Compressed Sensing in On-Grid MIMO Radar by Michael F. Minner

“…Relying upon standard far-field and narrowband assumptions, we analyze the efficacy of various recovery algorithms in determining the parameters of the scene through numerical simulations, with particular focus on the l1-squared Nonnegative Regularization method.…”
Get full text

Collaborative offloading computing scheme based on energy harvesting technology by WANG Jun, ZHAO Haodong

“…To solve this problem, a task offloading framework that combined energy harvesting and device-to-device (D2D) communication technology was proposed, using a deep reinforcement learning (DRL)-based edge collaborative offloading computing scheme to make autonomous decisions and solve resource allocation problems using simulated annealing algorithms to minimize the total cost of system operation. …”
Get full text

Encoding Cryptic Crossword Clues with TEI by Martin Holmes

“…Finally, I present a TEI schema and an approach to encoding the components of cryptic crossword clues in a way that enables algorithmic analysis of trends, features, and clue types, with a view to creating a historical corpus of encoded clues which will illuminate the evolution of the tradition.…”
Get full text

CYBERPUNK – GAME – POETRY: Rostislav Amelin’s “SimStab” by Daniil Leiderman, Mark Lipovetsky

“…Thus, in “SimStab” the ludic algorithmic with its procedural rhetoric (Ian Bogost) creates spaces of formlessness which repeats the liberatory promise of cyberpunk literature. …”
Get full text

A Review of Bias and Fairness in Artificial Intelligence by Rubén González-Sendino, Emilio Serrano, Javier Bajo, Paulo Novais

“…As a result, a new field of research on algorithmic fairness has emerged. In this area, detecting biases and mitigating them is essential to ensure fair and discrimination-free decisions. …”
Get full text

Preconditioning Filter Bank Decomposition Using Structured Normalized Tight Frames by Martin Ehler

“…We start with a given generalized frame whose elements allow for fast matrix vector multiplication, as, for instance, convolution operators, and compute a normalized tight frame, for which signal analysis and synthesis still preserve those fast algorithmic schemes.…”
Get full text

Realistic challenges and path options for the high-quality development of smart stadiums in China by Shaoquan Chu

“…The study finds that the problems of high-quality construction of smart stadiums in China include: information technology treats the masses as a tame object and a test object for the safety valve, there is a paradox between algorithmic "de-deviation" and "personalised" sports services, and there is a lack of product standards and construction standards for smart stadium facilities. …”
Get full text

Convergence Analysis Hilbert Space Approach for Fuzzy Integro-Differential Models by Jingwen Zhang

“…Separate evaluations are made of the algorithms’ correctness and sloppiness, as well as their foundations in the computationally effective kernel Hilbert space, which has been extensively researched in the past. …”
Get full text

Assessment of Human Sperm Kinematic Parameters Using Computer-Assisted Semen Analysis by Nazlı Irmak Karaark, Hüseyin Kurtuldu

“…This study presents a novel computer-assisted sperm analysis (CASA) system designed to evaluate sperm motility through digital micrographs, utilizing 14 distinct kinematic parameters. The algorithms and parameters developed offer a quantitative approach to characterizing infertility.…”
Get full text

Design and Construction of an Interactive Intelligent Learning System for English Learners in Higher Education Institutions by Ping Chen

“…This paper proposes an interactive intelligent learning system based on artificial intelligence algorithms. This new English teaching system with the interaction theory realizes the transformation of a new student-centered teaching mode, which is a great contribution to English classroom learning in higher education institutions.…”
Get full text

Mega LEO Satellite Constellations Networking: Challenges and Key Technologies by SUN Yaohua, FENG Xinao, PENG Mugen

“…In light of these features, this paper first summarized the challenges of mega LEO constellations networking from five aspects: constellation design, protocol integration, topology representation, routing algorithms, and network simulation. It then introduced the key technologies for mega constellation networking, included network architecture, protocol design, network addressing, inter-satellite link establishment, and fault recovery, and provided outlooks on their development directions, aimed to offer references for the construction of Chinese satellite Internet.…”
Get full text

Identification of Important Genes of Keratoconus and Construction of the Diagnostic Model by Lin Wang, Yuqing Wang, Juan Liu, Wencheng Zhao

“…Through the LASSO, RFE, and RF algorithms and comparing the three sets of DEGs, a total of 8 overlapping DEGs were obtained. …”
Get full text

Deep Learning Model for Predicting Spreading Rates of Pandemics, “COVID-19 as Case Study” by Maha A. Al-Bayati

“…A hybrid approach is presented where two deep learning algorithms; LSTM and GRU are brought up together to achieve good prediction with rewarding levels of (MAE = 0.109), (MAPE = 0.191) and (RMSE = 0.134).…”
Get full text

Robust multi-dimensional trust model for improving the survivability of ad hoc networks by CHEN Shen-long1, ZHANG Yu-qing1

“…Attackers could perform the blended attack against ad hoc networks through utilizing several attack methods together.Under this circumstance,a robust multi-dimensional trust model（RMTM） to improve the survivability of ad hoc networks was proposed.RMTM was based on D-S theory.Nodes’ attack evidences were classified into several dimen-sions and the trust of each dimension was computed according to basic probability assignment function.Then RMTM implemented the comprehensive evaluation through the multi-dimensional trust fusion.In order to resist the attacks against trust models themselves,the corresponding tolerant algorithms were designed to enhance the RMTM’s robustness.The simulations show that RMTM can effectively defense against both ad hoc network blended attack and trust model attacks with limited overload and consequently it significantly improves the survivability of ad hoc networks.…”
Get full text

Personalized recommendation model with multi-level latent features by Qing SHEN, Wenbin GUO, Jungang LOU, Qiangguo YU

“…Personalized recommendation has become one of the most effective means to solve information overload, and it is also a hot technology in the research field of massive data mining.However, traditional recommendation algorithms often only use the user’s rating information on the item, and lack a comprehensive consideration of the potential characteristics of the user and the item.The factorization machine, wide neural network, crossover network and deep neural network were combined to extract the shallow latent features, low-order nonlinear latent features, linear cross latent features, and high-order nonlinear latent features of users and items.Thus, a new deep learning personalized recommendation model with multilevel latent features was established.The experimental results on four commonly used data sets show that considering the multi-level potential features of users and items can effectively improve the prediction accuracy of personalized recommendations.Finally, the influence of factors such as the dimensions of the embedding layer and the number of neurons on the prediction performance of the new model was studied.…”
Get full text

Malicious DNS traffic detection based neural networks by SHAN Kangkang, YUAN Shuhong, CHEN Wenzhi, WANG Zhibo

“…To solve the problems of low detection accuracy and speed caused by low efficiency in extracting traffic features using machine learning to detect malicious DNS traffic, a malicious DNS traffic detection method FDS-DL was proposed, which combines frequency domain feature aggregation analysis and neural networks algorithms. Firstly, DNS traffic was converted from time-domain space to frequency-domain space through discrete Fourier transform, which could significantly compress the data scale while retaining key log information. …”
Get full text

Method for Creating Domain-Specific Dataset Ontologies from Text in Uncontrolled English by Minab Shokoufeh Salem, Nazaruka Erika

“…The prominent technologies for implementation of the proposed method are machine learning, including classification algorithms and natural language processing using a large language model. …”
Get full text

Linear and Nonlinear Schemes Applied to Pitch Control of Wind Turbines by Hua Geng, Geng Yang

“…Although nonlinear algorithms can be implemented in a powerful digital processor nowadays, they need time to be accepted by the industry and their reliability needs to be verified in the commercial products. …”
Get full text

The tumour histopathology "glossary" for AI developers. by Soham Mandal, Ann-Marie Baker, Trevor A Graham, Konstantin Bräutigam

“…By providing this essential knowledge to the computational community, we aim to accelerate the development of AI algorithms for cancer research.…”
Get full text

Policy conflict detection in software defined network by using deep learning by Chuanhuang LI, Cheng CHENG, Xiaoyong YUAN, Lijie CEN, Weiming WANG

“…In OpenFlow-based SDN(software defined network),applications can be deployed through dispatching the flow polices to the switches by the application orchestrator or controller.Policy conflict between multiple applications will affect the actual forwarding behavior and the security of the SDN.With the expansion of network scale of SDN and the increasement of application number,the number of flow entries will increase explosively.In this case,traditional algorithms of conflict detection will consume huge system resources in computing.An intelligent conflict detection approach based on deep learning was proposed which proved to be efficient in flow entries’ conflict detection.The experimental results show that the AUC (area under the curve) of the first level deep learning model can reach 97.04%,and the AUC of the second level model can reach 99.97%.Meanwhile,the time of conflict detection and the scale of the flow table have a linear growth relationship.…”
Get full text