DMR: disentangled and denoised learning for multi-behavior recommendation by Yijia Zhang, Wanyu Chen, Fei Cai, Zhenkun Shi, Feng Qi

“…First, the irrelevant auxiliary behaviors that do not align with the target behavior, can negatively impact the prediction accuracy for user preference in the target behavior. …”
Get full text

Calibrated Adaptive Teacher for Domain-Adaptive Intelligent Fault Diagnosis by Florent Forest, Olga Fink

“…Recent methods have relied on self-training with confident pseudo-labels for the unlabeled target samples. However, the confidence-based selection of pseudo-labels is hindered by poorly calibrated uncertainty estimates in the target domain, primarily due to over-confident predictions, which limits the quality of pseudo-labels and leads to error accumulation. …”
Get full text

Hybrid SARIMA+BO-LSTM Framework for Forecasting EV Adoption: A Road to Net-Zero in Ireland by Afaq Khattak, Brian Caulfield

“…To support the Climate Action Plan target of registering 945,000 electric vehicles (EVs) by 2030, this study develops a hybrid time series forecasting framework that combines a Seasonal Autoregressive Integrated Moving Average (SARIMA) model with a Bayesian Optimized Long Short-Term Memory (BO-LSTM) network. …”
Get full text

Comparing Volumetric-modulated Arc Therapy and Intensity-modulated Radiation Therapy for Hippocampus-sparing Whole-brain Radiotherapy: A Dosimetric Evaluation by Soumya Roy, Anirban Halder, Saumen Basu, Suman Joardar

“…Results and Discussion: On average, the hippocampal avoidance volume was 17 cm3, occupying 1.32% of the whole-brain planned target volume. …”
Get full text

Features of the arterial hypertension clinical course in patients with ischemic heart disease and atrial fibrillation. by M. I. Yalovenko, O. O. Khaniukov

“…Objective: to study the features of the AH clinical course, the nature of the target organs lesion in patients with ischemic heart disease with and without permanent form of atrial fibrillation. …”
Get full text

ANALISIS TERJEMAHAN TINDAK TUTUR MEMUJI (COMPLIMENT) PADA SUBTITLE FILM TWILIGHT SERIES DAN KUALITAS TERJEMAHANNYA by Wahyudi Wahyudi, M.R. Nababan, Tri Wiratno

“…The aims of the study are to analyze the translations of compliment in subtitle film Twilight Series  between source text (English) and target text (Indonesian). To identify classifications of compliment in source text and target text, to identify shifting type of compliment, to identify the translations techniques, and to describe translation quality result in target text subtitle film Twilight Series. …”
Get full text

Enhancing Few-Shot SAR Ship Recognition: Pseudospectrum Information Generation and Fusion by Gui Gao, WenXi Liu, Xi Zhang

“…The limited number of samples in synthetic aperture radar (SAR) ship datasets hampers the advancement of target recognition performance using deep learning. …”
Get full text

Adversarial patch defense algorithm based on PatchTracker by Zhenjie XIAO, Shiyu HUANG, Feng YE, Liqing HUANG, Tianqiang HUANG

“…The application of deep neural networks in target detection has been widely adopted in various fields.However, the introduction of adversarial patch attacks, which add local perturbations to images to mislead deep neural networks, poses a significant threat to target detection systems based on vision techniques.To tackle this issue, an adversarial patch defense algorithm based on PatchTracker was proposed, leveraging the semantic differences between adversarial patches and image backgrounds.This algorithm comprised an upstream patch detector and a downstream data enhancement module.The upstream patch detector employed a YOLOV5 (you only look once-v5) model with attention mechanism to determine the locations of adversarial patches, thereby improving the detection accuracy of small-scale adversarial patches.Subsequently, the detected regions were covered with appropriate pixel values to remove the adversarial patches.This module effectively reduced the impact of adversarial examples without relying on extensive training data.The downstream data enhancement module enhanced the robustness of the target detector by modifying the model training paradigm.Finally, the image with removed patches was input into the downstream YOLOV5 target detection model, which had been enhanced through data augmentation.Cross-validation was performed on the public TT100K traffic sign dataset.Experimental results demonstrated that the proposed algorithm effectively defended against various types of generic adversarial patch attacks when compared to situations without defense measures.The algorithm improves the mean average precision (mAP) by approximately 65% when detecting adversarial patch images, effectively reducing the false negative rate of small-scale adversarial patches.Moreover, compared to existing algorithms, this approach significantly enhances the accuracy of neural networks in detecting adversarial samples.Additionally, the method exhibited excellent compatibility as it does not require modification of the downstream model structure.…”
Get full text

Research on 3D Obstacle Avoidance Path Planning for Apple Picking Robotic Arm by Xinyan Chen, Chun Lu, Ziliang Guo, Chengkai Yin, Xuanbo Wu, Xiaolan Lv, Qing Chen

“…In the 3D simulation, compared to RRT* and IRRT*, the average path cost is reduced by 1110.17 mm and 469.97 mm and the average search time is reduced by 37.82 s and 11.26 s. …”
Get full text

Gestural augmentation in facilitating tense marker use: a pre-post comparison by Sneha Roslyn Shaji, Divya M Vernekar, Amulya P Rao

“…A case study design was employed as the intention was to bring in improvement in the target behaviour and not the efficacy of the gestural augmentation. …”
Get full text

FUZZY LOGIC APPLICATION ON EMPLOYEE ACHIEVEMENT ASSESSMENT (CASE STUDY: EDUCATION QUALITY ASSURANCE INSTITUTE OF MALUKU PROVINCE) by Nurhidayah Nurhidayah, Yopi Andry Lesnussa, Zeth Arthur Leleury

“…The value of employee achievement is determined by 60% of the target value of employee achievement and 40% of the average employee behavior value consisting of service orientation, integrity, commitment, discipline, and cooperation. …”
Get full text

Methods of Sparse Measurement Matrix Optimization for Compressed Sensing by Renjie Yi, Shunan Han, Peng Liu, Bo Zhang, Hang Liu

“…The optimized sparse measurement matrix is formulated by minimizing the Frobenius norm of the difference between the Gram matrix of the sensing matrix and the target Gram matrix. First, the approach for updating the target Gram matrix is designed to reduce the maximal, average, and global coherence simultaneously. …”
Get full text

Hounsfield unit change in metastatic abdominal lymph nodes treated with combined hyperthermia and radiotherapy. by Young Kyu Lee, Kyu Hye Choi, Wonjoong Cheon, Bohyun Kim, In-Ho Kim, Young-Nam Kang, HongSeok Jang

“…In the HTRT-treated group, the average HU value of the tumor was lower by 9.05%, with an average of -8.47 HU. …”
Get full text

Autonomous Obstacle Avoidance with Improved Deep Reinforcement Learning Based on Dynamic Huber Loss by Xiaoming Xu, Xian Li, Na Chen, Dongjie Zhao, Chunmei Chen

“…Specifically, in static environments, the Dynamic Huber-loss-based DRL framework achieves a 98.85% success rate with an optimized average path length of 10.73; in dynamic environments, it attains a 74.20% success rate with an average path length of 37.04; adding wind disturbances in a dynamic environment, it attains a 70.95% success rate with an average path length of 40.40, highlighting its enhanced performance and adaptability.…”
Get full text

Reduction of Energy Consumption in Mobile Cloud Computing by ‎Classification of Demands and Executing in Different Data Centers by H. Yeganeh, A. Salahi, M. A Pourmina

“…The time average cost is at most O(1/V) above the optimum target, while the average queue size is O(V). …”
Get full text

INVESTIGATION INTO THE EFFECT OF ORGANIZATIONAL SILENCE ON EMOTIONAL LABOUR AMONG NURSES by Demet Ünalan, Buket Kaya

“…The average value of the proactive silence subscale of those working in the profession for 22 years and above was significantly higher than the average value of the forceful silence subscale of those working in the job between 0 – 10 years.…”
Get full text

Effective Estimation of Hourly Global Solar Radiation Using Machine Learning Algorithms by Abdurrahman Burak Guher, Sakir Tasdemir, Bulent Yaniktepe

“…In estimate modelling on selected target locations, various computer-based and experimental methods and techniques are employed. …”
Get full text

Development of a multi-level feature fusion model for basketball player trajectory tracking by Tao Wang

“…The research results indicated that in the object detection experiment, the detection time of the proposed object detection algorithm was always below 0.4 s, and its average accuracy reached up to 0.63. In trajectory tracking testing, the final built tracking model had a multi-target tracking accuracy of up to 0.98, and its tracking overlap rate was as low as 0.02. …”
Get full text

Binocular stereo vision-based relative positioning algorithm for drone swarm by Qing Cheng, Yazhe Wang

“…Finally, the extracted feature points from UAVs are input into a binocular vision localization model to compute their three-dimensional coordinates. The average of the three-dimensional coordinates of all feature points is used to determine the three-dimensional position of the target UAV. …”
Get full text

Detection of Small-Sized Electronics Endangering Facilities Involved in Recycling Processes Using Deep Learning by Zizhen Liu, Shunki Kasugaya, Nozomu Mishima

“…The results show that the model’s average precision value reached 0.996. Then, the target was expanded to three categories of fire-causing items, including mobile batteries, heated tobacco (electronic cigarettes), and smartphones. …”
Get full text