Analysis of damage control of thin plate with piezoelectric actuators using finite element and machine learning approach by Asraar Anjum, Abdul Aabid, Meftah Hrairi

“…To optimize performance, we utilized machine learning algorithms to examine how these characteristics affect the repair process. …”
Get full text

In-Network Filtering Schemes for Type-Threshold Function Computation in Wireless Sensor Networks by Guillermo G. Riva, Jorge M. Finochietto

“…Both of them are based on the integration of metaheuristics and learning algorithms inspired by nature. In particular, we consider the computation of the maximum function as case study for these schemes. …”
Get full text

A security detection approach based on autonomy-oriented user sensor in social recommendation network by Shanshan Wan, Ying Liu

“…Then, AOUSD is first simulated on NetLogo and it is compared with other algorithms based on the Amazon data. The results prove the advantages of AOUSD in the efficiency and accuracy on shilling attack detection.…”
Get full text

Research on nanosecond time synchronization technology for 5G base station based on GNSS neighborhood similarity by Wenxue LIU, Shijun CHEN, Jian GE, Hong YUAN, Cuiling GONG

“…For precision positioning requirements in the LTE-A/5G service developed by the 3GPP,the nanosecond precision time synchronization technology based on global navigation satellite system (GNSS) for 5G base station was studied which broke through the current GNSS receiver’s hundred nanosecond timing accuracy.By analyzing the characteristics of neighborhood similarity of GNSS errors and combining the characteristics of time synchronization requirements of 5G base stations,a nanosecond precision time synchronization theory and related receiver algorithms for 5G base stations was proposed which based on the principle of neighborhood similarity of GNSS signals.The specific characteristics of the time synchronization technology under regional and wide-area conditions were studied.The simulation and experimental results show that compared with the current time synchronization accuracy within hundred nanosecond rang of base stations,the proposed method can achieve precision time synchronization within 3 ns between the regional base stations,and support 5G base station meter-level precision location based service(LBS) and other advanced incremental services.…”
Get full text

Bulk Handling Facility Modeling and Simulation for Safeguards Analysis by Benjamin B. Cipiti, Nathan Shoman

“…Machine learning techniques are being applied, but these techniques need large amounts of data for training and testing the algorithms. The SSPM can provide that training data. …”
Get full text

Multi-function supported privacy protection data aggregation scheme for V2G network by Baiji HU, Xiaojuan ZHANG, Yuancheng LI, Rongxin LAI

“…In view of the problem that the functions of the current privacy protection data aggregation scheme were insufficient to meet the increasingly rich application requirements, a multi-function supported privacy protection data aggregation (MFPDA) scheme for V2G network was proposed.By using cryptographic algorithms such as BGN, BLS, and Shamir’s secret sharing, as well as fog computing and consortium blockchain technology, multiple security functions like fault tolerance, resistance to internal attacks, batch signature verification, no need for trusted third parties, and multiple aggregation functions were integrated into one privacy protection data aggregation scheme.Security analysis shows that the proposed scheme can protect data aggregation’s security, privacy and reliability.The performance evaluation shows that the introduction of fog computing can significantly reduce the computing overhead of the control center, and the reduction rate can be as high as 66.6%; the improvement of the consortium blockchain can effectively reduce the communication and storage overhead of the system, and the reduction rate can reach 16.7% and 24.9% respectively.…”
Get full text

Research on Strategies and Technologies for Resource Management and Control of Heterogeneous Network of High and Low Orbit Satellites by Meirong ZHANG, Mengting HAO, Chuang WANG, Gengxin ZHANG

“…With the vigorous development of space communication technology and the continuous advancement of space-integrated-ground information network, satellite communication networks resource management and control is becoming more and more complex.Due to the scarcity of satellite resources, the slowness of resource scheduling compared to the status refreshing, and uneven distribution of business, eff ciently managing resources has become one of urgent problems to be solved in the development of satellite communications.In view of the heterogeneous network system architecture of high and low orbit satellites, the challenges, its network resource management and control facing, were analyzed.Integrating on the basis of traditional management and control architecture, the collaborative management and control architecture based on group management was introduced.The management strategy of satellite network virtual resource pool was explained to relieved resources scarcity.Resource scheduling algorithms based on deep reinforcement learning(DRL) was introduced to solved the mismatch problem of traditional scheduling methods in complex environments.Beam-hopping technology was adopted to deal with the two-dimensional unevenness of service distribution in time and space.…”
Get full text

Recommendations for the Development of Artificial Intelligence Applications for the Retail Level by Jim Hartman

“…Because this paradigm shift is less familiar to food safety professionals, a comparison between pattern recognition algorithms and cognitive models is offered. An explanation of cognitive models is included to raise awareness of this approach.…”
Get full text

RADENN: A Domain-Specific Language for the Rapid Development of Neural Networks by Israel Pineda, Dustin Carrion-Ojeda, Rigoberto Fonseca-Delgado

“…The primary objective of this language is to make neural network algorithms more accessible to a broader audience. RADENN is built on top of Keras API with Tensorflow as its back-end. …”
Get full text

Data Mining Classification Techniques for Diabetes Prediction by Hindreen Rashid Abdulqadir, Adnan Mohsin Abdulazeez, Dilovan Assad Zebari

“…Many analyses include multiple Machine Learning algorithms for various disease assessments and predictions to improve overall issues. …”
Get full text

Mounting Angle Prediction for Automotive Radar Using Complex-Valued Convolutional Neural Network by Sunghoon Moon, Younglok Kim

“…The predicted offsets can then be used for physical radar alignment or integrated into compensation algorithms to enhance data interpretation accuracy in ADAS applications. …”
Get full text

SAMPLING OF THE PLAN OF REPAIRS OF THE MAIN EQUIPMENT IN THE ELECTRICAL POWER SYSTEM by O. I. Alexandrov

“…The main problems that hinder mathematical modeling of decision-making concerning operational applications for the repair of the main power equipment of power system are: the need for a coherent account of a large number of limiting factors and indicators of effectiveness of the solutions; the need of information and algorithmic trade-offs with the objectives of adjacent levels of spatial, temporal and functional hierarchy; the lack of developments in the standardization of information structures that adequately reflect the process of finding solutions; the computational complexity of several restrictions of the optimization problem subject to mandatory registration.…”
Get full text

Research on Load Balancing and Caching Strategy for Central Network by Zhi-hong Wang, A-liang Dong

“…By analyzing the load scheduling requirements of network nodes, combined with the transmission characteristics of resource requests in the central network, a cache node load balancing method suitable for the requirements of the central network was proposed based on the existing load balancing algorithms. In addition, by analyzing the cache management strategy and its impact on the performance of the network system, a cache node information forwarding model with resource requests as the object in the central network environment was given. …”
Get full text

Machine learning for predicting earthquake magnitudes in the Central Himalaya by Ram Krishna Tiwari, Rudra Prasad Poudel, Harihar Paudyal

“…The findings illustrate that RFR is achieving better performance than the other two algorithms, as the predicted magnitudes are close to the actual magnitudes. …”
Get full text

Big Data Approach to Sentiment Analysis in Machine Learning-Based Microblogs: Perspectives of Religious Moderation Public Policy in Indonesia by Mhd. Furqan, Ahmad Fakhri Ab. Nasir

“…Sentiment analysis was conducted on three primary microblogs such as Twitter, Instagram and YouTube using six machine learning algorithms. These include Naïve Bayes, Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Bagging Classifier, Random Forest, and Gradient Boosting Classifier. …”
Get full text

A System for Sentiment Analysis of Colloquial Arabic Using Human Computation by Afnan S. Al-Subaihin, Hend S. Al-Khalifa

“…The game produces necessary linguistic resources that will be used by the second component which is the sentimental analyzer. Two different algorithms have been designed to employ these linguistic resources to analyze text and classify it according to its sentimental polarity. …”
Get full text

Driver anomaly detection in cargo terminal by Shahab Emaani, Abbas Saghaei

“…Subsequently, Isolation Forest, KNN, and HBOS algorithms are applied to detect abnormal behavior using data mining techniques. …”
Get full text

Viral Justice: TikTok Activism, Misinformation, and the Fight for Social Change in Southeast Asia by Nuurrianti Jalli

“…However, they also face significant challenges, including rampant harassment and the precarious nature of algorithmic visibility. The study highlights the complexities of digital activism, where the pursuit of virality can sometimes undermine the depth of political movements. …”
Get full text

A network intrusion detection method designed for few-shot scenarios by Weichen HU, Congyuan XU, Yong ZHAN, Guanghui CHEN, Siqing LIU, Zhiqiang WANG, Xiaolin WANG

“…Existing intrusion detection techniques often require numerous malicious samples for model training.However, in real-world scenarios, only a small number of intrusion traffic samples can be obtained, which belong to few-shot scenarios.To address this challenge, a network intrusion detection method designed for few-shot scenarios was proposed.The method comprised two main parts: a packet sampling module and a meta-learning module.The packet sampling module was used for filtering, segmenting, and recombining raw network data, while the meta-learning module was used for feature extraction and result classification.Experimental results based on three few-shot datasets constructed from real network traffic data sources show that the method exhibits good applicability and fast convergence and effectively reduces the occurrence of outliers.In the case of 10 training samples, the maximum achievable detection rate is 99.29%, while the accuracy rate can reach a maximum of 97.93%.These findings demonstrate a noticeable improvement of 0.12% and 0.37% respectively, in comparison to existing algorithms.…”
Get full text

Comparative Analysis of Diabetes Prediction Models Using the Pima Indian Diabetes Database by Zhao Yize

“…In comparison, the random forest model, which builds multiple decision trees (DT) to do their predictions, demonstrates superior performance over several widely used algorithms such as K-Nearest Neighbours (KNN), Logistic Regression (LR), DT, Support Vector Machines (SVM), and Gradient Boosting (GB). …”
Get full text