Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 295291 - 295320 of 5159228

Full-Text Articles in Entire DC Network

Effect Of Zno Nps On Ovarian Histological Structure And Function In Adult Female Rats, Noori M. Luaibi, Faisal G. Lazim, Haidar J. Muhammed Oct 2024

Effect Of Zno Nps On Ovarian Histological Structure And Function In Adult Female Rats, Noori M. Luaibi, Faisal G. Lazim, Haidar J. Muhammed

Baghdad Science Journal

Nanotechnology is one of the most important techniques that is widely used in many fields by changing the physical and chemical properties of materials to form new scale substances called nanoparticles to make them more effective. ZnO NPs is one of these particles that is used in multiple applications, especially in cosmetic and sunscreen products. Thus, the uses of these particles in great quantities make them in constant contact with the body and can enter the circulating blood in a different ways. The aim of this study was to find out the effect of ZnO NPs on the histological structure …

Go to article

Synthesis, Characterization, Industrial And Biological Studies Of Azo Dye Ligand And Their Some Metallic Ions, Abaas Obaid Hussein, Rana Abdulilah Abbas, Jinan M. M. Al-Zinkee, Amerj. Jarad Oct 2024

Synthesis, Characterization, Industrial And Biological Studies Of Azo Dye Ligand And Their Some Metallic Ions, Abaas Obaid Hussein, Rana Abdulilah Abbas, Jinan M. M. Al-Zinkee, Amerj. Jarad

Baghdad Science Journal

4-((2-hydroxy-3,5-dinitrophenyl)diazenyl)-1,5-dimethyl-2-phenyl-1H-pyrazol-3(2H)-one was produced through the reaction of diazonium salt from 4-amino antipyrine with 2,4-dinitrophenol. This ligand is examined by (UV-Vis, FTIR,1H,13CNMR, and LC-Mass) spectral techniques and micro elemental analysis (C.H.N.O). Co(II), Ni(II), Cu(II), and Zn(II) complexes were also performed and depicted. Metal chelates were distinguished by utilizing flame atomic absorption, infrared analysis, and elemental, visible, as well as ultraviolet spectroscopy, in addition to conductivity and magnetic quantification. Methods of mole ratio and continuous contrast have been studied to determine the nature of the compounds. Beer's law was followed throughout a condensation reach of about 1×10-4 - 3×10-4 M/L. A higher …

Go to article

Synthesis And Characterization Of Some New Pyrazole, Triazole, Oxadiazole, Thiazole, Thiadiazole Derivatives Bearing P-Toluenesulfonamide, Maha A. Al-Hamad, Ammar H. Al-Sabawi Oct 2024

Synthesis And Characterization Of Some New Pyrazole, Triazole, Oxadiazole, Thiazole, Thiadiazole Derivatives Bearing P-Toluenesulfonamide, Maha A. Al-Hamad, Ammar H. Al-Sabawi

Baghdad Science Journal

A series of new heterocyclic derivatives A5-A15 have been synthesized using 4-(toluene-4-sulfinylamino)-benzoic acid ethyl ester A2 as a predecessor. This compound A2 was successfully used in synthesis of some new derivatives of oxadiazole, pyrazole, triazole, thiadiazole, thiazole and fused heterocyclic containing p-toluene sulfonamide moiety that supposed to have important biological activities. 1H-NMR, 13C-NMR and FT-IR spectroscopy were used to confirm the prepared compounds.

Go to article

Radioactive Source-Detector System: Design And Monte Carlo Opinion, Zainab Kareem Ali, Ali N. Mohammed Oct 2024

Radioactive Source-Detector System: Design And Monte Carlo Opinion, Zainab Kareem Ali, Ali N. Mohammed

Baghdad Science Journal

In the current research, a computer simulation program was designed and written according to the Monte Carlo method to serve as a virtual practical system instead of a real one. The program has been statistically, geometrically and numerically tested for virtual radioactive source-detector setup. The simulation program is carried out for NaI(Tl) detector, and once for Gieger-Muller counter, for a range of energy up to 10 MeV. The Law of Large Numbers and the Central Limit Theorem were used to test the accuracy and precision of the program’s workflow and an indication of how the results are close to their …

Go to article

Amoxicillin And Favipiravir Bio-Degradation By Aspergillus Flavus Fungus, Rana Hadi Hameed Al-Shammari, Shaimaa Satae M. Ali, Ayad M.J. Al-Mamoori Oct 2024

Amoxicillin And Favipiravir Bio-Degradation By Aspergillus Flavus Fungus, Rana Hadi Hameed Al-Shammari, Shaimaa Satae M. Ali, Ayad M.J. Al-Mamoori

Baghdad Science Journal

The aim of this study is to isolate and characterize Amoxicillin and Favipiravir biodegrading fungi as well as determine their characteristics and degradation pathways. The antibiotic-degrading fungus A. flavus was isolated from polluted wastewater samples using standard Potato Dextrose agar and Czapek–Dox medium. The biodegradation method was investigated in previous mediums with (Amoxicillin and Favipiravir), as the sole carbon sources. Main degradation intermediates were analyzed by high-performance liquid chromatography (HPLC) and used to deduce the antibiotic degradation pathway of strain A. flavus fungal hyphae by Scanning Electron Microscopy before and after 7 days of treatment to find out the accumulation …

Go to article

Antioxidant Activity, Mineral Absorptivity And Chemical Analysis Of P. Graveolens, Kazheen H. Jawzal, Lina Y. Mohammed, Shinwar A. Idrees Oct 2024

Antioxidant Activity, Mineral Absorptivity And Chemical Analysis Of P. Graveolens, Kazheen H. Jawzal, Lina Y. Mohammed, Shinwar A. Idrees

Baghdad Science Journal

This article focuses on Pelargonium graveolens, a fragrant medicinal plant from the Geraniaceae family. The study examines the plant's phytochemical composition, antioxidant activity, and mineral absorptivity, with the plant being grown indoors. The study also examined the plant's ash content and antioxidant activity using a variety of techniques, and the results demonstrated that P. graveolens is effective at absorbing lead. The plant contains eight different minerals, including Cu, Mn, Co, Ni, Pb, Mg, Fe, and Ca. Statistical analysis was used to determine the level of antioxidants present, using DPPH, reducing power, and total antioxidant capacity methods. The extraction process used …

Go to article

Synergistic Influence Of Non-Thermal Plasma And Hydrogen Peroxide On Oxidative Desulfurization (Ods) Of Model Fuel, Noor M. Abdullah, Hussien Q. Hussien, Rana R. Jalil Oct 2024

Synergistic Influence Of Non-Thermal Plasma And Hydrogen Peroxide On Oxidative Desulfurization (Ods) Of Model Fuel, Noor M. Abdullah, Hussien Q. Hussien, Rana R. Jalil

Baghdad Science Journal

Desulfurization is the process of removing the organic sulfur component from fuel oils. In this work, model fuel containing the sulfur compounds benzothiophene and dibenzothiophene was oxidized using plasma technique and plasma technique assisted by 30% hydrogen peroxide. Acetonitrile was used as a polar solvent in a liquid-liquid extraction stage that followed the oxidation reaction to remove the produced sulfones from the model fuel. The oxidation process was performed at operating conditions including the molar ratio of hydrogen peroxide to sulfur (5:1), temperature 50 ºC, air flow rate 75 ml/min, and voltage 11000 volts. The oxidation reaction was done using …

Go to article

The Effectiveness Of Calcium Supplement As Orally Contrast Media For Gastric Magnetic Resonance Imaging, Zainab Abdulla Mankhi, Khalid Ibrahim Riah, Ahmed Mehmood Abdul-Lettif Oct 2024

The Effectiveness Of Calcium Supplement As Orally Contrast Media For Gastric Magnetic Resonance Imaging, Zainab Abdulla Mankhi, Khalid Ibrahim Riah, Ahmed Mehmood Abdul-Lettif

Baghdad Science Journal

The objective of the present work aims to find an alternative oral contrast agent that could be used in magnetic resonance imaging (MRI) of the gastrointestinal system and satisfy the following criteria: it should be safe, it has no or few side effects, it is inexpensive, and it produces the highest imaging quality. The method: We prepared samples (solutions) as oral contrast agents by separately dissolving calcium and magnesium supplements (taken daily dose) in varied quantities of distilled water. In order to identify the sample with the lowest concentration and best quantitative image, the samples were examined in MRI by …

Go to article

Digits Recognition For Arabic Handwritten Through Convolutional Neural Networks, Local Binary Patterns, And Histogram Of Oriented Gradients, Bushra Mahdi Hasan, Zahraa Jasim Jaber, Ahmad Adel Habeeb Oct 2024

Digits Recognition For Arabic Handwritten Through Convolutional Neural Networks, Local Binary Patterns, And Histogram Of Oriented Gradients, Bushra Mahdi Hasan, Zahraa Jasim Jaber, Ahmad Adel Habeeb

Baghdad Science Journal

The recognition of handwritten text is a topic of study that has several applications. One of these applications is the recognition of handwriting in official documents, historical scripts, bank checks, etc., which is a problem that might be considered relatively a security issue. The topic of handwriting recognition has been the subject of a significant amount of study and analysis in recent years. People from a variety of countries, including all of the countries that use Arabic as their primary language, as well as Persian, Urdu, and Pashto languages, also use Arabic characters in their scripts. As people's handwriting is …

Go to article

Jasbo: Jaya Average Subtraction Based Optimization With Deep Learning Model For Multi-Classification Of Infectious Disease From Unstructured Data, Vian Sabeeh, Ahmed Bahaaulddin A. Alwahhab, Ali Abdulmunim Ibrahim Al-Kharaz Oct 2024

Jasbo: Jaya Average Subtraction Based Optimization With Deep Learning Model For Multi-Classification Of Infectious Disease From Unstructured Data, Vian Sabeeh, Ahmed Bahaaulddin A. Alwahhab, Ali Abdulmunim Ibrahim Al-Kharaz

Baghdad Science Journal

Infectious diseases have become an unavoidable big trouble in today's environment with a similar symptomatology that makes difficult of early detection and clear separation of infection. Hence, it is required to generate a new technique that best utilizes the various symptomatologies present in the illnesses for its multi-classification. Medical documents are considered an essential source for modern, invented, and robust analysis methods for accurate infection diagnoses. Accordingly, enriching medical text processing is beneficial in health informatics. In this research, proposed Jaya Average Subtraction Based Optimization (JASBO), which is enabled by Deep Learning (DL) is used to classify infectious diseases into …

Go to article

A New Invariant Regarding Irreversible K-Threshold Conversion Processes On Some Graphs, Ramy Shaheen, Suhail Mahfud, Ali Kassem Oct 2024

A New Invariant Regarding Irreversible K-Threshold Conversion Processes On Some Graphs, Ramy Shaheen, Suhail Mahfud, Ali Kassem

Baghdad Science Journal

An irreversible k-threshold conversion (k-conversion in short) process on a graph ��=(��,��)is a specific type of graph diffusion problems which particularly studies the spread of a change of state of the vertices of the graph starting with an initial chosen set while the conversion spread occurs according to a pre -determined conversion rule. Irreversible k-conversion study the diffusion of a conversion of state (from 0 to 1) on the vertex set of a graph ��=(��,��). At the first step ��=0,a set ��0⊆��.is selected and for ��∈{1,2,...,};����is obtained by adding all vertices that have k or more neighbors in ����−1to ����−1. …

Go to article

Fixed Point Results For Almost Contraction Mappings In Fuzzy Metric Space, Raghad I. Sabri, Buthainah A. A. Ahmed Oct 2024

Fixed Point Results For Almost Contraction Mappings In Fuzzy Metric Space, Raghad I. Sabri, Buthainah A. A. Ahmed

Baghdad Science Journal

In certain mathematical, computing, economic, and modeling issues, the presence of a solution to a theoretical or real-world problem is synonymous with the presence of a fixed point (Fp) for an appropriate mapping. Consequently, Fp plays an essential role in a wide variety of mathematical and scientific contexts. In its own right, the theory is a stunning amalgamation of analysis (both pure and applied), geometry, and topology. Recent years have shown the theory of Fps is a highly strong and useful tool in the study of nonlinear events. Fp theorems are concerned with mappings f of a set X into …

Go to article

Biogenic Functionalized Zno/Cuo Nanocomposite Sensor For Potentiometric Determination Of Pseudoephedrine-Hcl In Pure And Commercial Products, Fadam M. Abdoon, Sarhan A. Salman, Hasan M. Hasan, Suham T. Ameen, Maha F. El-Tohamy Oct 2024

Biogenic Functionalized Zno/Cuo Nanocomposite Sensor For Potentiometric Determination Of Pseudoephedrine-Hcl In Pure And Commercial Products, Fadam M. Abdoon, Sarhan A. Salman, Hasan M. Hasan, Suham T. Ameen, Maha F. El-Tohamy

Baghdad Science Journal

The ultrafunctional potential of zinc oxide (ZnO) and copper oxide (CuO) nanoparticles (NPs) has generated a great interest in using such metal oxides as remarkable and electroactive nanocomposites in the studies on potentiometry and sensors. These nano-oxides were prepared from the extract of Leucaena leucocephala seeds as an environmentally friendly process. The development of a ZnO/CuO “core-shell nanocomposite-modified” coated copper wire film sensor was proposed as a new method for potentiometric determination of pseudoephedrine hydrochloride (PSD) in pure and pharmaceutical dosage forms. With the existence of polyvinyl chloride (PVC) as a polymer with high molecular weight and “o-nitrophenyl octyl ether …

Go to article

Third-Order Differential Subordination For Generalized Struve Function Associated With Meromorphic Functions, Suha J. Hammad, Abdul Rahman S. Juma, Hassan H. Ebrahim Oct 2024

Third-Order Differential Subordination For Generalized Struve Function Associated With Meromorphic Functions, Suha J. Hammad, Abdul Rahman S. Juma, Hassan H. Ebrahim

Baghdad Science Journal

Previously, many works dealt with the study of the order differential subordination and shortly after that other studies dealt with the order differential subordination in the unit disc. Recently the order differential subordination was presented by Antonino and Miller (2011). This paper looks at a considerably broader class of order differential inequalities and subordination. The authors define the criteria on an admissible class of operators, implying that order differentiale subordination exists. Meromorphic in is a function that is holomorphic in domain except for poles. If it simply states the function is meromorphic. Meromorphic functions in are those that may be …

Go to article

Context-Aware Location Privacy Protection Method, Haohua Qing, Roliana Ibrahim, Hui Wen Nies Oct 2024

Context-Aware Location Privacy Protection Method, Haohua Qing, Roliana Ibrahim, Hui Wen Nies

Baghdad Science Journal

Location privacy protection has drawn increasing attention with the popularity of location-based services. This study proposes a context-aware location privacy protection method (CA-LP). CA-LP evaluates users' location privacy needs by mining their historical trajectories and estimating the privacy leakage degree of locations. Experiments compare CA-LP with other methods on metrics like privacy protection level, quality of service, privacy leakage risk, information loss, and average anonymous time. Results demonstrate CA-LP provides better privacy protection and service quality when considering all factors. CA-LP shows extensive practical value in location sharing applications.

Go to article

A Stage Structure Prey Predator Model Using Pentagonal Fuzzy Numbers And Functional Response, Vinothini P., Kavitha K. Oct 2024

A Stage Structure Prey Predator Model Using Pentagonal Fuzzy Numbers And Functional Response, Vinothini P., Kavitha K.

Baghdad Science Journal

In the present study, our work is focused on a prey predator model with a stage structure for the prey. The objective of the study is to find the behavior of the model using parameter values in the presence of Pentagonal fuzzy numbers. The interaction between the species is done by using functional responses, such as the Holling type I reaction for immature prey and the Crowley Martin functional response for mature prey. Prey population categorized as immature and mature prey. The idea of the problem is to construct a fuzzy theoretical method which helps us to create a model …

Go to article

Sexual Dimorphism And Reproductive Biology Of Bronze Featherback (Notopterus Notopterus, Pallas 1769) From Kelekar River, Ogan Ilir, South Sumatra, Indonesia, Muslim Muslim, Mochamad Syaifudin, Ferdinand Hukama Taqwa, Muhammad Iqbal Saputra Oct 2024

Sexual Dimorphism And Reproductive Biology Of Bronze Featherback (Notopterus Notopterus, Pallas 1769) From Kelekar River, Ogan Ilir, South Sumatra, Indonesia, Muslim Muslim, Mochamad Syaifudin, Ferdinand Hukama Taqwa, Muhammad Iqbal Saputra

Baghdad Science Journal

Sexual dimorphism and reproductive biology are fundamental aspects of fish breeding studies. The aim of this research was to analyze the sexual dimorphism and reproductive biology of Notopterus notopterus. A total of 74 N. notopterus were collected from the Kelekar River in Ogan Ilir Regency, Indonesia, consisting of 38 males (TL: 18–23.6 cm; BW: 35.1–92.1 g) and 36 females (TL: 19.6-26.3 cm; BW: 49.4–133.8 g). Seventeen morphometric characters, three meristic characters, and five reproductive biological parameters were analyzed. The results showed the differences in the morphometric characteristics of male and female N. notopterus. However, there was no difference in the …

Go to article

Comparison Of Physical Characteristics Of Mass And Luminosity Function Of Disk Systems In Barred And Unbarred Spiral Galaxies, Al Najm M.N., Y. E. Rashed, H. H. Al-Dahlaki Oct 2024

Comparison Of Physical Characteristics Of Mass And Luminosity Function Of Disk Systems In Barred And Unbarred Spiral Galaxies, Al Najm M.N., Y. E. Rashed, H. H. Al-Dahlaki

Baghdad Science Journal

Among the most important ways to investigate galaxies' distribution over cosmic time is the luminosity function LF in terms of baryonic disc mass ψ^S(Ms), magnitude Ø^B(MB). We have studied an estimate of the baryon mass density in the sample of barred and unbarred spiral-type galaxies from previous literature, which virtually involves, for each class of objects with visible baryon content, an integral over the luminosity of the product of the luminosity function (LF) and the mass-to-light ratio. The multiple regression technique used the statistical software package in our study and results, such as database analysis and graphing software (Statistics Win …

Go to article

Transformer-Based Joint Learning Approach For Text Normalization In Vietnamese Automatic Speech Recognition Systems, The Viet Bui, Tho Chi Luong, Oanh Thi Tran Oct 2024

Transformer-Based Joint Learning Approach For Text Normalization In Vietnamese Automatic Speech Recognition Systems, The Viet Bui, Tho Chi Luong, Oanh Thi Tran

Research Collection School Of Computing and Information Systems

In this article, we investigate the task of normalizing transcribed texts in Vietnamese Automatic Speech Recognition (ASR) systems in order to improve user readability and the performance of downstream tasks. This task usually consists of two main sub-tasks: predicting and inserting punctuation (i.e., period, comma); and detecting and standardizing named entities (i.e., numbers, person names) from spoken forms to their appropriate written forms. To achieve these goals, we introduce a complete corpus including of 87,700 sentences and investigate conditional joint learning approaches which globally optimize two sub-tasks simultaneously. The experimental results are quite promising. Overall, the proposed architecture outperformed the …

Go to article

Hisoma: A Hierarchical Multi-Agent Model Integrating Self-Organizing Neural Networks With Multi-Agent Deep Reinforcement Learning, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan Oct 2024

Hisoma: A Hierarchical Multi-Agent Model Integrating Self-Organizing Neural Networks With Multi-Agent Deep Reinforcement Learning, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Multi-agent deep reinforcement learning (MADRL) has shown remarkable advancements in the past decade. However, most current MADRL models focus on task-specific short-horizon problems involving a small number of agents, limiting their applicability to long-horizon planning in complex environments. Hierarchical multi-agent models offer a promising solution by organizing agents into different levels, effectively addressing tasks with varying planning horizons. However, these models often face constraints related to the number of agents or levels of hierarchies. This paper introduces HiSOMA, a novel hierarchical multi-agent model designed to handle long-horizon, multi-agent, multi-task decision-making problems. The top-level controller, FALCON, is modeled as a class …

Go to article

Motif Graph Neural Network, Xuexin Chen, Ruicui Cai, Yuan Fang, Min Wu, Zijian Li, Zhifeng Hao Oct 2024

Motif Graph Neural Network, Xuexin Chen, Ruicui Cai, Yuan Fang, Min Wu, Zijian Li, Zhifeng Hao

Research Collection School Of Computing and Information Systems

Graphs can model complicated interactions between entities, which naturally emerge in many important applications. These applications can often be cast into standard graph learning tasks, in which a crucial step is to learn low-dimensional graph representations. Graph neural networks (GNNs) are currently the most popular model in graph embedding approaches. However, standard GNNs in the neighborhood aggregation paradigm suffer from limited discriminative power in distinguishing high-order graph structures as opposed to low-order structures. To capture high-order structures, researchers have resorted to motifs and developed motif-based GNNs. However, the existing motif-based GNNs still often suffer from less discriminative power on high-order …

Go to article

Joint Weakly Supervised Image Emotion Analysis Based On Interclass Discrimination And Intraclass Correlation, Xinyue Zhang, Zhaoxia Wang, Guitao Cao, Seng-Beng Ho Oct 2024

Joint Weakly Supervised Image Emotion Analysis Based On Interclass Discrimination And Intraclass Correlation, Xinyue Zhang, Zhaoxia Wang, Guitao Cao, Seng-Beng Ho

Research Collection School Of Computing and Information Systems

Regional information-based image emotion analysis has recently garnered significant attention. However, existing methods often focus on identifying region proposals through layered steps or merely rely on visual saliency. These approaches may lead to an underestimation of emotional categories and a lack of comprehensive interclass discrimination perception and emotional intraclass contextual mining. To address these limitations, we propose a novel approach named InterIntraIEA, which combines interclass discrimination and intraclass correlation joint learning capabilities for image emotion analysis. The proposed method not only employs category-specific dictionary learning for class adaptation, but also models intraclass contextual relationships and perceives correlations at the channel …

Go to article

Temporal Relational Graph Convolutional Network Approach To Financial Performance Prediction, Jeyaraman Brindha Priyadarshini, Bing Tian Dai, Yuan Fang Oct 2024

Temporal Relational Graph Convolutional Network Approach To Financial Performance Prediction, Jeyaraman Brindha Priyadarshini, Bing Tian Dai, Yuan Fang

Research Collection School Of Computing and Information Systems

Accurately predicting financial entity performance remains a challenge due to the dynamic nature of financial markets and vast unstructured textual data. Financial knowledge graphs (FKGs) offer a structured representation for tackling this problem by representing complex financial relationships and concepts. However, constructing a comprehensive and accurate financial knowledge graph that captures the temporal dynamics of financial entities is non-trivial. We introduce FintechKG, a comprehensive financial knowledge graph developed through a three-dimensional information extraction process that incorporates commercial entities and temporal dimensions and uses a financial concept taxonomy that ensures financial domain entity and relationship extraction. We propose a temporal and …

Go to article

Enhancing Recipe Retrieval With Foundation Models: A Data Augmentation Perspective, Fangzhou Song, Bin Zhu, Yanbin Hao, Shuo Wang Oct 2024

Enhancing Recipe Retrieval With Foundation Models: A Data Augmentation Perspective, Fangzhou Song, Bin Zhu, Yanbin Hao, Shuo Wang

Research Collection School Of Computing and Information Systems

Learning recipe and food image representation in common embedding space is non-trivial but crucial for cross-modal recipe retrieval. In this paper, we propose a new perspective for this problem by utilizing foundation models for data augmentation. Leveraging on the remarkable capabilities of foundation models (i.e., Llama2 and SAM), we propose to augment recipe and food image by extracting alignable information related to the counterpart. Specifically, Llama2 is employed to generate a textual description from the recipe, aiming to capture the visual cues of a food image, and SAM is used to produce image segments that correspond to key ingredients in …

Go to article

Risurconv : Rotation Invariant Surface Attention-Augmented Convolutions For 3d Point Cloud Classification And Segmentation, Zhiyuan Zhang, Licheng Yang, Xiang Zhiyu Oct 2024

Risurconv : Rotation Invariant Surface Attention-Augmented Convolutions For 3d Point Cloud Classification And Segmentation, Zhiyuan Zhang, Licheng Yang, Xiang Zhiyu

Research Collection School Of Computing and Information Systems

Despite the progress on 3D point cloud deep learning, most prior works focus on learning features that are invariant to translation and point permutation, and very limited efforts have been devoted for rotation invariant property. Several recent studies achieve rotation invariance at the cost of lower accuracies. In this work, we close this gap by proposing a novel yet effective rotation invariant architecture for 3D point cloud classification and segmentation. Instead of traditional pointwise operations, we construct local triangle surfaces to capture more detailed surface structure, based on which we can extract highly expressive rotation invariant surface properties which are …

Go to article

Desk2desk : Optimization-Based Mixed Reality Workspace Integration For Remote Side-By-Side Collaboration, Ludwig Sidenmark, Tianyu Zhang, Leen Al Lababidi, Jiannan Li, Tovi Grossman Oct 2024

Desk2desk : Optimization-Based Mixed Reality Workspace Integration For Remote Side-By-Side Collaboration, Ludwig Sidenmark, Tianyu Zhang, Leen Al Lababidi, Jiannan Li, Tovi Grossman

Research Collection School Of Computing and Information Systems

Mixed Reality enables hybrid workspaces where physical and virtual monitors are adaptively created and moved to suit the current environment and needs. However, in shared settings, individual users’ workspaces are rarely aligned and can vary significantly in the number of monitors, available physical space, and workspace layout, creating inconsistencies between workspaces which may cause confusion and reduce collaboration. We present Desk2Desk, an optimization-based approach for remote collaboration in which the hybrid workspaces of two collaborators are fully integrated to enable immersive side-by-side collaboration. The optimization adjusts each user’s workspace in layout and number of shared monitors and creates a mapping …

Go to article

Improving Out-Of-Distribution Detection With Disentangled Foreground And Background Features, Choubo Ding, Guansong Pang Oct 2024

Improving Out-Of-Distribution Detection With Disentangled Foreground And Background Features, Choubo Ding, Guansong Pang

Research Collection School Of Computing and Information Systems

Detecting out-of-distribution (OOD) inputs is a principal task for ensuring the safety of deploying deep-neural-network classifiers in open-set scenarios. OOD samples can be drawn from arbitrary distributions and exhibit deviations from in-distribution (ID) data in various dimensions, such as foreground features (e.g., objects in CIFAR100 images vs. those in CIFAR10 images) and background features (e.g., textural images vs. objects in CIFAR10). Existing methods can confound foreground and background features in training, failing to utilize the background features for OOD detection. This paper considers the importance of feature disentanglement in out-of-distribution detection and proposes the simultaneous exploitation of both foreground and …

Go to article

Zero-Shot Object Counting With Good Exemplars, Huilin Zhu, Jingling Yuan, Zhengwei Yang, Yu Guo, Zheng Wang, Xian Zhong, Shengfeng He Oct 2024

Zero-Shot Object Counting With Good Exemplars, Huilin Zhu, Jingling Yuan, Zhengwei Yang, Yu Guo, Zheng Wang, Xian Zhong, Shengfeng He

Research Collection School Of Computing and Information Systems

Zero-shot object counting (ZOC) aims to enumerate objects in images using only the names of object classes during testing, without the need for manual annotations. However, a critical challenge in current ZOC methods lies in their inability to identify high-quality exemplars effectively. This deficiency hampers scalability across diverse classes and undermines the development of strong visual associations between the identified classes and image content. To this end, we propose the Visual Association-based Zero-shot Object Counting (VA-Count) framework. VACount consists of an Exemplar Enhancement Module (EEM) and a Noise Suppression Module (NSM) that synergistically refine the process of class exemplar identification …

Go to article

Onerestore : A Universal Restoration Framework For Composite Degradation, Yu Guo, Yuan Gao, Yuxu Lu, Huilin Zhu, Ryan Wen Liu, Shengfeng He Oct 2024

Onerestore : A Universal Restoration Framework For Composite Degradation, Yu Guo, Yuan Gao, Yuxu Lu, Huilin Zhu, Ryan Wen Liu, Shengfeng He

Research Collection School Of Computing and Information Systems

In real-world scenarios, image impairments often manifest as composite degradations, presenting a complex interplay of elements such as low light, haze, rain, and snow. Despite this reality, existing restoration methods typically target isolated degradation types, thereby falling short in environments where multiple degrading factors coexist. To bridge this gap, our study proposes a versatile imaging model that consolidates four physical corruption paradigms to accurately represent complex, composite degradation scenarios. In this context, we propose OneRestore, a novel transformer-based framework designed for adaptive, controllable scene restoration. The proposed framework leverages a unique cross-attention mechanism, merging degraded scene descriptors with image features, …

Go to article

Latent Representation Learning For Geospatial Entities, Ween Jiann Lee, Hady Wirawan Lauw Oct 2024

Latent Representation Learning For Geospatial Entities, Ween Jiann Lee, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Representation learning has been instrumental in the success of machine learning, offering compact and performant data representations for diverse downstream tasks. In the spatial domain, it has been pivotal in extracting latent patterns from various data types, including points, polylines, polygons, and networked structures. However, existing approaches often fall short of explicitly capturing both semantic and spatial information, relying on proxies and synthetic features. This article presents GeoNN, a novel graph neural network-based model designed to learn spatially-aware embeddings for geospatial entities. GeoNN leverages edge features generated from geodesic functions, dynamically selecting relevant features based on relative locations. It introduces …

Go to article

First Prev Next Last