Token Approach Research Articles

HTC-retina: A hybrid retinal diseases classification model using transformer-Convolutional Neural Network from optical coherence tomography images

Retinal diseases are among nowadays major public health issues, deservedly needing advanced computer-aided diagnosis. We propose a hybrid model for multi label classification, whereby seven retinal diseases are automatically classified from Optical Coherence Tomography (OCT) images. We show that, by combining the strengths of Convolutional Neural Networks (CNNs) and Visual Transformers (ViTs), we can produce a more powerful type of model for medical image classification, especially when considering local lesion information such as retinal diseases. CNNs are indeed proved to be efficient at parameter utilization and provide the ability to extract local features and multi-scale feature maps through convolutional operations. On the other hand, ViT’s self-attention procedure allows processing long-range and global dependencies within an image. The paper clearly shows that the hybridization of these complementary capabilities (CNNs-ViTs) presents a high image processing potential that is more robust and efficient. The proposed model adopts a hierarchical CNN module called Convolutional Patch and Token Embedding (CPTE) instead of employing a direct tokenization approach using the raw input OCT image in the transformer. The CPTE module’s role is to incorporate an inductive bias, to reduce the reliance on large-scale datasets, and to address the low-level feature extraction challenges of the ViT. In addition, considering the importance of local lesion information in OCT images, the model relies on a parallel module called Residual Depthwise-Pointwise ConvNet (RDP-ConvNet) for extracting high-level features. RDP-ConvNet utilizes depthwise and pointwise convolution layers within a residual network architecture. The overall performance of the HTC-Retina model was evaluated on three datasets: the OCT-2017, OCT-C8, and OCT-2014 ; outperforming previous established models, achieving accuracy rates of 99.40%, 97.00%, and 99.77%, respectively ; and sensitivity rates of 99.41%, 97.00%, and 99.77%, respectively. Notably, the model showed high performance while maintaining computational efficiency.

Immutable Identity Validation Using Soul bound Token Abhishek Sharma,

The "Immutable Identity Validation System: A Blockchain and Soulbound Token Approach" paper introduces an innovative method for verifying digital identities. By combining blockchain technology and Soulbound Tokens (SBTs), it enhances security and privacy in identity verification processes. SBTs, designed as non-transferable and tamper-proof digital assets, play a crucial role in bolstering the security and reliability of the system. Their unique properties ensure that user privacy is prioritized while also facilitating swift verification through blockchain transparency. This approach addresses the growing demand for robust identity verification solutions, particularly in sectors like education and corporations, where fraud prevention and streamlined processes are critical. The methodology involves various steps, including SBT generation, blockchain integration, user control mechanisms, and stringent security measures. Both frontend and backend development, along with the integration of blockchain using tools like Ganache and decentralized data storage through IPFS, contribute to building a secure and user-friendly system. Thorough testing, documentation, and knowledge transfer are essential to ensuring the system's reliability, security, and compliance with legal standards. Ultimately, the goal is to establish a globally accepted framework for identity verification in today's interconnected digital landscape. Keywords:; privacy; security; Blockchain; Cryptography; Decentralization; Soul Bound Token (SBT), distributed ledger.

Semantic-Based Optimization of Deep Learning for Efficient Real-Time Medical Image Segmentation

In response to the critical need for advanced solutions in medical imaging segmentation, particularly for real-time applications in diagnostics and treatment planning, this study introduces SM-UNet. This novel deep learning architecture efficiently addresses the challenge of real-time, accurate medical image segmentation by integrating convolutional neural network (CNN) with multilayer perceptron (MLP). The architecture uniquely combines an initial convolutional encoder for detailed feature extraction, MLP module for capturing long-range dependencies, and a decoder that merges global features with high-resolution CNN map. Further optimization is achieved through a tokenization approach, significantly reducing computational demands. Its superior performance is confirmed by evaluations on standard datasets, showing interaction times drastically lower than comparable networks—between 1/6 to 1/10, and 1/25 compared to SOTA models. These advancements underscore SM-UNet's potential as a groundbreaking tool for facilitating real-time, precise medical diagnostics and treatment strategies.

The Milestone Token Approach: An Adaptive Tokenized Crowdfunding Strategy for Ecosystem Projects

The Milestone Token Approach: An Adaptive Tokenized Crowdfunding Strategy for Ecosystem Projects

The Milestone Token Approach: An Adaptive Tokenized Crowdfunding Strategy for Ecosystem Projects

The Milestone Token Approach: An Adaptive Tokenized Crowdfunding Strategy for Ecosystem Projects

Jeu de mots paronomasia: a StackOverflow-driven bug discovery approach

Locating bug code snippets (short for BugCode) has been a complex problem throughout the history of software security, mainly because the constraints that define BugCode are obscure and hard to summarize. Previously, security analysts attempted to define such constraints manually (e.g., limiting buffer size to detect overflow), but were limited to the types of BugCode. Recent researchers address this problem by extracting constraints from program documentation, which shows the potential for API misuse. But for bugs beyond the scope of API misuse, such an approach becomes less effective since the corresponding constraints are not defined in documents, not to mention the programs without documentation In this paper, inspired by the fact that expert programmers often correct the BugCode on open forums such as StackOverflow, we design an approach to automatically extract knowledge from StackOverflow and leverage it to detect BugCode. As we all know, the contexts in StackOverflow come from ordinary developers. Their writing tends to be loosely organized and in various styles, which are more challenging to analyze than program documentation. To address the challenges, we design a custom tokenization approach to segment sentences and employ sentiment analysis to find the Controversial Sentences (CSs) that typically contain the constraints we need for code analysis. Then we use constituency parsing to extract knowledge from CSs, which helps locate BugCode. We evaluated our system on 41,144 comments from the questions tagged with Java and Android. The results show that our approach achieves 95.5% precision in discovering CSs. We have discovered 276 pieces of BugCode proved to be true through manual validation including an assigned CVE. 89.3% of the discovered bugs remained in the current version of answers, which are unknown to users.

Progressive Token Reduction and Compensation for Hyperspectral Image Representation

Hyperspectral images (HSIs) have been widely used in Earth observation because they contain continuous and detailed spectral information which is beneficial for the fine-grained diagnosis of the land cover. In the past few years, convolutional neural network (CNN)-based methods show limitations in modeling spectral-wise long-range dependences. Recently, transformer-based deep learning methods are proposed and have shown superiority in modeling the continuous representation of the spectral signatures because the self-attention (SA) mechanism has a global receptive field. Due to the special tokenization of the transformer-based methods, the redundant tokens contained in spectral embeddings are always involved in SA operation. Redundant tokens do not positively contribute to classification. Specifically, the overlapped group-wise tokenization approach may aggravate the Hughes phenomenon and impose additional computations. To address this issue, a lightweight spatial–spectral pyramid transformer (SSPT) framework is proposed to efficiently extract the spatial–spectral features of HSI by progressively reducing redundant tokens in an end-to-end manner. In particular, a token reduction (TR) method is proposed to decide which tokens will be involved by computing and comparing token attentiveness between spectral embeddings and the class token. In addition, for those tokens that are defined as redundant information, a token compensation mechanism is proposed to automatically extract supplementary information for classification. Extensive experiments on three standard datasets quantitatively show the superiority of our methods, and the ablation experiments qualitatively prove our hypothesis about the feature distribution in transformer architecture.

Ensuring the security of web applications operating on the basis of the SSL/TLS protocol

SSL/TLS (Secure Socket Layer/Transport Layer Security)-enabled web applications are designed to provide authentication based on a public key certificate, as well as generating a secure session key and traffic privacy based on a symmetric key. Today, a large number of e-commerce applications such as stock trading, banking, shopping and gaming rely on the robustness of the SSL/TLS protocol. Recently, a potential threat known as a Man-in-the-Middle or main-in-the-middle (MITM) attack has been used by attackers to attack SSL/TLS-enabled web applications, especially when users want to connect to an SSL/TLS-enabled web server. SSL/TLS. The current article discusses the Man-in-the-Middle attack threat for SSL/TLS-enabled web applications. The existing solution space for countering a MITM attack on SSL/TLS-enabled applications is also considered, and an effective solution is proposed that can resist a MITM attack on SSL/TLS-enabled applications. The proposed solution uses a soft token approach for user authentication in addition to SSL/TLS security features. The proposed solution is claimed to be safe, effective and user-friendly compared to similar approaches.

A tokenization technique for improving the security of EMV contactless cards

ABSTRACT This paper focuses on the EMV contactless payment cards and their vulnerability of leaking sensitive information such as the cardholder name, Primary Account Number (PAN), and the expiry date of the EMV card. Such data can be sniffed using off-the-shelf hardware or software without the knowledge of the genuine cardholder. The paper proposes a tokenization technique to replace the PAN of the actual EMV contactless card’s with a token to protect the genuine data from being sniffed by an attacker and used in the Card-No-Present (CNP) attack or any other attacks. The proposal was inspired by the implementation of the tokenization in the EMV Mobile payment such as Apple, Google, and Samsung mobile payments. We argue that the proposed tokenization technique is easy to adopt and cost-effective to implement by EMV protocol as it does not require any changes to the infrastructure of existing payment systems. A vital feature of the proposal is that all the changes in the EMV protocol are at the personalization phase of the EMV card. The paper presents a successful implementation of the tokenization approach using a Java contactless card framework to represent EMV contactless cards to demonstrate its effectiveness in improving the security and protecting the privacy of the card’s information.

Prevention of session hijacking using token and session id reset approach

Session hijacking is the term used to describe the theft of user’s cookies and make clone of that cookies. The hacker uses packet sniffer to capture traffic between user and the server to steal the cookies which contain session information. The same then be used to impersonate the user and act as actual user on web. In this paper, Token and Session id Reset Approach has been proposed and implemented, to prevent the session hijacking by cookies cloning. Proposed technique uses; session id, token, IP and bowser fingerprints to authenticate the user on the web server. This technique stores token at the client side in local storage and it will not be stored in cookies. It has been observed that the Man In The Middle, Cross Site Scripting, Session fixation, Cookie-stealing malware, Predictable token and session id, Physical data theft, and Cookie Cloning attacks is hard to perform on the proposed approach.

Data Mining K-Means Document Clustering using TFIDF and Word Frequency Count

In the rapid development of www the amount of documents used increases in a rapid speed. This produces huge gigabyte of text document processing. For indexing as well as retrieving the required text document an efficient algorithms produce better performance by achieving good accuracy. The algorithms available in the field of data mining also provide a variety of new innovations regarding data mining. This increases the interest of the researchers to develop many essential models in the field of text data mining. In the proposed model is a two step text document clustering approach by K-Means algorithm. The first step includes Pre_Processing and second step includes clustering process. For Pre-Processing the method performs the tokenization approach. The distinct words are identified and the distinct words frequency of occurrence, TFIDF weights of the occurrences are calculated to form a document feature vector separately. In the clustering phase the feature vector is clustered by performing K-means algorithm by implementing various similarity measures.

Distributed-Memory Load Balancing With Cyclic Token-Based Work-Stealing Applied to Reverse Time Migration

Reverse time migration (RTM) is a prominent technique in seismic imaging. Its resulting subsurface images are used in the industry to investigate with higher confidence the existence and the conditions of oil and gas reservoirs. Because of its high computational cost, RTM must make use of parallel computers. Balancing the workload distribution of an RTM is a growing challenge in distributed computing systems. The competition for shared resources and the differently-sized tasks of the RTM are some of the possible sources of load imbalance. Although many load balancing techniques exist, scaling up for large problems and large systems remains a challenge because synchronization overhead also scales. This paper proposes a cyclic token-based work-stealing (CTWS) algorithm for distributed memory systems applied to RTM. The novel cyclic token approach reduces the number of failed steals, avoids communication overhead, and simplifies the victim selection and the termination strategy. The proposed method is implemented as a C library using the one-sided communication feature of the message passing interface (MPI) standard. Results obtained by applying the proposed technique to balance the workload of a 3D RTM system present a factor of 14.1% speedup and reductions of the load imbalance of 78.4% when compared to the conventional static distribution.

Bootstrapping a New LHC Data Transfer Ecosystem

GridFTP transfers and the corresponding Grid Security Infrastructure (GSI)-based authentication and authorization system have been data transfer pillars of the Worldwide LHC Computing Grid (WLCG) for more than a decade. However, in 2017, the end of support for the Globus Toolkit - the reference platform for these technologies - was announced. This has reinvigorated and expanded efforts to replace these pillars. We present an end-to-end alternate utilizing HTTP-based WebDAV as the transfer protocol, and bearer tokens for distributed authorization. This alternate ecosystem, integrating significant pre-existing work and ideas in the area, adheres to common industry standards to the fullest extent possible, with minimal agreed-upon extensions or common interpretations of the core protocols. The bearer token approach allows resource providers to delegate authorization decisions to the LHC experiments for experiment-dedicated storage areas. This demonstration touches the entirety of the stack - from multiple storage element implementations to FTS3 to the Rucio data management system. We show how the traditional production and user workflows can be reworked utilizing bearer tokens, eliminating the need for GSI proxy certificates for storage interactions.

A Proposed Adaptive Scheme for Arabic Part-of Speech Tagging

This paper presents an Arabic-compliant part-of-speech (POS) tagging scheme based on using atomic tag markers that are grouped together using brackets. This scheme promotes the speedy production of annotations while preserving the richness of resultant annotations. The proposed scheme is comprised of two main elements, a new tokenization approach and a custom tool that enables the semi-automatic implementation of this scheme. The proposed model can serve in many scenarios where the user is in a need for better Arabic support and more control over the Part-of-Speech tagging process. This scheme was used to annotate sample narratives and it demonstrated capability and adaptability while addressing the various distinguishing features of Arabic language including its unique declension system. It also sets new baselines that are prospect for further exploration by future efforts.

Textual Analysis in Real Estate

Summary This paper incorporates text data from MLS listings into a hedonic pricing model. We show that the comments section of the MLS, which is populated by real estate agents who arguably have the most local market knowledge and know what homebuyers value, provides information that improves the performance of both in-sample and out-of-sample pricing estimates. Text is found to decrease pricing error by more than 25%. Information from text is incorporated into a linear model using a tokenization approach. By doing so, the implicit prices for various words and phrases are estimated. The estimation focuses on simultaneous variable selection and estimation for linear models in the presence of a large number of variables using a penalized regression. The LASSO procedure and variants are shown to outperform least-squares in out-of-sample testing. Copyright © 2016 John Wiley & Sons, Ltd.

Enhance Inverted Index Using in Information Retrieval

This paper proposes a method to represent the first step in information retrieval (IR) (that prepare the document set (preprocessing), In Information retrieval systems, tokenization is an integral part whose prime objective is to identify the token and their count. In this paper, an effective tokenization approach which is based on proposed new method called enhance inverted index (EII). The result shows that efficiency/ effectiveness of the proposed algorithm. Tokenization on documents helps to satisfy user’s information need more precisely and reduced search sharply, believed to be a part of information retrieval. Pre-processing of input document is an integral part of Tokenization, which involves preprocessing of documents and generates its respective tokens, which is the basis of these tokens. Probabilistic IR generates its scoring and gives reduced search space. The comparative analysis based on the two parameters; reduce the time of search space, Pre-processing time

RST-SHELO: sketch-based image retrieval using sketch tokens and square root normalization

Sketch-based image retrieval (SBIR) is an emergent research area with a variety of applications, specially when an example image is not available for querying. Moreover, making a sketch has become a very attractive and simple task due to the already ubiquitous touch-screen and mobile technologies. Although a sketch is a natural way for representing the structure of a thought object, it may easily get confused in a dataset with high variability turning the retrieval task a quite challenging problem. Indeed, the state-of-the-art methods still show low performance on diverse evaluation datasets. Thereby, a robust sketch descriptor together with a better strategy for representing regular images as sketches are demanded. In this work, we present RST-SHELO, and improved version of SHELO (Soft Histogram of Edge Logal Orientations), an efficient state-of-the-art method for describing sketches. The proposed improvements comes from two aspects: a better technique for obtaining sketch-like representations and a better normalization strategy of SHELO. For the first case, we propose to use the sketch token approach [21], aiming to detect image contours by means of mid-level features. For the second case, we demonstrate that a square root normalization positively affect the effectiveness on the retrieval task. Based on our improvements, we present new state-of-the-art performance. To validate our achievements, we have conducted diverse experiments using two public datasets, Flickr15K and Saavedra's. Our results show an effectiveness gain of 62 % in the first and 5 % in the second dataset.

An Effective Pre-Processing Algorithm for Information Retrieval Systems

The Internet is probably the most successful distributed computing system ever. However, our capabilities for data querying and manipulation on the internet are primordial at best. The user expectations are enhancing over the period of time along with increased amount of operational data past few decades. The data-user expects more deep, exact, and detailed results. Result retrieval for the user query is always relative o the pattern of data storage and index. In Information retrieval systems, tokenization is an integrals part whose prime objective is to identifying the token and their count. In this paper, we have proposed an effective tokenization approach which is based on training vector and result shows that efficiency/ effectiveness of proposed algorithm. Tokenization on documents helps to satisfy user’s information need more precisely and reduced search sharply, is believed to be a part of information retrieval. Pre-processing of input document is an integral part of Tokenization, which involves preprocessing of documents and generates its respective tokens which is the basis of these tokens probabilistic IR generate its scoring and gives reduced search space. The comparative analysis is based on the two parameters; Number of Token generated, Pre-processing time.

Information sharing policies based on tokens to improve supply chain performances

One of the most studied dynamics of supply chains is a phenomenon that has been named ‘the bullwhip effect’. What happens is that variations in customer demand are translated into wider and wider variations in orders issued by companies along the supply chain, affecting performances and increasing the level of complexity in transactions and relationships among partners. This paper introduces the opportunity of measuring the performance of a supply chain in case of disruption, proposing a progressive information sharing technique (token approach) in order to control bullwhip effect. This technique relies on dividing orders into two streams: the first stream transmits the value of the demand to the whole supply chain echelons whereas the second one includes the adjustments needed to keep a stable inventory for each partner of the network. To investigate the token approach, a simulation model is developed for a four-echelon supply chain where it is assumed that lead times for transferring information or materials are deterministic and suppliers have unlimited production and inventory capacities. Four different ordering policies are evaluated and the results analysed to identify general findings.

Behavioural Treatment Increases Activity in the Cognitive Neuronal Networks in Children with Attention Deficit/Hyperactivity Disorder

Response cost and token approach (RCT) within the scope of a summer camp training is an effective treatment program for attention deficit hyperactivity disorder (ADHD). It is likely that intensive RCT training influences networks responsible for ADHD symptoms. Functional magnetic resonance imaging (fMRI) was carried out in 12 children with ADHD before and after the RCT program and in 12 healthy control children twice. For fMRI, a Go/No-go paradigm was used to investigate the influence of RCT training on attention and impulsivity. The No-go condition revealed only weak activation in the dorsal part of the anterior cingulate cortex (ACC), parietal and dorsolateral prefrontal cortex (DLPFC) before the training in children with ADHD compared to healthy children. However, this activation in these brain regions was significantly more pronounced after the training. This increase in hemodynamic response cannot be attributed merely to repetition of the measurement since the effect was not observed in healthy children. The increase in hemodynamic response in the ACC and right DLPFC was significantly associated with a reduction in response time variability and clinical symptoms in ADHD patients. After the RCT training, the children with ADHD demonstrated more pronounced activation of cortical structures which are typically related to response monitoring and self-control. It seems likely that children with ADHD learned more cognitive control in a continuous performance task as was revealed by both neuropsychological outcome and fMRI.