ResearchBerg
Not a member yet
161 research outputs found
Sort by
A Review: Impact of Static and Impact Load on the Mechanical Properties of Plastic Concrete
Get PDFThis review search seeks to know how the replacement effect on concrete is by replacing aggregate (coarse or fine) with plastic granules. Plastic does not dissolve in the climate and provides an early warning for collapses when mixed with concrete to give it more flexibility, making it more crucial to resist tensile stresses, increasing its strength, and seeking to make it more durable. The use of plastic is expanding day by day because of the rapid population increase and their constant demand. Every day, this causes a considerable amount of rubbish, which is harmful and causes pollution and plastic materials to take hundreds of years to dissolve. Solid waste management is currently a difficulty in any country, and the large-scale depletion of resources is causing environmental issues. For the concrete business, an alternative or alternative product must be produced. Plastic waste is the most challenging problem in solid waste management globally. In many countries, concrete has been one of the most excellent solutions for construction materials. It has hastened the pollution of the environment. It would be worthwhile to use plastic waste in concrete to solve the dual problems of a lack of raw materials and the safe disposal of plastic trash. This research aims to see if waste plastic can be used as a fine aggregate in concrete
A Comparative Analysis of Adversarial Capabilities, Attacks, and Defenses Across the Machine Learning Pipeline in White-Box and Black-Box Settings
Get PDFThe increasing adoption of machine learning models across various domains has brought to light the critical issue of their vulnerability to adversarial attacks, raising concerns about their security and reliability. This research discusses the adversarial capabilities that can be exploited at different stages of the machine learning pipeline: training, testing, and deployment. We investigate the distinct challenges and opportunities adversaries face in both transparent (white-box) and opaque (black-box) settings. Adversaries can tamper with the training data during the initial phase of the machine learning pipeline, compromising the model\u27s learning process. In a transparent setup, adversaries possess the ability to directly alter, introduce, or eliminate samples, injecting malicious patterns. Conversely, in an opaque setup, adversaries can indirectly sway the training process by manipulating data collection or preprocessing stages. Safeguarding against training-stage attacks necessitates data cleansing, anomaly identification, and resilient training techniques like adversarial training. Moving on to the testing phase, adversaries concentrate on designing deceptive examples that mislead the trained model. Adversaries with comprehensive knowledge of the model, operating in a white-box scenario, can meticulously craft highly targeted adversarial instances. On the other hand, black-box adversaries, lacking direct access to the model, employ techniques such as transferability to generate adversarial examples. Effective countermeasures against testing-stage attacks encompass adversarial training, ensemble approaches, and randomized defense mechanisms. As the model is deployed and used in real-world contexts, adversaries exploit vulnerabilities to undermine its performance. In a white-box setting, adversaries can meticulously examine the model\u27s behavior and engineer targeted attacks. Conversely, black-box adversaries probe the model and exploit weaknesses by carefully constructing malicious inputs. To protect against deployment-stage threats, defenses such as real-time monitoring, anomaly detection, secure deployment practices, and regular security assessments are also discussed
Improving Patient Care with Machine Learning: A Game-Changer for Healthcare
Get PDFMachine learning has revolutionized the field of healthcare by offering tremendous potential to improve patient care across various domains. This research study aimed to explore the impact of machine learning in healthcare and identify key findings in several areas.Machine learning algorithms demonstrated the ability to detect diseases at an early stage and facilitate accurate diagnoses by analyzing extensive medical data, including patient records, lab results, imaging scans, and genetic information. This capability holds the potential to improve patient outcomes and increase survival rates.The study highlighted that machine learning can generate personalized treatment plans by analyzing individual patient data, considering factors such as medical history, genetic information, and treatment outcomes. This personalized approach enhances treatment effectiveness, reduces adverse events, and contributes to improved patient outcomes.Predictive analytics utilizing machine learning techniques showed promise in patient monitoring by leveraging real-time data such as vital signs, physiological information, and electronic health records. By providing early warnings, healthcare providers can proactively intervene, preventing adverse events and enhancing patient safety.Machine learning played a significant role in precision medicine and drug discovery. By analyzing vast biomedical datasets, including genomics, proteomics, and clinical trial information, machine learning algorithms identified novel drug targets, predicted drug efficacy and toxicity, and optimized treatment regimens. This accelerated drug discovery process holds the potential to provide more effective and personalized treatment options.The study also emphasized the value of machine learning in pharmacovigilance and adverse event detection. By analyzing the FDA Adverse Event Reporting System (FAERS) big data, machine learning algorithms uncovered hidden associations between drugs, medical products, and adverse events, aiding in early detection and monitoring of drug-related safety issues. This finding contributes to improved patient safety and reduced occurrences of adverse events.The research demonstrated the remarkable potential of machine learning in medical imaging analysis. Deep learning algorithms trained on large datasets were able to detect abnormalities in various medical images, facilitating faster and more accurate diagnoses. This technology reduces human error and ultimately leads to improved patient outcomes.While machine learning offers immense benefits, ethical considerations such as patient privacy, algorithm bias, and transparency must be addressed for responsible implementation. Healthcare professionals should remain central to decision-making processes, utilizing machine learning as a tool to enhance their expertise rather than replace it. This study showcases the transformative potential of machine learning in revolutionizing healthcare and improving patient care
The Impact of Erectile Dysfunction on Husband’s and Wife’s Quality of life: A Study on Malaysia
Get PDFIt has been hypothesized that the quality of life for men who suffer from ED is lower than that of men who do not suffer from ED. Men with ED also have a negative effect on their female partners’ quality of life, who may have problems in their relationships and a decline in their level of happiness in their partnership. This research investigates these two hypotheses in the context of Malaysia. We employed Ferrans and Power\u27s Quality Of Life Index to assess the life qualities of the husband and wife among the study participants. The International Index of Erectile Function (IIEF) is used to determine the level of erectile dysfunction. The data estimation suggested that erectile dysfunction has significant negative impacts on the life quality index of both husband and wife. Even though ED is not a deadly illness, the findings of this research show that improved management and availability of effective ED treatments are needed to assist reduce the intimacy cost of this condition. These results also highlight the need for increased knowledge about ED, a better grasp of the various treatment choices, and a greater comprehension of the physical and mental cost that ED may put on men and their relationships
A Review on Current and Potential Applications of Robotics In Mental Health Care
Get PDFRobotics technology is most commonly associated with robots, that are physically embodied systems capable of causing physical change in the world. Robots execute this transformation via effectors that either move the robot itself (locomotion) or move items in the environment (manipulation), and they frequently make judgments based on data from sensors. Robot autonomy can range from totally teleoperated to fully autonomous (the robot is entirely independent). The word robotics technology also encompasses related technologies, such as sensor systems, data processing algorithms, and so forth. While in recent years this has evolved outward, with an emphasis on difficulties connected to dealing with actual people in the real world. This transition has been referred to as human-centered robotics in the literature, and a developing topic in the last decade focused on difficulties in this arena is known as human robot interaction (HRI). The application of robotics technology in mental health treatment is still in its early stages, but it offers a potentially beneficial tool in the professional\u27s arsenal
Applications of Artificial Intelligence in the Treatment of Behavioral and Mental Health Conditions
Get PDFIntroduction
Artificial intelligence (AI) is the branch of science that studies and designs intelligent devices. For individuals unfamiliar with artificial intelligence, the concept of intelligent machines may bring up visions of attractive human-like computers or robots, like those described in science fiction. Others may consider AI technology to be mysterious machines limited to research facilities or a technical triumph that will come in the far future. Popular media accounts on the deployment of aerial drones, autonomous autos, or the potential dangers of developing super-intelligent technologies may have raised some broad awareness of the subject
Application of Artificial Intelligence in IoT Security for Crop Yield Prediction
Get PDFThis research explores the application of Artificial Intelligence (AI) in the Internet of Things (IoT) for crop yield prediction in agriculture. IoT devices, like sensors and drones, collect data on temperature, humidity, soil moisture, and crop health. AI algorithms process and integrate this data to provide a comprehensive view of the agricultural environment.AI-driven anomaly detection helps identify threats to crop yield, such as pests, diseases, and adverse weather conditions. Predictive analytics, based on historical and real-time data, forecast crop yield for informed decision-making in irrigation and fertilization.AI-powered image recognition detects early signs of pests and diseases, aiding timely treatment to prevent crop losses. Resource optimization allocates water and fertilizers efficiently, minimizing waste and environmental impact.AI-driven decision support systems offer personalized recommendations for ideal planting schedules and crop rotations, maximizing yield. Autonomous farming integrates AI into machinery for precision tasks like planting and monitoring.Secure communication protocols protect sensitive agricultural data from cyber threats, ensuring data integrity and privacy
Digital Tools in Art Education: From Expanding Creative Horizons and Facilitating Collaboration to Increasing Access and Resources for a Diverse Student Population
Get PDFThe purpose of the article is to explore the various ways in which digital tools can impact art education. It aims to examine how these tools can provide new opportunities for creative expression and experimentation, facilitate new forms of creative collaboration, and increase accessibility and resources for a wide range of students. The article also aims to highlight the potential of digital tools in enhancing the art education experience for students by providing them with new opportunities for creative expression and experimentation, and increasing accessibility to resources and materials. The overall goal of the article is to demonstrate the potential of digital tools in art education and how they can be utilized to improve the education experience for students. Digital tools can have a significant impact on art education in a variety of ways. One of the key ways is by providing new opportunities for creative expression and experimentation. Digital tools such as graphic design software, 3D modeling software, and animation software can open up new possibilities for creative expression that were not previously available. This can help students to create digital artworks, animations, and designs that can be shared and exhibited online. Additionally, digital tools can facilitate new forms of creative collaboration, by allowing students to share ideas and collaborate on art projects with classmates and teachers from around the world. Another important way that digital tools can impact art education is by providing access to a wider range of resources and materials. Digital tools such as the internet and online databases allow students to access a vast amount of information and resources that would otherwise be difficult or impossible to find. Additionally, digital tools can also make art education more accessible to a wider range of students such as students who live in rural areas, older students, students with special needs, and students with language barriers. This can be done by providing online classes, video tutorials, mobile apps and creating art education programs that are tailored to different skill levels and learning styles. Overall, digital tools can greatly enhance the art education experience by providing students with new opportunities for creative expression and experimentation, and by making art education more accessible to a wider range of students
AI Governance in Healthcare: Explainability Standards, Safety Protocols, and Human-AI Interactions Dynamics in Contemporary Medical AI Systems
Get PDFThe fast-growing incorporation of artificial intelligence (AI) into the modern healthcare industry necessitates immediate consideration of its legal and ethical dimensions. In this research, we focused on three principal areas requiring specific, contextual direction from both governmental entities and industry participants to guide the responsible and ethical progression of AI in healthcare. First, the research discusses standards for explainability. Within healthcare, understanding AI-driven decisions is vital because of their profound implications for human health. Various participants, from patients to oversight bodies, require differing levels of transparency and explanation from AI systems. Next, we examine safety protocols. Given that employing AI in healthcare could result in decisions that carry severe ramifications, we argue for evaluating its objective criteria, search parameters, training applicability, risk for of poor data, and possible risks. Finally, the dynamics of human-AI interaction were discussed. Optimal interaction necessitates the creation of AI systems that augment human capabilities and acknowledge human cognitive processes. The involvement of AI system users in healthcare, defined through tiers of understanding, contribution, and oversight, spans from elementary to advanced engagements. Each tier relates to the depth of comprehension, the scope of data contribution, and the level of oversight exercised by the healthcare specialist regarding the AI instrument. This research emphasizes the necessity for specific guidelines for each of the three dimensions to guarantee the secure, ethical, and efficient utilization of AI in healthcare
Addressing Barriers in Data Collection, Transmission, and Security to Optimize Data Availability in Healthcare Systems for Improved Clinical Decision-Making and Analytics
Get PDFData availability in healthcare faces numerous challenges that stem from various technical, environmental, and security issues. These include medical device malfunctions, unreliable data transmission protocols, and failures in authentication systems,that disrupt the timely and accurate collection and transmission of healthcare data. This study explores the core barriers to data availability in healthcare systems, categorizing them into three broad areas: (1) echnological Failures, such as device malfunctions and calibration errors that compromise data collection; (2) Authentication and Security Bottlenecks, which involve failures in access control systems that prevent authorized personnel from accessing critical data; and (3) Environmental and Infrastructural Constraints, such as network instability, electromagnetic interference, and power outages that interrupt data transmission. This paper also provides an in-depth evaluation of existing solutions aimed at addressing these challenges and proposes new methods to improve data availability. Specifically, it discusses data transmission protocols, real-time device diagnostics, decentralized security architectures like blockchain, and improved device calibration techniques using machine learning algorithms. The proposed solutions focus on increasing the resilience of healthcare data collection and transmission, integrating state-of-the-art technologies such as edge computing, predictive maintenance models, and biometric authentication systems. These technologies can improve data reliability, reduce latency, and ensure that healthcare data remains available in the correct format in order to supoport both real-time clinical decisions and long-term healthcare analytics