In a world where travellers want the perfect stay, a new system emerges as the one that goes beyond simple hotel recommendations. By analysing details like interaction words and prices, it predicts hotel ratings using...
详细信息
With the rapid development of the information age, current data information is an important resource in the new era. The design and application of computer network information security systems using intelligent contro...
详细信息
ObjectivesThis research aims to examine the integration of Artificial Intelligence (AI), Internet of Things (IoT), and Cyber-Physical systems (CPS), focusing on their synergistic manifestations and transformative pote...
详细信息
Cyberstalking has become an increasingly prevalent and concerning issue in today's digital landscape. The widespread use of online platforms and social media has made individuals more susceptible to predatory beha...
详细信息
The most widely grown crop in the nation is paddy. The lack of nutrients and pathogens causes a significant amount of crop loss. The management of diseases is the answer to minimizing this loss. Human experts mostly d...
详细信息
Human-centered intelligentsystems (HCIS), which are at the forefront of the AI and HCI fields, are dedicated to enhancing human experiences and interactions with technology. HCIS are designed to be intuitive, respons...
详细信息
Human-centered intelligentsystems (HCIS), which are at the forefront of the AI and HCI fields, are dedicated to enhancing human experiences and interactions with technology. HCIS are designed to be intuitive, responsive, and adaptable to human needs and preferences, aiming to empower users and foster positive interactions. By utilizing AI techniques, such as machine learning, natural language processing, and computer vision, HCIS aims to make technology more accessible and beneficial across various industries and domains.
Due to their large size, generative Large Language Models (LLMs) require significant computing and storage resources. This paper introduces a new post-training quantization method, GPTQT, to reduce memory usage and en...
详细信息
ISBN:
(纸本)9798350364200;9798350364194
Due to their large size, generative Large Language Models (LLMs) require significant computing and storage resources. This paper introduces a new post-training quantization method, GPTQT, to reduce memory usage and enhance processing speed by expressing the weight of LLM in 3bit/2bit. Practice has shown that minimizing the quantization error of weights is ineffective, leading to overfitting. Therefore, GPTQT employs a progressive two-step approach: initially quantizing weights using Linear quantization to a relatively high bit, followed by converting obtained int weight to lower bit binary coding. A re-explore strategy is proposed to optimize initial scaling factor. During inference, these steps are merged into pure binary coding, enabling efficient computation. Testing across various models and datasets confirms GPTQT's effectiveness. Compared to the strong 3-bit quantization baseline, GPTQT further reduces perplexity by 4.01 on opt-66B and increases speed by 1.24x on opt-30b. The results on Llama2 show that GPTQT is currently the best binary coding quantization method for such kind of LLMs.
Quadrotor aircraft is a highly coupled and underactuated controlled object, and it faces challenges such as external disturbances and model uncertainties during flight. Therefore, high precision attitude estimation an...
详细信息
ISBN:
(纸本)9798350372113;9798350372106
Quadrotor aircraft is a highly coupled and underactuated controlled object, and it faces challenges such as external disturbances and model uncertainties during flight. Therefore, high precision attitude estimation and flight controllers are required. This paper proposes a cascaded linear active disturbances rejection control (CLADRC) method for attitude control of quadrotor aircraft, based on feedforward compensation. The control method effectively constrains the attitude angles of the quadrotor aircraft. Simulation results demonstrate that compared to traditional linear active disturbances rejection control methods, the proposed control method can effectively suppress system oscillations and achieve faster response, thereby improving the stability of the quadrotor aircraft.
In this paper, a non-visual robotic formation control method based on a streaming communication architecture and a leader-follower control model is studied. The proposed stream-based communication architecture is insp...
详细信息
ISBN:
(纸本)9798350361261;9798350361278
In this paper, a non-visual robotic formation control method based on a streaming communication architecture and a leader-follower control model is studied. The proposed stream-based communication architecture is inspired by the flocking behavior of fish. We analogize it into a form resembling an Nary tree for communication purposes. Communication proceeds to the next layer only when all nodes in the upper layer have completed the follower selection. We also introduce a fault-tolerance mechanism and a termination filtering mechanism to prevent multiple leaders from choosing the same follower, avoiding a scenario where the robots in the last layer enter an endless loop of follower selection. The proposed stream-based communication architecture, built upon serial and parallel tracking, can achieve more complex formations, such as rectangular formations, closely resembling real-world scenarios, significantly enhancing formation efficiency. Simulation experiments on the e-puck platform validate the effectiveness and robustness of this architecture.
Poultry farming based products significantly contribute in providing healthy and protein-based food to human beings. The rapid increase in demand for poultry-based products and the growth of information and communicat...
详细信息
ISBN:
(纸本)9781665477062
Poultry farming based products significantly contribute in providing healthy and protein-based food to human beings. The rapid increase in demand for poultry-based products and the growth of information and communication tools lead to smart poultry farms. The environment of the poultry farm has a significant impact on the health of the birds and the production of the farm. This article proposes a low-cost edge computing and Internet of Things ( IoT)-based solution for poultry farms to control the farm environment with minimal human intervention and control of diseases in poultry farm. The model will sense the temperature, humidity, greenhouse gases, and light intensity inside the poultry farm and send these signals to the local server developed with the help of the Raspberry Pi. With the help of edge computing, data is processed at the local server and intelligent information is extracted to control the various actuators inside the farm. The cost of the system is affordable for the farmers due to usage of low-cost computing devices like the Raspberry Pi.
暂无评论