The problem of preserving and using the labor potential of older workers today is one of the key problems of our country’s economy to ensure not only technological but also personnel sovereignty of the country. As a tool for maintaining a high level of qualification of this category of personnel to extend their professional career, it is proposed to use the capabilities of the additional vocational education (APE) system, which can provide a modern working specialist with the opportunity to implement the “lifelong learning” strategy. The passivity of the domestic business community in connecting and financing the solution to this problem is noted compared to employers of foreign companies, due to the entrenched idea of a serious decrease in the ability of older demographic representatives to learn and retrain, which leads to a decrease in the level of their motivation for learning and desire to extend their career. To refute this stereotype, the authors conduct research data on the initial capabilities of older age groups for effective labor activity from the point of view of their socio-psychological characteristics and intellectual capabilities. In addition, based on the analysis of foreign and domestic practice, the problems and possibilities of implementing the DPO system for older employees are considered, and the problems of the Russian DPO system in the university are formulated. Among the most significant of them, the negative attitude and desire to minimize the costs of employers on training and development of older workers, insufficient awareness of teaching staff about modern realities and problems of business practice, their unpreparedness to work with adult students, as well as the weakness of the material and technical base, software, information and methodological support or imperfection of their use are highlighted. The purpose of the study was to analyze stereotypes and substantiate the system of measures and proposals for training and retraining older workers through the active participation of representatives of the business community in the creation and implementation of DPO programs of the university. The most significant proposals are to achieve this goal through the active introduction of digitalization elements into this process, maximum approximation of programs to their customer, organization of training and development courses for the teaching and administrative staff of educational institutions to increase their awareness of current and future problems of business practice and the formation of competencies necessary for establishing effective interaction with older students. The theoretical significance of the research lies in the possibility of solving a number of scientific and applied problems related to the use of additional professional education to preserve the labor potential of older workers.The results of the study can be taken as a basis for increasing the customer-focusedness of training and retraining programs for older personnel of organizations, carried out through the system of additional professional education of Russian vocational education institutions, contributing to the preservation of the labor potential of older workers. Further research in this direction will reduce the impact of negative factors on the process of training and retraining of older workers in Russian vocational education institutions, taking into account the socio-psychological, motivational and other characteristics of older workers.

The scientific article was prepared at the junction of three areas of research: the field of labor market research, the field of research on technological trends and the needs of domestic companies in the field of information technology in the context of systemic transformations of the national economy. The purpose of the scientific article is to develop a system of proposals for adapting basic educational processes and, in a broad sense, a system for the reproduction of human capital to the new challenges and opportunities created by the platform economy. According to the results of the study, an algorithm for the chronological implementation of the proposed innovation system is proposed in such a way that, by transferring the experience of the core of the innovation process to other elements of the national platform for the reproduction of human capital, it becomes possible to scale innovations with the maximum involvement of all educational and educational institutions at the end of the planned innovation period.

DEVELOPMENT OF AMINOFUNCTIONALIZED SILICA MATRIX AS A POTENTIAL ADSORBENT FOR Pt4+ IONS IN PRECONCENTRATION SYSTEMS FOR FAAS ANALYSIS. The use of materials such as organofunctionalized silica for application in solid phase extraction (SPE) allows the preconcentration of several ions, including Pt, and subsequent detection. This work aims to synthesize and characterize an organofunctionalized silica (Sil-TMSDT) with the silylant N’(trimethoxysilyl)propylethylenetriamine and its application as a solid phase in the preconcentration Pt4+ ions in aqueous media, using detection by flame atomization atomic absorption spectroscopy (FAAS). The Fourier-transform infrared spectroscopy (FTIR) spectra and scanning electron microscopy (SEM) coupled with energy-dispersive spectroscopy (EDS) confirmed the aminofunctionalization of the silica. For the adsorption process, a preconcentration mini-column with 200 mg of Sil-TMSDT, a solution of 0.485 mg L-1 of K2[PtCl6] at pH 10 and HNO3 0.5 mol L-1 as eluent were used, obtaining an enrichment factor of 15-fold with retention efficiency higher than 99%. The Pt4+ ion determined by FAAS showed a linear response between 0.02 and 0.40 mg L-1; a linear coefficient where R = 0.9981; a 16-fold preconcentration factor; a limit of quantification (LOQ) and limit of detection (LOD) of 0.045 and 0.014 mg L-1, respectively. The proposal system showed analytical applicability to determining Pt4+ ion in an aqueous medium and could be used to detect traces of this potentially toxic metal in biological fluids such as urine and blood.

In the field of die and mold machining, determining appropriate cutting conditions is crucial. Factors such as tool geometry, machining path, work material characteristics, machining efficiency, and finishing accuracy must be taken into consideration. However, the current method of determining cutting conditions relies heavily on the intuition and experience of skilled engineers, and there is a need for a system to replace such knowledge. One of the critical factors affecting machining accuracy and efficiency is the tool overhang length, which is directly related to tool geometry. Unfortunately, there is no clear guideline for its determination. In a previous study, researchers developed a system to quickly derive cutting conditions using a data mining method and Random Forest Regression (RFR) applied to a tool catalog database. In this study, we constructed a new cutting condition compensation system based on the existing model, which accounts for the tool overhang length. The results of cutting experiments under high aspect ratio overhang lengths confirm that the correction coefficients proposed by the system are significant.

Abstract. This article examines the situation of cybersymbiosis between humans and artificial intelligence in order to consider how this phenomenon can be applied in the BRICS countries. The article proposes a structure that will allow the use of expert systems and the capabilities of people in order to improve justice with the integrated use of modern technologies. Using the research design discussed in the article, it can be noted that artificial intelligence is expected to help cope with tasks in the analysis and systematization of various phenomena, and intelligent models make it possible to create a system of responsibilities and proposals that can take a personalized approach to the issue of rulemaking. The main goal of this article is thoughtful cooperation within the framework of cybersymbiosis between humans and artificial intelligence, which will help the BRICS countries to target the vector of development of law-making activities, including such provisions of the vector of change as court cases, cases, writing regulations and much more. However, there remain a number of threats that need to be resolved in order to get rid of ethical and other misunderstandings on the part of artificial intelligence developers, the operation of various automated systems and other problems. In addition, the article offers a number of suggestions and solutions that will help potentially get rid of the above problems.

Design is a complex and clever process with multiple concepts attempting to explain it. To validate ideas and quantitatively characterize the design process, design experiments, and data analysis are required and predictable. Applying data analysis in design experiments can be challenging, and data are often underutilized. In this study, we develop an experimentation Interactive Evolutionary Computing Design (IECD) model using Upgraded Particle Swarm Optimization (UPSO) within the personalized interior design to iteratively analyze the new color combinations based on 116 designer’s preferences. The study proposed data-infused research into interior design via experimental techniques and the proposal system is evaluated, with additional feedback collected from experimented 116 designers, and data visualization analysis using Color Histogram Analysis and Auto encoders for data’s structure and patterns of the data, thus enhancing user preferences. A proposal system is developed using the collected data to suggest design options that align with individual user preferences and then integrated into the IECD framework to generate personalized design solutions that are more efficient and intelligent. The results are the effectiveness of data analysis and visualization in revealing design patterns and the impact of the data-infused IECD system to enhance the personalization and efficiency of interior design solutions. The IECD system enhances interior design efficiency and personalization through a proposal system, revealing design patterns, and aligning options with individual user preferences.

Abstract With the passage of the Climate Change Act, and to help meet its net zero obligations by 2060, Nigeria must transition from its dependence on fossil fuel energy sources to renewable energy. This will involve the procurement of large amounts of renewable energy by the government. In the past, procurement of power from the government-owned bulk trader has been chaotic, with no discernible strategy, and it is doubtful whether the government or Nigeria's citizens have derived value for money from the process. This article suggests a transition from the current, mostly unsolicited, proposal system to energy auctions, as the authors believe that this will help the country achieve low prices for renewable energy. The article also examines polices that have been implemented in other countries to drive energy auctions, with a view to applying relatable practices to the Nigerian exercise.

Graphical passwords, as opposed to textual passwords, require the user to pick pictures or draw symbols rather than input written letters. They are an option that may be explored in order to get over the issues that are caused by the system of passwords that are based on text. It has been hypothesized that graphical passwords are more difficult to crack using a brute force technique or to figure out through guessing. This paper proposes an authentication system based on a graphical password method. The proposed system computes the password points using histogram arithmetic and encrypts the chosen password points using SHA512. The envisioned system has been realized as an android application and evaluated with existing research considering multiple measurements such as required login time, password space, and entropy. The findings reveal that the new suggested system outperforms the reference work by more than 85% in terms of login latency and more than 72% in terms of entropy results.

This paper presents the development and functionalities of the AI-FEED web-based platform (ai-feed.ai), designed to address food and nutrition insecurity challenges within the food charity ecosystem. AI-FEED leverages advancements in artificial intelligence (AI) and blockchain technology to facilitate improved access to nutritious food and efficient resource allocation, aiming to reduce food waste and bolster community health. The initial phase involved comprehensive interviews with various stakeholders to gather insights into the ecosystem’s unique challenges and requirements. This informed the design of four distinct modules in the AI-FEED platform, each targeting the needs of one of four stakeholder groups (food charities, donors, clients, and community leaders). Prototyping and iterative feedback processes were integral to refining these modules. The food charity module assists charities in generating educational content and predicting client needs through AI-driven tools. Based on blockchain technology, the food donor module streamlines donation processes, enhances donor engagement, and provides donor recognition. The client module provides real-time information on food charity services and offers a centralized repository for nutritional information. The platform includes a comprehensive mapping and proposal system for community leaders to strategically address local food insecurity issues. AI-FEED’s integrated platform approach allows data sharing across modules, enhancing overall functionality and impact. The paper also discusses ethical considerations, potential biases in AI systems, and the transformation of AI-FEED from a research project to a sustainable entity. The AI-FEED platform exemplifies the potential of interdisciplinary collaboration and technological innovation in addressing societal challenges, particularly in improving food security and community health.

Textual Question Answering targets answering questions defined in natural language. Question Answering Systems offer an automated approach to procuring answers to queries expressed in natural language. The need for Multilingual Question Answering without performing machine translation is ever existing. Besides that, automating tasks with the help of technology to assist humans, has been the main aim of research in recent years. This paper presents an automated answer evaluation system for reading comprehension-based questions in the Hindi language without requiring translation in any other language. The system accepts text, question, and handwritten answer of a student in the form of an image for answer evaluation. This is accomplished by developing a textual question-answering system for reading comprehension. It is an extractive approach that utilizes RoBERTa transformer model and fine-tunes it for Hindi question-answering. The answer to the question is extracted as a span from the provided text. Further, a handwritten text recognizer model is developed employing a Convolutional Recurrent Neural Network with Connectionist Temporal Classification module along with two layers of Bidirectional LSTM. Experimentation is performed using existing as well as self-created datasets to show the effectiveness of the proposed approach. An accuracy of 98.69% is obtained on the self-created Hindi-QA dataset and the proposed system outperformed the other existing methods. The paper also discusses potential research directions in the field.

Vision Training is important for basketball players to effectively search for teammates who has wide-open opportunities to shoot, observe the defenders around the wide-open teammates and quickly choose a proper way to pass the ball to the most suitable one. We develop an immersive virtual reality (VR) system called VisionCoach to simulate the player's viewing perspective and generate three designed systematic vision training tasks to benefit the cultivating procedure. By recording the player's eye gazing and dribbling video sequence, the proposed system can analyze the vision-related behavior to understand the training effectiveness. To demonstrate the proposed VR training system can facilitate the cultivation of vision ability, we recruited 14 experienced players to participate in a 6-week between-subject study, and conducted a study by comparing the most frequently used 2D vision training method called Vision Performance Enhancement (VPE) program with the proposed system. Qualitative experiences and quantitative training results are reported to show that the proposed immersive VR training system can effectively improve player's vision ability in terms of gaze behavior and dribbling stability. Furthermore, training in the VR-VisionCoach Condition can transfer the learned abilities to real scenario more easily than training in the 2D-VPE Condition.

The subject of the research is the process of constructing recommendations in individual insurance tasks. The aim is to develop an approach for building recommendations in personalized insurance projects using temporal knowledge to adapt proposed insurance plans according to client behavior on insurance company websites. Objectives: to structure temporal rules considering the peculiarities of the online insurance recommendation process; to develop a method for constructing recommendations for insurance product selection using temporal knowledge. Conclusions: temporal rules have been structured for the task of building recommendations in personalized insurance projects. These rules generalize behavior in relative time for multiple users, enabling the generalization of user action sequences. A method for constructing online recommendations using temporal knowledge has been developed. The method consists of two phases: temporal knowledge formation and recommendation construction. The first phase is performed offline and is designed to form a base of temporal rules that generalize knowledge about user behavior. The second phase is executed online and involves refining and further utilizing temporal rules to adapt recommendations according to current user behavior. The method enables prompt adaptation of recommendations considering the user's current actions, creating conditions for increasing user trust in the recommender system's proposals.

The importance of scientific and technical information management in Chinese universities as a resource base for generating innovations and extracting new knowledge is proven. A conceptual model of digital transformation and factors influencing its successful implementation, including: digital management, digital services, and digital innovations, is proposed. Organizational, technical-technological and resource factors are mentioned among the factors influencing digital transformation, the importance of providing administrative, financial, personnel, technical-technological and security support for the digitalization of the communication infrastructure of Chinese universities is emphasized. A system of countermeasures and proposals, including political support and technical training, data exchange and network security, as well as standards and talents cultivation, aimed at improving the level of scientific and technical information management of Chinese universities, and the growth of their research and innovation potential, is justified.

The platform economy is an objective stage in the evolution of the digital economy, whose development is carried out under the influence of the trend of involving a large number of SMEs and individuals in economic relations as their direct participants. Unlike the pre-digital era, when operational commercial direct interaction between small participants in economic relations turned out to be impossible, communication technologies of the second decade of the 21st century have created favorable opportunities for the development of independent businesses of individuals and small professional teams. The process of commercialization of household resources is actively taking place in the form of the development of private blogs as platforms for commercial advertising and mutual trade of goods and services by individuals online, which creates a direct competitive threat to traditional trading companies. The current stage in the development of online participation of SMEs and individuals in commercial relations is the development of outsourcing relationships, within which part of the processes implemented by large businesses independently using hired personnel and their own infrastructure will be delegated to independent network structures on a competitive basis. At the same time, in proportion to the growing popularity of e-commerce, public demands for the security of such transactions are increasing, which is especially important in conditions of sanctions uncertainty and high risks of supply chain collapse. This circumstance determines the business request for systematization of the digital space and its centralization, the terminal stage of which is an inter-industry digital platform. The purpose of the scientific article is to develop a system of proposals for the formation of a national intersectoral outsourcing platform based on the “economic cross” model. A system of innovative solutions has been developed regarding the organization of economic interaction between subjects, the procedure for financing the activities of the platform by its participants, and the distribution of indirect industry income arising from the functioning of the platform.

The aim of this paper is to present the development of a real-time measurement system for glucose in aqueous media. The proposed system incorporates two lines of research: i) design, synthesis, and implementation of a non-enzymatic electrochemical sensor of Multi-Walled Carbon Nanotubes with Copper nanoparticles (MWCNT-Cu) and ii) design and implementation of a machine learning algorithm based on an Artificial Neural Network Multilayer Perceptron (ANN-MLP), which is embedded in an ESP32 SoC (System on Chip). From the current data that is extracted in real-time during the oxidation-reduction process to which an aqueous medium is subjected, it feeds the algorithm embedded in the ESP32 SoC to estimate the glucose value. The experimental results show that the nanostructured sensor improves the resolution in the amperometric response by identifying an ideal place for data collection. For its part, the incorporation of the algorithm based on an ANN embedded in a SoC provides a level of 97.8 % accuracy in the measurements. It is concluded that incorporating machine learning algorithms embedded in low-cost SoC in complex experimental processes improves data manipulation, increases the reliability of results, and adds portability.

Perching on the surface of moving objects, like vehicles, could extend the flight time and range of quadrotors. Suction cups are usually adopted for surface attachment due to their durability and large adhesive force. To seal on a surfaces, suction cups must be aligned with the surface and possess proper relative tangential velocity. However, quadrotors’ attitude and relative velocity errors would become significant when the object surface is moving and inclined. To address this problem, we proposed a real-time trajectory planning algorithm. The time-optimal aggressive trajectory is efficiently generated through multimodal search in a dynamic time-domain. The velocity errors relative to the moving surface are alleviated. To further adapt to the residual errors, we design a compliant gripper using self-sealing cups. Multiple cups in different directions are integrated into a wheel-like mechanism to increase the tolerance to attitude errors. The wheel mechanism also eliminates the requirement of matching the attitude and tangential velocity. Extensive tests are conducted to perch on static and moving surfaces at various inclinations. Results demonstrate that our proposed system enables a quadrotor to reliably perch on moving inclined surfaces (up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1.07m/s$</tex-math> </inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$90^\circ$</tex-math> </inline-formula> ) with a success rate of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$70\%$</tex-math> </inline-formula> or higher. The efficacy of the trajectory planner is also validated. Our gripper has larger adaptability to attitude errors and tangential velocities than conventional suction cup grippers. The success rate increases by 45% in dynamic perches. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper was motivated by the problem of perching on moving inclined surfaces using quadrotors. It can be used for perching on the various angled surfaces of an automobile to save energy and enlarge flight distance. It can also be exploited in air-ground cooperative tasks. In recent years, various grippers and trajectory planning methods have been devised to enable quadrotors to perch on static inclined surfaces. These strategies can not be used for perching on moving inclined surfaces. The task poses high requirements for the efficiency of trajectory planning and the grippers’ adaptability to pose errors. This paper proposes a real-time planning method to generate trajectories. The trajectories respect kinematic and motor lift constraints. They allow large attitude maneuvering of quadrotors. A multimodal search in a dynamic time-domain is developed to seek the minimum feasible time for the trajectory planner. Considering large pose errors in dynamic perching, a compliant gripper based on multiple independent suction cups is designed. The wheel and multidirectional layout of cups increase the adaptability to attitude and velocity errors. Results suggest that the proposed system is effective and reliable. In practice, our multiple cups would add weight penalty and increase the drag. The suction cups should be placed close to a quadrotor’s central axis to reduce the drag and disturbance in flow. The proposed system relies on an external motion capture system. In future research, we will focus on onboard sensing and control methods to achieve perching on moving inclined surfaces outdoors.

Ultrasound image guidance could display the movement of soft tissue in real time, which provides an important basis for the operation path selection of tumor for examinations and interventions such as precise localization and puncture biopsy. However, factors such as tissue deformation, patient motion, and instrument contact pose great challenges for real-time smooth localization tracking of target tissues and maintaining a suitable acoustic window. Not only does it reduce the accuracy of ultrasound examination, but also may prolong the examination time. In this paper, a real-time autonomous ultrasound robot trajectory planning framework is proposed to achieve global scanning of breast tissue and real-time local tracking of suspicious tumor targets. In addition, an ultrasound suspicious tumor target next moment motion attitude and position estimation algorithm and an acceleration-continuous online trajectory generation (ACOTG) algorithm are proposed. Experiments on breast phantom showed that the fluctuation difference of both global scanning and tracking scanning force was less than 5 N <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\pm$</tex-math> </inline-formula> 15%, and ACOTG takes less than 1 microsecond to calculate the next moment state. The position, velocity, and acceleration of the tracking path did not change abruptly when the unknown target changed. The ultrasound image of the suspected tumor target could always be smoothly maintained in a suitable acoustic window, while the errors between the center of the suspected tumor target image and the center of the acoustic window in the horizontal direction and the depth direction were less than <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\pm$</tex-math> </inline-formula> 1 mm and 30 mm <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\pm$</tex-math> </inline-formula> 10%, respectively. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The motivation of this study was to solve the clinical problem of difficulty in keeping the suspected breast tumor target stably in the center of the field of view under the influence of tissue deformation, patient motion and instrument contact in ultrasound guidance. We proposed the idea of global conventional scanning and local online tracking to achieve the autonomous scanning, detecting and tracking of suspicious tumor targets within the global scope of the breast. ACOTG algorithm is proposed and implemented, which can make the ultrasound image of suspicious tumor target can be displayed stably in the center of the acoustic window. With the help of this system, the accuracy of ultrasound examination can be improved and the time of examination can be reduced. The proposed system can also be applied to ultrasound scanning of other parts of the body.

يعد تشفير النص في الفيديو أداة حيوية في العديد من الصناعات حيث تكون حماية المعلومات الحساسة هي الأكثر أهمية. عادةً ما تواجه الخوارزميات وطرق الكشف الآلي صعوبة في تحديد موقع النص المخفي في إطارات الفيديو. تزيد هذه المقاومة من أمان المعلومات المخفية لأنه من الصعب على الأطراف غير المدعوة اكتشاف وجود نص مشفر. كما أنه يجمع بين المحتوى المكتوب والمرئي لتقديم كلا النوعين من المعلومات في وقت واحد وبسلاسة. في هذا البحث ، نقدم طريقة جديدة لتشفير النص داخل الفيديو باستخدام خوارزمية التشفير Salsa20 و Harris Corner Detection. الهدف من هذه الدراسة هو زيادة سرية وأمن المعلومات النصية المضمنة في محتوى الفيديو ، وهناك خطوتان أساسيتان في المنهجية المقترحة. لتحديد الزوايا أو النقاط المهمة داخل إطارات الفيديو ، تم استخدام طريقة Harris Corner Detection لأول مرة. تعمل هذه الزوايا كنقاط ميزة قوية يمكن استخدامها لدمج النص. تساعد طريقة Harris Corner Detection في تحديد الأماكن التي قد يتم إخفاء النص بها بدقة ، وذلك دون التقليل من جودة الصورة المرئية الإجمالية للفيديو ، وثانيًا ، يتم إنشاء مفتاح التشفير باستخدام تقنية التشفير Salsa20. Salsa20 هو تشفير دفق شائع يوفر تشفيرًا موثوقًا وتشغيلًا فعالاً. يتم تحويل النص المضمن إلى نص تشفير بواسطة XOR باستخدام مفتاح التشفير قبل تضمينه في الفيديو ، مما يضمن سريته وحمايته من الوصول غير المصرح به. تكشف مقارنة الطريقة المقترحة مع طرق تشفير النص الحالية عن عدد من المزايا. تدمج تقنية Harris Corner Detection النص في إطارات الفيديو بحيث يتم دمجها بشكل أقل وضوحًا ، مما يجعل من الصعب على الخصوم تحديد وجود المعلومات المخفية. يضمن استخدام Salsa20 أيضًا المستوى العالي من الأمان والحماية للنص المشفر ، والدفاع عنه ضد الهجمات المحتملة. يتم تقييم النظام المقترح باستخدام MSE و PSNR والارتباط و NPCR و UACI والإنتروبيا ، وتوفر مقاييس التقييم هذه نتائج ممتازة.

The importance of scientific and technical information management in Chinese universities as a resource base for generating innovations and extracting new knowledge is proven. A conceptual model of digital transformation and factors influencing its successful implementation, including: digital management, digital services, and digital innovations, is proposed. Organizational, technical-technological and resource factors are mentioned among the factors influencing digital transformation, the importance of providing administrative, financial, personnel, technical-technological and security support for the digitalization of the communication infrastructure of Chinese universities is emphasized. A system of countermeasures and proposals, including political support and technical training, data exchange and network security, as well as standards and talents cultivation, aimed at improving the level of scientific and technical information management of Chinese universities, and the growth of their research and innovation potential, is justified.

In recent years, deep learning has shown potential and efficiency in a wide area including computer vision, image and signal processing. Yet, translational challenges remain for user applications due to a lack of interpretability of algorithmic decisions and results. This black box problem is particularly problematic for high-risk applications such as medical-related decision-making. The current study goal was to design an interpretable deep learning system for time series classification of electroencephalogram (EEG) for sleep stage scoring as a step toward designing a transparent system. We have developed an interpretable deep neural network that includes a kernel-based layer guided by a set of principles used for sleep scoring by human experts in the visual analysis of polysomnographic records. A kernel-based convolutional layer was defined and used as the first layer of the system and made available for user interpretation. The trained system and its results were interpreted in four levels from microstructure of EEG signals, such as trained kernels and effect of each kernel on the detected stages, to macrostructures, such as transitions between stages. The proposed system demonstrated greater performance than prior studies and the system learned information consistent with expert knowledge.