Challenges In Terms Of Accuracy Research Articles

Real-Time Sign Language Recognition and Translation Using Deep Learning Techniques

Sign Language Recognition (SLR) recognizes hand gestures and produces the corresponding text or speech. Despite advances in deep learning, the SLR still faces challenges in terms of accuracy and visual quality. Sign Language Translation (SLT) aims to translate sign language images or videos into spoken language, which is hampered by limited language comprehension datasets. This paper presents an innovative approach for sign language recognition and conversion to text using a custom dataset containing 15 different classes, each class containing 70-75 different images. The proposed solution uses the YOLOv5 architecture, a state-of-the-art Convolutional Neural Network (CNN) to achieve robust and accurate sign language recognition. With careful training and optimization, the model achieves impressive mAP values (average accuracy) of 92% to 99% for each of the 15 classes. An extensive dataset combined with the YOLOv5 model provides effective real-time sign language interpretation, showing the potential to improve accessibility and communication for the hearing impaired. This application lays the groundwork for further advances in sign language recognition systems with implications for inclusive technology applications.

A novel microfluidic chip integrating with microcolumn array electrodes for rapid and ultrasensitive detection of alpha-fetoprotein

BackgroundCancer posed a serious threat to human health, and early diagnosis of cancer biomarker was extremely important for the treatment and control of cancer. Electrochemistry-based assays were low-cost, responsive and easy to operate, but there were some challenges in terms of accuracy, detection limit, efficiency and portability. The combination of microfluidic devices and electrochemical methods was expected to construct a high-performance sensing platform, but long-time antigen-antibody incubation was still required. Therefore, a novel microfluidic chip needs to be developed, which has the advantages of good portability, short incubation time, high accuracy, low detection limit and great application to point-of-care testing. ResultsA microfluidic sensor based on microcolumn array electrodes was developed, in which microcolumns could create local mixed flow to reduce the incubation time of target molecules and enhance their interaction with the sensing interface. Besides, three dimensional Mxene fibers-gold nanoparticles (3D MF-Au) was modified on the microcolumn array electrodes to increase active sites and provide more electrolyte shuttle holes. The electrolyte turbulence caused by the microcolumn array electrodes could heighten the contact between the target molecules and sensing interface and accelerate the transfer of redox pairs, thus reducing the incubation time of the target molecules and improving the electrochemical responses in synergy with the 3D MF-Au. Herein, the detection of AFP was chosen as a model, and the microfluidic sensor possessed superior performance for analysis of AFP in the range of 0.1 pg mL−1 - 200 ng mL−1 with a low detection limit (LOD) of 0.0648 pg mL−1. SignificanceThis microfluidic chip integrating with microcolumn array electrodes has been successfully implemented to detect AFP in human serum, and the results were consistent with that of electrochemical chemiluminescence method. The microfluidic chip provided a new strategy of portability, shortening incubation time and enhancing electrical signals for antigen detection of real samples, which showed great utilization potentiality in point-of-care testing.

Impedance-based polymer microneedle patch sensor for continuous interstitial fluid glucose monitoring

Early detection and effective blood glucose control are critical for preventing and managing diabetes-related complications. Conventional glucometers provide point-in-time measurements but are painful and cannot facilitate continuous monitoring. Continuous glucose monitoring systems are comfortable but face challenges in terms of accuracy, cost, and sensor lifespan. This study aimed to develop a microneedle-based sensor patch for minimally invasive, painless, and continuous glucose monitoring in the interstitial fluid to address these limitations. Experimental results confirm painless and minimally invasive penetration of the skin tissue with cylindrical microneedles (3 × 3 array) to a depth of approximately 520 μm with minimal loading. The microneedle sensors fabricated with precision using the complementary metal-oxide semiconductor process were immobilized with glucose oxidase, as confirmed through phase angle analysis. Long-term tests confirmed the effective operation of the sensor for up to seven days. Glucose concentrations determined from the fitted concentration–impedance curves correlated well with those measured using commercial glucometers, indicating the reliability and precision of the microneedle sensor. The flexible and minimally invasive sensor developed in this study facilitates painless and continuous glucose monitoring.

Deep learning innovations in diagnosing diabetic retinopathy: The potential of transfer learning and the DiaCNN model

Diabetic retinopathy (DR) is a significant cause of vision impairment, emphasizing the critical need for early detection and timely intervention to avert visual deterioration. Diagnosing DR is inherently complex, as it necessitates the meticulous examination of intricate retinal images by experienced specialists. This makes the early diagnosis of DR essential for effective treatment and prevention of eventual blindness. Traditional diagnostic methods, relying on human interpretation of medical images, face challenges in terms of accuracy and efficiency. In the present research, we introduce a novel method that offers superior precision in DR diagnosis, compared to traditional methods, by employing advanced deep learning techniques. Central to this approach is the concept of transfer learning. This entails the utilization of pre-existing, well-established models, specifically InceptionResNetv2 and Inceptionv3, to extract features and fine-tune selected layers to cater to the unique requirements of this specific diagnostic task. Concurrently, we also present a newly devised model, DiaCNN, which is tailored for the classification of eye diseases. To prove the efficacy of the proposed methodology, we leveraged the Ocular Disease Intelligent Recognition (ODIR) dataset, which comprises eight different eye disease categories. The results are promising. The InceptionResNetv2 model, incorporating transfer learning, registered an impressive 97.5% accuracy in both the training and testing phases. Its counterpart, the Inceptionv3 model, achieved an even more commendable 99.7% accuracy during training, and 97.5% during testing. Remarkably, the DiaCNN model showcased unparalleled precision, achieving 100% accuracy in training and 98.3% in testing. These figures represent a significant leap in classification accuracy when juxtaposed with existing state-of-the-art diagnostic methods. Such advancements hold immense promise for the future, emphasizing the potential of our proposed technique to revolutionize the accuracy of DR and other eye disease diagnoses. By facilitating earlier detection and more timely interventions, this approach stands poised to significantly reduce the incidence of blindness associated with DR, thus heralding a new era of improved patient outcomes. Therefore, this work, through its novel approach and stellar results, not only pushes the boundaries of DR diagnostic accuracy but also promises a transformative impact in early detection and intervention, aiming to substantially diminish DR-induced blindness and champion enhanced patient care.

Controlling of Unmanned Underwater Vehicles Using the Dynamic Planning of Symmetric Trajectory Based on Machine Learning for Marine Resources Exploration

Unmanned underwater vehicles (UUV) are widely used tools in ocean development, which can be applied in areas such as marine scientific research, ocean resources exploration, and ocean security. However, as ocean exploration advances, UUVs face increasingly challenging operational environments with weaker communication signals. Consequently, autonomous obstacle avoidance planning for UUVs becomes increasingly important. With the deepening of ocean exploration, the operational environment of UUVs has become increasingly difficult to access, and the communication signals in the environment have become weaker. Therefore, autonomous obstacle avoidance planning of UUVs has become increasingly important. Traditional dynamic programming methods face challenges in terms of accuracy and real-time performance, requiring the design of auxiliary strategies to achieve ideal avoidance and requiring cumbersome perception equipment to support them. Therefore, exploring an efficient and easy-to-implement dynamic programming method has significant theoretical and practical value. In this study, an LSTM-RNN network structure suitable for UUVs was designed to learn the dynamic programming mode of UUVs in an unknown environment. The research was divided into three main aspects: collecting the required sample dataset for training deep networks, designing the LSTM-RNN network structure, and utilizing LSTM-RNN to achieve dynamic programming. Experimental results demonstrated that LSTM-RNN can learn planning patterns in unknown environments without the need for constructing an environment model or complex perception devices, thus providing significant theoretical and practical value. Consequently, this approach offers an effective solution for autonomous obstacle avoidance planning for UUVs.

Efficient mapping of accurate long reads in minimizer space with mapquik.

DNA sequencing data continue to progress toward longer reads with increasingly lower sequencing error rates. We focus on the critical problem of mapping, or aligning, low-divergence sequences from long reads (e.g., Pacific Biosciences [PacBio] HiFi) to a reference genome, which poses challenges in terms of accuracy and computational resources when using cutting-edge read mapping approaches that are designed for all types of alignments. A natural idea would be to optimize efficiency with longer seeds to reduce the probability of extraneous matches; however, contiguous exact seeds quickly reach a sensitivity limit. We introduce mapquik, a novel strategy that creates accurate longer seeds by anchoring alignments through matches of k consecutively sampled minimizers (k-min-mers) and only indexing k-min-mers that occur once in the reference genome, thereby unlocking ultrafast mapping while retaining high sensitivity. We show that mapquik significantly accelerates the seeding and chaining steps-fundamental bottlenecks to read mapping-for both the human and maize genomes with [Formula: see text] sensitivity and near-perfect specificity. On the human genome, for both real and simulated reads, mapquik achieves a [Formula: see text] speedup over the state-of-the-art tool minimap2, and on the maize genome, mapquik achieves a [Formula: see text] speedup over minimap2, making mapquik the fastest mapper to date. These accelerations are enabled from not only minimizer-space seeding but also a novel heuristic [Formula: see text] pseudochaining algorithm, which improves upon the long-standing [Formula: see text] bound. Minimizer-space computation builds the foundation for achieving real-time analysis of long-read sequencing data.

PENGGUNAAN APLIKASI E- AUDIT DALAM SISTEM INFORMASI MANAJEMEN INSPEKTORAT POLRI

This research investigates the utilization of e-audit applications in the management information system of the Indonesian National Police Inspectorate. The Inspectorate plays a crucial role in upholding the integrity and efficiency of the Republic of Indonesia Police. However, the manual audit process faces challenges in terms of accuracy, efficiency, and standardization. Therefore, the utilization of e-audit applications is seen as a potential solution to enhance the effectiveness and efficiency of the audit system.This study employs a mixed-methods approach that combines literature review, observation, interviews, and surveys. The literature review provides an understanding of the utilization of e-audit applications and management information systems in the context of the Inspectorate. Observations and interviews were conducted to observe the existing audit processes and gain direct insights from auditors and Inspectorate staff. Surveys were utilized to collect data on users' perceptions and experiences with e-audit applications. The findings indicate that the utilization of e-audit applications can enhance the efficiency, accuracy, and consistency of the audit process. E-audit applications enable process automation, accurate data collection, quick analysis, and efficient report generation. However, the implementation of e-audit applications also faces challenges such as the need for deep understanding, staff competence development, and adequate information technology infrastructure. This research contributes to understanding the role and benefits of utilizing e-audit applications in the management information system of the Inspectorate. Recommendations are provided to strengthen awareness and understanding, enhance staff competence, and overcome information technology infrastructure constraints. It is expected that the utilization of e-audit applications can improve the overall quality of internal supervision and transparency within the Indonesian National Police.

On the use of a multigrid-reduction-in-time algorithm for multiscale convergence of turbulence simulations

Simulations of turbulent flow present challenges in terms of accuracy and affordability on modern highly-parallel computer architectures. A multigrid-reduction-in-time algorithm is used to provide a framework for separately evolving different scales of turbulence and for parallelizing the temporal domain, thereby increasing the concurrency. It is hypothesized that the space–time locality of the small scales of turbulence can be used to circumvent difficulties in applying temporal multigrid to flows dominated by inertial physics. For algorithms that fall well short of spectral accuracy (fourth-order is used in this work) attention must be paid to the accuracy of features on scales transferred between multigrid levels. Numerical experiments were performed using implicit large-eddy simulation. Results from applying the approach to an infinite-Reynolds number Taylor–Green flow and a double-shear flow at a Reynolds number of 11650 provide strong evidence that the approach has merit. The multigrid-reduction-in-time framework can be used to parallelize the temporal domain of a high-Reynolds-number turbulent flow and permit independent convergence of different scales. Establishing this foundation allows for future research in reducing the wall-clock time to solve turbulent flows while retaining the same accuracy as sequential solvers. Current performance results from parallelizing the temporal domain are not competitive with those from sequential-in-time methods.

The Notorious GPT: science communication in the age of artificial intelligence

ChatGPT provides original, human-like responses to user prompts based on supervised and reinforcement machine learning techniques. It has become the poster child of generative AI, which is widely diagnosed to disrupt many realms of life — including science communication. This essay reflects on this development. It discusses opportunities for the practice of science communication, such as generative AI’s translational and multimodal capacities and its capacity to provide dialogical science communication at scale, but also challenges in terms of accuracy, ‘wrongness at scale’ or job market implications. It also ponders implications for research on science communication, which has largely neglected (generative) AI so far. It argues that scholars should analyze public communication “about” AI as well as communication “with” AI, given its ‘increased agency’. Furthermore, scholars should analyze the impact of AI on science communication itself and the larger science communication ecosystem.

Sistem Informasi Manajemen Outbound Call (OBC) Subunit Payment Collection Pada Witel Lampung Berbasis Web

The regional division of PT. Telekomunikasi Indonesia (Telkom) in Lampung, known as Witel Lampung, is responsible for managing telecommunication services for customers in the area. However, the current manual process of recording outbound call data in Microsoft Excel spreadsheets poses challenges in terms of accuracy, reliability, and efficiency. This affects the decision-making process of finance officers who rely on this data to calculate various metrics and indicators. To address these challenges, Witel Lampung requires an information system that can automate the process of collecting, storing, and analyzing outbound call data. The main objective of this research is to design and develop a user-friendly front-end system for finance officers to automatically calculate outbound call data. The implementation of this system will improve data accuracy and reliability, reduce time and effort required for data management, and enhance the overall efficiency of Witel Lampung's operations, resulting in better customer service and satisfaction. Investing in this system will help Witel Lampung improve its data management capabilities, decision-making process, and overall competitiveness in the telecommunications industry.

КОРПОРАТИВНАЯ КУЛЬТУРА КАК КРАЕУГОЛЬНЫЙ КАМЕНЬ ЭКОНОМИЧЕСКОЙ УСТОЙЧИВОСТИ ОРГАНИЗАЦИИ

Problem context. Corporate culture (CC) of an organization is often represented by implicit factors in research models, the measurement of which poses a significant challenge in terms of accuracy and reliability. However, there is a high demand for such measurements (direct or indirect), particularly in analyzing and forecasting the organization’s level of economic resilience. Research objective. This study aims to establish a link between the corporate culture of an organization and its economic resilience by proposing adequate measures of corporate culture quality. Research methodology. The process of modeling an organization using a normalized system of balanced indicators (NSBI) consisting of 64 indicators across 7 strategic perspectives is described. The relationships between indicators in the NSBI model are inherently fuzzy in nature. By quantitatively measuring these indicators, the quality of CC can be assessed through a reverse process. Results. Three cases are presented where the indicators of “CC Quality” and business efficiency are directly linked using fuzzy logic. Conclusion. An approach is presented that establishes a connection between the quality of corporate culture and the level of organizational resilience through a normalized multi-layered NSBI.

Combining machine learning algorithm to improve prediction performance of ab initio method for vibrational energy spectra of HF/HBr/H<sup>35</sup>Cl/Na<sup>35</sup>Cl

Halides play an important role in atmospheric chemistry, corrosion of steel, and also in controlling the abundance of O<sub>3</sub>. Moreover high-precision vibrational energy spectra contain a large amount of quantum information of molecular system and are basic data for people to understand and manipulate molecules. At present, ab-initio methods have achieved many calculation results of the potential energy surfaces and corresponding vibrational energy of molecules, but they still face challenges in terms of accuracy and computational cost. Recently, data-driven machine learning methods have demonstrated very strong capability of extracting high-dimensional functional relationships from massive data and have been widely used in spectrum studies. ​Therefore, a theoretical approach to combining ab-initio method and machine learning algorithm is presented here to predict the vibrational energy of diatomic systems, which improves the accuracy and simultaneously reduces the computational cost. Firstly, the vibrational energy levels of 42 diatomic molecules are obtained by using different CCSD(T) methods to calculate the configurations from simple to complex and the corresponding experimental results are also collected. ​A machine learning algorithm is then used to learn the difference between the CCSD(T) method calculated vibrational results and the experimental vibrational results, and a high-dimensional error function is finally constructed to improve the original CCSD(T) computational accuracy. The results for HF, HBr, H<sup>35</sup>Cl and Na<sup>35</sup>Cl (they did not appear in the training set) and other halogen molecules show that compared with the CCSD(T)/cc-pV5Z calculation method alone, the present method reduces the prediction error by more than 50% and the computational cost by nearly one order of magnitude. It is worth noting that the method proposed in this paper is not only limited to the energy level prediction of diatomic systems, but also applicable in other fields where data can be obtained by ab initio methods and experimental methods simultaneously, such as the energy spectrum properties of macromolecular systems.

PrecipGradeNet: A New Paradigm and Model for Precipitation Retrieval with Grading of Precipitation Intensity

Near-real-time precipitation retrieval plays an important role in the study of the evolutionary process of precipitation and the prevention of disasters caused by heavy precipitation. Compared with ground-based precipitation observations, the infrared precipitation estimations from geostationary satellites have great advantages in terms of geographical coverage and temporal resolution. However, precipitation retrieved from multispectral infrared data still faces challenges in terms of accuracy, especially in extreme cases. In this paper, we propose a new paradigm for satellite multispectral infrared data retrieval of precipitation and construct a new model called PrecipGradeNet. This model uses FY-4A L1 FDI data as the input, IMERG precipitation data as the training target, and improves the precipitation retrieval accuracy by grading the precipitation intensity through Res-UNet, a semantic segmentation network. To evaluate the precipitation retrieval of the model, we compare the retrieval results with the FY-4A L2 QPE operational product to the IMERG precipitation. IMERG is considered as the ground truth. We evaluate the precipitation retrieval from the precipitation fall area identification, the precipitation intensity interval discrimination, and the precipitation quantification. Experimental results show that PrecipGradeNet has better overall performance compared with the FY-4A QPE product in precipitation fall area identification with POD increased by 48% and CSI and HSS improved by 21% and 14%. PrecipGradeNet also has better performance in light precipitation with POD increased by 114% and CSI and HSS improved by 64% and 52%, and better overall precipitation quantification, with RMSE and CC improved by 16% and 15%. In addition, PrecipGradeNet avoids the overall bias in the low and extreme high precipitation cases. Therefore, the new paradigm proposed in this paper has the potential to improve the retrieval accuracy of satellite precipitation estimation products. This study suggests that the application of semantic segmentation methods may provide a new path to correct the intensity bias of the satellite-based precipitation products.

Masticatory system-inspired microneedle theranostic platform for intelligent and precise diabetic management.

Integrated systems for diabetic theranostics present advanced technology to regulate diabetes yet still have critical challenges in terms of accuracy, long-term monitoring, and minimal invasiveness. Inspired by the feature and functions of animal masticatory system, we presented a biomimetic microneedle theranostic platform (MNTP) for intelligent and precise management of diabetes. The MNTP was supported by a miniatured circuit, which used microneedle arrays for on-demand skin penetration, enabling interstitial fluid exudation for simultaneous detection of glucose and physiological ions, and subcutaneous insulin delivery. Interstitial fluid exudation enabled sensing in oxygen-rich environment via the incorporated epidermal sensor functionalized with hybrid carbon nanomaterials. This feature addressed the biosafety issues due to implanted electrodes and the "oxygen-deficit" issues in vivo. The MNTP was demonstrated to accurately detect glucose and ions and deliver insulin to regulate hyperglycemia. The biomimetic and intelligent features of the MNTP endowed it as a highly advanced system for diabetes therapy.

DFTrans: Dual Frequency Temporal Attention Mechanism-Based Transportation Mode Detection.

In recent years, with the diversification of people's modes of transportation, a large amount of traffic data is generated when people travel every day, and this data can help transportation mode detection to be of great use in a variety of applications. Although transportation mode detection has been investigated, there are still challenges in terms of accuracy and robustness. This paper presents a novel transportation mode detection algorithm, DFTrans, which is based on Temporal Block and Attention Block. Low- and high-frequency components of traffic sequences are obtained using discrete wavelet transforms. A two-channel encoder is carefully designed to accurately capture the temporal and spatial correlation between low- and high-frequency components in both long- and short-term patterns. With the Temporal Block, the inductive bias of the CNN is introduced at high frequencies to improve generalization performance. At the same time, the network is generated with the same length as the input, ensuring a long effective history. Low frequencies are passed through Attention Block, which has fewer parameters to capture the global focus and solves the problem that RNNs cannot be computed in parallel. After fusing the output of the feature by Temporal Block and Attention Block, the classification results are output by MLP. Extensive experimental results show that the DFTrans algorithm achieves macro F1 scores of 86.34% on the real-world SHL dataset and 87.64% on the HTC dataset. Our model can better identify eight modes of transportation, including stationary, walking, running, cycling, bus, car, underground, and train, and has better performance in transportation mode detection than other baseline algorithms.

The Hilti SLAM Challenge Dataset

Research in Simultaneous Localization and Mapping (SLAM) has made outstanding progress over the past years. SLAM systems are nowadays transitioning from academic to real world applications. However, this transition has posed new demanding challenges in terms of accuracy and robustness. To develop new SLAM systems that can address these challenges, new datasets containing cutting-edge hardware and realistic scenarios are required. We propose the Hilti SLAM Challenge Dataset. Our dataset contains indoor sequences of offices, labs, and construction environments and outdoor sequences of construction sites and parking areas. All these sequences are characterized by featureless areas and varying illumination conditions that are typical in real-world scenarios and pose great challenges to SLAM algorithms that have been developed in confined lab environments. Accurate sparse ground truth, at millimeter level, is provided for each sequence. The sensor platform used to record the data includes a number of visual, lidar, and inertial sensors, which are spatially and temporally calibrated. The purpose of this dataset is to foster the research in sensor fusion to develop SLAM algorithms that can be deployed in tasks where high accuracy and robustness are required, e.g., in construction environments. Many academic and industrial groups tested their SLAM systems on the proposed dataset in the Hilti SLAM Challenge. The results of the challenge, which are summarized in this paper, show that the proposed dataset is an important asset in the development of new SLAM algorithms that are ready to be deployed in the real-world.

Nanobiomimetic Medicine

AbstractThe application of nanotechnology in medicine aims at developing the precise theranostics of diseases by leveraging the extraordinary effects of engineered nanomedicines, materdicine, and biomaterials. However, finely controlling the biological behavior of nanomaterials in the complex living systems remains a great challenge in terms of accuracy and intelligence. Inspired by nature, biomimetics has become an attractive strategy based on the highly ordered natural biological structure for the development of clinically valuable materials and technologies, arising from the superior bioavailability. The rapid development of biomimetics in nanomedical applications prompts the authors to propose the concept of “nanobiomimetic medicine”, which is a considerable subdiscipline in nanomedicine and materdicine that applies the concept and strategies of biomimetics to facilitate and promote the disease theranostics. Herein, the authors aim to furnish a state‐of‐the‐art review on the latest progress in the field of nanobiomimetic medicine. The design strategies, structural features and biological properties of biomimetic materials are initially introduced to reveal the inherent bionic mechanism and the potential structure‐function relationships. Furthermore, advances with respect to the applications of diverse biomimetic materials are comprehensively summarized. Finally, the current challenges and future direction of nanobiomimetic medicine are discussed and prospected in order to stimulate more biomimetic fundamental and technological breakthroughs in nanomedicine.

Novel Force Measurement System for Soft Tissue Balance in Total Knee Arthroplasty Based on Flexible Pressure Sensor Arrays

Total knee arthroplasty (TKA) is a common treatment for terminal knee arthropathy. Soft tissue balance is one of the key factors affecting the success rate of TKA. However, current measurement systems still face great challenges in terms of accuracy and timeliness. Herein, a novel force measurement system based on a smart spacer is proposed to measure soft tissue balance in a timely and accurate manner. The smart spacer is designed according to the simulated results, where six flexible pressure sensors with a high sensitivity of 99.56 N−1 and a wide detection range of 50 N are attached to the spacer base to directly detect the soft tissue balance force. Moreover, a soft tissue balance measurement system is constructed, which can measure the force at different positions, such as the extension position (0°), the middle position (45°), and the flexion position (90°), and display them on the computer in a timely manner. This novel real‐time knee soft tissue balance measurement system provides a way for surgeons or knee joint replacement surgery robots to accurately evaluate soft tissue balance and paves the way for improving the success rate of TKA and the patient's postoperative rehabilitation.

A DEEP LEARNING FRAMEWORK TO IMPROVE CUSTOMER RETENTION

Customer retention is the most significant challenge going through the companies. Acquiring a new customer is a costly process, so organizations should keep their existing loyal customers to increase their profit and revenue and avoid customer churn. The deep learning techniques significantly impact improving and predicting customer retention. There are a lot of scientific papers that use traditional machine learning techniques to improve customer retention, but these techniques face many challenges in terms of accuracy. For this purpose, the research community began to use deep learning techniques to improve customer retention, and these techniques increased the accuracy. However, they did not focus on improving dataset quality. Therefore, this research aims to introduce a framework to improve customer retention in telecommunications companies by using deep learning techniques. In addition, this research focused on improving dataset quality using data preprocessing techniques, such as noise removal, fill null values, feature scaling (normalization, standardization), discretization, and dimensionality reduction to maximize the accuracy and get better results. The experiment is performed on a telecom dataset obtained from Kaggle called Cell2Cell. Our research achieved more accurate results, especially in predicting the loss of customers and improving customer retention by applying data quality techniques with Deep Neural Network (DNN). Our proposed model achieved good performance, demonstrating achieved 99.80% accuracy. The early identification of customers who are leaving the company and going to another vendor can assist the administration in offering them fantastic deals and lower pricing.

Stereo Vision-Based Relative Position and Attitude Estimation of Non-Cooperative Spacecraft

In on-orbit services, the relative position and attitude estimation of non-cooperative spacecraft has become the key issues to be solved in many space missions. Because of the lack of prior knowledge about manual marks and the inability to communicate between non-cooperative space targets, the relative position and attitude estimation system poses great challenges in terms of accuracy, intelligence, and power consumptions. To address these issues, this study uses a stereo camera to extract the feature points of a non-cooperative spacecraft. Then, the 3D position of the feature points is calculated according to the camera model to estimate the relationship. The optical flow method is also used to obtain the geometric constraint information between frames. In addition, an extended Kalman filter is used to update the measurement results and obtain more accurate pose optimization results. Moreover, we present a closed-loop simulation system, in which the Unity simulation engine is employed to simulate the relative motion of the spacecraft and binocular vision images, and a JetsonTX2 supercomputer is involved to conduct the proposed autonomous relative navigation algorithm. The simulation results show that our approach can estimate the non-cooperative target’s relative pose accurately.