Drug discovery and development pipelines are long, complex and depend on numerous factors. Machine learning (ML) approaches provide a set of tools that can improve discovery and decision making for well-specified questions with abundant, high-quality data. Opportunities to apply ML occur in all stages of drug discovery. Examples include target validation, identification of prognostic biomarkers and analysis of digital pathology data in clinical trials. Applications have ranged in context and methodology, with some approaches yielding accurate predictions and insights. The challenges of applying ML lie primarily with the lack of interpretability and repeatability of ML-generated results, which may limit their application. In all areas, systematic and comprehensive high-dimensional data still need to be generated. With ongoing efforts to tackle these issues, as well as increasing awareness of the factors needed to validate ML approaches, the application of ML can promote data-driven decision making and has the potential to speed up the process and reduce failure rates in drug discovery and development.

No abstract

With the powerful deep network architectures, such as generative adversarial networks and variational autoencoders, large amounts of photorealistic images can be generated. The generated images, already fooling human eyes successfully, are not initially targeted for deceiving image authentication systems. However, research communities as well as public media show great concerns on whether these images would lead to serious security issues. In this paper, we address the problem of detecting deep network generated (DNG) images by analyzing the disparities in color components between real scene images and DNG images. Existing deep networks generate images in RGB color space and have no explicit constrains on color correlations; therefore, DNG images have more obvious differences from real images in other color spaces, such as HSV and YCbCr, especially in the chrominance components. Besides, the DNG images are different from the real ones when considering red, green, and blue components together. Based on these observations, we propose a feature set to capture color image statistics for detecting the DNG images. Moreover, three different detection scenarios in practice are considered and the corresponding detection strategies are designed. Extensive experiments have been conducted on face image datasets to evaluate the effectiveness of the proposed method. The experimental results show that the proposed method is able to distinguish the DNG images from real ones with high accuracies. Index TermsImage generative model, generative adversarial networks, fake image identification, image statistics.

No abstract

Abstract-Cognitive satellite-terrestrial networks (CSTNs) have been recognized as a promising network architecture for addressing spectrum scarcity problem in next-generation communication networks. In this paper, we investigate the secure transmission for CSTNs where the terrestrial base station (BS) serving as a green interference resource is introduced to enhance the security of the satellite link. Adopting a stochastic model for the channel state information (CSI) uncertainty, we propose a secure and robust beamforming framework to minimize the transmit power, while satisfying a range of outage (probabilistic) constraints concerning the signal-to-interference-plus-noise ratio (SINR) recorded at the satellite user and the terrestrial user, the leakage-SINR recorded at the eavesdropper, as well as the interference power recorded at the satellite user. The resulting robust optimization problem is highly intractable and the key observation is that the highly intractable probability constraints can be equivalently reformulated as the deterministic versions with Gaussian statistics. In this regard, we develop two robust reformulation methods, namely S-Procedure and Bernstein-type inequality restriction techniques, to obtain a safe approximate solution. In the meantime, the computational complexities of the proposed schemes are analyzed. Finally, the effectiveness of the proposed schemes are demonstrated by numerical results with different system parameters.

This paper considers a relay-assisted bidirectional cellular network where the base station (BS) communicates with each mobile station (MS) using OFDMA for both uplink and downlink. The goal is to improve the overall system performance by exploring the full potential of the network in various dimensions including user, subcarrier, relay, and bidirectional traffic. In this work, we first introduce a novel three-time-slot time-division duplexing (TDD) transmission protocol. This protocol unifies direct transmission, one-way relaying and network-coded two-way relaying between the BS and each MS.Using the proposed three-time-slot TDD protocol, we then propose an optimization framework for resource allocation to achieve the following gains: cooperative diversity (via relay selection), network coding gain (via bidirectional transmission mode selection), and multiuser diversity (via subcarrier assignment). We formulate the problem as a combinatorial optimization problem, which is NP-complete.To make it more tractable, we adopt a graph-based approach. We first establish the equivalence between the original problem and a maximum weighted clique problem in graph theory. A metaheuristic algorithm based on any colony optimization (ACO) is then employed to find the solution in polynomial time.Simulation results demonstrate that the proposed protocol together with the ACO algorithm significantly enhances the system total throughput. Index TermsBidirectional communications, network coding, maximum weighted clique problem (MWCP), ant colony optimization (ACO), orthogonal frequency-division multiple-access (OFDMA).

No abstract

No abstract