Adversarial example defense algorithm for MNIST based on image reconstruction by Zhongyuan QIN, Zhaoxiang HE, Tao LI, Liquan CHEN

“…With the popularization of deep learning, more and more attention has been paid to its security issues.The adversarial sample is to add a small disturbance to the original image, which can cause the deep learning model to misclassify the image, which seriously affects the performance of deep learning technology.To address this challenge, the attack form and harm of the existing adversarial samples were analyzed.An adversarial examples defense method based on image reconstruction was proposed to effectively detect adversarial examples.The defense method used MNIST as the test data set.The core idea was image reconstruction, including central variance minimization and image quilting optimization.The central variance minimization was only processed for the central area of the image.The image quilting optimization incorporated the overlapping area into the patch block selection.Considered and took half the size of the patch as the overlap area.Using FGSM, BIM, DeepFool and C＆amp;W attack methods to generate adversarial samples to test the defense performance of the two methods, and compare with the existing three image reconstruction defense methods (cropping and scaling, bit depth compression and JPEG compression).The experimental results show that the central variance minimization and image quilting optimization algorithms proposed have a satisfied defense effect against the attacks of existing common adversarial samples.Image quilting optimization achieves over 75% classification accuracy for samples generated by the four attack algorithms, and the defense effect of minimizing central variance is around 70%.The three image reconstruction algorithms used for comparison have unstable defense effects on different attack algorithms, and the overall classification accuracy rate is less than 60%.The central variance minimization and image quilting optimization proposed achieve the purpose of effectively defending against adversarial samples.The experiments illustrate the defense effect of the proposed defense algorithm in different adversarial sample attack algorithms.The comparison between the reconstruction algorithm and the algorithm shows that the proposed scheme has good defense performance.…”
Get full text

Monte Carlo simulation of interferometric measurement and wavefront shaping under influence of shot noise and camera noise by Chunghyeong Lee, Jaeyeon Oh, Hakseok Ko, Mooseok Jang

“…In particular, we have focused on evaluating wavefront shaping fidelity under the influence of shot noise with practical considerations on the operation of digital image sensors, including readout noise, dark current noise, and digitization with finite bit-depth. Based on some exemplary simulation results, we provide practical guidance for setting up an interferometric measurement system for wavefront shaping applications.…”
Get full text

A Performance Analysis of Business Intelligence Techniques on Crime Prediction by Ivan, Niyonzima, Emmanuel Ahishakiye, Elisha Opiyo Omulo, Ruth Wario

“…Also the execution time in seconds of J48, Naïve bayes, Multilayer perceptron and SVO is 0.06, 0.14, 9.26 and 0.66 respectively using windows7 32 bit. Hence, Decision Tree (J48) out performed Naïve bayes, Multilayer perceptron and Support Vector Machine (SMO) algorithms, and manifested higher performance both in execution time and in accuracy. …”
Get full text

Design of an FPGA-Based High-Speed Data Acquisition System for Frequency Scanning Interferometry Long-Range Measurement by Sivagunalan Sivanathan, Mohammed Ali Roula, Kang Li, Dun Qiao, Nigel Joseph Copner

“…The hardware employs a 160-MS/s, 16-bit dual-channel ADC interfaced to the FPGA via a low-voltage differential signaling (LVDS). …”
Get full text

Vehicle Detection Algorithm Based on Embedded Video Image Processing in the Background of Information Technology by Rui Liang, Gaoqing Ji

“…Developers need to support complex configurations and various aspects, such as different resolutions/display sizes, different bit rates, real-time issues, and even the reliability of the video source. …”
Get full text

Experimental and Simulation Study on Breaking Rock under Coupled Static Loading and Ultrasonic Vibration by Yan Zhao, Congshan Zhang, Zengzeng Zhang, Ke Gao, Dajun Zhao, Zihang Sun, Xiaoshu Lv, Yu Zhou, Guobing Zhai

“…Under the same weight on bit (WOB), the penetration of rotary ultrasonic drilling can be increased by 13.93% ∼ 38.11% compared with conventional rotary drilling.…”
Get full text

Tourism planning and development: The case of Portugal’s Norte region by Ana Paula Lopes, Filomena Soares

“…Comparing the forecast values in terms of overnight stays, tourists and revenue set by PENT, the reality showed that the results were a little bit far from the expected; however, the findings confirm the common perception that Portugal’s Norte region is still experiencing a trend towards growth as a tourist destination.…”
Get full text

Experimental demonstration of 8190-km long-haul semiconductor-laser chaos synchronization induced by digital optical communication signal by Anbang Wang, Junli Wang, Lin Jiang, Longsheng Wang, Yuncai Wang, Lianshan Yan, Yuwen Qin

“…Results show that high-quality synchronization can be achieved as the drive signal rate is larger than the laser relaxation frequency and the transmission bit error ratio is below a critical value. Chaos synchronization over 8191-km fiber transmission was experimentally achieved. …”
Get full text

Optimal reception of multiple phase shift keying and quadrature amplitude modulation signals with non-coherent processing of harmonic interference by G. V. Kulikov, T. T. Do, A. A. Lelyukh, V. D. Nguyen

“…The dependences of the bit error probability on the signal-to-noise ratio, interference detuning, and inaccuracy in setting the frequency and level of the interference sample in the receiver were obtained. …”
Get full text

Machine Learning Approach to Predict the DC Bias for Adaptive OFDM Transmission in Indoor Li-Fi Applications by Marwah T. Salman, David R. Siddle, Amadi G. Udu

“…These biased signals are clipped according to optical power constraints, imposing clipping noise that affects the transmission bit error rate (BER). This performance degradation is conditioned by the adjustments made to the DC bias, which requires continuous modification to support adaptive transmission. …”
Get full text

Reactive dye extraction utilizing regenerated bleaching earth by M. Shahi, M.R. Sabour, G.A. Dezvareh

“…This removal efficiency is a bit higher than activated virgin bleaching earth and much higher than virgin bleaching earth, which has adsorption capacities of 66.75% and 51.56%, respectively. …”
Get full text

Growth and bioactivity of Phellinus linteus in the mushroom farm, at different cultivation times by Jitchum Supapitch, Tabtimmai Lueacha, Phoohinkong Weerachon, Thumthanaruk Benjawan, Zhang Xiaoshuan, Suttisintong Khomson, Rungsardthong Vilai

“…PL growths at each location were not significantly different during 12 months, while a bit higher growth of PL at the Bottom zone was observed at 18 months. …”
Get full text

Preamble Design and Noncoherent ToA Estimation for Pulse-Based Wireless Networks-on-Chip Communications in the Terahertz Band by Pankaj Singh, Sung-Yoon Jung

“…Recent advancements highlight the potential of the terahertz (THz) band, a largely untapped frequency range, for enabling ultrafast tera-bit-per-second links in chip multiprocessors. However, the ultrashort duration of THz pulses, often in the femtosecond range, makes synchronization a critical challenge, as even minor timing errors can cause significant data loss. …”
Get full text

Optimal Nozzle Structure for an Abrasive Gas Jet for Rock Breakage by Yong Liu, Juan Zhang, Tao Zhang, Huidong Zhang

“…By combining aerodynamics and by fixing the condition of the nozzle in the drill bit, we design four types of preliminary nozzles. …”
Get full text

Strategies for enhancing deep video encoding efficiency using the Convolutional Neural Network in a hyperautomation mechanism by Xiaolan Wang

“…The results demonstrate that, compared to the original test platform method (HTM-16.2), the proposed method achieves an average Bjøntegaard delta bit rate (BDBR) savings of 8.12% across all tested video sequences. …”
Get full text

The role of GPT in promoting inclusive higher education for people with various learning disabilities: a review by Thippa Reddy Gadekallu, Gokul Yenduri, Rajesh Kaluri, Dharmendra Singh Rajput, Kuruva Lakshmanna, Kai Fang, Junxin Chen, Wei Wang

Get full text

Noise Cancellation Method for Mud Pulse Telemetry Based on Discrete Fourier Transform by Jingchen Zhang, Zitong Sha, Xingbin Tu, Zhujun Zhang, Jiang Zhu, Yan Wei, Fengzhong Qu

“…The field experiment results demonstrate that the demodulation of the received data achieves advanced data rate communication and a low bit error rate (BER) in a 3000 m drilling system.…”
Get full text

Review of Adaptive Cell Selection Techniques in LTE-Advanced Heterogeneous Networks by M. A. Gadam, Maryam Abdulazeez Ahmed, Chee Kyun Ng, Nor Kamariah Nordin, Aduwati Sali, Fazirulhisyam Hashim

“…Moreover, more accurate cell load estimation is obtained in the extended RBUR adaptive CRE bias technique through constant bit rate (CBR) traffic, which further improved load balancing as against the estimation based on the number of user equipment (UE). …”
Get full text

CDMA/OTFS Sensing Outperforms Pure OTFS at the Same Communication Throughput by Hugo Hawkins, Chao Xu, Lie-Liang Yang, Lajos Hanzo

“…Hence, this work characterises both the communication Bit Error Rate (BER) and sensing Root Mean Square Error (RMSE) performance of Code Division Multiple Access OTFS (CDMA/OTFS), and contrasts them to pure OTFS. …”
Get full text

A deep transfer learning based convolution neural network framework for air temperature classification using human clothing images by Maqsood Ahmed, Xiang Zhang, Yonglin Shen, Nafees Ali, Aymen Flah, Mohammad Kanan, Mohammad Alsharef, Sherif S. M. Ghoneim

“…The framework incorporates various deep transfer learning approaches, including DeepLabV3 Plus for semantic segmentation and others for classification such as BigTransfer (BiT), Vision Transformer (ViT), ResNet101, VGG16, VGG19, and DenseNet121. …”
Get full text