Computer Science, Software Engineering

Proceedings Paper Computer Science, Artificial Intelligence

YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Chien-Yao Wang, Alexey Bochkovskiy, Hong-Yuan Mark Liao

Summary: Real-time object detection is an important research topic in computer vision, and the development of new approaches in architecture optimization and training optimization has led to two related research topics. To address these topics, a trainable solution combining flexible and efficient training tools, proposed architecture, and compound scaling method is proposed. YOLOv7 outperforms all known object detectors in terms of speed and accuracy, achieving the highest AP accuracy of 56.8% among real-time object detectors with 30 FPS or higher on GPU V100.

2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR (2023)

Article Computer Science, Software Engineering

X-Net: a dual encoding-decoding method in medical image segmentation

Yuanyuan Li, Ziyu Wang, Li Yin, Zhiqin Zhu, Guanqiu Qi, Yu Liu

Summary: This paper proposes a dual encoding-decoding structure of X-shaped network (X-Net) that integrates the characteristics of CNNs and Transformer. It can serve as a good alternative to the traditional pure convolutional medical image segmentation network.

VISUAL COMPUTER (2023)

Article Computer Science, Information Systems

CCAFNet: Crossflow and Cross-Scale Adaptive Fusion Network for Detecting Salient Objects in RGB-D Images

Wujie Zhou, Yun Zhu, Jingsheng Lei, Jian Wan, Lu Yu

Summary: This paper proposes a crossflow and cross-scale adaptive fusion network (CCAFNet) for detecting salient objects in RGB-D images. The network effectively fuses depth and high-level RGB features through channel fusion and spatial fusion modules, extracting accurate semantic and spatial information. Experimental results show that the performance of CCAFNet is comparable to state-of-the-art RGB-D SOD models.

IEEE TRANSACTIONS ON MULTIMEDIA (2022)

Article Computer Science, Information Systems

DisCOV: Distributed COVID-19 Detection on X-Ray Images With Edge-Cloud Collaboration

Xiaolong Xu, Hao Tian, Xuyun Zhang, Lianyong Qi, Qiang He, Wanchun Dou

Summary: In this paper, a distributed COVID-19 detection model training method called DisCOV is proposed, which utilizes edge-cloud collaboration to improve training efficiency and model accuracy. The use of lightweight models and resource allocation algorithm has shown promising results compared to existing baselines.

IEEE TRANSACTIONS ON SERVICES COMPUTING (2022)

Article Computer Science, Information Systems

Deep Learning-based Smart Predictive Evaluation for Interactive Multimedia-enabled Smart Healthcare

Zhihan Lv, Zengchen Yu, Shuxuan Xie, Atif Alamri

Summary: This study prepared two-dimensional bi-component structures consisting of cobalt and permalloy elliptical dots and investigated the frequency dependence of thermally excited magnetic eigenmodes. It also developed an interactive smart healthcare prediction and evaluation model based on deep learning, which showed higher accuracy and smaller error in performance.

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS (2022)

Article Computer Science, Information Systems

Task offloading strategy with emergency handling and blockchain security in SDN-empowered and fog-assisted healthcare IoT

Junyu Ren, Jinze Li, Huaxing Liu, Tuanfa Qin

Summary: This article introduces a smart healthcare application based on wireless body area networks using fog computing, software-defined networking, and blockchain. It includes strategies for task offloading, security, and blockchain sharding. Extensive simulation experiments have been conducted to validate the superior performance of the proposed methods.

TSINGHUA SCIENCE AND TECHNOLOGY (2022)

Article Computer Science, Software Engineering

A multibranch CNN-BiLSTM model for human activity recognition using wearable sensor data

Sravan Kumar Challa, Akhilesh Kumar, Vijay Bhaskar Semwal

Summary: This paper proposes a hybrid CNN-BiLSTM network for HAR, which automatically extracts features from raw sensor data and allows the model to learn local features and long-term dependencies. Different filter sizes capture various temporal local dependencies to improve the feature extraction process. Experiment results show that the proposed model outperforms other methods with high accuracies on benchmark datasets.

VISUAL COMPUTER (2022)

Article Computer Science, Information Systems

Fast and Secure Data Accessing by Using DNA Computing for the Cloud Environment

Suyel Namasudra

Summary: This article proposes a novel DNA computing based secure and fast Access Control Model (ACM) to improve data security and solve access control issues in a cloud environment. The theoretical analysis and experimental results demonstrate the efficiency and effectiveness of the proposed model over some well-known existing models.

IEEE TRANSACTIONS ON SERVICES COMPUTING (2022)

Article Computer Science, Hardware & Architecture

Understanding Node Capture Attacks in User Authentication Schemes for Wireless Sensor Networks

Chenyu Wang, Ding Wang, Yi Tu, Guoai Xu, Huaxiong Wang

Summary: Despite years of research, designing a practical multi-factor user authentication scheme for wireless sensor networks is still challenging due to the security versus efficiency dilemma. Common security failures include smart card loss attacks and node capture attacks, with the latter receiving less attention compared to the former. This article systematically explores node capture attacks, providing insights for secure user authentication scheme design in WSNs.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING (2022)

Article Computer Science, Software Engineering

RefactoringMiner 2.0

Nikolaos Tsantalis, Ameya Ketkar, Danny Dig

Summary: Refactoring detection is essential for various applications and tasks, but the accuracy of existing refactoring mining tools has been questioned. Most tools rely on code similarity thresholds, and finding universal threshold values for all projects is challenging. Researchers have introduced a refactoring mining tool that does not require code similarity thresholds and extended it to support low-level refactorings within method bodies. Evaluation results demonstrate that this approach achieves high precision and recall, and is significantly faster than other competitive tools.

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING (2022)

Article Computer Science, Software Engineering

Collaborative Work in Augmented Reality: A Survey

Mickael Sereno, Xiyao Wang, Lonni Besancon, Michael J. Mcguffin, Tobias Isenberg

Summary: This paper presents the state of existing work at the intersection of augmented reality and computer-supported collaborative work (AR-CSCW), categorizing 65 papers and deriving design considerations for collaborative AR environments. It also identifies under-explored research topics, providing useful information for newcomers, interested readers, and domain experts.

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS (2022)

Article Computer Science, Information Systems

A Two-stage Multi-population Genetic Algorithm with Heuristics for Workflow Scheduling in Heterogeneous Distributed Computing Environments

Yi Xie, Feng-Xian Gui, Wei-Jun Wang, Chen-Fu Chien

Summary: This study formulates the workflow scheduling problem in Heterogeneous Distributed Computing Environments (HDCEs) as an integer programming mathematical model, and proposes a novel two-stage multi-population genetic algorithm with heuristics for workflow scheduling. Extensive experiments show that the proposed algorithm outperforms conventional approaches in various scenarios.

IEEE TRANSACTIONS ON CLOUD COMPUTING (2023)

Article Computer Science, Information Systems

Apple leaf disease recognition method with improved residual network

Helong Yu, Xianhe Cheng, Chengcheng Chen, Ali Asghar Heidari, Jiawen Liu, Zhennao Cai, Huiling Chen

Summary: This paper proposes an MSO-ResNet apple leaf disease recognition model based on ResNet50, which improves the identification accuracy and speed of the model by optimizing the model structure and parameters. The experimental results demonstrate that the proposed model achieves high precision and fast recognition in leaf disease identification.

MULTIMEDIA TOOLS AND APPLICATIONS (2022)

Article Computer Science, Information Systems

A Semi-Centralized Trust Management Model Based on Blockchain for Data Exchange in IoT System

Yuan Liu, Chuang Zhang, Yu Yan, Xin Zhou, Zhihong Tian, Jie Zhang

Summary: This study proposes a semi-centralized trust management system architecture based on blockchain to support various applications and services with massive IoT devices. The IoT devices are centralized organized by cloud servers, which maintain a rating data ledger within each domain using the proposed rotation-based consensus protocol. A computational trust model is proposed to identify and mitigate the influence of malicious devices by aggregating direct and indirect trust information. Simulation experiments and comparisons with classical models demonstrate the effectiveness of the proposed trust model in identifying and mitigating the influence of malicious devices.

IEEE TRANSACTIONS ON SERVICES COMPUTING (2023)

Article Computer Science, Software Engineering

Deep Learning Based Vulnerability Detection: Are We There Yet?

Saikat Chakraborty, Rahul Krishna, Yangruibo Ding, Baishakhi Ray

Summary: This paper investigates the performance of state-of-the-art deep learning-based vulnerability prediction techniques in real-world scenarios and finds that their performance drops by more than 50 percent. The authors identify challenges with training data and model choices as the causes of this drop and propose a more principled approach to data collection and model design, leading to significantly improved solutions compared to existing methods.

IEEE TRANSACTIONS ON SOFTWARE ENGINEERING (2022)

Article Computer Science, Hardware & Architecture

Integration of fuzzy-weighted zero-inconsistency and fuzzy decision by opinion score methods under a q-rung orthopair environment: A distribution case study of COVID-19 vaccine doses

A. S. Albahri, O. S. Albahri, A. A. Zaidan, Alhamzah Alnoor, H. A. Alsattar, Rawia Mohammed, A. H. Alamoodi, B. B. Zaidan, Uwe Aickelin, Mamoun Alazab, Salem Garfan, Ibraheem Y. Y. Ahmaro, M. A. Ahmed

Summary: Due to limitations of Pythagorean fuzzy and intuitionistic fuzzy sets, a new fuzzy set called q-rung orthopair fuzzy set (q-ROFS) has been developed to address restrictions in multicriteria decision making (MCDM). This study extended two MCDM methods under q-ROFS, resulting in q-rung orthopair fuzzy-weighted zero-inconsistency (q-ROFWZIC) and q-rung orthopair fuzzy decision by opinion score method (q-ROFDOSM). The methodology involved two phases and was tested on a COVID-19 vaccine distribution case study, showing systematic ranking and sensitivity analysis results.

COMPUTER STANDARDS & INTERFACES (2022)

Article Computer Science, Interdisciplinary Applications

Mountain Gazelle Optimizer: A new Nature-inspired Metaheuristic Algorithm for Global Optimization Problems

Benyamin Abdollahzadeh, Farhad Soleimanian Gharehchopogh, Nima Khodadadi, Seyedali Mirjalili

Summary: This paper proposes a novel meta-heuristic algorithm called the Mountain Gazelle Optimizer (MGO), which is inspired by the social life and hierarchy of wild mountain gazelles. The MGO algorithm formulates the hierarchical and social life of gazelles mathematically to develop an optimization algorithm. It is evaluated and tested using standard benchmark functions and engineering problems, and compared with other meta-heuristic algorithms to validate its effectiveness. The experiments show that the MGO performs better than the comparable algorithms and maintains good performance even when increasing problem dimensions.

ADVANCES IN ENGINEERING SOFTWARE (2022)

Article Computer Science, Hardware & Architecture

A Collaborative V2X Data Correction Method for Road Safety

Liang Zhao, Hongmei Chai, Yuan Han, Keping Yu, Shahid Mumtaz

Summary: This article presents a collaborative vehicle data correction method for correcting V2X data errors to enhance driving safety. Experimental results demonstrate the effectiveness of the method in detecting and correcting erroneous data.

IEEE TRANSACTIONS ON RELIABILITY (2022)

Article Computer Science, Information Systems

Metaverse: Perspectives from graphics, interactions and visualization

Yuheng Zhao, Jinjing Jiang, Yi Chen, Richen Liu, Yalong Yang, Xiangyang Xue, Siming Chen

Summary: This study presents a framework for the visual construction and exploration of the metaverse and introduces graphics, interaction, and visualization techniques. It discusses current applications and future opportunities by classifying interaction technologies and visualization techniques.

VISUAL INFORMATICS (2022)

Article Computer Science, Software Engineering

Amplified locality-sensitive hashing-based recommender systems with privacy protection

Xiaoxiao Chi, Chao Yan, Hao Wang, Wajid Rafique, Lianyong Qi

Summary: With the increasing variety and volume of web services in the IoT age, this article proposes a unique amplified locality-sensitive hashing (LSH)-based service recommendation method, SRAmplified-LSH, to address the challenges of user privacy and efficient recommendation.

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE (2022)