Search Results (18)

Sound source localization (SSL) adds a spatial dimension to auditory perception, allowing a system to pinpoint the origin of speech, machinery noise, warning tones, or other acoustic events, capabilities that facilitate robot navigation, human–machine dialogue, and condition monitoring. While existing surveys provide valuable historical context, they typically address general audio applications and do not fully account for robotic constraints or the latest advancements in deep learning. This review addresses these gaps by offering a robotics-focused synthesis, emphasizing recent progress in deep learning methodologies. We start by reviewing classical methods such as time difference of arrival (TDOA), beamforming, steered-response power (SRP), and subspace analysis. Subsequently, we delve into modern machine learning (ML) and deep learning (DL) approaches, discussing traditional ML and neural networks (NNs), convolutional neural networks (CNNs), convolutional recurrent neural networks (CRNNs), and emerging attention-based architectures. The data and training strategy that are the two cornerstones of DL-based SSL are explored. Studies are further categorized by robot types and application domains to facilitate researchers in identifying relevant work for their specific contexts. Finally, we highlight the current challenges in SSL works in general, regarding environmental robustness, sound source multiplicity, and specific implementation constraints in robotics, as well as data and learning strategies in DL-based SSL. Also, we sketch promising directions to offer an actionable roadmap toward robust, adaptable, efficient, and explainable DL-based SSL for next-generation robots. Full article

We present a novel sketch generation scheme from an image using the flowpath and the value through the flow (VTF). The first stage of our scheme is to produce grayscale noisy sketch using a deep learning-based approach. In the second stage, the unclear contour and unwanted noises in the grayscale noisy sketch are resolved using our flowpath and VTF-based schemes. We build a flowpath by integrating the tangent flow extracted from the input image. The integrated tangent flow produces a strong clue for the salient contour of the shape in the image. We further compute VTF by sampling values through the flowpath to extract line segments that correspond to the sketch stroke. By combining the deep learning-based approach and VTF, we can extract salient sketch strokes from various images that suppresses unwanted noises. We demonstrate the excellence of our scheme by generating sketches from various images including portrait, landscape, objects, animals, and animation scenes. Full article

Clothing image synthesis has emerged as a crucial technology in the fashion domain, enabling designers to rapidly transform creative concepts into realistic visual representations. However, the existing methods struggle to effectively integrate multiple guiding information sources, such as sketches and texture patches, limiting their ability to precisely control the generated content. This often results in issues such as semantic inconsistencies and the loss of fine-grained texture details, which significantly hinders the advancement of this technology. To address these issues, we propose the Fast Fourier Asymmetric Context Aggregation Network (FCAN), a novel image generation network designed to achieve controllable clothing image synthesis guided by design sketches and texture patches. In the FCAN, we introduce the Asymmetric Context Aggregation Mechanism (ACAM), which leverages multi-scale and multi-stage heterogeneous features to achieve efficient global visual context modeling, significantly enhancing the model’s ability to integrate guiding information. Complementing this, the FCAN also incorporates a Fast Fourier Channel Dual Residual Block (FF-CDRB), which utilizes the frequency-domain properties of Fast Fourier Convolution to enhance fine-grained content inference while maintaining computational efficiency. We evaluate the FCAN on the newly constructed SKFashion dataset and the publicly available VITON-HD and Fashion-Gen datasets. The experimental results demonstrate that the FCAN consistently generates high-quality clothing images aligned with the design intentions while outperforming the baseline methods across multiple performance metrics. Furthermore, the FCAN demonstrates superior robustness to varying texture conditions compared to the existing methods, highlighting its adaptability to diverse real-world scenarios. These findings underscore the potential of the FCAN to advance this technology by enabling controllable and high-quality image generation. Full article

The literature shows that both in laboratory and in industrial conditions, the photocatalytic oxidation method copes quite well with degradation of most environmental toxins and pathogenic microorganisms. However, the effective utilization of photocatalytic processes for environmental decontamination and disinfection requires significant technological advancement in both the area of semiconductor material synthesis and its application. Here, we focused on the presence and “photocatalytic capability” of photocatalysts among soil minerals and their potential contributions to the environmental decontamination in vitro and in vivo. Reactions caused by sunlight on the soil surface are involved in its normal redox activity, taking part also in the soil decontamination. However, their importance for decontamination in vivo cannot be overstated, due to the diversity of soils on the Earth, which is caused by the environmental conditions, such as climate, parent material, relief, vegetation, etc. The sunlight-induced reactions are just a part of complicated soil chemistry processes dependent on a plethora of environmental determinates. The multiplicity of affecting factors, which we tried to sketch from the perspective of chemists and environmental scientists, makes us rather skeptical about the effectiveness of the photocatalytic decontamination in vivo. On the other hand, there is a huge potential of the soils as the alternative and probably cheaper source of useful photocatalytic materials of unique properties. In our opinion, establishing collaboration between experts from different disciplines is the most crucial opportunity, as well as a challenge, for the advancement of photocatalysis. Full article

The path from life’s origin to the emergence of the eukaryotic cell was long and complex, and as such it is rarely treated in one publication. Here, we offer a sketch of this path, recognizing that there are points of disagreement and that many transitions are still shrouded in mystery. We assume life developed within microchambers of an alkaline hydrothermal vent system. Initial simple reactions were built into more sophisticated reflexively autocatalytic food-generated networks (RAFs), laying the foundation for life’s anastomosing metabolism, and eventually for the origin of RNA, which functioned as a genetic repository and as a catalyst (ribozymes). Eventually, protein synthesis developed, leading to life’s biology becoming dominated by enzymes and not ribozymes. Subsequent enzymatic innovation included ATP synthase, which generates ATP, fueled by the proton gradient between the alkaline vent flux and the acidic sea. This gradient was later internalized via the evolution of the electron transport chain, a preadaptation for the subsequent emergence of the vent creatures from their microchamber cradles. Differences between bacteria and archaea suggests cellularization evolved at least twice. Later, the bacterial development of oxidative phosphorylation and the archaeal development of proteins to stabilize its DNA laid the foundation for the merger that led to the formation of eukaryotic cells. Full article

Deep neural networks (DNNs) are easily exposed to backdoor threats when training with poisoned training samples. Models using backdoor attack have normal performance for benign samples, and possess poor performance for poisoned samples manipulated with pre-defined trigger patterns. Currently, research on backdoor attacks focuses on image classification and object detection. In this article, we investigated backdoor attacks in facial sketch synthesis, which can be beneficial for many applications, such as animation production and assisting police in searching for suspects. Specifically, we propose a simple yet effective poison-only backdoor attack suitable for generation tasks. We demonstrate that when the backdoor is integrated into the target model via our attack, it can mislead the model to synthesize unacceptable sketches of any photos stamped with the trigger patterns. Extensive experiments are executed on the benchmark datasets. Specifically, the light strokes devised by our backdoor attack strategy can significantly decrease the perceptual quality. However, the FSIM score of light strokes is 68.21% on the CUFS dataset and the FSIM scores of pseudo-sketches generated by FCN, cGAN, and MDAL are 69.35%, 71.53%, and 72.75%, respectively. There is no big difference, which proves the effectiveness of the proposed backdoor attack method. Full article

Hydrogeological maps must synthesize scientific knowledge about the hydraulic features and the hydrogeological behavior of a specific area, and, at the same time, they must meet the expectations of land planners and administrators. Thus, hydrogeological maps can be fully effective when they are purpose-designed, especially in complex interconnected systems. In this case study, purpose-designed graphical solutions emphasize all the hydraulic interconnections that play significant roles in recharging the multilayered alluvial aquifer, where the majority of wells have been drilled for human purposes, artificial channels are used for agricultural purposes, and the shallow groundwater feeds protected groundwater-dependent ecosystems. The hydrogeological map was then designed to be the synthesis of three different and hydraulically interconnected main contexts: (i) the alluvial aquifer, (ii) the hydrographic basin of the Taro losing river, and (iii) those hard-rock aquifers whose springs feed the same river. The main hydrogeological map was integrated with two smaller sketches and one hydrogeological profile. One small map was drawn from a modeling perspective because it facilitates visualization of the alluvial aquifer bottom and the “no-flow boundaries.” The other small sketch shows the artificial channel network that emphasizes the hydraulic connection between water courses and groundwater within the alluvial aquifer. The hydrogeological profile was reconstructed to be able to (i) show the main heterogeneities within the aquifer system (both layered and discontinuous), (ii) visualize the coexistence of shallower and deeper groundwater, (iii) emphasize the hydraulic interconnections between subsystems, and (iv) suggest the coexistence of groundwater pathways with different mean residence times. Full article

The photo-sketch matching problem is challenging because the modality gap between a photo and a sketch is very large. This work features a novel approach to the use of an intermediate latent space between the two modalities that circumvents the problem of modality gap for face photo-sketch recognition. To set up a stable homogenous latent space between a photo and a sketch that is effective for matching, we utilize a bidirectional (photo → sketch and sketch → photo) collaborative synthesis network and equip the latent space with rich representation power. To provide rich representation power, we employ StyleGAN architectures, such as StyleGAN and StyleGAN2. The proposed latent space equipped with rich representation power enables us to conduct accurate matching because we can effectively align the distributions of the two modalities in the latent space. In addition, to resolve the problem of insufficient paired photo/sketch samples for training, we introduce a three-step training scheme. Extensive evaluation on a public composite face sketch database confirms superior performance of the proposed approach compared to existing state-of-the-art methods. The proposed methodology can be employed in matching other modality pairs. Full article

The synthesis between face sketches and face photos has important application values in law enforcement and digital entertainment. In cases of a lack of paired sketch-photo data, this paper proposes an unsupervised model to solve the problems of missing key facial details and a lack of realism in the synthesized images of existing methods. The model is built on the CycleGAN architecture. To retain more semantic information in the target domain, a multi-scale feature extraction module is inserted before the generator. In addition, the convolutional block attention module is introduced into the generator to enhance the ability of the model to extract important feature information. Via CBAM, the model improves the quality of the converted image and reduces the artifacts caused by image background interference. Next, in order to preserve more identity information in the generated photo, this paper constructs the multi-level cycle consistency loss function. Qualitative experiments on CUFS and CUFSF public datasets show that the facial details and edge structures synthesized by our model are clearer and more realistic. Meanwhile the performance indexes of structural similarity and peak signal-to-noise ratio in quantitative experiments are also significantly improved compared with other methods. Full article

Nowadays, the contamination of wastewater by organic persistent pollutants is a reality. These pollutants are difficult to remove from wastewater with conventional techniques; hence, it is necessary to go on the hunt for new, innovative and environmentally sustainable ones. In this context, advanced oxidation processes have attracted great attention and have developed rapidly in recent years as promising technologies. The cornerstone of advanced oxidation processes is the selection of heterogeneous catalysts. In this sense, the possibility of using metal–organic frameworks as catalysts has been opened up given their countless physical–chemical characteristics, which can overcome several disadvantages of traditional catalysts. Thus, this review provides a brief review of recent progress in the research and practical application of metal–organic frameworks to advanced oxidation processes, with a special emphasis on the potential of Fe-based metal–organic frameworks to reduce the pollutants present in wastewater or to render them harmless. To do that, the work starts with a brief overview of the different types and pathways of synthesis. Moreover, the mechanisms of the generation of radicals, as well as their action on the organic pollutants and stability, are analysed. Finally, the challenges of this technology to open up new avenues of wastewater treatment in the future are sketched out. Full article

This paper presents simple yet effective optimizations for implementing data stream frequency estimation sketch kernels using High-Level Synthesis (HLS). The paper addresses design issues common to sketches utilizing large portions of the embedded RAM resources in a Field Programmable Gate Array (FPGA). First, a solution based on Load-Store Queue (LSQ) architecture is proposed for resolving the memory dependencies associated with the hash tables in a frequency estimation sketch. Second, performance fine-tuning through high-level pragmas is explored to achieve the best possible throughput. Finally, a technique based on pre-processing the data stream in a small cache memory prior to updating the sketch is evaluated to reduce the dynamic power consumption. Using an Intel HLS compiler, a proposed optimized hardware version of the popular Count-Min sketch utilizing 80% of the embedded RAM in an Intel Arria 10 FPGA, achieved more than 3x the throughput of an unoptimized baseline implementation. Furthermore, the sketch update rate is significantly reduced when the input stream is skewed. This, in turn, minimizes the effect of high throughput on dynamic power consumption. Compared to FPGA sketches in the published literature, the presented sketch is the most well-rounded sketch in terms of features and versatility. In terms of throughput, the presented sketch is on a par with the fastest sketches fine-tuned at the Register Transfer Level (RTL). Full article

This paper aims to solve the task of coloring a sketch image given a ready-colored exemplar image. Conventional exemplar-based colorization methods tend to transfer styles from reference images to grayscale images by employing image analogy techniques or establishing semantic correspondences. However, their practical capabilities are limited when semantic correspondences are elusive. This is the case with coloring for sketches (where semantic correspondences are challenging to find) since it contains only edge information of the object and usually contains much noise. To address this, we present a framework for exemplar-based sketch colorization tasks that synthesizes colored images from sketch input and reference input in a distinct domain. Generally, we jointly proposed our domain alignment network, where the dense semantic correspondence can be established, with a simple but valuable adversarial strategy, that we term the structural and colorific conditions. Furthermore, we proposed to utilize a self-attention mechanism for style transfer from exemplar to sketch. It facilitates the establishment of dense semantic correspondence, which we term the spatially corresponding semantic transfer module. We demonstrate the effectiveness of our proposed method in several sketch-related translation tasks via quantitative and qualitative evaluation. Full article

The recent development in the area of IoT technologies is likely to be implemented extensively in the next decade. There is a great increase in the crime rate, and the handling officers are responsible for dealing with a broad range of cyber and Internet issues during investigation. IoT technologies are helpful in the identification of suspects, and few technologies are available that use IoT and deep learning together for face sketch synthesis. Convolutional neural networks (CNNs) and other constructs of deep learning have become major tools in recent approaches. A new-found architecture of the neural network is anticipated in this work. It is called Spiral-Net, which is a modified version of U-Net fto perform face sketch synthesis (the phase is known as the compiler network C here). Spiral-Net performs in combination with a pre-trained Vgg-19 network called the feature extractor F. It first identifies the top n matches from viewed sketches to a given photo. F is again used to formulate a feature map based on the cosine distance of a candidate sketch formed by C from the top n matches. A customized CNN configuration (called the discriminator D) then computes loss functions based on differences between the candidate sketch and the feature. Values of these loss functions alternately update C and F. The ensemble of these nets is trained and tested on selected datasets, including CUFS, CUFSF, and a part of the IIT photo–sketch dataset. Results of this modified U-Net are acquired by the legacy NLDA (1998) scheme of face recognition and its newer version, OpenBR (2013), which demonstrate an improvement of 5% compared with the current state of the art in its relevant domain. Full article

Curcumin and curcuminoids have been discussed frequently due to their promising functional groups (such as scaffolds of α,β-unsaturated β-diketone, α,β-unsaturated ketone and β′-hydroxy-α,β-unsaturated ketone connected with aromatic rings on both sides) that play an important role in various bioactivities, including antioxidant, anti-inflammatory, anti-proliferation and anticancer activity. A series of novel curcuminoid derivatives (a total of 55 new compounds) and three reference compounds were synthesized with good yields using three-step organic synthesis. The anti-proliferative activities of curcumin derivatives were examined for six human cancer cell lines: HeLaS3, KBvin, MCF-7, HepG2, NCI-H460 and NCI-H460/MX20. Compared to the IC₅₀ values of all the synthesized derivatives, most α,β-unsaturated ketones displayed potent anti-proliferative effects against all six human cancer cell lines, whereas β′-hydroxy-α,β-unsaturated ketones and α,β-unsaturated β-diketones presented moderate anti-proliferative effects. Two potent curcuminoid derivatives were found among all the novel derivatives and reference compounds: (E)-5-hydroxy-7-phenyl-1-(3,4,5-trimethoxyphenyl)hept-1-en-3-one (compound 3) and (1E,4E)-1,7-bis(3,4,5-trimethoxyphenyl)hepta-1,4-dien-3-one (compound MD12a). These were selected for further analysis after the evaluation of their anti-proliferative effects against all human cancer cell lines. The results of apoptosis assays revealed that the number of dead cells was increased in early apoptosis and late apoptosis, while cell proliferation was also decreased after applying various concentrations of (E)-5-hydroxy-7-phenyl-1-(3,4,5-trimethoxyphenyl)hept-1-en-3-one (compound 3) and (1E,4E)-1,7-bis(3,4,5-trimethoxyphenyl)hepta-1,4-dien-3-one (compound MD12a) to MCF-7 and HpeG2 cancer cells. Analysis of the gene expression arrays showed that three genes (GADD45B, SESN2 and BBC3) were correlated with the p53 pathway. From the quantitative PCR analysis, it was seen that (1E,4E)-1,7-bis(3,4,5-trimethoxyphenyl)hepta-1,4-dien-3-one (compound MD12a) effectively induced the up-regulated expression of GADD45B, leading to the suppression of MCF-7 cancer cell formation and cell death. Molecular docking analysis was used to predict and sketch the interactions of the GADD45B-α,β-unsaturated ketone complex for help in drug design. Full article

The emergence of smart technologies in homes comes with various services and functions for everyday life. While a smart home (SH) is associated with great potential in terms of comfort and risk treatment, it also introduces new and alters existing risks. Despite a growing number of academic studies on SH risks, research is fragmented with regard to its focus on certain disciplines and is still rather technology-focused. In this paper, we fill this gap by providing a comprehensive understanding of relevant risks through a systematic literature review. Following the guidelines of the PRISMA reporting protocol, we search 1196 academic and practitioners’ publications related to household risks or risk perceptions of SH users. A final set of 59 records results in three main themes. They include (1) a synthesis of pre-existing and emerging risks sketching the new risk landscape of SH households, (2) a discussion of the prevailing risk evaluation methods, and (3) a presentation of SH-related risk treatment options with a particular emphasis on insurance. We specify the influence of SH on risks and risk perception, and highlight the relevance of analyzing the interconnection of risks in complex systems, such as SH. Our review lays the basis for assessing SH risks and for enabling more comprehensive and effective risk management optimization. Full article