In mobile crowdsensing activities, it is usually necessary for participants to upload sensing data and related locations. The existing location privacy-preserving mechanisms cannot well protect a user's trajectory privacy because attackers can mine the user's trajectory features through data analysis techniques. Aiming at the trajectory privacy protection problem, this article proposes a differential location privacy-preserving mechanism based on trajectory obfuscation (LPMT). LPMT first extracts the stay points as the features of a trajectory based on the sliding window algorithm, and then obfuscates each stay point to a target obfuscation subregion through the exponential mechanism, and finally performs the Laplace sampling in the target obfuscation subregion to obtain the obfuscated GPS points. Compared with the baseline mechanisms, LPMT can reduce data quality loss by more than 20% while providing the same level of obfuscation quality, which indicates that LPMT has the advantages of strong security and high quality of service.

In this article, some methods are proposed for enhancing the converging velocity of the COA (chaos optimization algorithm) based on using carrier wave two times, which can greatly increase the speed and efficiency of the first carrier wave's search for the optimal point in implementing the sophisticated searching during the second carrier wave is faster and more accurate. In addition, the concept of using the carrier wave three times is proposed and put into practice to tackle the multi-variables opti- mization problems, where the searching for the optimal point of the last several variables is frequently worse than the first several ones.

Cancerlectins are cancer-related proteins that function as lectins. They have been identified through computational identification techniques, but these techniques have sometimes failed to identify proteins because of sequence diversity among the cancerlectins. Advanced machine learning identification methods, such as support vector machine and basic sequence features (n-gram), have also been used to identify cancerlectins. In this study, various protein fingerprint features and advanced classifiers, including ensemble learning techniques, were utilized to identify this group of proteins. We improved the prediction accuracy of the original feature extraction methods and classification algorithms by more than 10% on average. Our work provides a basis for the computational identification of cancerlectins and reveals the power of hybrid machine learning techniques in computational proteomics.