Towards deep neural networks robust to adversarial examples by Matyasko, Alexander

“…We generalize a support vector machine (SVM) margin maximization objective to deep neural networks. …”
Get full text

Structured sparse representations for supervised and unsupervised learning by Zeng, Yijie

“…In this thesis, a discriminative dictionary learning approach is proposed for image classification which explicitly enforces the coding vectors to possess similar sparsity structure among the same class. …”
Get full text

CC meets FIPS : a hybrid test methodology for first order side channel analysis by Roy, Debapriya Basu, Bhasin, Shivam, Guilley, Sylvain, Heuser, Annelie, Patranabis, Sikhar, Mukhopadhyay, Debdeep

“…Common Criteria (CC) and FIPS 140-3 are two popular side channel testing methodologies. Test Vector Leakage Assessment Methodology (TVLA), a potential candidate for FIPS, can detect the presence of side-channel information in leakage measurements. …”
Get full text

Cold atoms laboratory in a hollow core fiber by Leong, Wui Seng

“…However, the short quantum spin coherence time of $\sim$\SI{100}{\micro\second} due to the differential AC stark shift from the trapping beam is a major obstacle to reaching high sensitivity of the optically trapped atom interferometer inside the HCF. By introducing a vector light shift from the dipole trap to cancel the differential scalar light shift, the quantum spin coherence time is increased to hundreds of milliseconds. …”
Get full text

An improvement on the upper bounds of the partial derivatives of NURBS surfaces by Tian, Ye, Ning, Tao, Li, Jixing, Zheng, Jianmin, Chen, Zhitong

“…The Non-Uniform Rational B-spline (NURBS) surface not only has the characteristics of the rational Bezier surface, but also has changeable knot vectors and weights, which can express the quadric surface accurately. …”
Get full text

Using cluster analysis to reconstruct dengue exposure patterns from cross-sectional serological studies in Singapore by Sangkaew, Sorawat, Tan, Li Kiang, Ng, Lee Ching, Ferguson, Neil M., Dorigatti, Ilaria

Get full text

Development of novel attention galibration protocols for EEG-based BCI system by Tchen, Jee Ern

“…The collected data from calibration will be used to train a support-vector machine (SVM), which will provide real-time classification of the user’s attention states. …”
Get full text

Using AI / machine learning to solve real world problems by Lok, Ignatius Zhengrong

“…Different supervised machine learning models including Random Forests, Support Vector Machines, XGBoost, LGBM and Ensemble learning methods are then applied to predict the restaurant revenue, allowing a better decision to be made when opening new restaurants and to increase the effectiveness of investments in new restaurant sites.…”
Get full text

Game of drones by Wei, LuoBin

“…Efficient Trajectory Planning is achieved by generating a Cubic Hermite Spline trajectory utilizing gate positions as data-points for interpolation and a vector pointing to the subsequent gate as the constraint. …”
Get full text

Sentiment analysis on yelp reviews by Wong, Hong Yong

“…Various supervised machine learning classifiers namely Naïve Bayes, Random Forest, Neural Networks, Support Vector Machine and Logistic Regression have been used to label reviews by performing text classification. …”
Get full text

Persistent elevation of intrathecal pro-inflammatory cytokines leads to multiple sclerosis-like cortical demyelination and neurodegeneration by James, Rachel E., Schalks, Renee, Browne, Eleanor, Eleftheriadou, Ioanna, Munoz, Carmen Picon, Mazarakis, Nicholas D., Reynolds, Richard

“…PhosphoRIP3+ and phosphoMLKL+ neurons were present in TNF + IFNγ vector injected animals, indicating activation of necroptosis. …”
Get full text

Hybrid machine learning method to determine the optimal operating process window in aerosol jet 3D printing by Zhang, Haining, Moon, Seung Ki, Ngo, Teck Hui

“…Then, the influence of the sheath gas flow rate (SHGFR) and the carrier gas flow rate (CGFR) on the printed line quality is analyzed by a K-means clustering approach, and an optimal operating process window is determined by a support vector machine. To efficiently identify more operating process windows at different print speeds, a transfer learning approach is applied to exploit relatedness between different operating process windows. …”
Get full text

Lane-aware image enhancement for lane detection in rain (part B - communications) by Tian, Zichen

“…All the diagrams are drawn in vector graph format, so readers can zoom in to check the details.…”
Get full text

Full-reference image quality assessment by combining features in spatial and frequency domains by Tang, Zhisen, Zheng, Yuanlin, Gu, Ke, Liao, Kaiyang, Wang, Wei, Yu, Miaomiao

“…Compared with support vector regression, RF can obtain better prediction results. …”
Get full text

Modeling, air balancing and optimal pressure set-point selection for the ventilation system with minimized energy consumption by Jing, Gang, Cai, Wenjian, Zhang, Xin, Cui, Can, Yin, Xiaohong, Xian, Huacai

“…In the study reported here, a comprehensive mathematical model was established to simulate the non-linear behavior of the ventilation system, and a supervised machine learning algorithm for a support vector machine was used to obtain values for unknown parameters in the model. …”
Get full text

iN6-methylat (5-step) : identifying DNA N⁶-methyladenine sites in rice genome using continuous bag of nucleobases via Chou's 5-step rule by Le, Nguyen Quoc Khanh

“…In this study, we treat DNA sequences by the continuous bags of nucleobases, including sub-word information of its biological words, which then serve as features to be fed into a support vector machine algorithm to identify them. Our model which uses this hybrid approach could identify DNA N⁶-methyladenine sites with achieved a jackknife test sensitivity of 86.48%, specificity of 89.09%, accuracy of 87.78%, and MCC of 0.756. …”
Get full text

The interaction problem of two Zener–Stroh cracks with a nearby inhomogeneity by Fan, M., Xiao, Zhongmin, Zhang, Yanmei

“…The influence of material properties, crack–crack positions and other parameters, such as crack length and Burgers vector of the Zener–Stroh crack, on the target crack tip stress intensity factor, plastic zone size and crack tip opening displacement are examined. …”
Get full text

Precious metal price prediction using deep neural networks by Peng, Zhiling

“…Then, four traditional regression methods in machine learning are used to train and evaluate the same dataset of the gold price, including the linear regression, support vector regression (SVR), decision tree regression and the random forest algorithm. …”
Get full text

A framework for analytical power flow solution using Gaussian process learning by Pareek, Parikshit, Nguyen, Hung D.

“…We use the Gaussian process (GP) regression to learn node voltage as a function of effective bus load or negative net-injection vector. The proposed approximation is valid over a subspace of load and provides an understanding of system behavior under uncertainty via GP interpretability. …”
Get full text

Aiding therapy using speech emotion recognition by Koh, En Rong

“…In this project, an AI Speech Emotion Recognition system is experimented with using Deep Learning techniques to alternative traditional methods like Support Vector Machine or Hidden Markov Model. We will explore the use of a Convolutional Neural network, a type of Deep Learning method, to train and predict human emotions. …”
Get full text