these risks.Results: This study primarily focuses on the practical features of electronic health records and laboratory information management systems in medical laboratories. The analysis presented here examines the present condition of these systems, with a particular emphasis on their deployment and utilisation. However, it needs to precisely delve into the specific tactics for mitigating data loss concerns or enhancing patient care.Conclusion: This study emphasises the crucial significance of electronic health records and laboratory information management systems in medical laboratories, emphasising the relevance of efficient data management.
The paper focuses on problem of short text matching for literature heritage entities alignment from heterogeneous data sources. The overview of existing methods showed that all of them works well for long texts. The paper proposes modification of Jacquard similarity metric for solving the problem based on similarity of unique text tokens adjusted to the specifics of literature heritage domain. Achieved results were evaluated on the literature heritage of the A.S. Pushkin gathered from the various heterogeneous sources (datasets, full works compilations. Encyclopedia of A.S. Pushkin) and shown high accuracy of finding corresponding entities within the system by developed method.
It has been proven that several recently published protocols for exchanging by keys over noiseless channels of the same authors as in the current paper, have real vulnerability to eavesdropping rooted in the attacker’s receiver optimization procedure. Moreover, we have proved that binary bits and real-valued numbers exchange protocols have zero secret capacity and are therefore unpromising in their applications. Protocols of exchanging by real-valued vectors and by matrices have nonzero secret capacity under the condition of hard decoding by eavesdroppers. The use of optimal soft decoding results in a compromise of such protocols. Thus, a problem is still open about an existence or non-existence for reliable key sharing protocols executed over noiseless public channels.
Background: As vacations and tourism become more important in contemporary society, better management systems are needed to handle trip planning and booking. Digital solutions provide improved processes, but many travel businesses have yet to use them fully. Objective: This study introduces an online tourist management system to fill deficiencies in the travel and tourism industry. This platform centralizes booking and information transmission to improve the customer experience and corporate productivity. Methods: The prototype uses HTML and PHP for a front end and Microsoft SQL Server 2008. It helps global clients book activities, lodgings, and places by providing thorough information. However, administrators may provide hotel and travel agency vacation packages. Customers may see their booking information in “my booking” after confirmation. Results: The integrated platform centralizes passenger information and booking. It streamlines vacation planning and gives travel businesses a good way to market their packages. This program may eliminate mistakes, improve the user experience, and boost travel and tourist efficiency. Conclusion: This new tourist management system should simplify trip planning and booking for end-users and service providers. This technology might revolutionize the travel business, making it more accessible and pleasurable for everyone.
Background: As the demand for wireless communications grows, optimizing various access strategies becomes more important. This article compares Orthogonal Multiple Access (OMA) and Non-Orthogonal Multiple Access (NOMA) wireless communication methods.Objective: The primary aim is to understand and assess the capacity, spectrum efficiency, and energy efficiency of both OMA and NOMA systems using real data from thorough simulations and analysis.Methods: The study employs simulation data and practical analyses to assess multiple access approaches and their underlying technologies. It focuses on the two systems’ performance metrics in real-world circumstances.Results: The results show that NOMA systems outperform OMA systems regarding capacity and spectrum efficiency. NOMA supports more users within the same bandwidth and has greater system throughput. Furthermore, the energy efficiency study shows that NOMA outperforms OMA, implying a more energy-efficient system with improved overall network performance.Conclusion: The findings provide light on the performance dynamics of OMA and NOMA systems. These discoveries are critical for designing, optimizing, and developing improved wireless communication networks capable of meeting the needs of current wireless applications.
Background: As smartphones, particularly Android devices, have increased in popularity, so have e-commerce applications. Online purchasing, divided into B2C (business-to-consumer) and B2B (business-to-business) sectors, provides customers with ease and a wealth of options. However, security issues and a disconnected experience across numerous platforms present difficulties.Objective: This article aims to create a user-centric Android shopping application coupled with a cart application on an XAMPP server. The objective is to provide a unified, smooth shopping experience across all product lines and platforms.Methods: By developing the app in Java and XML to guarantee compatibility and usability across multiple Android devices. A connection between the application and a MySQL database will be created, allowing for shared resources with a web server and assuring effective operation.Results: With a single complete interface, this integrated strategy attempts to eliminate fragmentation in the online purchasing experience by eliminating the need for different applications and logins. It also anticipates personalised ideas, pricing, and promotions to improve the buying experience.Conclusion: By focusing on user experience, design, and integration, this Android shopping software has the potential to transform the e-commerce environment by reducing operations and creating a more immersive, safe, and efficient purchasing experience.
