Accepted Papers

Novel Approach, Multi Model Video Supervision for Safety and Awareness"

Lokesh Kumar1, AnubhavSingh2, 1Senior Staff Engineer @Nagarro, Dehradun,India, 2Associate Data Scientist, @Mathco, Chandigarh, India

Abstract

In the modern era, surveillance systems, notably Closed-Circuit Television (CCTV) technology, have undergone a significant evolution through the integration of computer vision algorithms and deep learning methodologies, enabling them to carry out a multitude of tasks and objectives. However, a considerable portion of these systems remains far from achieving the distinction of 'smart' CCTV. In response, we introduce an innovative approach that harnesses multi-model techniques to enhance the effectiveness of CCTV supervision across a wide array of scenarios. The omnipresence of CCTV systems, functioning around the clock, leads to the accumulation of vast volumes of data, a substantial portion of which eventually becomes redundant. The conventional approach requires human supervisors to painstakingly review captured frames and subsequently deduce information pertaining to the events within those frames. This process, apart from being labour-intensive, is also time-consuming. Our novel multi-model approach represents a transformative paradigm shift within this landscape. It not only enables the system to comprehend visual data but also provides real-time analysis, alerts, and action-based responses. This advancement carries the potential to revolutionise the utilisation of CCTV systems, optimising their role in surveillance and security operations. As the world continues to witness the widespread deployment of CCTV technology, our research highlights the paradigm shift brought about by multi-model approaches, offering a pathway towards the development of intelligent, efficient, and proactive surveillance systems. This work marks our initial step in exploring the multi-modal capabilities required to understand, reason, and formulate sequences of action to enhance the current state of CCTV technology. To this end, we first conduct experiments on 87 tasks using various LLMs, including Flan-T5-Large, Vicuna, Llama 2, BLOOM, GPT-3.5, and GPT-4. These experiments show LLMs have a grasp of reasoning and can understand a scenario and act on it.

Keywords

CCTV, Large Language Models, Surveillance, Alert Generation, Image to Text & Question and Answers on multiple images.

Semantic Segmentation of Road Traffic Sign Based on Improved Deeplabv3+

Wang Huifengl1 and Wu Jianfeng2, 1School of Electronic &Control Engineering Chang’an University, Xi’an 710064, Shaanxi, Chin, 2School of Information Engineering Chang’an University, Xi’an 710054, Shaanxi, China

Abstract

Road traffic sign is a important facility to manage traffic and indicate the direction of traveling to ensure smooth road and driving safety. However, sign is usually small target, which is prone to the problem of missed detection and false detection. In addition, the deeplabv3+ model is a representative semantic segmentation network. It employs dilated convolution in the ASPP module, which is prone to lose small target information while expanding the sensory field. Aiming at above problem, an improved deepswin small target semantic segmentation based on deeplabv3+ is proposed. First of all, the ASPP module is replaced by swin-transformer block to enhance the signage feature extraction capability. Then, a channel and spatial fusion attention(CSFA) mechanism based on CBAM attention mechanism is utilized to enhance the extraction capability of channel and spatial features. The experimental results show that compared with the original network, the MIOU and mPA of the network proposed in this paper are improved by 4.0% and 4.9%, respectively.

Keywords

Road traffic sign, deep learning, semantic segmentation, swin-transformer, attention mechanism.

Use of Dendrograms to Confirm % of Suspicions in Values That Do Not Comply With Benford's Law and Specifically Locate The Data Elements Considered Suspicious

Carlos Carrion R, Department of Data Science Technology, Andres Bello High Tech Institute, Quito, Ecuador

Abstract

It is estimated that only 12% of financial/tax fraud and less than 30% of electoral fraud worldwide are detected with clear evidence, making it likely that intentional anomalies will increase aided by Artificial Intelligence and commercial access with quantum processors, since the amount of economic benefits and power is tempting, because it involves bigData, trying to clean tracks and eliminate evidence that certain systems and applications allow or do not consider taking care of. In Monitoring Audit of the normal operations behavior with help of Data Science and Technological advances, the variants of Benford's Law are available as a starting point at general level to know percentage of suspicion of values that do not comply with it; therefore, a technique is important to confirm these suspicions by more than 95% and specifically locate them through Dendrograms so that the data elements that produced suspicion are analyzed in depth, which is reason for this methodological proposal.

Keywords

Types of Fraud, bigData, Artificial Intelligence, Benford Law, Dendrograms, Normal Operations Behavior.

Notorious Failure of Ms Excel With Accounting Spreadsheet in 2 Conditional Functions Giving Incorrect Results in All Versions/idioms, Reported Since 2011 That Still Persists.

Carlos Carrion R, Department of Data Science Technology, Andres Bello High Tech Institute, Quito, Ecuador

Abstract

Millions of business and organizations users in the world use MS Excel spreadsheet every hour and have kept their records with calculations without considering there is any slight difference in results even if key decisions are made, such as in accounting area, when using 2 widely used conditional functions (SUMIF, COUNTIF) that in their main comparison parameter may have overflowing if it is floating point, which is used to save storage and processing due to the presence of large volume of data for the accounting action of business operations. Even more so today, with AI and social networks, millions of records are generated in business operations, it justify to abbreviate storage of business identification by country/city or IP addresses (IPv4/IPv6) where it can easily exceed 15 digits, to arrange them in floating point and use conditional functions in spreadsheet to group or differentiate them, which with this failure is sure to make wrong decisions.

Keywords

Accounting Spreadsheet, Wrong Results, Artificial Intelligence, Business Operations, Software Failure.

Criteria for Evaluating Alternative Encryption Algorithms Using Artificial Neural Networks

Olga Fenina, Eurasian Nationality University by named L. Gumilev, Astana, Kazakhstan

Abstract

As is known an Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems, ANN has emerged over the years and has made remarkable contribution to the advancement of various fields of activities. In its turn cryptography is the one of the main categories of computer security that changes information from its normal form into an converted form. The purpose of this paper is to using neural networks on Cryptography. In this paper also, author has examined and analyzed the alternative encryption algorithms and criteria for its evaluating.

Keywords

Artificial Neural Network, Cryptography, Alternative encryption algorithms, Evaluating, Criteria.

Skin Cancer Detection and Classificationby using Deep Learning. Fps and Accuracy Comparison of Custom Model, Resnet 18 and Alexnet

Ismat Saira Gillani1, Muhammad Rizwan Munawar2, Muhammad Talha3, 1Department of Computer Science, Columbus State University, USA, 2Department of Computer Science, COMSATS University, Pakistan, 3Department of Electrical Engineering, GC University Faisalabad, Pakistan

Abstract

A recent study by the International Agency for Research on Cancer (IARC) predicts a 50% rise in yearly cancer cases by 2040, with one in five Americans facing a diagnosis in their lifetime. UV overexposure is the main cause of skin cancer, often hard to detect early due to its similarities. Recent tech advances aid detection, but challenges persist. Here, we introduce a deep learning model for skin cancer detection, outperforming prior methods like ResNet and AlexNet in accuracy and speed. Our model demands fewer features and achieves State of the Art results. Find the code at: https://github.com/RizwanMunawar/skin-cancer-binary-classification-computer-vision.

Keywords

Deep learning, Object Detection, Feature Extraction, Network Architecture.

A Creativity Monitoring Device (CMD) for Generating New Insights Into the Brain Mechanisms of Artistic, Scientific and Engineering Creative Acts

Nandor Ludvig, Translational Neuroscience Consultation, Astoria, New York, USA

Abstract

This paper introduces the basic design of a novel neuroscientific device named Creativity Monitoring Device, CMD, able to provide new insights into the brain mechanisms of artistic, scientific and engineering creative acts. The novelty of the device is threefold. First, it allows the artifact-free recording of association cortical EEG waves during such creative acts as painting artistic visions, composing music, running novel experiments in a laboratory or working on an engineering invention. Second, it allows the synchronous monitoring of the sounds and visual events in the environment of such actions along with the artist’s, scientist’s or engineer’s verbal and non-verbal interactions with this environment and his or her own notes on the engaged creative phase. Third, it allows the offline analysis of the synchronously collected EEG and audio-visual data with the new method of dynamic neurocombinatorics, which can reveal at 2 msec accuracy the relationships between the recorded objects of 5 sets: (1) the spatial occurrence codes of the recorded association cortical EEG waves; (2) the complexity codes of each of the recorded 0.2 - 200 Hz EEG waves; (3) the codes of the synchronously recorded environmental events including those of the subject’s verbal and non-verbal interactions with this environment; (4) the subject’s own dictated notes identifying the phase of the engaged creative act, and (5) the time-course of these continuously recorded objects within each of the indicated sets over the entire, at least 10-hour, creativity monitoring period. Thus, CMD studies should reveal the key electrical brain changes underlying the initiation, maintenance and termination of creative acts and should show the similarities and differences between artistic, scientific and engineering creativities.

Keywords

Artifact-free EEG headset, Wearable environment monitor, Dynamic Neurocombinatorics.

The Relationship Between Conceptual Perception and Student Achievement in the Science Subject Area of Chemistry

Ven B.Siri Sumedha, Assistant Director of Education, Ministry of Education, Sri Lanka

Abstract

The evaluation reports of the Sri Lanka Examination Department show that the minimum number of marks has been obtained for the science subject. The main interest of this research was to find the correlation between performance and conceptual understanding in the fields of chemistry and science. After a pilot study, 302 students from 13 secondary schools in Kegalle District, Sri Lanka were selected as the sample. Research was conducted through correlational study research strategy according to a quantitative research design. Standardized research instruments were administered to the sample, and the collected data were analyzed and interpreted. Here the correlation between students' concept perception and student achievement was r = 0.720. It was revealed that student achievement increases as students' conceptual understanding increases. For that one should always resort to using appropriate learning methods.

Keywords

Conceptual Perception, Student achievement, Chemistry, G.C.E (O/L), Science.

Steps and Challenges in Analyzing Real Sensor Data From a Productive Press Shop and Its Value for Predictive Maintenance Application

Safa Evirgen1 and Prof. Dr. Maylin Wartenberg2, 1Volkswagen AG, Berliner Ring 2, 38426 Wolfsburg, Germany, 2Hochschule Hannover, Recklinger Stadtweg 120,30459Wolfsburg, Germany

Abstract

This paper introduces the basic design of a novel neuroscientific device named Creativity Monitoring Device, CMD, able to provide new insights into the brain mechanisms of artistic, scientific and engineering creative acts. The novelty of the device is threefold. First, it allows the artifact-free recording of association cortical EEG waves during such creative acts as painting artistic visions, composing music, running novel experiments in a laboratory or working on an engineering invention. Second, it allows the synchronous monitoring of the sounds and visual events in the environment of such actions along with the artist’s, scientist’s or engineer’s verbal and non-verbal interactions with this environment and his or her own notes on the engaged creative phase. Third, it allows the offline analysis of the synchronously collected EEG and audio-visual data with the new method of dynamic neurocombinatorics, which can reveal at 2 msec accuracy the relationships between the recorded objects of 5 sets: (1) the spatial occurrence codes of the recorded association cortical EEG waves; (2) the complexity codes of each of the recorded 0.2 - 200 Hz EEG waves; (3) the codes of the synchronously recorded environmental events including those of the subject’s verbal and non-verbal interactions with this environment; (4) the subject’s own dictated notes identifying the phase of the engaged creative act, and (5) the time-course of these continuously recorded objects within each of the indicated sets over the entire, at least 10-hour, creativity monitoring period. Thus, CMD studies should reveal the key electrical brain changes underlying the initiation, maintenance and termination of creative acts and should show the similarities and differences between artistic, scientific and engineering creativities.

Keywords

Predictive Maintenance, smart database, sensor data analytics, data science, production.

The Impact of Authoritarian Education and Deterministic Policies on Societal Stability: a Case Study of Florida

Joan Manuel Quitian Ramos

Abstract

This paper explores the intertwined effects of authoritarian education, psychological trauma, and deterministic policies in Florida. It critically examines the societal and economic implications of these factors, particularly in the context of Florida's role in global trade. Additionally, the paper draws on historical eugenics practices in Latin America to propose potential strategies for mitigating the ongoing crisis in Florida. A comprehensive approach prioritizing psychological health, individuality, and community engagement is advocated to address these complex challenges.

Keywords

Authoritarian Education, Deterministic Policies, Psychological Trauma, Societal Stability, Eugenics, Florida, Global Trade Impact, Community Engagement.

On the Unification of Physics and the Elimination of Unbound Quantities

Joan Manuel Quitian Ramos

Abstract

It is known that in the initial process of knowledge, we have encountered projections of complex laws. Then we sought, through these projections represented by laws of a lower form such as force and momentum, to go to the complex laws. The difficulty, expressed figuratively, lies in the attempt to seek the number of leaves that produced the shadow of a tree from its shadow. The initial effort to solve the problem is initiated by Newton, who presents the projections of complex laws in a postulated form, then Einstein modifies them in the Special Theory of Relativity. The article presents the idea that these laws are derived from the law of energy conservation. The idea that force is derived from energy shows that it exists even when the object is at rest. A conclusion that is simply seen in Coulomb's electrostatic force or Newton's gravitational force. The object at rest reflects the minimal energy state. It is mirrored by the classical radius for objects up to the mass of Planck or the Schwarzschild radius for objects with a mass above it. The minimal energy state of the object is multiplied up to the maximum, where it reaches dimensions corresponding to those of Planck's length. From here, by exploiting the law of force propagation with the inverse of the square of the distance, we can find the value of the force wherever we want. This leads to the conclusion that eliminates the differences between the forces of nature by unifying them into one. The presentation also expresses the quantum character of energy. It removes from the scene the concepts of charge, electrostatic force, and gravitational constant, considering them as achievements of a time when we built theoretical physics through the laws of a simpler form. The achievement is ensured by introducing Sommerfeld's fine structure constant. The article presents a concept that, based on the quantum character of energy, should easily lead to the theory that expresses the quantum character of gravity.

Keywords

Unification of Physics, Unbounded Quantities, Energy as a Constant Quantity, Exposed and Unexposed Energy, Lorentz Factor, Law of Energy Conservation, Energy Transformation, Force as a Derivative of Energy, Quantum Gravitation, Principle of Energy Conservation, Elimination of Charge and Gravitational Constant Concepts, New Model Based on Energy, Unification of Forces of Nature, Quantum Character of Energy, Energy State and Maximum Radius.