Best AWS Marketplace Software - Page 146

Social distancing detection algorithm

The Social Distancing Detection Algorithm by Providence Healthcare is an advanced solution designed to monitor and enforce social distancing protocols in various environments, such as hospitals, offices, and public spaces. By leveraging computer vision and machine learning technologies, this algorithm analyzes real-time video feeds to detect and alert individuals who are not maintaining the recommended physical distance, thereby helping to reduce the spread of contagious diseases like COVID-19. Key Features and Functionality: - Real-Time Monitoring: Utilizes live video streams to continuously observe and assess the physical distances between individuals. - Automated Detection: Employs advanced object detection models, such as YOLO (You Only Look Once, to accurately identify people within the camera's field of view. - Distance Calculation: Measures the space between detected individuals using depth sensors and perspective mapping techniques to ensure precise distance assessments. - Immediate Feedback: Provides instant visual or auditory alerts when social distancing guidelines are violated, enabling prompt corrective actions. - Scalability: Designed to integrate seamlessly with existing surveillance systems, allowing for deployment across multiple locations without significant infrastructure changes. Primary Value and User Benefits: The Social Distancing Detection Algorithm addresses the critical need for maintaining safe interpersonal distances in shared spaces, a key measure in preventing the transmission of infectious diseases. By automating the monitoring process, it reduces the reliance on manual supervision, thereby enhancing efficiency and ensuring consistent compliance with health guidelines. Organizations can leverage this technology to create safer environments for employees, customers, and visitors, ultimately contributing to public health efforts and minimizing potential outbreaks.

Social Distancing Detector

Provectus Social Distancing Detector fits well into video analytic workloads for businesses that are to minimize disease transmission risks, gather data for decision-making processes, and ensure adequate personal space for their employees and clients. The solution performs isomorphic analysis by estimating distances between people based on their approximate height. That requires an adequate camera angle, usually placed well-above the queue or crowd so that an image frame does not look misleading.

Social Media Sentiment Analysis

If you want to know exactly how people feel about your business, sentiment analysis can do the job. Specifically, social media sentiment analysis takes the conversations of your product around the social space and puts them into context.

SoftEther VPN

Multi-protocol open source VPN software that can be used for remote private access across all sites.

Average Rating: 4.2/5.0

Total Reviews: 17

SolidCP Panel on AWS (Windows Server)

SolidCP Panel on AWS (Windows Server is a comprehensive, open-source control panel designed for hosting companies and IT providers to efficiently manage and automate multi-tenant services on Windows servers. This solution offers a centralized, web-based interface that simplifies the administration of various server applications, enhancing operational efficiency and scalability. Key Features and Functionality: - Multi-Server Management: SolidCP enables the management of multiple Windows servers through a single, responsive web interface, streamlining server administration tasks. - Extensive Application Support: The platform supports a wide range of server applications, including IIS, Microsoft SQL Server, MySQL, MariaDB, Microsoft Exchange, Microsoft SharePoint, Microsoft Lync, Microsoft Skype for Business, WebDAV, Microsoft RemoteApp (RDS, and Hyper-V deployments. - Responsive Design: SolidCP's interface is designed to be responsive across various devices, ensuring accessibility and ease of use for administrators on the go. - Open-Source and Extensible: Being fully open-source, SolidCP allows for customization and extension to meet specific organizational needs, providing flexibility and control over server management. Primary Value and Problem Solved: SolidCP Panel on AWS addresses the complexities associated with managing multiple Windows servers and diverse applications by providing a unified, user-friendly control panel. It automates the provisioning and management of multi-tenant services, reducing manual intervention and the potential for errors. This leads to increased operational efficiency, scalability, and the ability to deliver a wide array of services to clients with minimal overhead. By leveraging SolidCP on AWS, organizations can harness the power of cloud infrastructure while maintaining robust control over their Windows server environments.

Sonata Software AgentBridge

AgentBridge by Sonata Software is an enterprise-grade Agentic AI framework designed to accelerate AI-powered transformation across business functions. It enables organizations to centrally design, deploy, and govern intelligent AI agents, facilitating secure, scalable, and efficient enterprise automation. By addressing challenges such as fragmented AI initiatives and disconnected systems, AgentBridge empowers businesses to move beyond rule-based automation to intelligent, adaptable AI ecosystems. Key Features and Functionality: - Agent Marketplace: A functionally organized, compliance-aware catalog that allows users to discover, publish, and manage reusable AI agents, complete with built-in analytics and monetization capabilities. - Agent Builder: A visual, drag-and-drop designer featuring industry-specific blueprints, real-time debugging, and one-click publishing to the marketplace, enabling rapid development and deployment of AI agents. - Core Agent Logic: Supports configurable workflows, multi-channel processing (MCP), agent-to-agent (A2A) interactions, and full execution traceability, ensuring robust and adaptable AI operations. - Integrations & Orchestrators: Seamless connectivity with leading cloud providers, ERP systems, and enterprise databases, facilitating smooth integration into existing enterprise infrastructures. - Observability & ROI Dashboards: Provides real-time telemetry, drift analytics, and embedded compliance tools for responsible AI assurance, offering insights into performance and return on investment. - Cloud & Model Support: Ensures secure access to hosted and private models across multi-cloud environments, supporting flexible and scalable AI deployments. Primary Value and Solutions Provided: AgentBridge addresses the industry's growing need for scalable, secure, and compliant AI deployment by offering a unified platform for multi-agent orchestration. It empowers enterprises to drive AI adoption with governance and observability, enabling real efficiencies, new revenue streams, and next-level automation. By integrating AI agents seamlessly into business workflows, organizations can overcome the limitations of fragmented AI initiatives, achieve higher operational efficiency, and unlock the full potential of AI-driven transformation.

Sonatype SBOM Manager

Sonatype SBOM Manager helps organizations generate, centralize, and manage Software Bills of Materials (SBOMs) across their software portfolio so teams can meet compliance requirements and respond faster to supply chain risk. SBOMs are increasingly required for procurement, audits, and security programs - but collecting them from many teams and vendors, keeping them current, and turning them into actionable risk insights is hard. SBOM Manager brings SBOM creation and management together in a single place so security, compliance, and procurement teams can standardize how SBOMs are produced, stored, shared, and reviewed. Key capabilities: - Generate SBOMs for applications in widely used formats (CycloneDX and SPDX) - Import and manage SBOMs received from third-party software suppliers - Centralize SBOMs across teams and products for consistent governance and audit readiness - Support risk and compliance workflows by making SBOM data easy to access, distribute, and operationalize SBOM Manager pairs Sonatype’s component intelligence with dedicated SBOM management so organizations can strengthen their software supply chain security posture, stay ahead of evolving requirements, and reduce the effort of proving compliance.

Spark Cloud-Native Stack - Kubernetes Container Solution 2.0

Spark Cloud-Native Stack - Kubernetes Container Solution 2.0 enables computation applications which are almost 10x faster than traditional Hadoop MapReduce applications. It is a unified framework for processing large amounts of data near to real-time.

Speech Annotation Service for Machine Learning Datasets [English]

AnnotateIt provides low-latency, high-accuracy speech labeling purpose-built for Machine Learning applications. Our speech annotation service helps you build and label speech datasets for custom speech and natural language processing applications at any scale.

SpeedWise ML

SpeedWise® ML (SML) is a web-based software platform allowing everyone and every company to conduct cutting-edge machine learning practices and predictive analysis. Through the platform, everyone, with or without a deep understanding of machine learning, will be able to deliver high-quality production-level models through a few mouse clicks within minutes, without typing a single line of code. • Master machine learning easily without a data science background. • Powerful data preprocessing capabilities and intelligent data capture make data wrangling easy and fast. • Save time training and refining ML models rather than on countless coding hours (python knowledge not needed). • SML allows training of different models at the same time, displaying which is best. • Robust reporting conveys model validity. • Solve universal machine learning problems with a fast and intuitive data science workflow. SpeedWise® ML can be used by any company or organization that has data that is not yet fully exploited. This technology is applicable to any industry or sector, and it simply requires uploading an input data table (e.g., a .csv file) to start triggering thousands of machine learning models.

Average Rating: 2.5/5.0

Total Reviews: 1

Spend Passion

Analyze low-utilization credit card users customer data to discover spend behavior and relationships between products or services.

Spherical Defense API Security

Spherical Defense is an advanced API security solution that leverages unsupervised deep learning to autonomously protect APIs from a wide range of cyber threats. By continuously analyzing API traffic patterns, it builds a dynamic model of normal behavior, enabling the detection of anomalies and potential attacks without the need for manual configuration or predefined rules. This approach ensures robust protection against both known and emerging threats, including zero-day attacks, while minimizing false positives and maintaining optimal performance. Key Features and Functionality: - Rapid Deployment: Spherical Defense can be deployed on-premise or in a private cloud environment, with a simple 1-click installation process on AWS. Security models begin detecting malicious behavior within approximately four hours. - Unattended Learning: The system operates autonomously, continuously learning and adapting to new API traffic patterns without requiring human intervention. This ensures that the security model evolves alongside application changes and user behavior. - Comprehensive Threat Detection: Spherical Defense protects against various threats, including excessive data exposure, malicious injections , improper asset management, sensitive information transmission, authorized stateful attacks, mass assignment vulnerabilities, and adversarial API fuzzing. - Easy Integration: The solution integrates seamlessly with existing infrastructures, including API gateways and service meshes, without the need for extensive configuration. It supports inbound integrations using AWS Lambda functions and outbound integrations for event monitoring. - Secure and Confidential: All data remains within the user's network, ensuring that sensitive information is not exposed to third parties. The system operates without requiring external access to data, maintaining confidentiality and compliance with data protection regulations. Primary Value and Problem Solved: Spherical Defense addresses the critical need for robust API security in an era where APIs constitute a significant portion of web traffic and are frequent targets for cyberattacks. Traditional security measures often rely on static rules and signatures, which can be ineffective against sophisticated and evolving threats. By employing unsupervised deep learning, Spherical Defense provides a dynamic and adaptive security solution that detects and mitigates both known and unknown threats in real-time. This not only enhances the security posture of organizations but also reduces the operational burden associated with manual configuration and the management of false positives, allowing security teams to focus on strategic initiatives.

SPi SPARK

SPi Spark - Invoice Extraction Platform transforms the existing time consuming, error prone and manual invoice processes. It is an enterprise solution that uses artificial intelligence to automatically extract key data elements from invoices. The platform is able to handle invoices in various formats such as pdf and scanned pdfs with very high accuracy. It can be easily integrated with existing business workflows and requires no training.

Spline Labeling - Multiple Curves

Product Description: Spline Labeling - Multiple Curves is a Jupyter Notebook application designed to facilitate the creation of multiple configurable splines and hierarchical labels within images. This tool is particularly beneficial for machine learning practitioners and data annotators who require precise and efficient labeling capabilities. By leveraging this application, users can enhance the quality of their datasets, leading to more accurate model training and improved performance in tasks such as object detection and image classification. Key Features and Functionality: - Spline Keypoints: Enables the creation and manipulation of multiple splines, allowing for detailed and flexible annotation of image features. - Hierarchical Labels: Supports the assignment of hierarchical labels, facilitating structured and organized annotation processes. - Machine Learning Integration: Designed to seamlessly integrate with machine learning workflows, enhancing the efficiency of data preparation and annotation tasks. Primary Value and Problem Solved: Spline Labeling - Multiple Curves addresses the challenge of efficiently creating detailed and structured annotations in image datasets. By providing tools for configurable splines and hierarchical labeling, it streamlines the annotation process, reducing manual effort and minimizing errors. This leads to higher-quality datasets, which are crucial for training accurate and reliable machine learning models.

Spline Video Labeling

Spline Video Labeling is a Jupyter Notebook application designed to facilitate the preparation and annotation of video data for machine learning tasks. It enables users to efficiently split input videos into frames, generate input manifests, and create video templates compatible with Amazon SageMaker Ground Truth workflows. Key Features and Functionality: - Data Preparation: Automatically splits input videos into individual frames, simplifying the process of preparing video data for analysis. - Manifest Generation: Creates input manifests required for Amazon SageMaker Ground Truth, streamlining the integration of video data into machine learning pipelines. - Video Template Creation: Develops video templates tailored for SageMaker Ground Truth workflows, facilitating efficient labeling and annotation processes. - Ease of Installation: Designed for straightforward deployment, allowing users to set up and begin using the tool with minimal effort. Primary Value and Problem Solved: Spline Video Labeling addresses the challenges associated with preparing and annotating video data for machine learning applications. By automating the extraction of frames and the creation of necessary input files, it significantly reduces the time and effort required for data preparation. This efficiency enables data scientists and machine learning practitioners to focus more on model development and less on the labor-intensive tasks of data preprocessing and annotation.