Automated auscultation and cardiovascular screening systems for cardiac abnormalities have received growing interest in clinical applications. Still, they face challenges due to missing or invalid recordings caused by technical issues. To address this, we introduce a novel framework leveraging the masked autoencoder strategy, uniquely treating each heart valve recording as a distinct token. Our approach reconstructs missing valve data using existing representation and learnable mask tokens, achieving inter-valve integration through positional embeddings and TCNs. We demonstrate state-of-the-art (SOTA) performance on the CirCor DigiScope dataset, outperforming top participants and SOTA imputation methods in terms of mean cost of patient outcome, accuracy, F1-measure, and macro F1 score. Furthermore, our analysis highlights improved predictive accuracy on limited input data, while generative results indicate our capability to provide comprehensive reconstruction of auscultation recordings for further clinical evaluations.

Automated auscultation analysis using electronic stethoscope has received growing interest in clinical applications. Recently, researchers showed successes by using deep learning methods to distinguish between pathological respiratory sound classes. Nevertheless, the challenge persists due to the scarcity of abnormal samples, and the distinct characteristics between low-pitched and discontinuous crackles and high-pitched and continuous wheezes. In this study, we proposed a novel augmentation method, namely gamma patch-wise correction augmentation, which directly operates on spectrograms to handle with these two challenges. We achieved state-of-the-art performances on both 60-40 official split and 80-20 cross-validation of the public ICBHI dataset, outperforming previous top-performing studies by 11.82% in sensitivity and 5.27% in ICBHI score. Furthermore, Grad-CAM analysis shows that our approach better preserves the distinctive characteristics of crackles and wheezes than SpecAug.

To achieve reliable small cell millimeter-wave wireless backhauls, this study installs small cell base stations (SBSs) on overhead messenger wires to gain flexibility in physical deployments of SBSs ensuring in the line-of-sight connections between SBSs and gateway BSs. These installations pose challenges in aligning directional beams, whereby complicated wind-forced dynamics in on-wire SBSs require frequent beam training, and consequently, a large signaling overhead. To address this, this study aims at demonstrating the feasibility of learning-based beam tracking where a beam tracking policy is learned a priori to fix beam misalignment caused by the wind-forced dynamics. Because wind-forced dynamics in SBSs can be three-dimensional (3D), the proposed beam tracking newly exploits the 3D position/velocity of the SBS as state information. As a solution to fix beam misalignment, the beam tracking policy is learned via deep reinforcement learning wherein the 3D information and beam direction are regarded as a state and an action, respectively, and the received signal power at a gateway BS is maximized. The simulation results depict the feasibility of learning an appropriate beam tracking policy to prevent beam misalignment induced by wind-forced 3D dynamics in on-wire SBSs.

We propose a unidirectional communication system capable of pushing information from audio speakers to nearby audience via acoustic channels. Though constrained by short transmission distances and low data throughput of sound waves, information push services based on acoustic channels can be regarded as a cost-free message delivery scheme since music playback systems and handheld devices equipped with recording capabilities have become ubiquitous in our life. Furthermore, the proposed approach can provide better non-intrusiveness and more convenient user access than other auxiliary information delivery approaches like 2-D barcodes or watermarking schemes based on visual contents. To the best of our knowledge, our system is the first one that can effectively push information to receivers at feasible transmission throughput/robustness/distance within common noisy environments. Various interesting applications and new business models can be facilitated with the proposed scheme.

A novel data hiding scheme, denoted as unseen visible watermarking (UVW), is proposed. In UVW schemes, hidden information can be embedded covertly and then directly extracted using the human visual system as long as appropriate operations (e.g., gamma correction provided by almost all display devices or changes in viewing angles relative to LCD monitors) are performed. UVW eliminates the requirement of invisible watermarking that specific watermark extractors must be deployed to the receiving end in advance, and it can be integrated with 2-D barcodes to transmit machine-readable information that conventional visible watermarking schemes fail to deliver. We also adopt visual cryptographic techniques to guard the security of hidden information and, at the same time, increase the practical value of visual cryptography. Since UVW can be alternatively viewed as a mechanism for visualizing patterns hidden with least-significant-bit embedding, its security against statistical steganalysis is proved by empirical tests. Limitations and other potential extensions of UVW are also addressed.

Most researches of collusion-resistant multimedia fingerprinting consider only the designing of the traceability code. In this paper, we not only discuss the traceability of the fingerprints, but also try to prevent collusion attacks by making the colluded version of the video useless. The proposed collusion-resistant video fingerprinting scheme embeds a curve fingerprint into the video by temporally oscillating the video frames. This curve is smooth enough so that the oscillation of the video is imperceptible. However, once the colluders average or copy-and-paste the video frames, the fluctuation of the video will be so severe that users will feel uncomfortable while watching the video. In addition, a shot-based fingerprinting is employed to embed a hierarchical traceability code to increase the collusion-resistance. Experimental results show good performances of the proposed scheme. That is, the proposed system not only can trace the colluders successfully, but also can discourage users from removing the traceability code by collusion attacks.

On-chip networks (OCNs) have been proposed to solve the increasing scale and complexity of the designs in nanoscale multicore VLSI designs. The concept of irregular meshes is an important issue because IPs of different sizes may be supported by various vendors. In order to solve routing problems in irregular meshes, modified routing algorithms to detour oversized IPs (OIPs) are needed. However, directly applying fault-tolerant routing algorithms may cause two serious problems: 1) heavy traffic loads around OIPs and 2) unbalanced traffic loads in irregular meshes. In this paper, we propose an OIP avoidance prerouting (OAPR) algorithm to solve the aforementioned problems. The proposed OAPR can make traffic loads evenly spread on the networks and shorten the average paths of packets. Therefore, the networks using the OAPR have lower latency and higher throughput than those using fault- tolerant routing algorithms. In our experiments, four different cases are simulated to demonstrate that the proposed OAPR improves 13.3 percent to 100 percent sustainable throughputs than two previous fault-tolerant routing algorithms. Moreover, the hardware overhead of the OAPR is less than 1 percent compared to the cost of a whole router. Hence, the proposed OAPR algorithm has good performance and is practical for irregular mesh-based OCNs.

A novel data-hiding methodology, denoted as digital invisible ink (DII), is proposed to implement secure steganography systems. Like the real-world invisible ink, secret messages will be correctly revealed only after the marked works undergo certain prenegotiated manipulations, such as lossy compression and processing. Different from conventional data-hiding schemes where content processing or compression operations are undesirable, distortions caused by prenegotiated manipulations in DII-based schemes are indispensable steps for revealing genuine secrets. The proposed scheme is carried out based on two important data-hiding schemes: spread-spectrum watermarking and frequency-domain quantization watermarking. In some application scenarios, the DII-based steganography system can provide plausible deniability and enhance the secrecy by taking cover with other messages. We show that DII-based schemes are indeed superior to existing plausibly deniable steganography approaches in many aspects. Moreover, potential security holes caused by deniable steganography systems are discussed.

A novel data-hiding methodology, denoted as unseen visible watermarking (UVW), is proposed. The proposed scheme is inspired by real-world watermarks and possesses advantages of both visible and invisible watermarking schemes. After watermark embedding, the differences between the original work and the stego work are imperceptible under normal viewing conditions. However, when the hidden message is to be extracted, no explicit watermark extracting module is required. Semantically-meaningful watermark patterns can be directly recognized from the stego work as long as common imaging-related functions, e.g. gamma-correction or even simply changing the user-viewing angle relative to the LCD monitor, are performed. The proposed scheme outperforms existing invisible watermarking methods in its capability to practically convey metadata to users of legacy display devices lacking renewal capability. On the other hand, it does not suffer from the annoying quality-degradation problem of visible watermarking schemes. Limitations and possible extensions of the proposed schemes are also addressed. We believe that many interesting new applications can be facilitated using such unseen visible watermarking schemes.

A novel steganographic approach analogy to the real-world secret communication mechanism, in which secret messages are written on white papers using invisible ink like lemon juice and are revealed only after the papers are heated, is proposed. Carefully-designed informed embedders now play the role of "invisible ink"; some pre-negotiated attacks provided by common content-processing tools correspond to the required "heating" process. Theoretic models and feasible implementations of the proposed digital-invisible-ink watermarking approach based on both blind-detection spread-spectrum watermarking and quantization watermarking schemes are provided. The proposed schemes can prevent the supervisor from interpreting secret messages even when the watermark extractor and decryption tool, as well as session keys, are available to the supervisor. Furthermore, secret communication systems employing the proposed scheme can aggressively mislead the channel supervisor with fake watermarks and transmit genuine secrets at the same time.

MOTIVATION: RNA H-type pseudoknots are ubiquitous pseudoknots that are found in almost all classes of RNA and thought to play very important roles in a variety of biological processes. Detection of these RNA H-type pseudoknots can improve our understanding of RNA structures and their associated functions. However, the currently existing programs for detecting such RNA H-type pseudoknots are still time consuming and sometimes even ineffective. Therefore, efficient and effective tools for detecting the RNA H-type pseudoknots are needed. RESULTS: In this paper, we have adopted a heuristic approach to develop a novel tool, called HPknotter, for efficiently and accurately detecting H-type pseudoknots in an RNA sequence. In addition, we have demonstrated the applicability and effectiveness of HPknotter by testing on some sequences with known H-type pseudoknots. Our approach can be easily extended and applied to other classes of more general pseudoknots. AVAILABILITY: The web server of our HPknotter is available for online analysis at http://bioalgorithm.life.nctu.edu.tw/HPKNOTTER/ CONTACT: [email protected], [email protected]

Visible watermarking schemes are important intellectual property rights (IPR) protection mechanisms for digital images and videos that have to be released for certain purposes but illegal reproductions of them are prohibited. Visible watermarking techniques protect digital contents in a more active manner, which is quite different from the invisible watermarking techniques. Digital data embedded with visible watermarks will contain recognizable but unobtrusive copyright patterns, and the details of the host data should still exist. The embedded pattern of a useful visible watermarking scheme should be difficult or even impossible to be removed unless intensive and expensive human labors are involved. In this paper, we propose an attacking scheme against current visible image watermarking techniques. After manually selecting the watermarked areas, only few human interventions are required. For watermarks purely composed of thin patterns, basic image recovery techniques can completely remove the embedded patterns. For more general watermarks consisting of thick patterns, not only information in surrounding unmarked areas but also information within watermarked areas will be utilized to correctly recover the host image. Although the proposed scheme does not guarantee that the recovered images will be exactly identical to the unmarked originals, the structure of the embedded pattern will be seriously destroyed and a perceptually satisfying recovered image can be obtained. In other words, a general attacking scheme based on the contradictive requirements of current visible watermarking techniques is worked out. Thus, the robustness of current visible watermarking schemes for digital images is doubtful and needs to be improved.