Previous Work Research Articles

Literature Review on IoT-based Smart Retailing Management Systems in the Context of Smart Cart

Abstract: IoT technology has revolutionized retail, giving rise to Smart Retailing Management Systems (SRMS). This review explores IoT-based SRMS focusing on smart carts, investigating enhancements in shopping experiences like RFID tags, dynamic inventory management, and personalization. By comparing research and products, it evaluates SRMS in technology, cost, reliability, security, power use, and components. The goal is to unveil SRMS’s strengths and weaknesses, aiding retail progress. Objective: This study aimed to review IoT-based Smart Retailing Management Systems (SRMS) centered on smart carts, explore IoT's role in enhancing shopping, spotlighting RFID tags, dynamic inventory, and personalization, and evaluate SRMS via tech, cost, reliability, security, power, and components, unveiling diverse strengths and weaknesses. Method: A literature search in previous works and patents was conducted. The findings to pinpoint trends, tech shifts, and research gaps were analyzed. The real-world studies were synthesized to discuss IoT-based SRMS progress and an inclusive view of various approaches and outcomes was offered. Conclusion: IoT-based SRMS, especially in smart retail carts, elevate shopping via RFID tags, dynamic inventory, and personalization. The comparative analysis exposes SRMS potential and constraints, offering insights for informed retail decisions and advancement.

The Application of Kinesin Inhibitors in Medical Issues.

Kinesins are a group of motor proteins in charge of several crucial functions in the cell. These proteins often bind to microtubules and perform their functions using the energy produced by ATP hydrolysis. One function of mitotic kinesin, a subclass of kinesin that is expressed during cell division at the mitotic phase, is to create the mitotic spindle. Uncontrolled cell growth is one trait of cancerous cells. Traditional anticancer medications still used in clinics include taxanes (paclitaxel) and vinca alkaloids (vincristine, vinblastine), which interfere with microtubule dynamics. However, because non-dividing cells like post-mitotic neurons contain microtubules, unwanted side effects like peripheral neuropathy are frequently found in patients taking these medications. More than ten members of the mitotic kinesin family play distinct or complementary roles during mitosis. The mitotic kinesin family's KSP, or Eg5, is regarded as its most dramatic target protein. The current work systematically reviews the use of kinesin inhibitors in the medical field. The challenges of KSP and the practical solutions are also examined, and the outcomes of the previous works are reported. The significant gaps and shortcomings of the related works are also highlighted, which can be an onset topic for future works.

Divide and Retain: A Dual-Phase Modeling for Long-Tailed Visual Recognition.

This work explores visual recognition models on real-world datasets exhibiting a long-tailed distribution. Most of previous works are based on a holistic perspective that the overall gradient for training model is directly obtained by considering all classes jointly. However, due to the extreme data imbalance in long-tailed datasets, joint consideration of different classes tends to induce the gradient distortion problem; i.e., the overall gradient tends to suffer from shifted direction toward data-rich classes and enlarged variances caused by data-poor classes. The gradient distortion problem impairs the training of our models. To avoid such drawbacks, we propose to disentangle the overall gradient and aim to consider the gradient on data-rich classes and that on data-poor classes separately. We tackle the long-tailed visual recognition problem via a dual-phase-based method. In the first phase, only data-rich classes are concerned to update model parameters, where only separated gradient on data-rich classes is used. In the second phase, the rest data-poor classes are involved to learn a complete classifier for all classes. More importantly, to ensure the smooth transition from phase I to phase II, we propose an exemplar bank and a memory-retentive loss. In general, the exemplar bank reserves a few representative examples from data-rich classes. It is used to maintain the information of data-rich classes when transiting. The memory-retentive loss constrains the change of model parameters from phase I to phase II based on the exemplar bank and data-poor classes. The extensive experimental results on four commonly used long-tailed benchmarks, including CIFAR100-LT, Places-LT, ImageNet-LT, and iNaturalist 2018, highlight the excellent performance of our proposed method.

Hierarchical Organ-Aware Total-Body Standard-Dose PET Reconstruction From Low-Dose PET and CT Images.

Positron emission tomography (PET) is an important functional imaging technology in early disease diagnosis. Generally, the gamma ray emitted by standard-dose tracer inevitably increases the exposure risk to patients. To reduce dosage, a lower dose tracer is often used and injected into patients. However, this often leads to low-quality PET images. In this article, we propose a learning-based method to reconstruct total-body standard-dose PET (SPET) images from low-dose PET (LPET) images and corresponding total-body computed tomography (CT) images. Different from previous works focusing only on a certain part of human body, our framework can hierarchically reconstruct total-body SPET images, considering varying shapes and intensity distributions of different body parts. Specifically, we first use one global total-body network to coarsely reconstruct total-body SPET images. Then, four local networks are designed to finely reconstruct head-neck, thorax, abdomen-pelvic, and leg parts of human body. Moreover, to enhance each local network learning for the respective local body part, we design an organ-aware network with a residual organ-aware dynamic convolution (RO-DC) module by dynamically adapting organ masks as additional inputs. Extensive experiments on 65 samples collected from uEXPLORER PET/CT system demonstrate that our hierarchical framework can consistently improve the performance of all body parts, especially for total-body PET images with PSNR of 30.6 dB, outperforming the state-of-the-art methods in SPET image reconstruction.

Nucleus accumbens dopamine release reflects Bayesian inference during instrumental learning.

Dopamine release in the nucleus accumbens has been hypothesized to signal reward prediction error, the difference between observed and predicted reward, suggesting a biological implementation for reinforcement learning. Rigorous tests of this hypothesis require assumptions about how the brain maps sensory signals to reward predictions, yet this mapping is still poorly understood. In particular, the mapping is non-trivial when sensory signals provide ambiguous information about the hidden state of the environment. Previous work using classical conditioning tasks has suggested that reward predictions are generated conditional on probabilistic beliefs about the hidden state, such that dopamine implicitly reflects these beliefs. Here we test this hypothesis in the context of an instrumental task (a two-armed bandit), where the hidden state switches repeatedly. We measured choice behavior and recorded dLight signals reflecting dopamine release in the nucleus accumbens core. Model comparison among a wide set of cognitive models based on the behavioral data favored models that used Bayesian updating of probabilistic beliefs. These same models also quantitatively matched the dopamine measurements better than non-Bayesian alternatives. We conclude that probabilistic belief computation contributes to instrumental task performance in mice and is reflected in mesolimbic dopamine signaling.

Fully Distributed Event-Triggered Anti-Windup Consensus of Heterogeneous Systems With Input Saturation and an Active Leader.

This article addresses the event-based fully distributed consensus problem for linear heterogeneous multiagent systems (MASs) subject to input saturation. A leader with unknown but bounded control input is also considered. Based on an adaptive dynamic event-triggered protocol, all the agents can reach output consensus without knowing any global knowledge. Moreover, by applying a multiple-level saturation technique, the input-constrained leader-following consensus control is achieved. The given event-triggered algorithm can be utilized for the directed graph containing a spanning tree with the leader as the root. One distinct feature compared with previous works is that the proposed protocol can achieve saturated control without any a priori condition, instead, the local information is needed. Finally, the numerical simulations are illustrated to verify the performance of the proposed protocol.

Toward Subgraph-Guided Knowledge Graph Question Generation With Graph Neural Networks.

Knowledge graph (KG) question generation (QG) aims to generate natural language questions from KGs and target answers. Previous works mostly focus on a simple setting that is to generate questions from a single KG triple. In this work, we focus on a more realistic setting where we aim to generate questions from a KG subgraph and target answers. In addition, most previous works built on either RNN- or Transformer-based models to encode a linearized KG subgraph, which totally discards the explicit structure information of a KG subgraph. To address this issue, we propose to apply a bidirectional Graph2Seq model to encode the KG subgraph. Furthermore, we enhance our RNN decoder with a node-level copying mechanism to allow direct copying of node attributes from the KG subgraph to the output question. Both automatic and human evaluation results demonstrate that our model achieves new state-of-the-art scores, outperforming existing methods by a significant margin on two QG benchmarks. Experimental results also show that our QG model can consistently benefit the question-answering (QA) task as a means of data augmentation.

MetaSeg: Content-Aware Meta-Net for Omni-Supervised Semantic Segmentation.

Noisy labels, inevitably existing in pseudo-segmentation labels generated from weak object-level annotations, severely hamper model optimization for semantic segmentation. Previous works often rely on massive handcrafted losses and carefully tuned hyperparameters to resist noise, suffering poor generalization capability and high model complexity. Inspired by recent advances in meta-learning, we argue that rather than struggling to tolerate noise hidden behind clean labels passively, a more feasible solution would be to find out the noisy regions actively, so as to simply ignore them during model optimization. With this in mind, this work presents a novel meta-learning-based semantic segmentation method, MetaSeg, that comprises a primary content-aware meta-net (CAM-Net) to serve as a noise indicator for an arbitrary segmentation model counterpart. Specifically, CAM-Net learns to generate pixel-wise weights to suppress noisy regions with incorrect pseudo-labels while highlighting clean ones by exploiting hybrid strengthened features from image content, providing straightforward and reliable guidance for optimizing the segmentation model. Moreover, to break the barrier of time-consuming training when applying meta-learning to common large segmentation models, we further present a new decoupled training strategy that optimizes different model layers in a divide-and-conquer manner. Extensive experiments on object, medical, remote sensing, and human segmentation show that our method achieves superior performance, approaching that of fully supervised settings, which paves a new promising way for omni-supervised semantic segmentation.

Wasserstein Auto-Encoders of Merge Trees (and Persistence Diagrams).

This article presents a computational framework for the Wasserstein auto-encoding of merge trees (MT-WAE), a novel extension of the classical auto-encoder neural network architecture to the Wasserstein metric space of merge trees. In contrast to traditional auto-encoders which operate on vectorized data, our formulation explicitly manipulates merge trees on their associated metric space at each layer of the network, resulting in superior accuracy and interpretability. Our novel neural network approach can be interpreted as a non-linear generalization of previous linear attempts (Pont et al. 2023) at merge tree encoding. It also trivially extends to persistence diagrams. Extensive experiments on public ensembles demonstrate the efficiency of our algorithms, with MT-WAE computations in the orders of minutes on average. We show the utility of our contributions in two applications adapted from previous work on merge tree encoding (Pont et al. 2023). First, we apply MT-WAE to merge tree compression, by concisely representing them with their coordinates in the final layer of our auto-encoder. Second, we document an application to dimensionality reduction, by exploiting the latent space of our auto-encoder, for the visual analysis of ensemble data. We illustrate the versatility of our framework by introducing two penalty terms, to help preserve in the latent space both the Wasserstein distances between merge trees, as well as their clusters. In both applications, quantitative experiments assess the relevance of our framework. Finally, we provide a C++ implementation that can be used for reproducibility.

Feedback inhibition by a descending GABAergic neuron regulates timing of escape behavior in Drosophila larvae.

Escape behaviors help animals avoid harm from predators and other threats in the environment. Successful escape relies on integrating information from multiple stimulus modalities (of external or internal origin) to compute trajectories toward safe locations, choose between actions that satisfy competing motivations, and execute other strategies that ensure survival. To this end, escape behaviors must be adaptive. When a Drosophila melanogaster larva encounters a noxious stimulus, such as the focal pressure a parasitic wasp applies to the larval cuticle via its ovipositor, it initiates a characteristic escape response. The escape sequence consists of an initial abrupt bending, lateral rolling, and finally rapid crawling. Previous work has shown that the detection of noxious stimuli primarily relies on class IV multi-dendritic arborization neurons (Class IV neurons) located beneath the body wall, and more recent studies have identified several important components in the nociceptive neural circuitry involved in rolling. However, the neural mechanisms that underlie the rolling-escape sequence remain unclear. Here, we present both functional and anatomical evidence suggesting that bilateral descending neurons within the subesophageal zone of D. melanogaster larva play a crucial role in regulating the termination of rolling and subsequent transition to escape crawling. We demonstrate that these descending neurons (designated SeIN128) are inhibitory and receive inputs from a second-order interneuron upstream (Basin-2) and an ascending neuron downstream of Basin-2 (A00c). Together with optogenetic experiments showing that co-activation of SeIN128 neurons and Basin-2 influence the temporal dynamics of rolling, our findings collectively suggest that the ensemble of SeIN128, Basin-2, and A00c neurons forms a GABAergic feedback loop onto Basin-2, which inhibits rolling and thereby facilitates the shift to escape crawling.

Motion In-Betweening via Deep ∆-Interpolator.

We show that the task of synthesizing human motion conditioned on a set of key frames can be solved more accurately and effectively if a deep learning based interpolator operates in the delta mode using the spherical linear interpolator as a baseline. We empirically demonstrate the strength of our approach on publicly available datasets achieving state-of-the-art performance. We further generalize these results by showing that the ∆-regime is viable with respect to the reference of the last known frame (also known as the zero-velocity model). This supports the more general conclusion that operating in the reference frame local to input frames is more accurate and robust than in the global (world) reference frame advocated in previous work.

A Genetic Causal Explainer for Deep Knowledge Tracing

Knowledge tracing (KT) has become an increasingly relevant problem in intelligent education services. Deep learning-based knowledge tracing (DLKT) achieves superb performance in terms of prediction accuracy, but it lacks of explainability, which makes us hard to trust or understand models. The previous work on explaining DLKT was mainly based on gradients or attention scores, which is susceptible to spurious correlations, reducing the credibility of the explanation. To address this limitation, in this paper, we propose a causal explanation method based on the genetic algorithm (GA), named Genetic Causal Explainer(GCE), which constructs a causal framework to estimate the attribution of subsequence to the predictions of DLKT models, and a genetic coding system is designed. Further, A multi-strategy initialization method inspired by domain prior knowledge is proposed, and a global empirical matrix is introduced to capture the causal correlation knowledge during the search process across instances, and guiding the mutation operators. The GCE as a post hoc explanation method can generate explanation results without affecting model training, and can be applied to analyze different DLKT models. Experimental results demonstrate the GCE perform better than other explanation methods in terms of accuracy and readability in quantitative assessments. Meanwhile, the GCE also shows good application prospects in mining educational laws and comparing KT models.

Image Collage on Arbitrary Shape via Shape-Aware Slicing and Optimization.

Image collage is a very useful tool for visualizing an image collection. Most of the existing methods and commercial applications for generating image collages are designed on simple shapes, such as rectangular and circular layouts. This greatly limits the use of image collages in some artistic and creative settings. Although there are some methods that can generate irregularly-shaped image collages, they often suffer from severe image overlapping and excessive blank space. This prevents such methods from being effective information communication tools. In this article, we present a shape slicing algorithm and an optimization scheme that can create image collages of arbitrary shapes in an informative and visually pleasing manner given an input shape and an image collection. To overcome the challenge of irregular shapes, we propose a novel algorithm, called Shape-Aware Slicing, which partitions the input shape into cells based on medial axis and binary slicing tree. Shape-Aware Slicing,which is designed specifically for irregular shapes, takes human perception and shape structure into account to generate visually pleasing partitions. Then, the layout is optimized by analyzing input images with the goal of maximizing the total salient regions of the images. To evaluate our method, we conduct extensive experiments and compare our results against previous work. The evaluations show that our proposed algorithm can efficiently arrange image collections on irregular shapes and create visually superior results than prior work and existing commercial tools.

Complete 3D Relationships Extraction Modality Alignment Network for 3D Dense Captioning.

3D dense captioning aims to semantically describe each object detected in a 3D scene, which plays a significant role in 3D scene understanding. Previous works lack a complete definition of 3D spatial relationships and the directly integrate visual and language modalities, thus ignoring the discrepancies between the two modalities. To address these issues, we propose a novel complete 3D relationship extraction modality alignment network, which consists of three steps: 3D object detection, complete 3D relationships extraction, and modality alignment caption. To comprehensively capture the 3D spatial relationship features, we define a complete set of 3D spatial relationships, including the local spatial relationship between objects and the global spatial relationship between each object and the entire scene. To this end, we propose a complete 3D relationships extraction module based on message passing and self-attention to mine multi-scale spatial relationship features and inspect the transformation to obtain features in different views. In addition, we propose the modality alignment caption module to fuse multi-scale relationship features and generate descriptions to bridge the semantic gap from the visual space to the language space with the prior information in the word embedding, and help generate improved descriptions for the 3D scene. Extensive experiments demonstrate that the proposed model outperforms the state-of-the-art methods on the ScanRefer and Nr3D datasets.

When children choose fantastical events in fiction.

Although stories for children often feature supernatural and fantastical events, children themselves often prefer realistic events when choosing what should happen in a story. In two experiments, we investigated whether 3- to 5-year-olds (total N = 240 from diverse backgrounds) might be more likely to include fantastical events in stories about familiar fantasy characters. In Experiment 1, children saw stories about fantasy or real-world characters (e.g., a mermaid or an ordinary woman) and judged whether they would achieve goals using fantastic or realistic methods. Children were more likely to choose fantastic methods for the fantasy characters, and this tendency was more common in older children. In Experiment 2, children were asked yes/no questions about whether characters could use fantastic, realistic, and unusual methods to achieve goals. Children more often affirmed fantastic methods for fantasy than real-world characters. These findings contrast with previous work suggesting children avoid including fantastic events in fiction and suggest that children use precedent and familiarity to decide what can happen in a story. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Sex-dependent, lateralized engagement of anterior insular cortex inputs to the dorsolateral striatum in binge alcohol drinking.

How does alcohol consumption alter synaptic transmission across time, and do these alcohol-induced neuroadaptations occur similarly in both male and female mice? Previous work shows that anterior insular cortex (AIC) projections to the dorsolateral striatum (DLS) are uniquely sensitive to alcohol-induced neuroadaptations in male, but not female mice, and play a role in governing binge alcohol consumption in male mice. Here, by using high-resolution behavior data paired with in-vivo fiber photometry, we show how similar levels of alcohol intake are achieved via different behavioral strategies across sex, and how inter-drinking session thirst states predict future alcohol intakes in females, but not males. Further, we show how presynaptic calcium activity recorded from AIC synaptic inputs in the DLS across 3 weeks of water consumption followed by 3 weeks of binge alcohol consumption change across, fluid, time, sex, and brain circuit lateralization. By time-locking presynaptic calcium activity from AIC inputs to the DLS to peri-initiation of drinking events we also show that AIC inputs into the left DLS robustly encode binge alcohol intake behaviors relative to water consumption and AIC inputs into the right DLS in males, but not females. These findings suggest a fluid-, sex- and lateralization-dependent role for the engagement of AIC inputs into the DLS that encode binge alcohol consumption behaviors and further contextualize alcohol-induced neuroadaptations at AIC inputs to the DLS.

Separation of sticker-spacer energetics governs the coalescence of metastable biomolecular condensates.

Biological condensates often emerge as a multi-droplet state and never coalesce into one large droplet within the experimental timespan. Previous work revealed that the sticker-spacer architecture of biopolymers may dynamically stabilize the multi-droplet state. Here, we simulate the condensate coalescence using metadynamics approach and reveal two distinct physical mechanisms underlying the fusion of droplets. Condensates made of sticker-spacer polymers readily undergo a kinetic arrest when stickers exhibit slow exchange while fast exchanging stickers at similar levels of saturation allow merger to equilibrium states. On the other hand, condensates composed of homopolymers fuse readily until they reach a threshold density. Increase in entropy upon inter-condensate mixing of chains drives the fusion of sticker-spacer chains. We map the range of mechanisms of kinetic arrest from slow sticker exchange dynamics to density mediated in terms of energetic separation of stickers and spacers. Our predictions appear to be in excellent agreement with recent experiments probing dynamic nature of protein-RNA condensates.

Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting.

Transformers have been widely used for video processing owing to the multi-head self attention (MHSA) mechanism. However, the MHSA mechanism encounters an intrinsic difficulty for video inpainting, since the features associated with the corrupted regions are degraded and incur inaccurate self attention. This problem, termed query degradation, may be mitigated by first completing optical flows and then using the flows to guide the self attention, which was verified in our previous work - flow-guided transformer (FGT). We further exploit the flow guidance and propose FGT++ to pursue more effective and efficient video inpainting. First, we design a lightweight flow completion network by using local aggregation and edge loss. Second, to address the query degradation, we propose a flow guidance feature integration module, which uses the motion discrepancy to enhance the features, together with a flow-guided feature propagation module that warps the features according to the flows. Third, we decouple the transformer along the temporal and spatial dimensions, where flows are used to select the tokens through a temporally deformable MHSA mechanism, and global tokens are combined with the inner-window local tokens through a dual-perspective MHSA mechanism. FGT++ is experimentally evaluated to be outperforming the existing video inpainting networks qualitatively and quantitatively.

Video Coding for Machines: Compact Visual Representation Compression for Intelligent Collaborative Analytics.

As an emerging research practice leveraging recent advanced AI techniques, e.g. deep models based prediction and generation, Video Coding for Machines (VCM) is committed to bridging to an extent separate research tracks of video/image compression and feature compression, and attempts to optimize compactness and efficiency jointly from a unified perspective of high accuracy machine vision and full fidelity human vision. With the rapid advances of deep feature representation and visual data compression in mind, in this paper, we summarize VCM methodology and philosophy based on existing academia and industrial efforts. The development of VCM follows a general rate-distortion optimization, and the categorization of key modules or techniques is established including feature-assisted coding, scalable coding, intermediate feature compression/optimization, and machine vision targeted codec, from broader perspectives of vision tasks, analytics resources, etc. From previous works, it is demonstrated that, although existing works attempt to reveal the nature of scalable representation in bits when dealing with machine and human vision tasks, there remains a rare study in the generality of low bit rate representation, and accordingly how to support a variety of visual analytic tasks. Therefore, we investigate a novel visual information compression for the analytics taxonomy problem to strengthen the capability of compact visual representations extracted from multiple tasks for visual analytics. A new perspective of task relationships versus compression is revisited. By keeping in mind the transferability among different machine vision tasks (e.g. high-level semantic and mid-level geometry-related), we aim to support multiple tasks jointly at low bit rates. In particular, to narrow the dimensionality gap between neural network generated features extracted from pixels and a variety of machine vision features/labels (e.g. scene class, segmentation labels), a codebook hyperprior is designed to compress the neural network-generated features. As demonstrated in our experiments, this new hyperprior model is expected to improve feature compression efficiency by estimating the signal entropy more accurately, which enables further investigation of the granularity of abstracting compact features among different tasks.

HairStyle Editing via Parametric Controllable Strokes.

In this work, we propose a stroke-based hairstyle editing network, dubbed HairstyleNet, allowing users to conveniently change the hairstyles of an image in an interactive fashion. Different from previous works, we simplify the hairstyle editing process where users can manipulate local or entire hairstyles by adjusting the parameterized hair regions. Our HairstyleNet consists of two stages: a stroke parameterization stage and a stroke-to-hair generation stage. In the stroke parameterization stage, we first introduce parametric strokes to approximate the hair wisps, where the stroke shape is controlled by a quadratic Bézier curve and a thickness parameter. Since rendering strokes with thickness to an image is not differentiable, we opt to leverage a neural renderer to construct the mapping from stroke parameters to a stroke image. Thus, the stroke parameters can be directly estimated from hair regions in a differentiable way, enabling us to flexibly edit the hairstyles of input images. In the stroke-to-hair generation stage, we design a hairstyle refinement network that first encodes coarsely composed images of hair strokes, face, and background into latent representations and then generates high-fidelity face images with desirable new hairstyles from the latent codes. Extensive experiments demonstrate that our HairstyleNet achieves state-of-the-art performance and allows flexible hairstyle manipulation.