This paper introduces a novel variational autoencoder model termed DVAE to prevent posterior collapse in text modeling. DVAE employs a dual-path architecture within its decoder: path A and path B. Path A makes the direct input of text instances into the decoder, whereas path B replaces a subset of word tokens in the text instances with a generic unknown token before their input into the decoder. A stopping strategy is implemented, wherein both paths are concurrently active during the early phases of training. As the model progresses towards convergence, path B is removed. To further refine the performance, a KL weight dropout method is employed, which randomly sets certain dimensions of the KL weight to zero during the annealing process. DVAE compels the latent variables to encode more information about the input texts through path B and fully utilize the expressiveness of the decoder, as well as avoiding the local optimum when path B is active through path A and the stopping strategy. Furthermore, the KL weight dropout method augments the number of active units within the latent variables. Experimental results show the excellent performance of DVAE in density estimation, representation learning, and text generation.
As space technology advances, an increasing number of spacecrafts are being launched into space, making it essential to monitor and maintain satellites to ensure safe and stable operations. Acquiring 3D information of space targets enables the accurate assessment of their shape, size, and surface damage, providing critical support for on-orbit service activities. Existing 3D reconstruction techniques for space targets, which mainly rely on laser point cloud measurements or image sequences, cannot adapt to scenarios with limited observation data and viewpoints. We propose a novel method to achieve a high-quality 3D reconstruction of space targets. The proposed approach begins with a preliminary 3D reconstruction using the neural radiance field (NeRF) model, guided by observed optical images of the space target and depth priors extracted from a customized monocular depth estimation network (MDE). A NeRF is then employed to synthesize optical images from unobserved viewpoints. The corresponding depth information for these viewpoints, derived from the same depth estimation network, is integrated as a supervisory signal to iteratively refine the 3D reconstruction. By exploiting MDE and the NeRF, the proposed scheme iteratively optimizes the 3D reconstruction of spatial objects from seen viewpoints to unseen viewpoints. To minimize excessive noise from unseen viewpoints, we also incorporate a confident modeling mechanism with relative depth ranking loss functions. Experimental results demonstrate that the proposed method achieves superior 3D reconstruction quality under sparse input, outperforming traditional NeRF and DS-NeRF models in terms of perceptual quality and geometric accuracy.
Haiyang Zhang, Huizhen Chen, Lianglin Xiong
et al.
This paper aims to address the exponential stability and stabilization problems for a class of delayed nonlinear Markov jump systems under randomly occurring Denial-of-Service (DoS) attacks and packet loss. Firstly, the stochastic characteristics of DoS attacks and packet loss are depicted by the attack success rate and packet loss rate. Secondly, a Period Observation Window (POW) method and a hybrid-input strategy are proposed to compensate for the impact of DoS attack and packet loss on the system. Thirdly, A Dynamic Event-triggered Mechanism (DETM) is introduced to save more network resources and ensure the security and reliability of the systems. Then, by constructing a general common Lyapunov functional and combining it with the DETM and other inequality analysis techniques, the less conservative stability and stabilization criteria for the underlying systems are derived. In the end, the effectiveness of our result is verified through two examples.
I Gusti Lanang Trisna Sumantara, Made Windu Antara Kesiman, I Made Gede Sunarya
Periapical radiographs are commonly used by dentists to diagnose dental problems and overall dental health conditions. The varying abilities of dentists to diagnose may be limited by their visual acuity and individual skills. To address this issue, there is a need for an application capable of computationally recognizing and classifying periapical radiographs. The commonly used computational method for image processing, specifically image recognition, is the Convolutional Neural Network (CNN) method. This study aims to create an application that can classify periapical radiographs and analyze the capabilities of the Convolutional Neural Network (CNN) method in this classification process. In general, periapical classification is divided into five types: Primary Endo with Secondary Perio, Primary Endodontic Lesion, Primary Perio with Secondary Endo, Primary Periodontal Lesion, and True Combined Lesions. The periapical radiograph classification process was tested using four CNN models: ResNet50v2, EfficientNetB1, MobileNet, and Shalow CNN. The evaluation of the CNN method utilized a confusion matrix-based technique to generate accuracy, precision, recall, F1-score and Weighted Average F1-score values. Based on the evaluation results, the highest accuracy value was achieved by EfficientNetB1 with 82%, followed by ResNet50v2 with 76%, MobileNet with 75%, and Shallow CNN with 71%.
Seyedamirreza Enjavi, Shaban Elahi, Ali Shayan
et al.
Abstract Modern economic growth has been based on mass industrial production and consumption, which have heavily relied on fossil fuels and energy waste since the 18th century. Hence, current socio-technical systems are unsustainable in meeting humans’ basic needs, such as energy and mobility. Fossil energy resources are non-renewable and, on the one hand, contribute to emissions that cause unreliable harm to the environment. In this research, the prime theory of Transformational Change illuminates how to use science and technology policy to meet social needs sustainably and inclusively in societies. This article answers questions regarding the essential policies and governance measures that states need to implement for the transition to electric autonomous vehicles (AVs) in the socio-technical system. Using meta-synthesis, followed by a case study and interviews with experts in the electric AV field, the article identifies state policies and governance measures to facilitate the transition of the sociotechnical system into electric AVs. The conceptualization of these roles determines that the state’s role is influenced by policy, governance, and legal decisions, which are ultimately implemented through specific combinations of policies.
Bibliography. Library science. Information resources
Esraa Hassan, Samir Elmougy, Mai R. Ibraheem
et al.
Retinal optical coherence tomography (OCT) imaging is a valuable tool for assessing the condition of the back part of the eye. The condition has a great effect on the specificity of diagnosis, the monitoring of many physiological and pathological procedures, and the response and evaluation of therapeutic effectiveness in various fields of clinical practices, including primary eye diseases and systemic diseases such as diabetes. Therefore, precise diagnosis, classification, and automated image analysis models are crucial. In this paper, we propose an enhanced optical coherence tomography (EOCT) model to classify retinal OCT based on modified ResNet (50) and random forest algorithms, which are used in the proposed study’s training strategy to enhance performance. The Adam optimizer is applied during the training process to increase the efficiency of the ResNet (50) model compared with the common pre-trained models, such as spatial separable convolutions and visual geometry group (VGG) (16). The experimentation results show that the sensitivity, specificity, precision, negative predictive value, false discovery rate, false negative rate accuracy, and Matthew’s correlation coefficient are 0.9836, 0.9615, 0.9740, 0.9756, 0.0385, 0.0260, 0.0164, 0.9747, 0.9788, and 0.9474, respectively.
Shiuh Tong Lim, Joe Yee Yuan, Khai Wah Khaw
et al.
Travel insurance serves as a crucial financial safeguard, offering coverage against unforeseen expenses and losses incurred during travel. With the advent of the proliferation of insurance types and the amplified demand for Covid-related coverage, insurance companies face the imperative task of accurately predicting customers’ likelihood to purchase insurance. This can assist the insurance providers in focusing on the most lucrative clients and boosting sales. By employing advanced machine learning techniques, this study aims to forecast the consumer segments most inclined to acquire travel insurance, allowing targeted strategies to be developed. A comprehensive analysis was carried out on a Kaggle dataset comprising prior clients of a travel insurance firm utilizing the K-Nearest Neighbors (KNN), Decision Tree Classifier (DT), Support Vector Machines (SVM), Naïve Bayes (NB), Logistic Regression (LR), and Random Forest (RF) models. Extensive data cleaning was done before model building. Performance evaluation was then based on accuracy, F1 score, and the Area Under Curve (AUC) with Receiver Operating Characteristics (ROC) curve. Inexplicably, KNN outperformed other models, achieving an accuracy of 0.81, precision of 0.82, recall of 0.82, F1 score of 0.80, and an AUC of 0.78. The findings of this study are a valuable guide for deploying machine learning algorithms in predicting travel insurance purchases, thus empowering insurance companies to target the most lucrative clientele and bolster revenue generation.
Electronic computers. Computer science, Information technology
With the rise of the fourth industrial revolution, traditional methods of analyzing investment have been transformed into intelligent methods under big data and the Internet of Things. This has created a new approach to solving practical engineering problems. This paper examines the formation and evolution of the application of inversion theory in tunnel and underground engineering, summarizing research progress using traditional and intelligent inversion analysis methods to identify three types of target unknown quantities in tunnels and underground projects: initial ground stress, support structure load, and tunnel characteristic parameters. It also offers an outlook on how to optimize inversion analysis methods to solve more challenging and complex tunneling problems in the context of informatization, digitalization, and intelligence. In the current research process of tunnel and underground space engineering problems, the inversion theory system has been improved, but inversion analysis methods still face many challenges. These include the low reliability of initial ground stress inversion under complex geological conditions, the lack of indicators to objectively evaluate the accuracy of inversion analysis, and the high costs of intelligent inversion analysis means. Moving forward in the context of big data and the information era, the future development direction for inversion theory and inversion methods in tunnel and underground space engineering is to combine new monitoring technology, computer vision technology, and simulation analysis technology to establish multifaceted intelligent inversion analysis models.
This paper proposed a fuzzy expert system for diagnosing diabetes. In the proposed method, at first, the fuzzy rules are generated based on the Pima Indians Diabetes Database (PIDD) and then the fuzzy membership functions are tuned using the Harris Hawks optimization (HHO). The experimental data set, PIDD with the age group from 25-30 is initially processed and the crisp values are converted into fuzzy values in the stage of fuzzification. The improved fuzzy expert system increases the classification accuracy which outperforms several famous methods for diabetes disease diagnosis. The HHO algorithm is applied to tune fuzzy membership functions to determine the best range for fuzzy membership functions and increase the accuracy of fuzzy rule classification. The experimental results in terms of accuracy, sensitivity, and specificity prove that the proposed expert system has a higher ability than other data mining models in diagnosing diabetes.
The research's conclusions are based on the current state of development as a consequence of the factors of communication, media, technology, science, and information. As a result of this human requirement, it keeps creating new languages, specialists, and in-depth specialties in the sciences. Following the Industrial Revolution, new organizational science and art were developed in European nations by artists and activists, who then disseminated their work in the fields of business and journalism. In the present stage of life, the rules are provided to one of the human sciences, so it is continually attempted to examine it. Human sciences are always changing, and the rules are out of the same manner, aside from as a new genre in the field of media.
In the present stage of life, advertisement is counted as a human science, so it is continually attempted to explore it, as human sciences are continuously changing, and the rules are out of the same manner, aside from as a new genre in the area of media. We wish to learn via the study we are doing that the channels of communication have various reasons for selling the commodities they name because the rules have a strong link with the sciences of business, development, administration, and communication.
Swati A. Patil, G. Pradeepini, Thirupathi Rao Komati
Abstract Music Genre Classification (MGC) is a crucial undertaking that categorizes Music Genre (MG) based on auditory information. MGC is commonly employed in the retrieval of music information. The three main stages of the proposed system are data readiness, feature mining, and categorization. To categorize MG, a new neural network was deployed. The proposed system uses features from spectrographs derived from short clips of songs as inputs to a projected scheme building to categorize songs into an appropriate MG. Extensive experiment on the GTZAN dataset, Indian Music Genre(IMG) dataset, Hindustan Music Rhythm (HMR) and Tabala Dataset show that the proposed strategy is more effective than existing methods. Indian rhythms were used to test the proposed system design. The proposed system design was compared with other existing algorithms based on time and space complexity.
Computer engineering. Computer hardware, Information technology
Muhammad Sajid Haroon, Seong Ho Chae, Sang-Woon Jeon
Recently, aerial jammers (AJs) have been actively considered because of their swiftness and adaptability to maximize the impact of jammers. The previous studies mainly focused on the optimization of a single AJ (transmit power, location, etc.) consisting of intended users and eavesdroppers in single-cell environment. In this paper, macroscopic impact of multiple randomly deployed AJs to multiple radio access technologies (multi-RATs) is analyzed, which have been actively studied for future cellular systems. In particular, multi-radio heterogeneous networks consisting of WiFi-enabled small base stations (SBSs) and 5G-enabled macro/micro base stations (MBSs) are considered. An integrated framework is developed and evaluated for multi-RATs in the presence of both co-channel interference and AJ interference based on tools from stochastic geometry. The main challenge is to analyze the optimal control of portion of AJs to interfere two different RATs to maximize the outage probability. Both analytical and simulation results are presented to demonstrate the impacts of various network parameters to the overall outage probability.
Malaysia is taking steps to transform the economy from being production-based to being knowledge driven (K-economy). In line with this objective, information and communication technologies (ICT) have been identified as the strategic enabling tools that will support the growth of the Malaysian economy as well as enhance the living standard of the population. Hence, in the past decade various initiatives have been taken by the government to promote the use and development of ICT. However, there are many issues and challenges that need to be addressed by the country before a successful transformation to a K-economy can be made. One of the issues is ICT utilization for the development of an information society and economy in the country. The paper assesses the current state of ICT utilization in Malaysia based on secondary data. The result indicates that the level of ICT utilization in the country is still low compared to selected countries and there exist wide disparities among states in Malaysia in terms of accessibility to ICT.
The issue of protecting the firmware and the memory area for storing variables (NVRAM - Non Volatile Random Access Memory) of the UEFI (Unified Extensible Firmware Interface) system are discussed in the paper. The research methodology is a deduction. The problem of trusted computer loading, in particular, the proprietarity of the UEFI stage, is relevant in the field of computer security. For an introduction to the context and subject field, the components and environment of the UEFI system, attack vectors on the system, the consequences of successful attacks for the user and built-in security tools are briefly described. The advantages and disadvantages of using two memory areas with different access modes as a way to protect critical UEFI system data are considered. As a memory area with a configurable access policy, it is proposed to use the hardware implementation of the resident security component (HRSC). Finally, the functionality of the HRSC and the applicability of this solution for ensuring the security of the UEFI system are considered. As a result, the justification of the applicability of the HRSC as a tool for differentiating access to critical parts of UEFI firmware and NVRAM was obtained. In addition, the advantages of using the HRSC as a memory area with a configurable access policy are identified. In particular those are the ease of implementation, variability of access differentiation and platform independence from the model and architecture of a computer with UEFI.
With the development of knowledge as economy, knowledge become the asset for the organizations. In this context, it is very essential organizational strategy to cop up with environmental changes. order to survive and compete effectively in the global environment. Research purpose of the study is to examine the relationship between knowledge management and job satisfaction among the university librarians of the Punjab, Pakistan. For data collection process survey research method was used. On the basis of literature review, a questionnaire was designed for data collection. The analyzed data showed a good relationship of the research main constructs between satisfaction of librarians’ jobs and different aspects of knowledge management. It was evaluated that there was a good relation of knowledge acquisition and knowledge sharing with job satisfaction. There is positive impact of knowledge management process on an organization and help improve efficiency and effectiveness. Beside this, job satisfaction is a important aspect for organizational success. It plays a significant role in achieving the organizational goals. The study concluded that both job satisfaction and KM draw a significant task in increasing the services availability, efficiency, effectiveness, productivity and performance of the professionals. Academic libraries and other organizations can use the findings of this study to improve their practices. This might help to increase innovation, productivity, opportunity and competitive advantages.
Information theory, Management information systems
Recommendations are a very useful tool in many industries. Recommendations provide the best selection of what the user wants and provide satisfaction compared to ordinary searches. In the music industry, recommendations are used to provide songs that have similarities in terms of genre or theme. There are various kinds of genres in the world of music, including pop, classic, reggae and others. With genre, the difference between one song and another can be heard clearly. This genre can be analyzed by spectrogram analysis. In this study, a spectrogram analysis was developed which will be the input feature for the Convolutional Neural Network. CNN will classify and provide song recommendations according to what the user wants. In addition, testing was carried out with two different architectures from CCN, namely VGG-16 and RESNET-50. From the results of the study obtained, the best accuracy results were obtained by the VGG-16 model with 20 epochs with accuracy 60%, compared to the RESNET-50 model with more than 20 epochs. The results of the recommendations generated on the test data obtained a good similarity value for VGG-16 compared to RESNET-50.
Haley M. LaMonica, Tracey A. Davenport, Antonia Ottavio
et al.
Abstract Background Despite the widely acknowledged potential for health information technologies to improve the accessibility, quality and clinical safety of mental health care, implementation of such technologies in services is frequently unsuccessful due to varying consumer, health professional, and service-level factors. The objective of this co-design study was to use process mapping (i.e. service mapping) to illustrate the current consumer journey through primary mental health services, identify barriers to and facilitators of quality mental health care, and highlight potential points at which to integrate the technology-enabled solution to optimise the provision of care based on key service performance indicators. Methods Interactive, discussion-based workshops of up to six hours were conducted with representative stakeholders from each participating service, including health professionals, service managers and administrators from Open Arms – Veterans & Families Counselling Service (Sydney), a counselling service for veterans and their families, and five headspace centres in the North Coast Primary Health Network, primary youth mental health services. Service maps were drafted and refined in real time during the workshops. Through both group discussion and the use of post-it notes, participants worked together to evaluate performance indicators (e.g. safety) at each point in the consumer journey (e.g. intake) to indicate points of impact for the technology-enabled solution, reviewing and evaluating differing opinions in order to reach consensus. Results Participants (n=84 across participating services) created service maps illustrating the current consumer journey through the respective services and highlighting barriers to and facilitators of quality mental health care. By consensus, the technology-enabled solution as facilitated by the InnoWell Platform was noted to enable the early identification of risk, reduce or eliminate lengthy intake processes, enable routine outcome monitoring to revise treatment plans in relation to consumer response, and serve as a personal data record for consumers, driving person-centred, coordinated care. Conclusions Service mapping was shown to be an effective methodology to understand the consumer’s journey through a service and served to highlight how the co-designed technology-enabled solution can optimise service pathways to improve the accessibility, quality and clinical safety of care relative to key service performance indicators, facilitating the delivery of the right care.
With the rapid growth of scientific publications, research paper recommendation which suggests relevant research papers to users can bring great benefits to researchers. In this paper, we focus on the problem of recommending conference papers to the conference attendees. While most of the related existing methods depend on the content-based filtering, we propose a unified conference paper recommendation method named <inline-formula> <tex-math notation="LaTeX">$CPRec$ </tex-math></inline-formula>, which exploits both the contents and the authorship information of the papers. In particular, besides the contents, we exploit the relationships between a user and the authors of a paper for recommendation. In our method, we extract several features for a user-paper pair from the citation network, the coauthor network, and the contents, respectively. In addition, we derive a user’s pairwise preference towards the conference papers from the user’s bookmarked papers in each conference. Furthermore, we employ a pairwise learning to rank model which exploits the pairwise user preference to learn a function that predicts a user’s preference towards a paper based on the extracted features. We conduct a recommendation performance evaluation using real-world data and the experimental results demonstrate the effectiveness of our proposed method.