Search

Human immune system contains white blood cells (WBC) that are good indicator of many diseases like bacterial infections, AIDS, cancer, spleen, etc. White blood cells have been sub classified into four types: monocytes, lymphocytes, eosinophils and neutrophils on the basis of their nucleus, shape and cytoplasm. Traditionally in laboratories, pathologists and hematologists analyze these blood cells through microscope and then classify them manually. This manual process takes more time and increases the chance of human error. Hence, there is a need to automate this process. In this paper, first we have used different CNN pre-train models such as ResNet-50, InceptionV3, VGG16 and MobileNetV2 to automatically classify the white blood cells. These pre-train models are applied on Kaggle dataset of microscopic images. Although we achieved reasonable accuracy ranging between 92 to 95%, still there is need to enhance the performance. Hence, inspired by these architectures, a framework has been proposed to automatically categorize the four kinds of white blood cells with increased accuracy. The aim is to develop a convolution neural network (CNN) based classification system with decent generalization ability. The proposed CNN model has been tested on white blood cells images from Kaggle and LISC datasets. Accuracy achieved is 99.57% and 98.67% for both datasets respectively. Our proposed convolutional neural network-based model provides competitive performance as compared to previous results reported in literature.

Trapped-ion hardware based on the Magnetic Gradient Induced Coupling (MAGIC) scheme is emerging as a promising platform for quantum computing. Nevertheless, in this (as in any other) quantum-computing platform, many technical questions still have to be resolved before large-scale and error-tolerant applications are possible. In this work, we present a thorough discussion of the contribution of higher-order terms to the MAGIC setup, which can occur due to anharmonicities in the external potential of the ion crystal (e.g., through Coulomb repulsion) or through curvature of the applied magnetic field. These terms take the form of three-spin couplings as well as diverse terms that couple spins to phonons. We find that most of these are negligible in realistic situations, with only two contributions that need careful attention. First, there are parasitic longitudinal fields whose strength increases with chain length, but which can easily be compensated by a microwave detuning. Second, anharmonicities of the Coulomb interaction can lead to well-known two-to-one conversions of phonon excitations, which can be avoided if the phonons are ground-state cooled. Our detailed analysis constitutes an important contribution on the way of making magnetic-gradient trapped-ion quantum technology fit for large-scale applications, and it may inspire new ways to purposefully design interaction terms., Comment: 14 pages, 4 figures

We introduce jina-embeddings-v3, a novel text embedding model with 570 million parameters, achieves state-of-the-art performance on multilingual data and long-context retrieval tasks, supporting context lengths of up to 8192 tokens. The model includes a set of task-specific Low-Rank Adaptation (LoRA) adapters to generate high-quality embeddings for query-document retrieval, clustering, classification, and text matching. Evaluation on the MTEB benchmark shows that jina-embeddings-v3 outperforms the latest proprietary embeddings from OpenAI and Cohere on English tasks, while achieving superior performance compared to multilingual-e5-large-instruct across all multilingual tasks. With a default output dimension of 1024, users can flexibly reduce the embedding dimensions to as low as 32 without compromising performance, enabled by Matryoshka Representation Learning., Comment: 20 pages, pp11-13 references, pp14-20 appendix and experiment tables

Practical robotic adhoc networks (RANETs), a type of mobile wireless adhoc networks (WANETs) supporting the WiFi-Direct modes common in internet of things and phone devices, is proposed based on a strategy of exploiting WiFi-Direct connection modes to overcome hardware restrictions. For a certain period of time the community was enthusiastic about the endless opportunities in fair, robust, efficient, and cheap communication created by the Adhoc mode of the WiFi IEEE 802.11 independent basic service set (IBSS) configuration that required no dedicated access points. The mode was a main enabler of wireless Adhoc networks (WANETS). This communication mode unfortunately did not get into the standard network cards present in IoT and mobile phones, likely due to the high energy consumption it exacts. Rather, such devices implement WiFi-Direct which is designed for star topologies. Several attempts were made to overcame the restriction and support WANETs, but they break at least the fairness and symmetry property, thereby reducing applicability. Here we show a solution for fair RANETs and evaluate the behavior of various strategies using simulations., Comment: Presented at the FCRAR 24 conference in May 2024 (Florida Conference on Recent Advances in Robotics)

Multi-vector dense models, such as ColBERT, have proven highly effective in information retrieval. ColBERT's late interaction scoring approximates the joint query-document attention seen in cross-encoders while maintaining inference efficiency closer to traditional dense retrieval models, thanks to its bi-encoder architecture and recent optimizations in indexing and search. In this work we propose a number of incremental improvements to the ColBERT model architecture and training pipeline, using methods shown to work in the more mature single-vector embedding model training paradigm, particularly those that apply to heterogeneous multilingual data or boost efficiency with little tradeoff. Our new model, Jina-ColBERT-v2, demonstrates strong performance across a range of English and multilingual retrieval tasks., Comment: 8 pages, references at pp7,8; EMNLP workshop submission

We propose self-similar contracting groups as a platform for cryptographic schemes based on simultaneous conjugacy search problem (SCSP). The class of these groups contains extraordinary examples like Grigorchuk group, which is known to be non-linear, thus making some of existing attacks against SCSP inapplicable. The groups in this class admit a natural normal form based on the notion of a nucleus portrait, that plays a key role in our approach. While for some groups in the class the conjugacy search problem has been studied, there are many groups for which no algorithms solving it are known. Moreover, there are some self-similar groups with undecidable conjugacy problem. We discuss benefits and drawbacks of using these groups in group-based cryptography and provide computational analysis of variants of the length-based attack on SCSP for some groups in the class, including Grigorchuk group, Basilica group, and others., Comment: 37 pages, 13 figures

The global positioning system (GPS) has become an indispensable navigation method for field operations with unmanned surface vehicles (USVs) in marine environments. However, GPS may not always be available outdoors because it is vulnerable to natural interference and malicious jamming attacks. Thus, an alternative navigation system is required when the use of GPS is restricted or prohibited. To this end, we present a novel method that utilizes an Unmanned Aerial Vehicle (UAV) to assist in localizing USVs in GNSS-restricted marine environments. In our approach, the UAV flies along the shoreline at a consistent altitude, continuously tracking and detecting the USV using a deep learning-based approach on camera images. Subsequently, triangulation techniques are applied to estimate the USV's position relative to the UAV, utilizing geometric information and datalink range from the UAV. We propose adjusting the UAV's camera angle based on the pixel error between the USV and the image center throughout the localization process to enhance accuracy. Additionally, visual measurements are integrated into an Extended Kalman Filter (EKF) for robust state estimation. To validate our proposed method, we utilize a USV equipped with onboard sensors and a UAV equipped with a camera. A heterogeneous robotic interface is established to facilitate communication between the USV and UAV. We demonstrate the efficacy of our approach through a series of experiments conducted during the ``Muhammad Bin Zayed International Robotic Challenge (MBZIRC-2024)'' in real marine environments, incorporating noisy measurements and ocean disturbances. The successful outcomes indicate the potential of our method to complement GPS for USV navigation.

The research was conducted at the College of Agricultural Sciences Engineering/University of Sulaimani/ Kurdistan Region-Iraqi to investigate effects of different concentrations of IBA (0, 3000, 4000 and 5000 ppm) and soaking in water for 24 hours on propagation black mulberry (Morus nigra L.) by hardwood cuttings. In this research the parameters of rooting percentage, root number, root length, sprout bud number, shoot length and shoot diameter were measured. Effect of individual factors showed that the highest rooting percentage (15%) was achieved in cuttings soaked in water for 24 hours, as well as improving other traits. Also, the best (23.33%) rooting was found in cuttings dipped in 4000 ppm IBA. Interaction effects of the two factors showed that cuttings treated with 4000 ppm IBA and soaked in water for 24 hours gave the highest (40%) rooting, and the highest other root and shoot traits were achieved in the same interaction as well.

Randomization is a powerful tool that endows algorithms with remarkable properties. For instance, randomized algorithms excel in adversarial settings, often surpassing the worst-case performance of deterministic algorithms with large margins. Furthermore, their success probability can be amplified by simple strategies such as repetition and majority voting. In this paper, we enhance deep neural networks, in particular transformer models, with randomization. We demonstrate for the first time that randomized algorithms can be instilled in transformers through learning, in a purely data- and objective-driven manner. First, we analyze known adversarial objectives for which randomized algorithms offer a distinct advantage over deterministic ones. We then show that common optimization techniques, such as gradient descent or evolutionary strategies, can effectively learn transformer parameters that make use of the randomness provided to the model. To illustrate the broad applicability of randomization in empowering neural networks, we study three conceptual tasks: associative recall, graph coloring, and agents that explore grid worlds. In addition to demonstrating increased robustness against oblivious adversaries through learned randomization, our experiments reveal remarkable performance improvements due to the inherently random nature of the neural networks' computation and predictions.

The versatile nature of Visual Sentiment Analysis (VSA) is one reason for its rising profile. It isn't easy to efficiently manage social media data with visual information since previous research has concentrated on Sentiment Analysis (SA) of single modalities, like textual. In addition, most visual sentiment studies need to adequately classify sentiment because they are mainly focused on simply merging modal attributes without investigating their intricate relationships. This prompted the suggestion of developing a fusion of deep learning and machine learning algorithms. In this research, a deep feature-based method for multiclass classification has been used to extract deep features from modified ResNet50. Furthermore, gradient boosting algorithm has been used to classify photos containing emotional content. The approach is thoroughly evaluated on two benchmarked datasets, CrowdFlower and GAPED. Finally, cutting-edge deep learning and machine learning models were used to compare the proposed strategy. When compared to state-of-the-art approaches, the proposed method demonstrates exceptional performance on the datasets presented., Comment: 4 pages, 4 figures, 3 tables, IEEE International Conference on Multimedia Information Processing and Retrieval (MIPR) 2024

In this paper, we examine a discrete dynamical system defined by x(n+1) = Ax(n)+ w(n), where x takes values in a Hilbert space H and w is a periodic source with values in a fixed closed subspace W of H. Our goal is to identify conditions on some spatial sampling system G = {gj: j in J} of H that enable stable recovery of the unknown source term w from space-time samples {: n >=0,j in J}. We provide necessary and sufficient conditions on G = {g_j }_{j in J} to ensure stable recovery of any w in W . Additionally, we explicitly construct an operator R, dependent on G, such that R{}_n,j} = w., Comment: 12 pages

We show that, up to connected sums with integer homology $L$-spaces, bordered Floer homology detects handlebodies, as well as whether a mapping class extends over a given handlebody or compression body. Using this, we combine ideas of Casson-Long with the theory of train tracks to give an algorithm using bordered Floer homology to detect whether a mapping class extends over any compression body., Comment: 62 pages, 27 figures. V2: minor corrections to background

We present a model to describe the concentration-dependent growth of protein filaments. Our model contains two states, a low entropy/high affinity ordered state and a high entropy/low affinity disordered state. Consistent with experiments, our model shows a diffusion-limited linear growth regime at low concentration, followed by a concentration independent plateau at intermediate concentrations, and rapid disordered precipitation at the highest concentrations. We show that growth in the linear and plateau regions is the result of two processes that compete amid the rapid binding and unbinding of non-specific states. The first process is the addition of ordered molecules during the periods where the end of the filament is free of incorrectly bound molecules. The second process is the capture of defects, which occurs when consecutive ordered additions occur on top of incorrectly bound molecules. We show that a key molecular property is the probability that a diffusive collision results in a correctly bound state. Small values of this probability suppress the defect capture growth mode, resulting in a plateau in the growth rate when incorrectly bound molecules become common enough to poison ordered growth. We show that conditions that non-specifically suppress or enhance intermolecular interactions, such as the addition of depletants or osmolytes, have opposite effects on the growth rate in the linear and plateau regimes. In the linear regime stronger interactions promote growth by reducing dissolution events, but in the plateau regime stronger interactions inhibit growth by stabilizing incorrectly bound molecules., Comment: 20 pages, 7 figures

Effective flood hazard management requires evaluating and predicting flash flood susceptibility. Convolutional neural networks (CNNs) are commonly used for this task but face issues like gradient explosion and overfitting. This study explores the use of an attention mechanism, specifically the convolutional block attention module (CBAM), to enhance CNN models for flash flood susceptibility in the ungauged Rheraya watershed, a flood prone region. We used ResNet18, DenseNet121, and Xception as backbone architectures, integrating CBAM at different locations. Our dataset included 16 conditioning factors and 522 flash flood inventory points. Performance was evaluated using accuracy, precision, recall, F1-score, and the area under the curve (AUC) of the receiver operating characteristic (ROC). Results showed that CBAM significantly improved model performance, with DenseNet121 incorporating CBAM in each convolutional block achieving the best results (accuracy = 0.95, AUC = 0.98). Distance to river and drainage density were identified as key factors. These findings demonstrate the effectiveness of the attention mechanism in improving flash flood susceptibility modeling and offer valuable insights for disaster management.

Using refractive metasurfaces (RMTSs) as part of the antenna design offers a promising solution to the ever-increasing demand for improved energy efficiency of wireless communications. To overcome the limitations of using one RMTS layer, a recent proposal is to cascade multiple layers, a structure called stacked intelligent metasurfaces (SIMs) where the desired precoder and combiner is formed in the wave domain. However, while proposing the antenna structure, the analysis did not account for the attendant limitations imposed by the hardware used which has a significant impact on the performance of SIMs. In this paper, we study the achievable sum-rate of a SIM antenna in an uplink wireless communication scenario accounting for hardware limitations. We begin by proposing a system model that captures both the effect of noise and hardware limitations in these systems. We then formulate the achievable sum-rate problem; since optimizing the rate is non-convex, we propose two approaches: a gradient ascent algorithm and an interior point method to find a close-to-optimum combiner. To show the efficiency of using SIMs at a basestation, we compare the achievable sum-rate with that of a digital phased array (DPA). We provide two comparisons: first, in Rayleigh fading and realistic 3GPP channels and then under a constraint of an equal number of radio frequency (RF) chains and equal physical aperture size constraint. Our results show that SIM antennas can surpass DPA performance under an equal number of RF chains but has inferior performance under equal aperture size.

Dynamic Metasurface Antennas (DMAs) have emerged as promising candidates for basestation deployment in the next generation of wireless communications. While overlooking the practical and hardware limitations of DMA, previous studies have highlighted DMAs' potential to deliver high data rates while maintaining low power consumption. In this paper, we address this oversight by analyzing the impact of practical hardware limitations such as antenna efficiency, power consumed in required components, processing limitations, etc. Specifically, we investigate DMA-assisted wireless communications in the uplink and propose a model which accounts for these hardware limitations. To do so, we propose a concise model to characterize the power consumption of a DMA. For a fair assessment, we propose a wave-domain combiner, based on holography theory, to maximize the achievable sum rate of DMA-assisted antennas. We compare the achievable sum rate and energy efficiency of DMA antennas with that of a partially connected hybrid phased array. Our findings reveal the true potential of DMAs when accounting for the limitations of both designs.

Many tasks can be composed from a few independent components. This gives rise to a combinatorial explosion of possible tasks, only some of which might be encountered during training. Under what circumstances can transformers compositionally generalize from a subset of tasks to all possible combinations of tasks that share similar components? Here we study a modular multitask setting that allows us to precisely control compositional structure in the data generation process. We present evidence that transformers learning in-context struggle to generalize compositionally on this task despite being in principle expressive enough to do so. Compositional generalization becomes possible only when introducing a bottleneck that enforces an explicit separation between task inference and task execution., Comment: ICML 2024 workshop on Next Generation of Sequence Modeling Architectures

Quantum devices need precise control to achieve their full capability. In this work, we address the problem of controlling closed quantum systems, tackling two main issues. First, in practice the control signals are usually subject to unknown classical distortions that could arise from the device fabrication, material properties and/or instruments generating those signals. Second, in most cases modeling the system is very difficult or not even viable due to uncertainties in the relations between some variables and inaccessibility to some measurements inside the system. In this paper, we introduce a general model-free control approach based on deep reinforcement learning (DRL), that can work for any closed quantum system. We train a deep neural network (NN), using the REINFORCE policy gradient algorithm to control the state probability distribution of a closed quantum system as it evolves, and drive it to different target distributions. We present a novel controller architecture that comprises multiple NNs. This enables accommodating as many different target state distributions as desired, without increasing the complexity of the NN or its training process. The used DRL algorithm works whether the control problem can be modeled as a Markov decision process (MDP) or a partially observed MDP. Our method is valid whether the control signals are discrete- or continuous-valued. We verified our method through numerical simulations based on a photonic waveguide array chip. We trained a controller to generate sequences of different target output distributions of the chip with fidelity higher than 99%, where the controller showed superior performance in canceling the classical signal distortions.

The frequency-dependent optical spectrum is pivotal for a broad range of applications, from material characterization to optoelectronics and energy harvesting. Data-driven surrogate models, trained on density functional theory (DFT) data, have effectively alleviated the scalability limitations of DFT while preserving its chemical accuracy, expediting material discovery. However, prevailing machine learning (ML) efforts often focus on scalar properties such as the band gap, overlooking the complexities of optical spectra. In this work, we employ deep graph neural networks (GNNs) to predict the frequency-dependent complex-valued dielectric function across the infrared, visible, and ultraviolet spectra directly from crystal structures. We explore multiple architectures for multi-output spectral representation of the dielectric function and utilize various multi-fidelity learning strategies, such as transfer learning and fidelity embedding, to address the challenges associated with the scarcity of high-fidelity DFT data. Additionally, we model key solar cell absorption efficiency metrics, demonstrating that learning these parameters is enhanced when integrated through a learning bias within the learning of the frequency-dependent absorption coefficient. This study demonstrates that leveraging multi-output and multi-fidelity ML techniques enables accurate predictions of optical spectra from crystal structures, providing a versatile tool for rapidly screening materials for optoelectronics, optical sensing, and solar energy applications across an extensive frequency spectrum.

Orthogonal delay-Doppler (DD) division multiplexing (ODDM) has been recently proposed as a promising multicarrier modulation scheme to tackle Doppler spread in high-mobility environments. Accurate channel estimation is of paramount importance to guarantee reliable communication for the ODDM, especially when the delays and Dopplers of the propagation paths are off-grid. In this paper, we propose a novel grid refinement and adjustment-based sparse Bayesian inference (GRASBI) scheme for DD domain channel estimation. The GRASBI involves first formulating the channel estimation problem as a sparse signal recovery through the introduction of a virtual DD grid. Then, an iterative process is proposed that involves (i) sparse Bayesian learning to estimate the channel parameters and (ii) a novel grid refinement and adjustment process to adjust the virtual grid points. The grid adjustment in GRASBI relies on the maximum likelihood principle to attain the adjustment and utilizes refined grids that have much higher resolution than the virtual grid. Moreover, a low-complexity grid refinement and adjustment-based channel estimation scheme is proposed, that can provides a good tradeoff between the estimation accuracy and the complexity. Finally, numerical results are provided to demonstrate the accuracy and efficiency of the proposed channel estimation schemes.

In the domain of spatial crowdsourcing drone services, which includes tasks like delivery, surveillance, and data collection, secure communication is paramount. The Public Key Infrastructure (PKI) ensures this by providing a system for digital certificates that authenticate the identities of entities involved, securing data and command transmissions between drones and their operators. However, the centralized trust model of traditional PKI, dependent on Certificate Authorities (CAs), presents a vulnerability due to its single point of failure, risking security breaches. To counteract this, the paper presents D2XChain, a blockchain-based PKI framework designed for the Internet of Drone Things (IoDT). By decentralizing the CA infrastructure, D2XChain eliminates this single point of failure, thereby enhancing the security and reliability of drone communications. Fully compatible with the X.509 standard, it integrates seamlessly with existing PKI systems, supporting all key operations such as certificate registration, validation, verification, and revocation in a distributed manner. This innovative approach not only strengthens the defense of drone services against various security threats but also showcases its practical application through deployment on a private Ethereum testbed, representing a significant advancement in addressing the unique security challenges of drone-based services and ensuring their trustworthy operation in critical tasks., Comment: 11 pages, 9 figures, accepted and to be published in the proceedings of IEEE International Conference on Web Services (ICWS 2024)

We introduce a privacy-preserving framework for integrating consumer-grade drones into bushfire management. This system creates a marketplace where bushfire management authorities obtain essential data from drone operators. Key features include local differential privacy to protect data providers and a blockchain-based solution ensuring fair data exchanges and accountability. The framework is validated through a proof-of-concept implementation, demonstrating its scalability and potential for various large-scale data collection scenarios. This approach addresses privacy concerns and compliance with regulations like Australia's Privacy Act 1988, offering a practical solution for enhancing bushfire detection and management through crowdsourced drone services., Comment: 3 pages, 2 figures, accepted and to be published in the proceedings of IEEE International Conference on Web Services (ICWS 2024)

This study introduces the Distributed Drone Reputation Management (DDRM) framework, designed to fortify trust and authenticity within the Internet of Drone Things (IoDT) ecosystem. As drones increasingly play a pivotal role across diverse sectors, integrating crowdsourced drone services within the IoDT has emerged as a vital avenue for democratizing access to these services. A critical challenge, however, lies in ensuring the authenticity and reliability of drone service reviews. Leveraging the Ethereum blockchain, DDRM addresses this challenge by instituting a verifiable and transparent review mechanism. The framework innovates with a dual-token system, comprising the Service Review Authorization Token (SRAT) for facilitating review authorization and the Drone Reputation Enhancement Token (DRET) for rewarding and recognizing drones demonstrating consistent reliability. Comprehensive analysis within this paper showcases DDRM's resilience against various reputation frauds and underscores its operational effectiveness, particularly in enhancing the efficiency and reliability of drone services., Comment: 11 pages, 1 figure, accepted and to be published in the proceedings of IEEE International Conference on Web Services (ICWS 2024)

Recent deep reinforcement learning (DRL) methods in finance show promising outcomes. However, there is limited research examining the behavior of these DRL algorithms. This paper aims to investigate their tendencies towards holding or trading financial assets as well as purchase diversity. By analyzing their trading behaviors, we provide insights into the decision-making processes of DRL models in finance applications. Our findings reveal that each DRL algorithm exhibits unique trading patterns and strategies, with A2C emerging as the top performer in terms of cumulative rewards. While PPO and SAC engage in significant trades with a limited number of stocks, DDPG and TD3 adopt a more balanced approach. Furthermore, SAC and PPO tend to hold positions for shorter durations, whereas DDPG, A2C, and TD3 display a propensity to remain stationary for extended periods.

The study was conducted to determine the best irrigation frequency for rooting hardwood cuttings of some pomegranate genotypes that are cultivated in Halabja province, Kurdistan Region, Iraq. The hardwood cuttings were collected from 11 genotypes, which were 'Salakhani Trsh' (G1), 'Salakhani Mekhosh' (G2), 'Amriki' (G3), 'Twekl Sury Trsh' (G4), 'Twekl Astury Naw Spy' (G5), 'Hanara Sherina' (G6), 'Kawa Hanary Sherin' (G7), 'Kawa Hanary Trsh' (G8), 'Malesay Twekl Asture' (G9), 'Malesay Twekl Tank' (G10), and 'Sura Hanary Trsh' (G11). The genotypes were subjected to irrigation applications by 1-day, 2-day, 7-day, or 10-day frequencies. Among pomegranates, G11, G6, and G7 produced 95, 90, and 83% rooting percentages, which were significantly higher than the rest of other genotypes. The lowest rooting percentages (28, 36, 38, and 40%) were found in G1, G5, G3, and G10, respectively. The effect of irrigation frequencies on the genotypes confirmed that a 7-day frequency was the best irrigation frequency to achieve the maximum rooting percentages (93, 86, 80, 73, 53, and 40%) in G6, G9, G2, G4, G3, and G1, respectively. In contrast, the minimum rooting percentage (20%) was recorded in G3 with a 1-day frequency and in G1 with 10-day frequency. In this study, it was found that the cuttings of G11, G6, and G7 had the best ability to form roots, and irrigation with a 7-day frequency was the best for the cuttings of all the 11 pomegranate genotypes investigated.

In this paper, we define the non-commuting graph associated to a Lie algebra L and obtain some basic graph properties such as connectivity, diameter, girth, Hamiltonian and Eulerian. Moreover, planarity, outer planarity and isomorphism between two such graphs are also discussed in the paper., Comment: 11 pages

We present the Manuscripts of Handwritten Arabic~(Muharaf) dataset, which is a machine learning dataset consisting of more than 1,600 historic handwritten page images transcribed by experts in archival Arabic. Each document image is accompanied by spatial polygonal coordinates of its text lines as well as basic page elements. This dataset was compiled to advance the state of the art in handwritten text recognition (HTR), not only for Arabic manuscripts but also for cursive text in general. The Muharaf dataset includes diverse handwriting styles and a wide range of document types, including personal letters, diaries, notes, poems, church records, and legal correspondences. In this paper, we describe the data acquisition pipeline, notable dataset features, and statistics. We also provide a preliminary baseline result achieved by training convolutional neural networks using this data.

Transformers can under some circumstances generalize to novel problem instances whose constituent parts might have been encountered during training but whose compositions have not. What mechanisms underlie this ability for compositional generalization? By reformulating multi-head attention as a hypernetwork, we reveal that a low-dimensional latent code specifies key-query specific operations. We find empirically that this latent code is highly structured, capturing information about the subtasks performed by the network. Using the framework of attention as a hypernetwork we further propose a simple modification of multi-head linear attention that strengthens the ability for compositional generalization on a range of abstract reasoning tasks. In particular, we introduce a symbolic version of the Raven Progressive Matrices human intelligence test on which we demonstrate how scaling model size and data enables compositional generalization and gives rise to a functionally structured latent code in the transformer., Comment: Code available at https://github.com/smonsays/hypernetwork-attention

We investigate the coexistence of orthogonal time-frequency space (OTFS) modulation with current fourth- and fifth-generation (4G/5G) communication systems that primarily use orthogonal frequency-division multiplexing (OFDM) waveforms. We first derive the input-output-relation of OTFS in the considered coexisting system. In this derivation, we consider (i) the inclusion of multiple cyclic prefixes (CPs) with unequal lengths to the OTFS signal and (ii) edge carrier unloading (ECU), to account for the impacts of CP length, frame structure, and subcarrier arrangement described in 3GPP standards for 4G/5G systems. Our analysis reveals that the inclusion of multiple CPs to the OTFS signal and ECU lead to the channel response exhibiting spreading effects/leakage along the Doppler and delay dimensions, respectively. Consequently, the effective sampled delay-Doppler (DD) domain channel model for OTFS in coexisting systems may exhibit reduced sparsity. We also show that the effective DD domain channel coefficients for OTFS in coexisting systems are influenced by the unequal lengths of CPs. Subsequently, we propose an interference cancellation-based channel estimation (CE) technique for OTFS in coexisting systems. Through numerical results, we validate our analysis, highlight the importance of not ignoring the unequal lengths of CPs during signal detection, and show the significance of the proposed CE technique., Comment: This paper has been submitted for publication in an IEEE Journal. Copyright may be transferred without notice, after which this version may no longer be accessible. arXiv admin note: text overlap with arXiv:2311.06850

In recent years, machine learning (ML) techniques have created numerous opportunities for intelligent mobile networks and have accelerated the automation of network operations. However, complex network tasks may involve variables and considerations even beyond the capacity of traditional ML algorithms. On the other hand, large language models (LLMs) have recently emerged, demonstrating near-human-level performance in cognitive tasks across various fields. However, they remain prone to hallucinations and often lack common sense in basic tasks. Therefore, they are regarded as assistive tools for humans. In this work, we propose the concept of "generative AI-in-the-loop" and utilize the semantic understanding, context awareness, and reasoning abilities of LLMs to assist humans in handling complex or unforeseen situations in mobile communication networks. We believe that combining LLMs and ML models allows both to leverage their respective capabilities and achieve better results than either model alone. To support this idea, we begin by analyzing the capabilities of LLMs and compare them with traditional ML algorithms. We then explore potential LLM-based applications in line with the requirements of next-generation networks. We further examine the integration of ML and LLMs, discussing how they can be used together in mobile networks. Unlike existing studies, our research emphasizes the fusion of LLMs with traditional ML-driven next-generation networks and serves as a comprehensive refinement of existing surveys. Finally, we provide a case study to enhance ML-based network intrusion detection with synthesized data generated by LLMs. Our case study further demonstrates the advantages of our proposed idea.

In this article, we explore the feedback stabilization of a viscous Burgers equation around a non-constant steady state using localized interior controls and then develop error estimates for the stabilized system using finite element method. The system is not only feedback stabilizable but exhibits an exponential decay $-\omega<0$ for any $\omega>0$. The derivation of a stabilizing control in feedback form is achieved by solving a suitable algebraic Riccati equation posed for the linearized system. In the second part of the article, we utilize a conforming finite element method to discretize the continuous system, resulting in a finite-dimensional discrete system. This approximated system is also proven to be feedback stabilizable (uniformly) with exponential decay $-\omega+\epsilon$ for any $\epsilon>0$. The feedback control for this discrete system is obtained by solving a discrete algebraic Riccati equation. To validate the effectiveness of our approach, we provide error estimates for both the stabilized solutions and the stabilizing feedback controls. Numerical implementations are carried out to support and validate our theoretical results.

Contrastive Language-Image Pretraining (CLIP) is widely used to train models to align images and texts in a common embedding space by mapping them to fixed-sized vectors. These models are key to multimodal information retrieval and related tasks. However, CLIP models generally underperform in text-only tasks compared to specialized text models. This creates inefficiencies for information retrieval systems that keep separate embeddings and models for text-only and multimodal tasks. We propose a novel, multi-task contrastive training method to address this issue, which we use to train the jina-clip-v1 model to achieve the state-of-the-art performance on both text-image and text-text retrieval tasks., Comment: 4 pages, MFM-EAI@ICML2024

The NP-hard scheduling problem P||C_max encompasses a set of tasks with known execution time which must be mapped to a set of identical machines such that the overall completion time is minimized. In this work, we improve existing techniques for optimal P||C_max scheduling with a combination of new theoretical insights and careful practical engineering. Most importantly, we derive techniques to prune vast portions of the search space of branch-and-bound (BnB) approaches. We also propose improved upper and lower bounding techniques which can be combined with any approach to P||C_max. Moreover, we present new benchmarks for P||C_max, based on diverse application data, which can shed light on aspects which prior synthetic instances fail to capture. In an extensive evaluation, we observe that our pruning techniques reduce the number of explored nodes by 90$\times$ and running times by 12$\times$. Compared to a state-of-the-art ILP-based approach, our approach is preferable for short running time limits and for instances with large makespans.

The field of photonic integrated circuits has witnessed significant progress in recent years, with a growing demand for devices that offer high-performance reconfigurability. Due to the inability of conventional tunable directional couplers (TDCs) to maintain a fixed phase while tuning the reflectivity, Mach-Zehnder interferometers (MZIs) are employed as the primary building blocks for reflectivity tuning in constructing large-scale circuits. However, MZIs are prone to fabrication errors due to the need for perfect balanced directional couplers to achieve 0-1 reflectivity, which hinders their scalability. In this study, we introduce a design of a TDC based on coupling constant tuning in the thin film Lithium Niobate platform and present an optimized design. Our optimized TDC design enables arbitrary reflectivity tuning while ensuring a consistent phase across a wide range of operating wavelengths. Furthermore, it exhibits fewer bending sections than MZIs and is inherently resilient to fabrication errors in waveguide geometry and coupling length compared to both MZIs and conventional TDCs. Our work contributes to developing high-performance photonic integrated circuits with implications for various fields, including optical communication systems and quantum information processing.

Over the past decade, integrated quantum photonic technologies have shown great potential as a platform for studying quantum phenomena and realizing large-scale quantum information processing. Recently, there have been proposals for utilizing waveguide lattices to implement quantum gates, providing a more compact and robust solution compared to discrete implementation with directional couplers and phase shifters. We report on the first demonstration of precise control of single photon states on an $11\times 11$ continuously-coupled programmable waveguide array. Through electro-optical control, the array is subdivided into decoupled subcircuits and the degree of on-chip quantum interference can be tuned with a maximum visibility of 0.962$\pm$0.013. Furthermore, we show simultaneous control of two subcircuits on a single device. Our results demonstrate the potential of using this technology as a building block for quantum information processing applications.

Let P be a set of n weighted points, Q be a set of m unweighted points in the plane, and k a non-negative integer. We consider the problem of computing a subset $Q'\subseteq Q$ with size at most k such that the sum of the weights of the points of P dominated by at least one point in the set Q' is maximized. A point q in the plane dominates another point p if and only if $x(q)\ge x(p)$ and $y(q)\ge y(p)$, and at least one inequality is strict. We present a solution to the problem that takes O(n + m)-space and $O(k \min\{n+m, \frac{n}{k}+m^2\}\log m)$-time. We (conditionally) improve upon the existing result (the bounds of our solution are interesting when $m= o(\sqrt{n}))$. Moreover, we also present a simple algorithm solving the problem in $O(km^2+n\log m)$-time and $O(n+m)$-space. The bounds of the algorithm are interesting when $m= o(\sqrt{n})$.

Integrated sensing and communications is a key enabler for the 6G wireless communication systems. The multiple sensing modalities will allow the base station to have a more accurate representation of the environment, leading to context-aware communications. Some widely equipped sensors such as cameras and RADAR sensors can provide some environmental perceptions. However, they are not enough to generate precise environmental representations, especially in adverse weather conditions. On the other hand, the LiDAR sensors provide more accurate representations, however, their widespread adoption is hindered by their high cost. This paper proposes a novel approach to enhance the wireless communication systems by synthesizing LiDAR point clouds from images and RADAR data. Specifically, it uses a multimodal transformer architecture and pre-trained encoding models to enable an accurate LiDAR generation. The proposed framework is evaluated on the DeepSense 6G dataset, which is a real-world dataset curated for context-aware wireless applications. Our results demonstrate the efficacy of the proposed approach in accurately generating LiDAR point clouds. We achieve a modified mean squared error of 10.3931. Visual examination of the images indicates that our model can successfully capture the majority of structures present in the LiDAR point cloud for diverse environments. This will enable the base stations to achieve more precise environmental sensing. By integrating LiDAR synthesis with existing sensing modalities, our method can enhance the performance of various wireless applications, including beam and blockage prediction., Comment: 6 pages, 4 figures, conference

Large language models (LLMs), especially generative pre-trained transformers (GPTs), have recently demonstrated outstanding ability in information comprehension and problem-solving. This has motivated many studies in applying LLMs to wireless communication networks. In this paper, we propose a pre-trained LLM-empowered framework to perform fully automatic network intrusion detection. Three in-context learning methods are designed and compared to enhance the performance of LLMs. With experiments on a real network intrusion detection dataset, in-context learning proves to be highly beneficial in improving the task processing performance in a way that no further training or fine-tuning of LLMs is required. We show that for GPT-4, testing accuracy and F1-Score can be improved by 90%. Moreover, pre-trained LLMs demonstrate big potential in performing wireless communication-related tasks. Specifically, the proposed framework can reach an accuracy and F1-Score of over 95% on different types of attacks with GPT-4 using only 10 in-context learning examples.

The aqueous extract of Salix spp contains many compounds which may act as root-promoting agents in cuttings. S. alba is a deciduous tree containing variable phytochemicals which are variable throughout the year. So, in this study, one- and two-year-old shoots of S. alba were collected on the 15th of each month in the year 2022, extracted in 2% ethanol at 9 g.L-1, and placed in a water bath at 35 {\deg}C, then they applied to thornless blackberry cuttings for 1.5 hr. The results explained that the highest rooting percentage (66.67%) was obtained in the cuttings soaked in the extract of willow shoots collected on 15th of January. They were not significantly different from control cuttings, but they were different from the cuttings soaked in the extract of willow shoots collected on 15th of August and October (33.33%). The majority of other shoot and root traits were high in the cuttings soaked in the extract of willow shoots collected on 15th of December. The willow shoots collected on 15th of January contained the lowest total phenols (51.4 {\mu}g.mL-1) and total flavonoids (29.07 {\mu}g.mL-1). Moreover, the highest total phenols (57 {\mu}g.mL-1) and IAA (365.17 {\mu}g.mL-1) were recorded in the willow shoots collected on 15th of March, however each total flavonoids (44.96 {\mu}g.mL-1) and salicylic acid (492.61 {\mu}g.mL-1) were the highest in the willow shoots collected on 15th of April. Generally, based on rooting percentage, it is advisable to collect willow shoots on 15th of January and February for extraction and application to the thornless blackberry cuttings.

The orthogonal delay-Doppler (DD) division multiplexing(ODDM) modulation has been recently proposed as a promising modulation scheme for next-generation communication systems with high mobility. Despite its benefits, ODDM modulation and other DD domain modulation schemes face the challenge of excessive equalization complexity. To address this challenge, we propose time domain Tomlinson-Harashima precoding (THP) for the ODDM transmitter, to make the DD domain single-tap equalizer feasible, thereby reducing the equalization complexity. In our design, we first pre-cancel the inter-symbolinterference (ISI) using the linear time-varying (LTV) channel information. Second, different from classical THP designs, we introduce a modified modulo operation with an adaptive modulus, by which the joint DD domain data multiplexing and timedomain ISI pre-cancellation can be realized without excessively increasing the bit errors. We then analytically study the losses encountered in this design, namely the power loss, the modulo noise loss, and the modulo signal loss. Based on this analysis, BER lower bounds of the ODDM system with time domain THP are derived when 4-QAM or 16-QAM modulations are adopted for symbol mapping in the DD domain. Finally, through numerical results, we validate our analysis and then demonstrate that the ODDM system with time domain THP is a promising solution to realize better BER performance over LTV channels compared to orthogonal frequency division multiplexing systems with single-tap equalizer and ODDM systems with maximum ratio combining.

(Abridged) Observational estimates of galaxy properties rely on the inherent galaxy-wide initial mass function (gwIMF), which systematically varies with the global SFR and metallicity, as proposed by the integrated-galactic IMF (IGIMF) theory and supported by empirical evidence. We incorporate PARSEC and COLIBRI stellar isochrones into the GalIMF code, a galaxy chemical evolution (GCE) model featuring real-time updates of environment-dependent gwIMFs. This newly developed photometric GalIMF (photGalIMF) code allows the calculation of photometric properties for galaxies with diverse stellar populations. Subsequently, we analyze observed luminosities and metallicities of local star-forming galaxies to deduce their stellar masses assuming that they have constant SFRs over 13.6 Gyr. We also compute SFR$-$H$\alpha$ luminosity relations for varying stellar metallicities using a separate stellar population synthesis code based on PEGASE. Comparing the IGIMF theory to the canonical universal IMF, our analysis reveals that estimates of the stellar masses and SFRs for local star-forming galaxies differ by factors of $\approx 2$ and 10, respectively. The computed gas-depletion timescale increases with gas mass, implying lower star formation efficiencies in more massive galaxies, possibly due to stronger feedback regulation, aligning with theoretical expectations. Additionally, the characteristic stellar mass buildup timescale increases with stellar mass, indicating that massive disk galaxies initiate star formation earlier than their low-mass counterparts. The photGalIMF code enables self-consistent computations of galactic photometry, self-consistently with GCE modelling within the context of an environment-dependent gwIMF. Utilizing Ks-band and H$\alpha$ luminosities of galaxies, the outcomes include galaxy mass, SFR, and fitting functions for the SFR correction factor., Comment: Accepted for publication in Astronomy & Astrophysics (A&A), 19 pages, 11 figures, 2 tables. The photGalIMF code is publicly available on GitHub: https://github.com/juzikong/photGalIMF

Kansei Engineering (KE) is a user-centered design approach that emphasizes the emotional aspects of user experience. This paper explores the integration of KE in the case of a transportation company that focuses on connecting cargo owners with transportation providers. The methodology involves aligning the design process with the company's strategy, collecting and semantic scaling Kansei words, and evaluating website design through experimental and statistical analyses. Initially, we collaborated with the company to understand their strategic goals, using Use Case and Entity Relationship diagrams to learn about the website functionality. Subsequent steps involved collecting Kansei words that resonate with the company's vision. Website samples from comparable transportation companies were then evaluated by X subject in the survey. Participants were asked to arrange samples based on emotional feedback using a 5-point SD scale. We used Principal Component Analysis (PCA) to identify critical factors affecting users' perceptions of the design. Based on these results, we collaborated with designers to reformulate the website, ensuring the design features aligned with the Kansei principles. The outcome is a user-centric web design to enhance the site's user experience. This study shows that KE can be effective in creating more user-friendly web interfaces in the transportation industry., Comment: submitted to Springer journal for consideration